CN114500983A - Video picture content integrity evaluation method and electronic equipment - Google Patents

Abstract

A video picture content evaluation method. In the method, the electronic equipment can acquire the element group in the video to be detected according to the identified elements in the image frame of the video to be detected, and determine the image content evaluation result of the video to be detected according to the element group attribute of the element group. According to the technical scheme, the electronic equipment can automatically evaluate the video to be detected, and the video auditing efficiency is improved.

Description

A kind of video picture content integrity evaluation method and electronic device

technical field

The present application relates to the field of multimedia technologies, and in particular, to a method and an electronic device for evaluating the integrity of video image content.

Background technique

With the full popularity of smartphones and the growing maturity of the mobile Internet, the amount of video production and sharing by users has increased significantly. The daily average video upload volume of video platform users continues to increase, and the substantial increase in the number of videos poses a challenge to the platform's video quality review capabilities. The video platform needs to evaluate the completeness of the content of the video uploaded by the user. The main purpose is to check whether there are incomplete elements (subtitles, main body, characters, etc.) in the video image, which will lead to poor user viewing experience or affect the user's understanding of the video content.

At present, the video screen content integrity review method provided by the industry is mainly manual review. The steps are: (1) The video review task is issued to the reviewers; (2) The reviewers watch the video on the review platform, and during the viewing process, they can choose to watch at normal speed, accelerated viewing, and skip watching; (3) Reviewers find the video If the screen content is incomplete and affects the viewing experience of the video viewer, it is marked as "the video screen content is incomplete".

However, with the explosive growth of the number of short videos, in the face of large-scale video review requirements, labor costs are high, and the review efficiency of manual review can no longer meet the review needs of video platforms.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a method and an electronic device for evaluating the integrity of video image content, which are used to automatically review videos uploaded by users and improve the review efficiency of a video platform.

In a first aspect, the present application provides a video image content evaluation method, the method comprising: an electronic device identifying elements in at least two image frames in a video to be detected, the at least two image frames including a first image frame and a second image frame An image frame, the element is the basic element in the image frame; the electronic device determines an element group in the video to be detected according to the identified element, which includes a first element group, and the first element group includes the first element group the first element in the image frame and the first element in the second image frame; the electronic device determines the element group attribute of the first element group, the element group attribute of the first element group includes the first incomplete parameter value, the first element group attribute A defect parameter value is used to indicate the defect degree of the first element group; the electronic device determines the picture content evaluation result of the video to be detected at least according to the element group attribute of the first element group.

In the above embodiment, by automatically acquiring the element group in the video to be detected and determining the element group attribute of the element group, the picture content evaluation result of the video to be detected can be determined according to the element group attribute of the element group. The evaluation result of the video to be detected can be obtained directly without manual intervention, so that the video platform can automatically review the video to be detected, which improves the review efficiency of the video platform.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines the picture content evaluation result of the video to be detected at least according to the element group attribute of the first element group, which specifically includes: the electronic device according to the first element group. The element group attribute of an element group determines the effect of the first element group on the content of the video image to be detected; the electronic device determines the effect of the first element group on the content of the video image to be detected at least according to the effect of the first element group. The results of the picture content evaluation of the video.

In the above embodiment, the electronic device may first determine the effect of the first element group on the content of the video to be detected according to the element group attribute of the first element group, and then determine the evaluation of the image content of the video to be detected according to the effect. As a result, the influence of each element group on the content of the video picture can be determined more clearly, so that the evaluation result of the content of the video picture is more accurate.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines, according to the element group attribute of the first element group, the impact result of the first element group on the video image content to be detected, specifically including: the The electronic device determines the influence result of the first element group on the content of the video image to be detected according to the element group attribute of the first element group and the preset element group influence picture integrity rule.

In the above embodiment, the effect of the element group on the content of the video image to be detected can be quickly and accurately determined through the preset rules for affecting the picture integrity of the element group. The element group that has an influence on the video image to be detected participates in the subsequent calculation, which reduces the calculation amount of the subsequent calculation.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines the picture content evaluation result of the video to be detected at least according to the effect of the first element group on the picture content of the video to be detected, specifically including: The electronic device determines whether the to-be-detected video is complete at least according to the effect of the first element group on the to-be-detected video picture content; and/or, the electronic device determines the to-be-detected video picture content at least according to the first element group and/or, the electronic device at least according to the first element group's influence result on the to-be-detected video picture content and the elements of the first element group The group attribute determines the modification suggestion for the video to be detected, which includes the modification suggestion for the first element group.

In the above embodiment, by determining whether the detection video is complete, the video platform can feedback the complete result to the user or the video producer to complete the review; by determining the score of the detection video, the video platform can feed back the score result to Users or video producers can help users or video producers to understand the integrity of the video to be detected more objectively and visually; the video platform can use the modification suggestion as a specific modification suggestion by determining the modification suggestion of the video to be inspected. The evaluation results are fed back to users, which helps users or video producers to make targeted modifications based on modification suggestions to improve user experience.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines the picture content evaluation result of the video to be detected at least according to the element group attribute of the first element group, which specifically includes: the electronic device at least according to the The element group attribute of the first element group determines whether the video to be detected is complete; and/or, the electronic device determines the score of the video to be detected at least according to the element group attribute of the first element group and the classification information of the video to be detected; And/or, the electronic device determines, at least according to the element group attribute of the first element group, a modification suggestion for the video to be detected, which includes a modification suggestion for the first element group.

In the above embodiment, by determining whether the detection video is complete, the video platform can feedback the complete result to the user or the video producer to complete the review; by determining the score of the detection video, the video platform can feed back the score result to Users or video producers can help users or video producers to connect the integrity of the video to be detected more objectively and visually; the video platform can use the modification suggestion as a specific modification suggestion by determining the modification suggestion of the video to be inspected. The evaluation results are fed back to users, which helps users or video producers to make targeted modifications based on modification suggestions to improve user experience.

With reference to some embodiments of the first aspect, in some embodiments, the modification suggestion of the first element group includes at least one of: pass, can not be processed, crop, smear, delete frame, and blur.

In the above-mentioned embodiment, by determining the modification suggestion of the element group in the video to be detected, the video platform can feedback the modification suggestion of the element group to the video producer or user, so that the video producer and user can get targeted and concise , fool-like modification suggestions, and can make corresponding modifications to the element group according to the modification suggestions, improve the integrity of the video, and improve the user experience.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines, according to the identified elements, an element group in the video to be detected, which includes the first element group, and specifically includes: the electronic device will identify The elements representing the same basic element in the at least two image frames form an element group.

In the above embodiment, the video platform determines the element group through the elements, which preserves the temporal and spatial integrity of the elements in the video to be detected, which helps to improve the accuracy of the content evaluation result of the video to be detected.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device will form elements representing the same basic element in the at least two image frames identified to form an element group, which includes the first element group, which specifically includes : the electronic device determines the first element similarity between the first element in the first image frame and the first element in the second image frame, and the element similarity is used to indicate the similarity between the element images; the electronic device It is determined that the similarity of the first element is greater than a preset similarity threshold, and the first element in the first image frame and the first element in the second image frame form a first element group.

In the above-mentioned embodiment, the video platform determines the element group through the element, which preserves the temporal and spatial integrity of the element in the video to be detected. In the case that the video to be detected may be affected by editing or shooting techniques, using the element group instead of the element as the basic unit of the video evaluation method can effectively reflect the completeness of the screen content of the video to be detected.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines, according to the identified elements, an element group in the video to be detected, and after the step of including the first element group, the method further includes: the The electronic device calculates the completeness of the element group in the video to be detected, and the completeness is used to indicate whether the element group is complete; the electronic device filters out the incomplete element group from the element group in the to-be-detected video, including the first Element group, the completeness of the incomplete element group is incomplete.

In the above-mentioned embodiment, by judging the completeness of the element group and screening the element group whose completeness is incomplete for subsequent processing, the number of element groups in the subsequent processing can be reduced, and the calculation amount can be effectively reduced.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines, according to the identified elements, an element group in the video to be detected, and after the step of including the first element group, the method further includes: the The electronic device filters out a suspected incomplete element group from the element group in the video to be detected, including the first element group, and the suspected incomplete element group is an element group whose position and the distance between the edge of the screen are smaller than a preset second distance threshold.

In the above embodiment, considering the actual situation, the elements that affect the integrity of the video image to be detected often appear at the edge of the image. By judging the position of the element group to filter the element group, the number of element groups in the subsequent processing is reduced, and the number of element groups in the subsequent processing can be reduced. Effectively reduce the amount of calculation.

With reference to some embodiments of the first aspect, in some embodiments, after the electronic device selects the suspected incomplete element group from the element group in the video to be detected, the method further includes: the electronic device calculates the video to be detected The completeness of the suspected incomplete element group in the video, which is used to indicate whether the element group is complete; the electronic device filters out the incomplete element group from the suspected incomplete element group in the video to be detected, including the first element group, The completeness of the incomplete element group is incomplete.

In the above embodiment, by judging the completeness of the element group, and considering that the element group whose completeness is complete will not affect the picture content of the video to be detected, the element group whose completeness is incomplete is screened out. Participating in subsequent calculations reduces the number of element groups in subsequent processing, which can effectively reduce the amount of calculation.

With reference to some embodiments of the first aspect, in some embodiments, the element group attribute of the first element group further includes a second incomplete parameter value, and the second incomplete parameter value is used to indicate the incomplete type of the first element group, At least one of duration, importance, surrounding element group, and period type.

In the above embodiment, by determining the value of the second incomplete parameter in the element group attribute of the element group, more information of the element group can be obtained, and then the picture content evaluation result of the detected video can be more accurately determined.

With reference to some embodiments of the first aspect, in some embodiments, the classification information of the video to be detected includes: the subject of the video to be detected and/or the label of the video to be detected.

In the above embodiment, the video platform obtains the classification information of the video to be detected, and differentiates the videos to be detected with different themes and labels according to the classification information, so that the video to be detected can be more targeted to evaluate the screen content, and a more accurate picture can be obtained. evaluation result.

With reference to some embodiments of the first aspect, in some embodiments, before the step of identifying the elements in at least two image frames in the video to be detected by the electronic device, the method further includes: the electronic device extracts frames from the original video to obtain the video to be detected; or, the electronic device cuts the original video into N videos to be detected; or, after the electronic device cuts the original video into N intermediate videos, extracts frames from the N intermediate videos to obtain N the videos to be detected; the N is a positive integer.

In the above embodiment, by performing frame extraction operation on the original video, the number of image frames in the video to be detected is reduced, thereby reducing the number of element groups involved in the calculation, so the calculation amount is reduced; by cutting the original video, cutting Then, at least one video to be detected is obtained, which reduces the amount of calculation, and at the same time, reduces the calculation time by using parallel computing.

In a second aspect, an embodiment of the present application provides an electronic device, the electronic device includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program codes, The computer program code includes computer instructions invoked by the one or more processors to cause the electronic device to perform: identify elements in at least two image frames in the video to be detected, the at least two image frames including the first image frame and the second image frame, the element is the basic element in the image frame; according to the identified element, determine the element group in the video to be detected, including the first element group, the first element group includes the first element group the first element in an image frame and the first element in the second image frame; determine the element group attribute of the first element group, the element group attribute of the first element group includes the first incomplete parameter value, the first incomplete The parameter value is used to indicate the degree of incompleteness of the first element group; at least according to the element group attribute of the first element group, the picture content evaluation result of the video to be detected is determined.

In the above embodiment, the electronic device can automatically obtain the element group in the video to be detected and determine the element group attribute of the element group, and can determine the picture content evaluation result of the video to be detected according to the element group attribute of the element group. The evaluation result of the video to be detected can be obtained directly without manual intervention, so that the video platform can automatically review the video to be detected, which improves the review efficiency of the video platform. In addition, the electronic device can be a networked server or a computer of a user or a video producer, which facilitates the user or video producer to evaluate the video to be inspected anytime and anywhere, and improves the user experience.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are specifically configured to invoke the computer instruction to cause the electronic device to execute: determine the element group according to the element group attribute of the first element group The influence result of the first element group on the video picture content to be detected; at least according to the influence result of the first element group on the to-be-detected video picture content, determine the picture content evaluation result of the to-be-detected video.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: according to the element group attributes and presets of the first element group The first element group affects the picture integrity rule, and the effect of the first element group on the content of the video picture to be detected is determined.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: at least the video frame to be detected according to the first element group The influence result of the content, to determine whether the video to be detected is complete; and/or, at least according to the influence result of the first element group on the content of the video to be detected and the classification information of the video to be detected, determine the score of the video to be detected; and /or, at least according to the effect of the first element group on the content of the video to be detected and the element group attribute of the first element group, determine the modification suggestion of the to-be-detected video, which includes the modification suggestion for the first element group.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are specifically configured to invoke the computer instruction to cause the electronic device to execute: at least according to the element group attribute of the first element group, determine Whether the video to be detected is complete; and/or, at least according to the element group attribute of the first element group and the classification information of the video to be detected, determine the score of the video to be detected; and/or, at least according to the elements of the first element group The group attribute determines the modification suggestion for the video to be detected, which includes the modification suggestion for the first element group.

With reference to some embodiments of the second aspect, in some embodiments, the modification suggestion of the first element group includes at least one of: pass, can not be processed, crop, smear, delete frame, and blur.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: The elements of a base element that make up an element group.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to perform: determine the relationship between the first element in the first image frame and the The first element similarity of the first element in the second image frame, the element similarity is used to indicate the similarity between the element images; it is determined that the first element similarity is greater than the preset similarity threshold, and the first image frame The first element in and the first element in the second image frame form a first element group.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are further configured to invoke the computer instructions to cause the electronic device to execute: determine that the distance between the first position and the second position is less than a preset The first distance threshold; the first position is the position of the first element in the first image frame in the first image frame, and the second position is the first element in the second image frame in the second image position in the frame.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are further configured to invoke the computer instruction to cause the electronic device to execute: calculate the element group in the video to be detected The completeness is used to indicate whether the element group is complete; the incomplete element group is screened from the element group in the video to be detected, including the first element group, and the completeness of the incomplete element group is incomplete.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are further configured to invoke the computer instructions to cause the electronic device to perform: filter out the element group in the video to be detected The suspected incomplete element group includes the first element group, and the suspected incomplete element group is an element group whose distance between the position and the edge of the screen is less than a preset second distance threshold.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are further configured to invoke the computer instructions to cause the electronic device to perform: calculating the value of the suspected incomplete element group in the video to be detected Integrity, which is used to indicate whether the element group is complete; screen out the incomplete element group from the suspected incomplete element group in the video to be detected, including the first element group, and the integrity of the incomplete element group is incomplete .

With reference to some embodiments of the second aspect, in some embodiments, the element group attribute of the first element group further includes a second incompleteness parameter value, and the second incompleteness parameter value is used to represent the incompleteness type of the first element group, At least one of duration, importance, surrounding element group, and period type.

With reference to some embodiments of the second aspect, in some embodiments, the classification information of the video to be detected includes: the subject of the video to be detected and/or the label of the video to be detected.

With reference to some embodiments of the second aspect, in some embodiments, the one or more processors are further configured to invoke the computer instruction to cause the electronic device to perform: extract frames from the original video to obtain the video to be detected; or , cutting the original video into N videos to be detected; or, after cutting the original video into N intermediate videos, extracting frames from the N intermediate videos to obtain N videos to be detected; N is a positive integer .

In a third aspect, an embodiment of the present application provides a chip system, the chip system is applied to an electronic device, the chip system includes one or more processors, and the processors are configured to invoke computer instructions to cause the electronic device to perform the first Aspects and methods described in any possible implementation of the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer program product containing instructions, when the computer program product is run on an electronic device, the electronic device is made to perform any of the first aspect and any possible implementation manner of the first aspect. method described.

In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions, when the above-mentioned instructions are executed on an electronic device, the above-mentioned electronic device is made to execute the first aspect and any possible implementation manner of the first aspect method described.

It can be understood that the electronic device provided in the second aspect, the chip system provided in the third aspect, the computer program product provided in the fourth aspect, and the computer storage medium provided in the fifth aspect are all used to execute the methods provided by the embodiments of the present application. . Therefore, for the beneficial effects that can be achieved, reference may be made to the beneficial effects in the corresponding method, which will not be repeated here.

Description of drawings

Fig. 1 shows the scene of manual review video in the prior art;

2 to 6 are schematic diagrams of a group of exemplary user interfaces in the embodiments of the present application;

FIG. 7 is a schematic flowchart of a method for evaluating video image content integrity in an embodiment of the present application;

FIG. 8 is an exemplary schematic diagram of video cutting in an embodiment of the present application;

FIG. 9 is an exemplary schematic diagram of a non-adaptive frame extraction method in an embodiment of the present application;

10 is an exemplary schematic diagram of an adaptive frame extraction method in an embodiment of the present application;

11 is an exemplary schematic diagram of the original video being cut and framed in the embodiment of the application;

FIG. 12 and FIG. 13 are an exemplary schematic diagram of element detection in a single image frame in an embodiment of the present application;

14 is a schematic diagram of an exemplary scenario for acquiring an element group in an embodiment of the present application;

15 is a schematic diagram of another exemplary scenario for acquiring an element group in an embodiment of the present application;

FIG. 16 is an exemplary schematic diagram of a completeness judgment result of an element group in an embodiment of the present application;

17 is an exemplary schematic structural diagram of an element group affecting a picture integrity rule in an embodiment of the present application;

FIG. 18 is an exemplary schematic diagram of the effect of element groups on picture integrity in an embodiment of the present application;

19 is an exemplary schematic diagram of a BP neural network model in an embodiment of the application;

FIG. 20 is a schematic diagram of the architecture of the modification suggestion generation model in the embodiment of the present application;

21 is a schematic diagram of a modification suggestion of an original video picture output by a modification suggestion generation model in an embodiment of the present application;

FIG. 22 is a schematic structural diagram of an electronic device 100 provided by an embodiment of the present application;

23 is a schematic block diagram of a software structure of the electronic device 100 in the embodiment of the present invention;

FIG. 24 is another schematic diagram of the hardware structure of the electronic device 200 provided by the embodiment of the present application.

Detailed ways

The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations of the present application. As used in the specification of this application and the appended claims, the singular expressions "a," "an," "the," "above," "the," and "the" are intended to also include Plural expressions unless the context clearly dictates otherwise. It will also be understood that, as used in this application, the term "and/or" refers to and includes any and all possible combinations of one or more of the listed items.

Hereinafter, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as implying or implying relative importance or implying the number of indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, unless otherwise specified, the "multiple" The meaning is two or more.

For ease of understanding, related terms and related concepts involved in the embodiments of the present application are first introduced below:

(1) Elements and element types:

In this embodiment of the present application, an element is a basic element in an image frame that can carry or transmit visual information. An image frame is the smallest unit that makes up a video.

In some embodiments of the present application, the elements may include the main body, accompanying body, text, etc. in the image frame presentation screen. Among them, the subject is the main object that the video producer or the user pays attention to during the shooting process. In general, the subject is mostly a single object or a group of objects. For example, the subject can be a person, an animal, a plant, or even an abstract object; The body is the secondary focus of the video producer or user during the shooting process, and the body is the object used as a foil. In general, the body is mostly multiple independent objects. For example, the body can be living objects, buildings, Art, places of interest, etc.

In this embodiment of the present application, the element type is used to distinguish the classification of elements conveying different types of visual information.

In some embodiments of the present application, the element types may include people (skin color recognition such as Caucasian, yellow, black), human faces (male, female, old, young, etc.), text, other later texts, subtitles , copyright signs, station logos, watermarks, plant subjects (identifying plant species such as dandelions, chrysanthemums, etc.), animal subjects (identifying specific animal species such as dogs, cats, camels, etc.), landscape subjects, etc.

Exemplarily, if the element type of the A element is text, it means that the A element is the element to be photographed; if the B element is a subtitle, it means that the B element is a text subtitle added later after the video is shot, and its position is mostly located at the bottom of the video. And centered; if the C element is other post-processing text, it means that the C element is the text added later after the video is shot, but the position is different from the subtitle position.

Specifically, in the embodiment of the present application, the elements contained in the image frame can be obtained by performing data processing on the image frame, or performing image processing on the picture presented by the image frame, such as element detection. Exemplarily, as shown in Figures 12 to 13, image processing (element detection) is performed on the picture presented by the image frame to obtain the elements contained in the picture presented by the image frame, wherein the detected elements include: 1301 text 1, 1302 Icon 1, 1303 Animal 1, 1304 Food 1, 1305 Text 2. At the same time, the element type to which each detected element belongs can be identified. The identification results include: 1301 text 1 belongs to other later texts, 1302 icons belong to copyright signs, 1303 animal 1 belongs to animals (dogs), 1304 food 1 belongs to food, 1305 text 2 belongs to subtitle.

When the elements contained in the image frame are obtained, the element attributes of the elements can be obtained. The element attribute of an element is used to quantify the relationship between the elements, the relationship between the element and the video picture, and the like. The element attribute of an element can include many parameters, such as the position of the element, the degree of incompleteness of the element, and so on.

(2) Element group:

2.1. Definition of element group:

In this embodiment of the present application, the same or the same elements in multiple image frames of the video may be formed into an element group. It is understood that the type of the element group is the same as the element type of the elements in the element group.

When a video producer or user shoots a video, or when the video producer or user performs post-processing on the captured video, the video is affected by montage, mirror movement, transition and other shooting or editing techniques, so that only the The angle analysis of the completeness of elements cannot effectively reflect the completeness of the video content. Element groups are defined taking into account the spatiotemporal integrity properties of elements in the video.

Wherein, the element group includes: firstly, there are several image frames in a time sequence relationship, wherein several image frames may be continuous or discontinuous; secondly, the same element D exists in at least two image frames in the above-mentioned several image frames, The element D may be complete or incomplete; finally, the D-Group element group is a set of D elements in at least two image frames.

2.2, element group attributes:

The element group attribute of the element group contains the corresponding relationship between the parameters used to represent the characteristics of the element group and the parameter values of the corresponding parameters. For example, the element group attribute of the element group can include many parameters: the area occupied by the element group, the position of the element group, the incomplete ratio of the element group, the incomplete type of the element group, the duration of the element group, the importance of the element group, the element group The surrounding element group of the group, the period type of the element group, etc.

Exemplarily, as shown in Table 1 below, it is a schematic example of an element group attribute in this embodiment of the present application:

Table 1

As shown in Table 1, the element group attribute of the first element group includes a parameter value of incompleteness ratio of 1/2 and a parameter value of duration of 10 seconds.

It can be understood that the element group attribute of the element group may also have many other representations, such as an array, a matrix, etc., which are not limited here.

The element group attribute of an element group is related to the element attributes of the elements in the element group. The element group attribute of the element group is used to quantify the relationship between the element groups, the relationship between the element group and the video picture, and the like.

In some embodiments of the present application, the parameters included in the attribute of the element group may be the same as the parameters in the preset rule for affecting the picture integrity of the element group. The electronic device can determine whether the element group contributes to the content integrity of the video image by comparing the parameter value of the parameter in the element group attribute of an element group with the threshold or reference value of the parameter in the preset element group affecting picture integrity rule. influential. For details, reference may be made to the description in (4) Preset element group affects picture integrity, which will not be repeated here.

2.3. Determination of element group:

The element group type of the element group is the same as the element type of the elements in the element group, and has the same meaning expression.

In the embodiment of the present application, there may be many ways to obtain the same element D from at least two image frames, and form the same element D in different image frames into a D-Group element group, for example, using element similarity to obtain the element group, Obtain element groups through clustering algorithms, etc. The following uses the element similarity to obtain the element group as an example to introduce the method of obtaining the element group:

Obtain element groups using element similarity: Extract image features of all elements in all image frames through image processing algorithms or data processing algorithms. An element is arbitrarily selected as the reference element, and the similarity between the image feature of the reference element and the image feature of the compared element is calculated. When the similarity exceeds a preset threshold, the reference element and the compared element are considered to be the same element. Among them, the element similarity is: the distance between the image features between the reference element and the compared element, where the distance has various forms, including cosine distance, Euclidean distance, Manhattan distance, etc.

In the embodiments of the present application, there are many ways to select the elements to be compared. For example, the selection method of the compared element may be: traversing and selecting elements in an image frame different from the image frame where the reference element is located as the compared element; or traversing and selecting elements in an image frame different from the image frame where the reference element is located, The element with the same element type is used as the element to be compared; or the element with the same element type as the reference element and the element with the position close to the reference element in the image frame different from the reference element are selected by traversal as the element to be compared.

Judging that the position of the reference element is similar to that of the element being compared: a first distance threshold is preset. According to the result of element detection, it can be known that the position of the reference element is the position of the first element, and the position of the element being compared is the position of the second element. Whether the distance between the position of an element and the second element is less than the preset first distance threshold, if the position distance is less than the preset first distance threshold, it is considered that the reference element and the compared element are close in position. The value of the first distance threshold may be related to information such as the frame rate of the video.

Exemplarily, as shown in FIG. 14 , there are three image frames, including a first image frame, a second image frame, and a third image frame. The element 1401A in the first image frame is selected as the reference element, all elements in the second image frame and the third image frame are selected as the compared elements, and the similarity between the reference element and each of the compared elements is calculated. When the element similarity is greater than the preset element similarity threshold of 0.85, it is considered that the reference element 1401A and the compared element are the same element, that is, the reference element 1401A and the compared element belong to the same element group. Among them, the element similarity between the 1401B element of the second image frame and the reference element 1401A is 0.95, and the element similarity between the 1401C element of the third image frame and the reference element 1401A is 0.94. The element similarity is greater than 0.85, so 1401A, 1401B, and 1401C form an element group, which can be recorded as 1401-Group.

(3) The completeness of the element group:

In this embodiment of the present application, the completeness of the element group is used to indicate whether the element group is complete. The value of the completeness of the element group can be a binary value, including complete and incomplete.

In the implementation of this application, the completeness of the element group may be determined in various ways, for example, using a proportional relationship, using a projection feature, etc., which are not limited here.

Exemplarily, as an embodiment of the present application, an optional manner for determining the completeness of an element group using a proportional relationship combined with a projection feature is described below:

Element groups of different element group types may correspond to different preset standard scale intervals and preset suspected standard scale intervals. Wherein, the preset suspected standard proportion interval includes the preset standard proportion interval. For example, the element group type of the element group D-Group is Type-D, the corresponding preset standard scale interval is [0.8 to 1.2], and the corresponding preset suspected standard scale interval is [0.3 to 3].

When the aspect ratio or the aspect ratio of an element group exceeds the preset suspected standard ratio range, it may be determined that the completeness of the element group is incomplete. When the aspect ratio or the aspect ratio of an element group is within the preset standard ratio range, it can be determined that the completeness of the element group is complete.

When the aspect ratio or aspect ratio of an element group exceeds the preset standard scale interval, but is within the preset suspected standard scale interval, the projection characteristics of each element in the element group can be calculated, and the projection characteristics can be counted. Then, the completeness of the element group is determined according to the statistical results. For example, if the aspect ratio of the element group D-Group is 1.5, which is outside the preset standard ratio range [0.8 to 1.2], but within the preset suspected standard ratio range [0.3 to 3], the element group D-Group can be calculated. The projected feature of each element in the Group, and the projected feature distribution curve of the element group D-Group is calculated. By calculating the distance between the projected characteristic distribution curve of the D-Group and the preset threshold curve, when the distance is greater than the threshold distance, the element group D-Group is considered to be incomplete. There are many forms of distance, including Euclidean distance, Manhattan distance, etc.

The characteristic distribution curve can be characterized in the form of histogram statistics. The preset threshold curve corresponds to a complete "ji" glyph, that is, when the histogram of the projection feature of the element group D-Group is a complete "ji" glyph, the integrity of the element group D-Group can be determined as: Complete; if the “several” glyph gap in the histogram of the projected feature of the element group D-Group exceeds the preset statistical threshold, it can be determined that the completeness of the element group D-Group is incomplete.

In some embodiments of the present application, in the process of determining the completeness of the element group, parameters related to the degree of incompleteness of the element group (for example, the proportion of incompleteness, the type of incompleteness) can be directly obtained. In some embodiments of the present application, the degree of incompleteness of the element group may also be determined independently, which is not limited this time.

In some embodiments of the present application, it may be determined according to the integrity of an element group whether to continue to judge whether the element group affects the picture integrity. If the integrity of an element group is complete, it can be directly considered that the element group does not affect the integrity of the picture; if the integrity of an element group is incomplete, it can continue to judge whether the element group affects the integrity of the picture. The result of the effect of the element group on the content of the video screen. For a specific way of judging whether the element group affects the picture integrity, reference may be made to the description in the following (4) Preset rules of the element group affecting picture integrity, which will not be repeated here.

In some embodiments of the present application, element groups located at the edge of the picture may be screened into suspected incomplete element groups according to the positions of the element groups in the picture presented by the image frame, and then the completeness of these suspected incomplete element groups may be determined. In some embodiments of the present application, the completeness of the element group located at the edge of the picture may be directly determined as incomplete according to the position of the element group in the picture presented by the image frame. In some embodiments of the present application, the completeness of all element groups may also be directly determined directly. There is no limitation here.

(4) The preset element group affects the screen integrity rules:

In this embodiment of the present application, the rules for element groups affecting picture integrity are preset, and are used to record thresholds and/or reference values of parameters that affect the integrity of video picture content by element groups of each element group type.

Exemplarily, as shown in FIG. 16 , it is a schematic structural diagram of a rule affecting the screen integrity in this embodiment of the present application. Element Groups Affecting Picture Integrity There are many different types of element groups that can be included in an element group. The element group type is the same as the element type of the element. For example, the element group types may include: people, human faces, texts, other later texts, subtitles, copyright signs, station logos, watermarks, plant subjects, animal subjects, landscape subjects, and the like. The element groups of each element group type may correspond to multiple parameters, for example, the parameters may include: defect ratio, defect type, duration, time period type, importance, surrounding element groups, and the like.

Among them, the incompleteness ratio represents the value of the incompleteness degree of the element group, for example, the value range can be 0-1, the larger the value, the greater the degree of incompleteness; the incompleteness type represents the incompleteness direction of the element group, and the value can be horizontal or vertical, etc.; continuous Time indicates the shortest period of time when the elements in the element group are incomplete and discontinuous; the value of the period type is any period of time within the video duration, and the common values are several seconds after the start of the video and several seconds before the end of the video; the degree of importance is used to indicate The importance of the element group in the video; the surrounding element group is the surrounding element group of the element group.

In the rule of element group affecting picture integrity, different parameters corresponding to the element group type of each element group may include the threshold and/or reference value of the parameter of the element group of the element group type. Exemplarily, the following table 2 is an example of the preset element group affecting the picture integrity rule in the embodiment of the application:

Table 2

For example, in the preset rule of element group affecting picture integrity shown in Table 2, the element group whose element group type is other later texts corresponds to the incomplete ratio, incomplete type, duration, period type, importance, surrounding elements Group these 5 parameters. Among them, the threshold value of the corresponding incomplete ratio parameter is greater than or equal to 1/3, the threshold value of the corresponding duration parameter is greater than or equal to 15 seconds, the reference value of the corresponding incomplete type parameter is horizontal, and the corresponding period type parameter is The reference value is arbitrary, the reference value of the corresponding importance parameter is greater than 3, and the reference value of the corresponding surrounding element group parameter is none. The threshold of the parameter indicates that if the value of the parameter of the element group of the element group type exceeds the threshold, the element group may be judged to affect the integrity of the screen content, and the reference value of the parameter can be used to limit the judgment condition.

In this embodiment of the present application, the electronic device may determine whether the element group has an impact on the integrity of the video picture content according to the acquired parameter values of the element group and the preset element group influence picture integrity rule, that is, determine whether the element group affects the video picture content integrity. screen effect.

It can be understood that there can be many expressions of the result of the influence of the element group on the content integrity of the video image. For example, the result can be a binary value, and the binary value includes: influential, no influence; the result can be It is a multivariate value, and the multivariate value includes: no influence, certain influence, great influence, and influence. For the convenience of explanation, the effect of the element group on the content integrity of the video picture is taken as an example of a binary value, wherein the binary value includes: the element group affects the integrity of the picture content, and the element group does not affect the integrity of the picture. .

It can be understood that, according to different actual requirements, the parameters in the preset element group affecting the picture integrity rule may be more or less, which is not limited here.

Exemplarily, the following Table 3 is another example of the rule that the preset element group affects the picture integrity in the embodiment of the present application.

table 3

The preset element group effects shown in Table 3 only include the threshold of the incompleteness ratio parameter in the picture integrity rule. Among them, the threshold value of the incomplete ratio parameter corresponding to the element group whose element group type is other later text is greater than or equal to 1/3, which means that for an element group whose element group type is other later text in a video, if the incomplete ratio exceeds 1/3 , it can be determined that the element group will affect the integrity of the screen content. If its incomplete ratio does not exceed 1/3, it can be determined that the element group will not affect the integrity of the screen content.

Exemplarily, the following Table 4 is another example of the rule that the preset element group affects the picture integrity in the embodiment of the present application.

Table 4

The preset element group influence picture integrity rule shown in Table 4 includes the threshold value of the incomplete ratio parameter and the threshold value of the duration parameter. Among them, the threshold value of the incomplete ratio parameter corresponding to the element group whose element group type is other late text is greater than or equal to 1/3, and the threshold value of the duration parameter is greater than or equal to 15 seconds. For an element group in a video whose element group type is other later text, if its incomplete ratio exceeds 1/3 and the duration is greater than or equal to 15 seconds, it can be determined that the element group will affect the integrity of the picture content. In the same way, if the defect ratio does not exceed 1/3, regardless of its duration, it can be determined that the element group will not affect the integrity of the video content; if its duration is less than 15 seconds, no matter what the defect ratio is, It can be determined that the element group will not affect the integrity of the video image content.

Exemplarily, the following Table 5 is another example of the rule that the preset element group affects the picture integrity in the embodiment of the present application.

table 5

The preset element group influence picture integrity rule shown in Table 5 includes two parameter thresholds and one parameter reference value, wherein the parameter thresholds are the threshold value of the defect ratio parameter, the threshold value of the duration parameter, the defect type parameter reference value. Among them, the threshold value of the incomplete ratio parameter corresponding to the element group type of other later texts is greater than or equal to 1/3, the threshold value of the duration parameter is greater than or equal to 15 seconds, and the incomplete type is horizontal. For an element group whose type is other later text in a video, if its defect type is horizontal, and the defect ratio exceeds 1/3, and the duration is greater than or equal to 15 seconds, it can be determined that the element group will affect the integrity of the picture content; If the defect type is not horizontal, it can be determined that the element group will not affect the integrity of the screen content.

Exemplarily, the following Table 6 is another example of the rule that the preset element group affects the picture integrity in the embodiment of the present application.

There are two groups of rules for the element group of the same element type in the preset element group influence picture integrity rules shown in Table 6, wherein each group of rules respectively includes the same type of thresholds of two parameters and a reference value of one parameter , denoted as Rule 1 and Rule 2, respectively. The threshold value of the parameter is the threshold value of the defect proportion and the threshold value of the duration, and the reference value of the parameter is the reference value of the defect type.

When the defect type parameter of the element group is horizontal, to determine whether the element affects the picture integrity, it is necessary to refer to the parameter thresholds in rule 1: the threshold value of the defect ratio parameter is greater than or equal to 1/3, and the threshold value of the duration parameter is greater than or equal to 15 seconds ; When the incomplete type parameter is vertical, determine whether the element affects the picture integrity. Refer to the threshold of the parameter in rule 2: the threshold of the incomplete ratio parameter is greater than or equal to 1/5, and the threshold of the duration parameter is greater than or equal to 10 seconds.

Table 6

For the element group whose element group type is other late text, when its incomplete type is horizontal, its incomplete ratio is greater than or equal to 1/3, and its duration is greater than or equal to 15 seconds, it can be determined that the element group will affect the integrity of the screen content ; When the defect type is horizontal, the defect ratio is less than 1/3 or the duration is less than 15 seconds, it can be determined that the element group will not affect the integrity of the screen content.

For an element group whose elements are similar to other later texts, when the defect type is vertical, the defect ratio is greater than or equal to 1/3, and the duration is greater than or equal to 15 seconds, it can be determined that the element group will affect the integrity of the screen content; when When the defect type is vertical, the defect ratio is less than 1/3 or the duration is less than 15 seconds, it can be determined that the element group will not affect the integrity of the screen content.

Exemplarily, the preset element group influence picture integrity rule shown in Table 2 above includes reference values of two parameters and thresholds of multiple parameters. The values are the reference value of the incomplete type, the reference value of the period type, the reference value of the importance degree, and the reference value of the surrounding element group. Among them, when the incomplete type of the element group whose element type is other late text is horizontal, the importance degree is greater than 3, the incomplete ratio exceeds 1/3, and the duration is greater than or equal to 15 seconds, it can be determined that the element group affects the picture integrity; if it is important If the degree is less than or equal to 3, it can be determined that the element group does not affect the integrity of the picture; if the defect type is vertical, it can be determined that the element group does not affect the integrity of the picture.

It can be understood that, the preset rule for affecting the picture integrity of the element group may further include thresholds or reference values of other parameters related to the element group, which are not limited here.

In other embodiments, the element group affecting the picture integrity rule involved in the present application may be expressed as a function, a mapping relationship, or the like.

It is worth noting that the threshold value and/or the reference value of the parameter affected in the element group affecting the picture integrity rule involved in the present application may be derived from the element group attribute of the element group.

(5) Integrity judgment model:

In this embodiment of the present application, the integrity judgment model is used to determine whether the picture content of the video is complete.

The input of the integrity judgment model may include: the influence result of the element group on the content of the video picture. The output of the integrity judgment model includes: complete video image content and incomplete video image content.

The integrity judgment model is a model constructed by using machine learning methods or deep learning methods in the field of artificial intelligence. The model is done based on the training data. The label of the training data is that the content of the video image is complete or the content of the video image is incomplete.

It can be understood that the input of the integrity judgment model may also include many other data. For example, in some embodiments of the present application, the input of the integrity judgment model may also include element groups; in some embodiments of the present application , the input of the completeness judgment model may further include video classification information; in some embodiments of the present application, the input of the completeness judgment model may also include the element group attribute of the element group. There is no limitation here.

There are various ways to obtain video classification information. For example, the classification information of the video can be obtained according to the subject of the video; the classification information of the video can be obtained according to the information such as the column and division of the video selected by the user or the video producer when uploading the video; the classification information of the video can be obtained according to the name of the video ; It can predict the classification information of videos based on the historical upload records of users or video producers, user portraits and other information. This is not limited. The classification information of the video can be animals, numbers, people, daily life, food, etc.

(6) Scoring model:

In the embodiment of the present application, the scoring model is used to determine the scoring of the completeness of the picture content of the video.

The input of the scoring model includes: the effect of the element group on the content of the video image. The output of the scoring model is a score for the completeness of the video's picture content.

It can be understood that the input of the scoring model may also include many other data. For example, in some embodiments of the present application, the input of the integrity judgment model may also include element groups; in some embodiments of the present application, The input of the completeness judgment model may further include video classification information; in some embodiments of the present application, the input of the completeness judgment model may further include the element group attribute of the element group. There is no limitation here.

It can be understood that, when the content integrity of the video picture is scored, the classification information of the video may be considered. For example, when the classification information for the video is digital, element groups such as digital products, subtitles, and post-text texts have a greater impact on the content integrity score of the video, while when the classification information for the video is characters, elements such as characters The group has a greater impact on the score of the completeness of the video picture content.

The scoring model may be a model constructed by using the BP neural network model in the field of artificial intelligence. The model is done based on the training data. The training data is the first incomplete parameter group, element group attributes, etc. of the element group extracted from the video, and the label of the training data is the score of the content integrity of the video image. The schematic diagram of the model of the BP neural network is shown in Figure 18.

In this embodiment of the present application, the scoring model may be a model constructed by using other machine learning methods or other deep learning methods in the field of artificial intelligence.

(7) Modify the proposed generation model:

In the embodiment of the present application, the modification suggestion generation model is used to determine the modification suggestion of the picture content of the video.

The input for modifying the proposed generation model includes: whether the element group affects the screen integrity, and the element group attribute of the element group. The output of the scoring model is a suggestion for modifying the completeness of the video's picture content. Among them, the modification proposal includes the modification proposal for the element group. Wherein, the modification suggestion can be presented in the form of an audit report, and the audit report includes: the modification suggestion of the element group. The audit report can also include: Element group attributes for the element group.

It can be understood that the input of the modification suggestion generation model may also include many other data. For example, in some embodiments of the present application, the input of the integrity judgment model may also include element groups; in some embodiments of the present application , the input of the integrity judgment model may also include video classification information. There is no limitation here.

The modification suggestions for the element group include: no suggestion (Suggest), optional processing (Pass), clipping (Cut), smearing (Cover), frame deletion (Delete), blur (Blur) and so on. Among them, can not process (Pass) means that the element group will not affect the integrity of the video picture content; cut (Cut) means that the video edge can be cropped according to the height or width of the element group bounding box; smear (Cover) means that it can be covered by other icons. cover the element group; Delete means that the content integrity of the video picture can be improved by deleting the image frame; Blur means that the element group can be blurred by mosaic and Gaussian blur to improve the integrity of the video picture content.

The modification suggestion generation model may be a model constructed by using a decision tree algorithm in the field of artificial intelligence. The schematic diagram of the decision tree algorithm is shown in Figure 18. As shown in FIG. 18 , the node attribute of the decision tree can be derived from the element group attribute, and the node attribute of the decision tree can also be derived from the reference value and/or the threshold value of the element group affecting the picture integrity rule. The node attributes of the decision tree can also be derived from the classification information of the video.

In this embodiment of the present application, the modification suggestion generation model may be a model constructed by using other machine learning methods or other deep learning methods in the field of artificial intelligence.

In some embodiments of the present application, the input of the above (5) completeness judgment model, (6) scoring model, and (7) modification suggestion generation model may include the element group attribute of the element group, but not the element group to the video picture. Content affects results. The electronic device can directly determine the evaluation result of the picture content of the video according to the element group attribute of the element group: for example, whether it is complete or scored, without first determining the influence result of the element group on the video picture content. There is no limitation here.

The following first introduces a scenario of manually reviewing a video in the prior art.

Fig. 1 shows a scene of manual review of videos in the prior art.

As shown in Figure 1, the current industry-provided way of reviewing the content integrity of video images is mainly manual review. When reviewing videos, video reviewers often use methods such as double-speed browsing, skipping frames, etc., which are easy to miss or ignore video image frames that do not meet the video review specifications. Secondly, when video reviewers are reviewing videos, they need to manually browse the content of the video, which is limited by the working time and video duration, resulting in the efficiency of manual review being far from meeting the needs of video review. Third, different video reviewers have different specific evaluation criteria when reviewing videos, and they cannot give guidance for targeted revisions, which reduces the effectiveness of video review and is not conducive to maintaining the ecosystem of original video content.

In view of the above-mentioned problems existing in the field of current video review, the present application provides a method and electronic device for evaluating the content integrity of a video image. The video image content integrity evaluation method and electronic device provided in this application can automatically review videos uploaded by video producers, give an evaluation result of whether the video image content is complete, and improve the efficiency of video review; further, the video images provided in this application The content integrity evaluation method and the electronic device can give a score of the video image integrity; further, the video image content integrity evaluation method and electronic device provided by the present application can provide guidance for targeted modification of the video.

It can be understood that, the electronic device in the embodiment of the present application may implement the method for evaluating the integrity of the video image content in the embodiment of the present application by running the system for evaluating the integrity of the video image content.

2 to 6 are schematic diagrams of a group of exemplary user interfaces in the embodiments of the present application.

As shown in Figure 2, the user or video producer can upload the original video to be reviewed to the video image content integrity evaluation system. Optionally, when uploading the original video, the user or video producer can upload the classification information of the original video to the video image content integrity evaluation system at the same time.

As shown in FIG. 3 and FIG. 4 , after the user or video producer uploads the original video to be reviewed to the video image content integrity evaluation system in the electronic device, the electronic device will display the review result of the original video. The review results include: the content of the video screen is complete or the content of the video screen is incomplete. The method for evaluating the integrity of the video image content of the original video by the electronic device in the embodiment of the present application is shown in FIG. 7 .

As shown in FIG. 5 , optionally, after reviewing the original video, the electronic device will give a completeness score for the completeness of the image content of the original video, and the completeness score is used to evaluate the completeness of the original video image content. The video producer or user can understand the integrity of the original video more accurately through the integrity score, which helps the video producer or user to improve the quality of the original video created.

As shown in FIG. 6 , optionally, after reviewing the original video, the system will issue a review report for the element group that affects the integrity of the picture content of the original video. The audit report includes: the element group that affects the picture content of the original video, the position of the element group in the original video, the duration and first appearance time of the element group in the original video, the importance of the element group in the original video, the Recommendations for modification of element groups, etc. Among them, the modification suggestions include: passing, clipping, masking, smearing, blurring, deleting frames, etc. This system reviews the original video and gives corresponding revision opinions according to the completeness of the original video's screen content. The revision opinions are presented in the form of review reports, which can effectively help video producers or users to modify the original video. , to improve the picture content integrity of the original video.

The following introduces the method and electronic device for evaluating the integrity of video image content provided by the present application.

FIG. 7 is a schematic flowchart of a method for evaluating the content integrity of a video image according to an embodiment of the present application.

It should be noted that the video to be detected may be the original video, the first video or the second video in this application.

S701 and S7021 are for video processing, and image frames can be obtained. S7022 and S7023 are the steps of acquiring the element group. In S7024 and S7025, the incomplete element group is obtained by screening. S7026 is to calculate the element group attribute of the element group. S7027 is to calculate whether the element group affects the picture integrity. S703 is to generate a result of evaluating the integrity of the video image content.

S701: Cut the original video to obtain N segments of the first video.

After the electronic device receives the video uploaded from the video generator or the user and is awaiting completeness review, the electronic device regards the video as the original video and processes the original video, wherein the processing process includes: cutting. The cutting operation specifically includes: dividing the original video into N video segments according to the time length of the original video, video transition points and other information, where N is a positive integer greater than or equal to 1. When N is equal to 1, the original video is not cut at this time, and the first video is the original video. When N is greater than 1, the original video is cut at this time, and N segments of the first video are obtained after cutting.

It can be understood that, on the one hand, the original video is cut into N segments of the first video, and the subsequent integrity evaluation processing is performed on the N segments of the first video, which can make full use of the parallel computing capability of the electronic device and improve the computing efficiency; On the one hand, when cutting the original video according to the transition points and other information of the video, the influence of montage, mirror movement, transition and other shooting or editing techniques on the temporal and spatial integrity of the element group (element) is fully considered, which effectively improves the performance of the original video. The accuracy of the electronic device's assessment of the integrity of the video image content.

In some embodiments, the electronic device receives video classification information uploaded by the video producer or user when receiving the video uploaded from the video producer or the user awaiting completeness review, where the classification information includes the subject name of the video, the Video tags, etc.

In some embodiments, when the electronic device receives a video uploaded from a video generator or a user and is awaiting completeness review, the electronic device may obtain classification information of the video through an image processing algorithm.

FIG. 8 is an exemplary schematic diagram of video cutting in an embodiment of the present application.

As shown in FIG. 8 , the original video is cut into three video segments, which are a first video 1, a first video 2, and a first video 3, respectively.

In some embodiments, when there is no transition point information in the original video, the original video may be cut according to the length of the video, or the video may not be cut (in the case where N is equal to 1). For example, if the original video is 10 minutes and 30 seconds long, and there is no transition point information in the original video, the original video can be cut into three first videos of equal duration, where each first video is 210 seconds long.

In some embodiments, the duration or duration range of the first video after cutting the original video may be pre-specified. For example, the length of the first video is set to be 3 minutes. When the length of the original video is 10 minutes and 30 seconds, the original video can be divided into four segments. The first segment of the first video is 0 to 3 minutes, and the second segment of the first video 3 to 6 minutes, the third first video is 6 to 9 minutes, and the fourth first video is 9 minutes to 10 minutes and 30 seconds.

In some embodiments, overlapping parts may be used between the multiple segments of the first video after cutting the original video.

In some embodiments, when there is transition point information in the original video, the video may be preferentially cut according to the transition point information. Further, at least a piece of intermediate video is obtained after preliminarily cutting the video according to the transition point information, and the first video can be obtained by cutting the intermediate video again according to the video duration of the intermediate video.

After obtaining the N first videos, the electronic device may perform step S702 on all the N first videos or a part of the N first videos.

S702: including sequentially executed steps S7021, S7022, S7023, S7024, S7025, S7026, and S7027. Steps S7021 and S7024 are optional steps that do not affect the integrity of the solution.

S7021: extracting frames from the first video to obtain the second video.

After obtaining the first video, the electronic device extracts frames from the first video, and the video data after the frame extraction is recorded as the second video.

The frame extraction operation specifically includes: non-adaptive frame extraction and adaptive frame extraction, and the object of frame extraction is the first video; non-adaptive frame extraction specifically includes: a fixed time interval or frame interval for the extraction of frames. The object extracts an image frame; the adaptive frame extraction specifically includes: dynamically adjusting the time interval or time interval between the extracted next image frame and the current image frame according to the data difference (picture difference) between the current image frame and the next extracted image frame frame interval.

It can be understood that, by extracting frames from the first video, the number of image frames in the second video that needs to be processed in subsequent steps is reduced, and the calculation amount of the electronic device is reduced.

FIG. 9 is an exemplary schematic diagram of a non-adaptive frame extraction method in an embodiment of the present application.

As shown in Figure 9, if the L1 frame of the first video is used as the first frame of the frame to be extracted, and the frame interval of the frame extraction is set to L2, then the frame of the first frame is the L1+(Ith frame of the first video. -1)*(L2+1) frames. For example, in the case of L1=1, L2=2, the number of frames to be extracted is 1, 4, 7, . . . According to the original video frame rate, non-adaptive frame extraction can be achieved by setting the frame extraction interval.

In some embodiments, the frame rate may be 1 frame per second.

FIG. 10 is an exemplary schematic diagram of an adaptive frame extraction method in an embodiment of the present application.

As shown in FIG. 10 , the adaptive frame extraction includes: adaptively adjusting the frame extraction interval according to the data gap (picture gap) between the image frames of the first video. For example, the first frame of the first video is selected as the first frame of the extracted frame, and the frame is used as the reference frame to calculate the data gap between the subsequent frame and the reference frame. When comparing the second frame to the fourth frame, the data gap does not exceed the threshold; when comparing the fifth frame, the data gap between the image frame of the fifth frame and the image frame of the first frame is greater than the preset threshold, select the first The image frame of 5 frames is used as the second frame of the extracted frame. At this time, the fifth frame is selected as the reference frame, which is used to calculate the data gap between the subsequent frame and the reference frame, and then the seventh frame is selected as the third frame of the extracted frame. Therefore, the electronic device selects the first, fifth, and seventh image frames as the second video through adaptive frame extraction.

In the adaptive frame sampling method, the data gap is the Euclidean distance, absolute value distance, Chebyshev distance, etc. between the image frames of the two frames; the data gap in the adaptive frame sampling method is the picture content presented by the two image frames. (image content), where this gap can be obtained by an image-like matching algorithm.

FIG. 11 is an exemplary schematic diagram of an original video being cut and framed in an embodiment of the present application.

As shown in FIG. 11 , after the original video is cut and framed, a second video 1, a second video 2, and a second video 3 are obtained, which are respectively used for subsequent processing.

In some embodiments, the original video may be directly used as the second video for subsequent processing without cutting and/or frame extraction.

In some embodiments, the original video may only undergo a cutting operation for subsequent processing as the second video.

In some embodiments, the original video may be processed only as the second video after frame extraction.

It should be noted that step S7021 may not be executed, and the second video is the first video at this time.

Wherein S7022: Detect elements in each image frame in the second video.

Traverse each image frame in the second video data, and when any image frame is traversed, perform element detection on the image frame. After the element detection is performed on the image frame, the elements contained in the image frame, the element type of the element, and the element attribute of the element are obtained. The element attributes of the element include: the position of the element, etc.

For the definition of elements and element types, reference may be made to the above term explanation (1) content of elements and element types, and details are not repeated here.

Element detection includes: text detection, face detection, subject detection, icon detection, watermark detection, QR code detection, etc. Subject detection includes: dish identification, fruit and vegetable identification, animal identification, plant identification, vehicle identification, etc. In some embodiments, the position of the element occupying the screen may be represented by the coordinates of a rectangular marquee, wherein the range of the element may be based on the range selected by the rectangular marquee.

It can be understood that there are certain limitations in judging the content integrity of the original video picture by the integrity of the elements in a single image frame. Elements have spatiotemporal integrity attributes in the original video. When the video producer or user creates the original video by shooting and editing methods such as montage, mirror movement, switching animation, etc., the content of the original video is judged by the integrity of the element group within a single image frame. The integrity of the effect is poor.

FIG. 12 and FIG. 13 are an exemplary schematic diagram of element detection in a single image frame in an embodiment of the present application.

For example, there are more than one image frame in the second video. Through traversal, element detection is performed on all the image frames to obtain the elements appearing in the picture content corresponding to the image frames, the attributes of the elements, and the like. As shown in FIG. 12 , an image frame is selected for element detection, including character detection, two-dimensional code detection, and subject detection, respectively. Element detection is performed on the image frame shown in Figure 12, wherein, using text detection, the detected elements include: 1301 text 1 - "original video 1", 1305 text 2 - "dog is a good friend of human beings"; use a two-dimensional code Detection, no element is detected; using subject detection, the detected elements include: 1303 animal 1-dog, 1304 food 1-dog food; using icon detection, the detected elements include: 1302 icon - "HUAWEI HUAWE".

Further get the element type to which the element belongs, 1301 text 1-"original video 1" belongs to other later texts, 1302 icon-"HUAWEI" belongs to copyright marks, 1303 animal 1 belongs to animals, 1304 food 1 belongs to food, 1305 text 2-" Dogs are man's best friend" belongs to the subtitles.

After text detection, two-dimensional code detection, subject detection, and icon detection are performed on the image frame, the detection result of the image frame is shown in FIG. 13 . In this image frame, all elements can be selected with a rectangular marquee box, and the attributes of the elements and the element type to which the element belongs are known.

S7023: Select at least two image frames in the second video to obtain an element group.

At least two image frames in the second video data are selected, and element groups are obtained by means of element similarity, clustering algorithm, or the like. When acquiring the element group, you can also acquire some element group attributes of the element group, such as the element group position, etc. at the same time.

For the element group, the selection method, the definition of element similarity, and the method for calculating element similarity, reference may be made to the content of the above term explanation (2) element group, which will not be repeated here.

Wherein, obtaining the element group by using the clustering algorithm includes: after superimposing the image frames of the selected frame, by using the clustering algorithm on the superimposed image frame, the result of the clustering is the grouping result of the element group.

In some embodiments, when using a clustering algorithm such as the K-means algorithm, the number of clusters in the clustering algorithm, that is, the number of element groups, may be pre-determined according to the element detection result in step S7022 and the image frame of the selected frame.

It can be understood that the element group retains the spatiotemporal integrity of the elements in the video, and can be used as a basic unit for judging the integrity of the video image content.

FIG. 14 is a schematic diagram of an exemplary scenario for acquiring an element group in an embodiment of the present application.

As shown in FIG. 14 , after the second video data is obtained, the second video data includes three image frames. Wherein, after the element detection in S7022 is performed in each image frame, the detected element in each image frame can be selected by a dotted rectangle.

There are three existing image frames, including the first image frame, the second image frame, and the third image frame, and the element 1401A in the first image frame is selected as the reference element, and all elements in the second image frame and the third image frame are selected as the reference element. For the elements being compared, calculate the similarity between the reference element and each element being compared. When the element similarity is greater than the preset element similarity threshold of 0.85, it is considered that the reference element 1401A and the compared element are the same element, that is, the reference element 1401A and the compared element belong to the same element group. Among them, the element similarity between the 1401B element of the second image frame and the reference element 1401A is 0.95, and the element similarity between the 1401C element of the third image frame and the reference element 1401A is 0.94. The element similarity is greater than 0.85, so 1401A, 1401B, and 1401C form an element group, which can be recorded as 1401-Group-"original video 1". Similarly, element groups 1402-Group-"HUAWEI", 1403-Group-dog, 1404-Group-dog food, 1405-Group-"Dogs are good friends of human beings" can be obtained, and the process of obtaining element groups is no longer Repeat.

FIG. 15 is a schematic diagram of another exemplary scenario for acquiring an element group in an embodiment of the present application.

As shown in FIG. 15 , after the second video data is obtained, the second video data includes three image frames. Wherein, after the element detection in step S7022 is performed in each image frame, the detected element in each image frame can be selected by a dotted rectangle.

The three image frames are superimposed, and after superposition, the clustering algorithm that determines the number of clusters is used, and the number of clusters is specified as 5, and the element group is obtained. Element groups include: 1401-Group-"Original Video 1", 1402-Group-"Huawei HUAWE", 1403-Group-Dog, 1404-Group-Dog Food, 1405-Group-"Dogs are good friends of human beings".

Wherein S7024: Obtain a suspected incomplete element group according to the element group position.

When the position of the element group is close to and covers the edge of the video, the element group can be considered as a suspected incomplete element group.

If the distance between the position of the element group and the border of the video frame is smaller than the preset second distance threshold, it is considered that the position of the element group is close to and covers the edge of the frame.

According to the position of the element obtained in step S7022 and the element group to which the element belongs determined in step S7023, the position of the element group can be obtained. The position of an element group is the range occupied by the union of all elements belonging to the element group. The position of the element group can be expressed in various forms. For example, the range can be based on the range selected by the rectangular marquee, which is specifically expressed as a set of four-dimensional coordinates (x, y, h, w), where (x, y) is The coordinates of the upper left corner of the rectangular marquee, the coordinates take the lower left corner of the screen as the origin, the x-axis direction is from left to right, the y-axis direction is from bottom to top, h is the height of the rectangular marquee, and w is the width of the rectangular marquee . According to x and h, it can be calculated whether the element group is close to and covers the edge of the video in the x-axis (horizontal) direction; according to y and w, it can be calculated whether the element group is close to and covers the video screen in the y-axis (vertical) direction edge.

Exemplarily, for example, if the picture of the second video is a rectangle, its height is H, its width is W, and the preset second distance threshold is threshold1. If there is an element group, and the coordinates of the element group are (x1, y1, h1, w1), the boundary between the element group and the video picture is threshold2=min{min{abs(y1-h1),abs(H- y1)}, min{abs(W-x1-w1),x1}}, where min represents the minimum value, and abs represents the absolute value. When threshold2 is less than or equal to threshold1, it can be considered that the element group is close to and covers the edge of the video, and the element group can be considered as a suspected incomplete element group; when threshold2 is greater than threshold1, the element group can not be considered as a suspected incomplete element group element group.

As shown in Figure 14 and Figure 15, the suspected incomplete element groups include: 1401-Group-"Original Video 1", 1402-Group-"Huawei HUAWE", 1405-Group-"Dogs are good friends of human beings".

It should be noted that step S7024 may not be performed, that is, the element group may not be filtered, and at this time, the suspected incomplete element group is all the element groups.

It can be understood that, by screening suspected incomplete element groups, the number of processed element groups in subsequent steps is further reduced, and the amount of calculation is reduced.

S7025: Judge the completeness of the suspected incomplete element group, and obtain the incomplete element group

For the process of judging the completeness of the suspected incomplete element group, reference may be made to the content in the above term explanation (3) Integrity of the element group, which will not be repeated here.

When the completeness of the suspected incomplete element group is complete, the suspected incomplete element group is a complete element group; when the completeness of the suspected incomplete element group is incomplete, the suspected incomplete element group is a incomplete element group.

It is worth noting that step S7025 may not be executed, in this case, all suspected defective element groups are defective element groups.

It can be understood that the integrity of the element group is different from the integrity of the element. The integrity of the element group is a measurement parameter for whether the element group affects the integrity of the video image content under the consideration of the temporal and spatial integrity of the element group. That is, the complete element group is an element group that does not affect the integrity of the video picture content, and the incomplete element group is an element group that may affect the integrity of the video picture content.

In some embodiments, in the process of calculating the completeness of the suspected incomplete element group, the incompleteness ratio parameter of the element group may be calculated. For example, the degree of incompleteness of the element group can be calculated according to the distance between the proportional relationship of the element group and the preset proportional relationship threshold; the distance between the proportional relationship of the element group, the projected feature and the preset proportional relationship, and the projected feature threshold can be calculated and obtained. The degree of fragmentation of the element group. Among them, the degree of disability includes the proportion of disability and so on.

FIG. 16 is an exemplary schematic diagram of a completeness determination result of an element group in an embodiment of the present application.

As shown in Figure 16, after obtaining the element group type to which the element group belongs, the results obtained by further judging the degree of incompleteness through projection features, proportional relationships, etc. include: 403-Group-dog element group complete, 1404-Group-dog food element group Complete, 1405-Group-"Dogs are good friends of human beings" element group is incomplete, 1401-Group-"Original video 1" element group is incomplete, 1402-Group-"Huawei HUAWE" element group is incomplete.

Wherein S7026: Calculate the element group attribute of the incomplete element group.

According to the element group type to which the incomplete element group belongs, the element group attribute of each incomplete element group is determined respectively, wherein the element group attribute of the incomplete element group includes at least one first incomplete parameter value. The first incomplete parameter value is used to represent the incomplete ratio of the element group. The element group attribute of the incomplete element group may further include a second incomplete parameter value, a third incomplete parameter value, etc., which are used to indicate the type of the defect, the duration, the period type, the degree of importance, the surrounding element group, and the like.

The first incomplete parameter value can be represented in various forms, the first incomplete parameter value may be a numerical value, and the first incomplete parameter value may be a vector or a row in a matrix or a column in a matrix, etc., which are not limited here.

Exemplarily, when the first incompleteness parameter value is a column in a matrix, the first incompleteness parameter value is used to indicate the degree of incompleteness of any element in the element group in the image frame corresponding to the element. The process of calculating the degree of incompleteness includes: calculating the degree of incompleteness of elements using proportional relations, projection features, etc. Further, the defect ratio of the element group can be determined through the first defect parameter.

For example, when the second video is a video of M image frames, and image frames of all frames are selected when acquiring the element group, in this case, the attribute of the element group D-Group can be represented as a matrix of M columns. Wherein, at least one column of data in the matrix contains the degree of incompleteness of elements in the incomplete element group, which is the value of the first incompleteness parameter of the element group D-Group. When the data in the third column of the matrix represents the value of the first incomplete parameter of the element group D-Group, the data in the third column and the first row at this time represents the incomplete element of the first image frame in the second video in the element group D-Group degree. The incomplete ratio of D-Group is obtained according to the value of the first incomplete parameter of D-Group.

Exemplarily, when the expression form of the first incompleteness parameter is a numerical value, the value of the first incompleteness parameter is the proportion of the incompleteness of the element group.

According to the completeness of the elements in the incomplete element group on each image frame in the second video, the second incomplete parameter value in the second incomplete parameter group of each incomplete element group is respectively determined, wherein the second incomplete parameter value may include: duration , period type, surrounding element group, incomplete type, importance, etc.

Taking the duration as an example, the duration is the shortest period of time with discontinuities in which the elements of the incomplete element group appear incomplete in the second video. For any incomplete element group, you can use the code 1 to indicate incompleteness, 0 to indicate completeness, -1 to indicate that it does not appear, and the completeness of each frame (one frame per second) where the element appears can be expressed as: (30 bits in total) 000001100001111100001111110 -1-1-1, then the element group appearance time is 30 seconds, and the shortest incomplete time with discontinuity is 21 seconds, then the value of the duration in the second incomplete parameter value in the first incomplete parameter group of the incomplete element group is the value of 21 seconds. There can be various methods to define whether the element group in the element group is incomplete, complete, or not appearing in the frame of occurrence. When the degree value is greater than the preset incomplete degree threshold, the element is considered to be incomplete in the frame; if the incomplete degree value of a certain frame is the default value, it is considered that the element does not appear in the frame; When setting the threshold for the degree of incompleteness, the element is considered complete in the image frame. Alternatively, in step S7022, when the electronic device performs element detection on the image frame, when obtaining the element, it simultaneously detects whether the obtained element appears and whether the obtained element is complete if it appears.

The degree of importance is related to the element group type to which the element group belongs and the area occupied by the element group; the defect type is related to the proportional relationship of the element group. The values of the defect type include: horizontal defect and vertical defect; the positions of surrounding element groups and all element groups Relevant; the period type is a preset value, and the value of the period type can be 20 seconds after the video starts (before the end of the video), 20 seconds after the transition point (before the transition point), etc.

S7027: Calculate the result of the influence of the incomplete element group on the content of the video picture.

According to the element group attribute of the incomplete element group obtained in S7026 and the preset element group influencing picture integrity rule, the influence result of the element group on the video picture content can be determined, wherein the result includes: the incomplete element group affects the integrity of the video picture content. The degree and incomplete element group do not affect the integrity of the video picture.

For the rules of element group affecting picture integrity and determining the impact result of incomplete element group on video picture content, please refer to the above term explanation (4) Preset rules of element group affecting picture integrity, which will not be repeated here.

FIG. 17 is a schematic structural diagram of an exemplary structure of an element group affecting a picture integrity rule in an embodiment of the present application. As shown in FIG. 17 , element groups of different element group types, corresponding to at least one element group, affect the picture integrity rule.

The rule that the element group affects the picture integrity may also have other expressions, for example, the rule that the element group affects the picture integrity may be presented through the evaluation function f1. The reference value and the threshold value in the rules of the element group affecting the picture integrity are represented as the mapping relationship between the input and the output of the evaluation function f1. The input of the evaluation function f1 is the element group attribute of the incomplete element group, and the output is that the element group affects the content integrity of the video picture or the element group does not affect the video picture content integrity.

FIG. 18 is an exemplary schematic diagram of an effect result of an element group on picture integrity in an embodiment of the present application. As shown in FIG. 18 , taking the element group of other later text 1401-Group-“Original Video 1” as an example, its incompleteness degree is 0.15, its duration is 30s, and its importance degree is 5. Therefore, the output of the integrity evaluation function f1 of the element group of other later texts 1401-Group-"Original Video 1" is: This element group affects the picture content integrity of the original video. Similarly, the element group 1402-Group-"HUAWEI HUAWE" The output of the integrity evaluation function f1 is: the element group affects the picture content integrity of the original video; the output of the integrity evaluation function f1 of the element group 1403-Group- is: the element group does not affect the picture content integrity of the original video ; The output of the integrity evaluation function f1 of the element group 1404-Group-dog food is: the element group does not affect the integrity of the original video content; the integrity evaluation of the element group 1405-Group-“dogs are good friends of human beings” The output of the function f1 is: the element group does not affect the picture content integrity of the original video.

S703: Obtain the content integrity evaluation result of the original video image.

It can be understood that, when the original video is cut into N segments of the first video after step S701 is executed, N groups of data will be output after step S702 is executed, wherein each group of data includes: incomplete element group, incomplete element group. Influence results on the content of the video screen, element group attributes of the incomplete element group.

In this embodiment of the present application, the content integrity evaluation result of the original video image may be obtained according to N groups of data, or the image content integrity evaluation result of the second video may be obtained according to a group of data, and the original video content integrity evaluation result may be determined according to the N groups of image content integrity evaluation results. The content integrity evaluation result of the video image is not limited here.

In the embodiment of the present application, according to the result of the influence of the incomplete element group on the content of the video picture, there can be many specific ways to obtain the evaluation result of the integrity of the original video picture content:

(1) According to the effect of the incomplete element group on the content of the video picture, obtain whether the content of the original video picture is complete;

The integrity judgment model can be used to judge whether the content of the original video is complete, and notify the user or video producer of the result.

For the definition of the integrity judgment model, the construction and training of the integrity model, reference may be made to the above term explanation (5) Integrity judgment model, which will not be repeated here.

This application does not limit the input parameters of the integrity judgment model, and the input of the integrity judgment model can be other image features and data features without creative efforts by those skilled in the art. Such as the combination, linear superposition, non-linear superposition, etc. of the parameters in the element group attributes, or other parameters used to express the degree of incompleteness of the element group, or other parameters used to express the position of the element group, the area occupied by the element group, etc.

The representation of the integrity judgment model can also be a function or a mapping relationship. Taking the function f2 as an example, the picture integrity evaluation function f2 is a many-to-two function relationship. The input is the effect of the incomplete element group on the video picture content, and the incomplete element group. The output includes: the original video picture content is complete, the original video Screen content is incomplete. The mapping relationship from the input to the output of the function f2 can be: there is at least one incomplete element group in the input that affects the integrity of the video picture content, then the output is that the original video picture content is incomplete; 50% or more of the input (affecting the video picture content) The incomplete element group of the content integrity (number of incomplete element groups/number of element groups) affects the integrity of the video picture content, and the output is the incomplete picture content of the original video.

It is understandable that the integrity judgment model can quickly judge whether the content of the original video is complete, realize automatic machine review, and improve the review efficiency.

(2) According to the influence result of the incomplete element group on the video picture content and the classification information of the original video, obtain the score of the integrity of the original video picture content;

The content integrity score of the original video picture can be determined through the scoring model, and the result is notified to the user or the video producer.

For the definition of the scoring model, the construction and training of the scoring model, reference may be made to the above term explanation (6) Scoring model, which will not be repeated here. The scoring model may be a model constructed by using the BP neural network model in the field of artificial intelligence.

FIG. 19 is an exemplary schematic diagram of a BP neural network model in an embodiment of the present application.

As shown in Figure 19, the BP neural network model includes: an input layer, a hidden layer, and an output layer.

The present application does not limit the input parameters of the scoring model, and the input of the scoring model can be other image features and data features without creative efforts by those skilled in the art. Such as the combination, linear superposition, non-linear superposition, etc. of the parameters in the attribute of the element group, or other parameters used to express the degree of incompleteness of the element group, or used to express the position of the element group, the position of the element group, the area occupied by the element group, etc. Other parameters.

It is understandable that the scoring model can quantify the content integrity of the original video, which can more effectively distinguish original videos of different integrity, which is helpful for video producers or users to have a more comprehensive understanding of the integrity of the original video.

(3) According to the influence result of the incomplete element group on the content of the video picture and the element group attribute of the incomplete element group, the modification suggestion of the content integrity of the original video picture is obtained.

For the definition of the modification suggestion generation model, the construction and training of the modification suggestion generation model, you can refer to the above term explanation (7) Modification suggestion generation model, which will not be repeated here. The modification suggestion generation model may be a model constructed by using a decision tree algorithm.

The selection of node attributes in the decision tree algorithm is related to the parameters in the element group attribute of the element group. Or, the selection of node attributes in the decision tree algorithm is related to the threshold and/or reference value in the preset element group affecting the picture integrity rule.

The parameters in the element group attribute of the element group, the threshold value and/or the reference value in the element group influence picture integrity rule are the node attributes with high gain and high purity, which can effectively improve the robustness, accuracy, and reliability of the decision tree algorithm. accuracy, etc.

It is understandable that, when the video producer or user receives the modification suggestion provided by the electronic device, they can modify the original video in a targeted manner according to the content of the modification suggestion, so as to improve the picture content integrity of the original video. Among them, the form of revision suggestion can be an audit report.

This application does not limit the input parameters or node parameters of the modification suggestion generation model. Without creative work by those skilled in the art, the input of the modification suggestion generation model or the selection of node parameters in the decision tree algorithm can be other image features, data characteristics. Such as the combination, linear superposition, non-linear superposition, etc. of the parameters in the attribute of the element group, or other parameters used to express the degree of incompleteness of the element group, or used to express the position of the element group, the position of the element group, the area occupied by the element group, etc. Other parameters.

FIG. 20 is a schematic structural diagram of a modification suggestion generation model in an embodiment of the present application.

As shown in Figure 20, parameters such as the area occupied by the incomplete element group, duration, importance, degree of incompleteness, etc. can be selected as node attributes, and a decision tree algorithm is used to construct and train a modification suggestion generation model.

Exemplarily, when any incomplete element group is input into the modification suggestion generation model constructed and trained by using the decision tree algorithm: when the area of the element group is less than 5% of the video frame, and the degree of incompleteness of the element group is less than 1/ 3. The output of the modified proposed generation model for the incomplete element group is: can not be processed (Pass); when the area of the element group is less than 5% of the video screen, and the degree of incompleteness of the element group is greater than 1/3, and the element If the duration of the group is less than 15 seconds, this modification suggests that the output of the defective element group of the generated model is: Pass); when the area of the element group is less than 5% of the video screen, and the degree of incompleteness of the element group is greater than 1/3, and the duration of the element group is greater than 15 seconds and less than 30 seconds, this modification suggests that the output of the incomplete element group of the generated model is: Cut; when the area of the element group is less than 5 of the video screen %, and the incompleteness of the element group is greater than 1/3, and the duration of the element group is greater than 30 seconds, this modification suggests that the output of the incomplete element group of the generated model is: smear (Cover); The area is between 5% of the video frame and 50% of the video frame, and the duration is less than 1 second. This modification suggests that the output of the incomplete element group of the generated model is: Pass); when the area of the element group is Between 5% of the video frame and 50% of the video frame, and the duration is less than 1 second, and the degree of importance is less than or equal to 3, this modification suggests that the output of the incomplete element group of the generated model is: smear (Cover); when The area of the element group is between 5% of the video frame and 50% of the video frame, and the duration is less than 1 second, and the degree of importance is greater than 3. This modification suggests that the output of the incomplete element group of the generation model is: Cut (Cut); when the area of the element group is greater than 50% of the video frame, the modification suggests that the output of the incomplete element group of the generation model is: Cut (Cut).

FIG. 21 is a schematic diagram of an original video picture modification suggestion output by a modification suggestion generation model in an embodiment of the present application.

As shown in Figure 21, the picture modification suggestion of the original video includes: element group, element group type of the element group, start time of the element group, duration of the element group, position of the element group, and modification suggestion of the element group. For example, the modification suggestion for 1401-Group-“Original Video 1” element group is Cut; the modification suggestion for 1402-Group-“HUAWEI HUAWE” element group is Smear (Cover); 1403-Group-Dog element group modification The suggestion is to not process (Pass); the modification suggestion of 1404-Group-dog food element group is to not process (Pass); the modification suggestion of 1405-Group-“dogs are good friends of human beings” element group is to cut (Cut).

It is worth noting that a method for evaluating the integrity of video screen content involved in this application can be run on an offline electronic device or an electronic device in the cloud; wherein, the offline electronic device can be a video producer or user. On the local networked or non-networked electronic devices, such as computers, mobile terminals, etc.; the electronic devices in the cloud can be the cloud server of the video review system.

The electronic device in this embodiment of the present application may be a mobile electronic device or a PC, which is not limited here. Exemplarily, FIG. 22 is a schematic structural diagram of an electronic device 100 provided by an embodiment of the present application.

The embodiment will be described in detail below by taking the electronic device 100 as an example. It should be understood that the electronic device 100 may have more or fewer components than those shown in the figures, may combine two or more components, or may have different component configurations. The various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.

The electronic device 100 may include: a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charge management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2. Mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, buttons 190, motor 191, indicator 192, camera 193, display screen 194 and Subscriber identification module (SIM) card interface 195 and the like. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light. Sensor 180L, bone conduction sensor 180M, etc.

It can be understood that, the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 100 . In other embodiments of the present application, the electronic device 100 may include more or less components than shown, or combine some components, or separate some components, or arrange different components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor ( image signal processor, ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and/or neural-network processing unit (NPU), etc. . Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

The controller may be the nerve center and command center of the electronic device 100 . The controller can generate an operation control signal according to the instruction operation code and timing signal, and complete the control of fetching and executing instructions.

A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in processor 110 is cache memory. This memory may hold instructions or data that have just been used or recycled by the processor 110 . If the processor 110 needs to use the instruction or data again, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby increasing the efficiency of the system.

In some embodiments, the processor 110 may include one or more interfaces. The interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuitsound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver (universal asynchronous receiver) interface /transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and/or Universal serial bus (universal serial bus, USB) interface, etc.

The I2C interface is a bidirectional synchronous serial bus that includes a serial data line (SDA) and a serial clock line (SCL). In some embodiments, the processor 110 may contain multiple sets of I2C buses. The processor 110 can be respectively coupled to the touch sensor 180K, the charger, the flash, the camera 193 and the like through different I2C bus interfaces. For example, the processor 110 may couple the touch sensor 180K through the I2C interface, so that the processor 110 and the touch sensor 180K communicate with each other through the I2C bus interface, so as to realize the touch function of the electronic device 100 .

The I2S interface can be used for audio communication. In some embodiments, the processor 110 may contain multiple sets of I2S buses. The processor 110 may be coupled with the audio module 170 through an I2S bus to implement communication between the processor 110 and the audio module 170 . In some embodiments, the audio module 170 can transmit audio signals to the wireless communication module 160 through the I2S interface, so as to realize the function of answering calls through a Bluetooth headset.

The PCM interface can also be used for audio communications, sampling, quantizing and encoding analog signals. In some embodiments, the audio module 170 and the wireless communication module 160 may be coupled through a PCM bus interface. In some embodiments, the audio module 170 can also transmit audio signals to the wireless communication module 160 through the PCM interface, so as to realize the function of answering calls through the Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.

The UART interface is a universal serial data bus used for asynchronous communication. The bus may be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, a UART interface is typically used to connect the processor 110 with the wireless communication module 160 . For example, the processor 110 communicates with the Bluetooth module in the wireless communication module 160 through the UART interface to implement the Bluetooth function. In some embodiments, the audio module 170 can transmit audio signals to the wireless communication module 160 through the UART interface, so as to realize the function of playing music through the Bluetooth headset.

The MIPI interface can be used to connect the processor 110 with peripheral devices such as the display screen 194 and the camera 193 . The MIPI interface includes a camera serial interface (camera serial interface, CSI), a display serial interface (displayserial interface, DSI), and the like. In some embodiments, the processor 110 communicates with the camera 193 through a CSI interface, so as to realize the photographing function of the electronic device 100 . The processor 110 communicates with the display screen 194 through the DSI interface to implement the display function of the electronic device 100 .

The GPIO interface can be configured by software. The GPIO interface can be configured as a control signal or as a data signal. In some embodiments, the GPIO interface may be used to connect the processor 110 with the camera 193, the display screen 194, the wireless communication module 160, the audio module 170, the sensor module 180, and the like. The GPIO interface can also be configured as I2C interface, I2S interface, UART interface, MIPI interface, etc.

The SIM interface can be used to communicate with the SIM card interface 195 to realize the function of transferring data to the SIM card or reading data in the SIM card.

The USB interface 130 is an interface that conforms to the USB standard specification, and may specifically be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like. The USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transmit data between the electronic device 100 and peripheral devices. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices.

It can be understood that the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration, and does not constitute a structural limitation of the electronic device 100 . In other embodiments of the present application, the electronic device 100 may also adopt different interface connection manners in the foregoing embodiments, or a combination of multiple interface connection manners.

The charging management module 140 is used to receive charging input from the charger. The charger may be a wireless charger or a wired charger.

The power management module 141 is used for connecting the battery 142 , the charging management module 140 and the processor 110 . The power management module 141 receives input from the battery 142 and/or the charging management module 140 and supplies power to the processor 110 , the internal memory 121 , the external memory, the display screen 194 , the camera 193 , and the wireless communication module 160 .

The wireless communication function of the electronic device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modulation and demodulation processor, the baseband processor, and the like.

Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, the antenna 1 can be multiplexed as a diversity antenna of the wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 150 may provide wireless communication solutions including 2G/3G/4G/5G etc. applied on the electronic device 100 . The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA) and the like. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and then turn it into an electromagnetic wave for radiation through the antenna 1 . In some embodiments, at least part of the functional modules of the mobile communication module 150 may be provided in the processor 110 . In some embodiments, at least part of the functional modules of the mobile communication module 150 may be provided in the same device as at least part of the modules of the processor 110 .

The modem processor may include a modulator and a demodulator. Wherein, the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. The low frequency baseband signal is processed by the baseband processor and passed to the application processor. The application processor outputs sound signals through audio devices (not limited to the speaker 170A, the receiver 170B, etc.), or displays images or videos through the display screen 194 . In some embodiments, the modem processor may be a stand-alone device. In other embodiments, the modem processor may be independent of the processor 110, and may be provided in the same device as the mobile communication module 150 or other functional modules.

The wireless communication module 160 can provide wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), and global navigation satellite systems applied on the electronic device 100 . (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 . The wireless communication module 160 can also receive the signal to be sent from the processor 110 , perform frequency modulation on it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2 .

In some embodiments, the antenna 1 of the electronic device 100 is coupled with the mobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code Wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM , and/or IR technology, etc. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou satellite navigation system (BDS), a quasi-zenith satellite system (quasi- zenith satellite system, QZSS) and/or satellite based augmentation systems (SBAS).

The electronic device 100 implements a display function through a GPU, a display screen 194, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

Display screen 194 is used to display images, videos, and the like. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (active-matrix organic light-emitting diode). , AMOLED), flexible light-emitting diodes (flex light-emitting diodes, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diodes (quantum dot light emitting diodes, QLED) and so on. In some embodiments, the electronic device 100 may include one or N display screens 194 , where N is a positive integer greater than one.

The electronic device 100 may implement a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, an application processor, and the like.

The ISP is used to process the data fed back by the camera 193 . For example, when taking a photo, the shutter is opened, the light is transmitted to the camera photosensitive element through the lens, the light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on image noise, brightness, and skin tone. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP may be provided in the camera 193 .

Camera 193 is used to capture still images or video. The object is projected through the lens to generate an optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other formats of image signals. In some embodiments, the electronic device 100 may include 1 or N cameras 193 , where N is a positive integer greater than 1.

A digital signal processor is used to process digital signals, in addition to processing digital image signals, it can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy and so on.

Video codecs are used to compress or decompress digital video. The electronic device 100 may support one or more video codecs. In this way, the electronic device 100 can play or record videos in various encoding formats, for example, moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.

The NPU is a neural-network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transfer mode between neurons in the human brain, it can quickly process the input information, and can continuously learn by itself. Applications such as intelligent cognition of the electronic device 100 can be implemented through the NPU, such as image recognition, face recognition, speech recognition, text understanding, and the like.

The internal memory 121 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM).

Random access memory may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous Dynamic random access memory (double data rate synchronous dynamic random access memory, DDR SDRAM, such as fifth-generation DDR SDRAM is generally called DDR5 SDRAM), etc.;

Non-volatile memory may include magnetic disk storage devices, flash memory.

Flash memory can be divided into NOR FLASH, NAND FLASH, 3D NAND FLASH, etc. according to the operation principle, and can include single-level memory cell (SLC), multi-level memory cell (multi-level memory cell, SLC) according to the level of storage cell potential. cell, MLC), triple-level cell (TLC), quad-level cell (QLC), etc., according to storage specifications, it can include universal flash storage (English: universal flash storage, UFS), Embedded multimedia memory card (embedded multi media Card, eMMC) and so on.

The random access memory can be directly read and written by the processor 110, and can be used to store executable programs (eg, machine instructions) of an operating system or other running programs, and can also be used to store data of users and application programs.

The non-volatile memory can also store executable programs and store data of user and application programs, etc., and can be loaded into the random access memory in advance for the processor 110 to directly read and write.

The external memory interface 120 can be used to connect an external non-volatile memory, so as to expand the storage capacity of the electronic device 100 . The external non-volatile memory communicates with the processor 110 through the external memory interface 120 to realize the data storage function. For example, save music, video, etc. files in external non-volatile memory.

The electronic device 100 may implement audio functions through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, an application processor, and the like. Such as music playback, recording, etc.

The audio module 170 is used for converting digital audio information into analog audio signal output, and also for converting analog audio input into digital audio signal. Audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be provided in the processor 110 , or some functional modules of the audio module 170 may be provided in the processor 110 .

Speaker 170A, also referred to as a "speaker", is used to convert audio electrical signals into sound signals. The electronic device 100 can listen to music through the speaker 170A, or listen to a hands-free call.

The receiver 170B, also referred to as "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 answers a call or a voice message, the voice can be answered by placing the receiver 170B close to the human ear.

The microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can make a sound by approaching the microphone 170C through a human mouth, and input the sound signal into the microphone 170C. The electronic device 100 may be provided with at least one microphone 170C. In other embodiments, the electronic device 100 may be provided with two microphones 170C, which can implement a noise reduction function in addition to collecting sound signals. In other embodiments, the electronic device 100 may further be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and implement directional recording functions.

The earphone jack 170D is used to connect wired earphones. The earphone port 170D may be the USB port 130 or a 3.5mm open mobile terminal platform (OMTP) standard port, a cellular telecommunications industry association of the USA (CTIA) standard port.

The pressure sensor 180A is used to sense pressure signals, and can convert the pressure signals into electrical signals. In some embodiments, the pressure sensor 180A may be provided on the display screen 194 . There are many types of pressure sensors 180A, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, and the like. The capacitive pressure sensor may be comprised of at least two parallel plates of conductive material. When a force is applied to the pressure sensor 180A, the capacitance between the electrodes changes. The electronic device 100 determines the intensity of the pressure according to the change in capacitance. When a touch operation acts on the display screen 194, the electronic device 100 detects the intensity of the touch operation according to the pressure sensor 180A. The electronic device 100 may also calculate the touched position according to the detection signal of the pressure sensor 180A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities may correspond to different operation instructions. For example, when a touch operation whose intensity is less than the first pressure threshold acts on the short message application icon, the instruction for viewing the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, the instruction to create a new short message is executed.

The gyro sensor 180B may be used to determine the motion attitude of the electronic device 100 . In some embodiments, the angular velocity of electronic device 100 about three axes (ie, x, y, and z axes) may be determined by gyro sensor 180B. The gyro sensor 180B can be used for image stabilization. Exemplarily, when the shutter is pressed, the gyro sensor 180B detects the shaking angle of the electronic device 100, calculates the distance that the lens module needs to compensate according to the angle, and allows the lens to offset the shaking of the electronic device 100 through reverse motion to achieve anti-shake. The gyro sensor 180B can also be used for navigation and somatosensory game scenarios.

The air pressure sensor 180C is used to measure air pressure. In some embodiments, the electronic device 100 calculates the altitude through the air pressure value measured by the air pressure sensor 180C to assist in positioning and navigation.

The magnetic sensor 180D includes a Hall sensor. The electronic device 100 can detect the opening and closing of the flip holster using the magnetic sensor 180D. In some embodiments, when the electronic device 100 is a flip machine, the electronic device 100 can detect the opening and closing of the flip according to the magnetic sensor 180D. Further, according to the detected opening and closing state of the leather case or the opening and closing state of the flip cover, characteristics such as automatic unlocking of the flip cover are set.

The acceleration sensor 180E can detect the magnitude of the acceleration of the electronic device 100 in various directions (generally three axes). The magnitude and direction of gravity can be detected when the electronic device 100 is stationary. It can also be used to identify the posture of electronic devices, and can be used in applications such as horizontal and vertical screen switching, pedometers, etc.

Distance sensor 180F for measuring distance. The electronic device 100 can measure the distance through infrared or laser. In some embodiments, when shooting a scene, the electronic device 100 can use the distance sensor 180F to measure the distance to achieve fast focusing.

Proximity light sensor 180G may include, for example, light emitting diodes (LEDs) and light detectors, such as photodiodes. The light emitting diodes may be infrared light emitting diodes. The electronic device 100 emits infrared light to the outside through the light emitting diode. Electronic device 100 uses photodiodes to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near the electronic device 100 . When insufficient reflected light is detected, the electronic device 100 may determine that there is no object near the electronic device 100 . The electronic device 100 can use the proximity light sensor 180G to detect that the user holds the electronic device 100 close to the ear to talk, so as to automatically turn off the screen to save power. Proximity light sensor 180G can also be used in holster mode, pocket mode automatically unlocks and locks the screen.

The ambient light sensor 180L is used to sense ambient light brightness. The electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. The ambient light sensor 180L can also be used to automatically adjust the white balance when taking pictures. The ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether the electronic device 100 is in a pocket, so as to prevent accidental touch.

The fingerprint sensor 180H is used to collect fingerprints. The electronic device 100 can use the collected fingerprint characteristics to realize fingerprint unlocking, accessing application locks, taking pictures with fingerprints, answering incoming calls with fingerprints, and the like.

The temperature sensor 180J is used to detect the temperature. In some embodiments, the electronic device 100 uses the temperature detected by the temperature sensor 180J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 180J exceeds a threshold value, the electronic device 100 reduces the performance of the processor located near the temperature sensor 180J in order to reduce power consumption and implement thermal protection. In other embodiments, when the temperature is lower than another threshold, the electronic device 100 heats the battery 142 to avoid abnormal shutdown of the electronic device 100 caused by the low temperature. In some other embodiments, when the temperature is lower than another threshold, the electronic device 100 boosts the output voltage of the battery 142 to avoid abnormal shutdown caused by low temperature.

Touch sensor 180K, also called "touch panel". The touch sensor 180K may be disposed on the display screen 194 , and the touch sensor 180K and the display screen 194 form a touch screen, also called a “touch screen”. The touch sensor 180K is used to detect a touch operation on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to touch operations may be provided through display screen 194 . In other embodiments, the touch sensor 180K may also be disposed on the surface of the electronic device 100 , which is different from the location where the display screen 194 is located.

The keys 190 include a power-on key, a volume key, and the like. Keys 190 may be mechanical keys. It can also be a touch key. The electronic device 100 may receive key inputs and generate key signal inputs related to user settings and function control of the electronic device 100 .

Motor 191 can generate vibrating cues. The motor 191 can be used for vibrating alerts for incoming calls, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, playing audio, etc.) can correspond to different vibration feedback effects. The motor 191 can also correspond to different vibration feedback effects for touch operations on different areas of the display screen 194 . Different application scenarios (for example: time reminder, receiving information, alarm clock, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

The indicator 192 can be an indicator light, which can be used to indicate the charging state, the change of the power, and can also be used to indicate a message, a missed call, a notification, and the like.

The SIM card interface 195 is used to connect a SIM card. The SIM card can be contacted and separated from the electronic device 100 by inserting into the SIM card interface 195 or pulling out from the SIM card interface 195 . The electronic device 100 may support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM card, Micro SIM card, SIM card and so on. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the plurality of cards may be the same or different. The SIM card interface 195 can also be compatible with different types of SIM cards. The SIM card interface 195 is also compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to realize functions such as call and data communication.

In the embodiment of the present application, the processor 110 may call the computer instruction stored in the internal memory 121 to cause the electronic device 100 to execute the method for evaluating the integrity of the video image content in the embodiment of the present application.

FIG. 23 is a schematic block diagram of a software structure of the electronic device 100 in the embodiment of the present invention.

The layered architecture divides the software into several layers, and each layer has a clear role and division of labor. Layers communicate with each other through software interfaces. In some embodiments, the system is divided into four layers, from top to bottom, the application layer, the application framework layer, the runtime and system libraries, and the kernel layer.

The application layer can include a series of application packages.

As shown in FIG. 23 , the application package may include camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message and other applications (also referred to as applications).

In this embodiment of the present application, the application layer may further include a video evaluation module.

The video evaluation module may be used to execute the method for evaluating the integrity of video image content in the embodiment of the present application.

The application framework layer provides an application programming interface (application programming interface, API) and a programming framework for the applications of the application layer. The application framework layer includes some predefined functions.

As shown in FIG. 23 , the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, a Local Profile Assistant (LPA), and the like.

A window manager is used to manage window programs. The window manager can get the size of the display screen, determine whether there is a status bar, lock the screen, take screenshots, etc.

Content providers are used to store and retrieve data and make these data accessible to applications. The data may include video, images, audio, calls made and received, browsing history and bookmarks, phone book, etc.

The view system includes visual controls, such as controls for displaying text, controls for displaying pictures, and so on. View systems can be used to build applications. A display interface can consist of one or more views. For example, the display interface including the short message notification icon may include a view for displaying text and a view for displaying pictures.

The phone manager is used to provide the communication function of the electronic device 100 . For example, the management of call status (including connecting, hanging up, etc.).

The resource manager provides various resources for the application, such as localization strings, icons, pictures, layout files, video files and so on.

The notification manager enables applications to display notification information in the status bar, which can be used to convey notification-type messages, and can disappear automatically after a brief pause without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also display notifications in the status bar at the top of the system in the form of graphs or scroll bar text, such as notifications from applications running in the background, and can also display notifications on the screen in the form of a dialog interface. For example, text information is prompted in the status bar, a prompt sound is issued, the electronic device vibrates, and the indicator light flashes.

The runtime includes core libraries and virtual machines. The runtime is responsible for the scheduling and management of the Android system.

The core library consists of two parts: one is the functional functions that the java language needs to call, and the other is the core library.

The application layer and the application framework layer run in virtual machines. The virtual machine executes the java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, safety and exception management, and garbage collection.

A system library can include multiple functional modules. For example: surface manager (surface manager), media library (Media Libraries), 3D graphics processing library (eg: OpenGL ES), 2D graphics engine (eg: SGL), etc.

The Surface Manager is used to manage the display subsystem and provides a fusion of two-dimensional (2-Dimensional, 2D) and three-dimensional (3-Dimensional, 3D) layers for multiple applications.

The media library supports playback and recording of a variety of commonly used audio and video formats, as well as still image files. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

2D graphics engine is a drawing engine for 2D drawing.

The kernel layer is the layer between hardware and software. The kernel layer contains at least display drivers, camera drivers, audio drivers, sensor drivers, and virtual card drivers.

Exemplarily, FIG. 24 is a schematic diagram of a hardware structure of an electronic device 200 according to an embodiment of the present application.

The electronic device 200 includes:

An input device 201, an output device 202, a processor 203, and a memory 204 (wherein the number of processors 203 in the electronic device 200 may be one or more, and one processor 203 is taken as an example in FIG. 24). In some embodiments of the present application, the input device 201 , the output device 202 , the processor 203 , and the memory 204 may be connected by a bus or in other ways, wherein the connection by a bus is taken as an example in FIG. 24 .

Wherein, the processor 203 causes the electronic device 200 to execute the method for evaluating the integrity of the video image content in the embodiment of the present application by invoking the operation instruction stored in the memory 204 .

As used in the above embodiments, the term "when" may be interpreted to mean "if" or "after" or "in response to determining..." or "in response to detecting..." depending on the context. Similarly, depending on the context, the phrases "in determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining..." or "in response to determining..." or "on detecting (the stated condition or event)" or "in response to the detection of (the stated condition or event)".

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented in software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. The computer instructions may be stored on or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted over a wire from a website site, computer, server or data center (eg coaxial cable, optical fiber, digital subscriber line) or wireless (eg infrared, wireless, microwave, etc.) to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media integrated. The available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state drives), and the like.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented. The process can be completed by instructing the relevant hardware by a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed , which may include the processes of the foregoing method embodiments. The aforementioned storage medium includes: ROM or random storage memory RAM, magnetic disk or optical disk and other mediums that can store program codes.

Claims (29)

1. a video picture content evaluation method, is characterized in that, comprises: The electronic device identifies elements in at least two image frames in the video to be detected, the at least two image frames include a first image frame and a second image frame, and the elements are basic elements in the image frames; The electronic device determines, according to the identified elements, an element group in the video to be detected, which includes a first element group, and the first element group includes the first element and the second element in the first image frame the first element in the image frame; The electronic device determines an element group attribute of the first element group, where the element group attribute of the first element group includes a first incomplete parameter value, and the first incomplete parameter value is used to represent the value of the first element group. degree of disability; The electronic device determines, at least according to the element group attribute of the first element group, a picture content evaluation result of the video to be detected. 2. The method according to claim 1, wherein the electronic device determines, at least according to the element group attribute of the first element group, a picture content evaluation result of the video to be detected, specifically comprising: The electronic device determines, according to the element group attribute of the first element group, an effect result of the first element group on the content of the video image to be detected; The electronic device determines a picture content evaluation result of the to-be-detected video at least according to the effect of the first element group on the to-be-detected video picture content. 3. The method according to claim 2, wherein the electronic device determines, according to the element group attribute of the first element group, an effect result of the first element group on the content of the video image to be detected, Specifically include: The electronic device determines, according to the element group attribute of the first element group and a preset element group influence picture integrity rule, an influence result of the first element group on the content of the video picture to be detected. 4. The method according to claim 2 or 3, wherein the electronic device determines the picture content of the to-be-detected video at least according to the effect of the first element group on the to-be-detected video picture content Evaluation results, including: The electronic device determines whether the video to be detected is complete at least according to the effect of the first element group on the content of the video to be detected; And/or, the electronic device determines the score of the video to be detected at least according to the effect of the first element group on the content of the video to be detected and the classification information of the video to be detected; And/or, the electronic device determines a modification suggestion for the video to be detected at least according to the effect of the first element group on the content of the video to be detected and the element group attribute of the first element group, including a modification suggestion for the video to be detected. Suggested changes to the first element group. 5. The method according to claim 1, wherein the electronic device determines, at least according to the element group attribute of the first element group, a picture content evaluation result of the video to be detected, specifically comprising: The electronic device determines whether the video to be detected is complete at least according to the element group attribute of the first element group; And/or, the electronic device determines the score of the video to be detected at least according to the element group attribute of the first element group and the classification information of the video to be detected; And/or, the electronic device determines, at least according to the element group attribute of the first element group, a modification suggestion for the video to be detected, which includes a modification suggestion for the first element group. 6 . The method according to claim 4 or 5 , wherein the modification suggestion of the first element group includes at least one of: pass, can not be processed, crop, smear, delete frame, and blur. 7 . 7. The method according to any one of claims 1 to 6, wherein the electronic device determines, according to the identified elements, an element group in the video to be detected, which includes the first element group, specifically include: The electronic device forms an element group with elements representing the same basic element in the at least two image frames identified. 8 . The method according to claim 7 , wherein the electronic device forms an element group with elements representing the same basic element in the at least two image frames identified, including the first element group, 9 . Specifically include: The electronic device determines a first element similarity between the first element in the first image frame and the first element in the second image frame, where the element similarity is used to represent the similarity between element images; The electronic device determines that the similarity of the first element is greater than a preset similarity threshold, and forms a first element group with the first element in the first image frame and the first element in the second image frame. 9. The method according to claim 8, wherein the step of determining the first element similarity between the first element in the first image frame and the first element in the second image frame precedes the step , the method also includes: The electronic device determines that the distance between the first position and the second position is less than a preset first distance threshold; the first position is the position of the first element in the first image frame in the first image frame, The second position is the position of the first element in the second image frame in the second image frame. 10. The method according to any one of claims 1 to 9, wherein the electronic device determines, according to the identified elements, an element group in the video to be detected, including the step of the first element group Afterwards, the method further includes: The electronic device calculates the completeness of the element group in the video to be detected, and the completeness is used to indicate whether the element group is complete; The electronic device selects the incomplete element group from the element groups in the video to be detected, including the first element group, and the integrity of the incomplete element group is incomplete. 11. The method according to any one of claims 1 to 9, wherein the electronic device determines, according to the identified elements, an element group in the video to be detected, including the step of the first element group Afterwards, the method further includes: The electronic device filters out a suspected incomplete element group from the element group in the video to be detected, including the first element group, and the suspected incomplete element group is a position whose distance from the edge of the screen is less than a preset second distance. Threshold element group. 12. The method according to claim 11, wherein after the electronic device selects the suspected incomplete element group from the element group in the video to be detected, the method further comprises: The electronic device calculates the completeness of the suspected incomplete element group in the video to be detected, and the completeness is used to indicate whether the element group is complete; The electronic device selects an incomplete element group from the suspected incomplete element group in the video to be detected, including the first element group, and the integrity of the incomplete element group is incomplete. 13. The method according to any one of claims 1 to 12, wherein the element group attribute of the first element group further comprises a second incomplete parameter value, and the second incomplete parameter value is used to represent the at least one of the defect type, duration, importance level, surrounding element group, and time period type of the first element group. 14. An electronic device, characterized in that the electronic device comprises: one or more processors and a memory; The memory is coupled to the one or more processors for storing computer program code, the computer program code including computer instructions that the one or more processors invoke to cause the Electronic equipment performs: Identifying elements in at least two image frames in the video to be detected, the at least two image frames including a first image frame and a second image frame, and the elements are basic elements in the image frames; According to the identified elements, determine an element group in the video to be detected, which includes a first element group, and the first element group includes the first element in the first image frame and the element in the second image frame the first element; determining an element group attribute of the first element group, where the element group attribute of the first element group includes a first incomplete parameter value, and the first incomplete parameter value is used to indicate the degree of incompleteness of the first element group; At least according to the element group attribute of the first element group, the evaluation result of the picture content of the video to be detected is determined. 15. The electronic device according to claim 14, wherein the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: According to the element group attribute of the first element group, determine the effect result of the first element group on the content of the video image to be detected; Determine the picture content evaluation result of the to-be-detected video at least according to the effect of the first element group on the to-be-detected video picture content. 16. The electronic device according to claim 15, wherein the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: According to the element group attribute of the first element group and the preset element group influence picture integrity rule, the influence result of the first element group on the to-be-detected video picture content is determined. 17. The electronic device according to claim 15 or 16, wherein the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: Determine whether the video to be detected is complete at least according to the effect of the first element group on the content of the video to be detected; And/or, determining the score of the video to be detected at least according to the effect of the first element group on the content of the video to be detected and the classification information of the video to be detected; And/or, at least according to the influence result of the first element group on the content of the video picture to be detected and the element group attribute of the first element group, determine the modification suggestion of the video to be detected, which includes the first element group suggested amendments. 18. The electronic device according to claim 14, wherein the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: At least according to the element group attribute of the first element group, determine whether the video to be detected is complete; And/or, at least according to the element group attribute of the first element group and the classification information of the video to be detected, determine the score of the video to be detected; And/or, at least according to the element group attribute of the first element group, determine the modification suggestion of the video to be detected, which includes the modification suggestion for the first element group. 19. The electronic device according to claim 17 or 18, wherein the modification suggestion of the first element group includes at least one of: pass, can not be processed, crop, smear, delete frame, and blur. 20. The electronic device according to any one of claims 14 to 19, wherein the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: Elements representing the same basic element in the identified at least two image frames are formed into an element group. 21. The electronic device according to claim 20, wherein the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: determining the first element similarity between the first element in the first image frame and the first element in the second image frame, where the element similarity is used to represent the similarity between element images; It is determined that the similarity of the first element is greater than a preset similarity threshold, and the first element in the first image frame and the first element in the second image frame are formed into a first element group. 22. The electronic device according to claim 21, wherein the one or more processors are further configured to invoke the computer instructions to cause the electronic device to execute: It is determined that the distance between the first position and the second position is less than a preset first distance threshold; the first position is the position of the first element in the first image frame in the first image frame, and the second The position is the position of the first element in the second image frame in the second image frame. 23. The electronic device according to any one of claims 14 to 22, wherein the one or more processors are further configured to invoke the computer instructions to cause the electronic device to execute: Calculate the completeness of the element group in the video to be detected, and the completeness is used to indicate whether the element group is complete; An incomplete element group is screened from the element groups in the video to be detected, including the first element group, and the integrity of the incomplete element group is incomplete. 24. The electronic device according to any one of claims 14 to 22, wherein the one or more processors are further configured to invoke the computer instructions to cause the electronic device to execute: A suspected incomplete element group is screened from the element groups in the video to be detected, including the first element group, and the suspected incomplete element group is an element group whose position and the edge of the screen are less than a preset second distance threshold. . 25. The electronic device according to any one of claims 24, wherein the one or more processors are further configured to invoke the computer instructions to cause the electronic device to execute: Calculate the completeness of the suspected incomplete element group in the video to be detected, and the completeness is used to indicate whether the element group is complete; An incomplete element group is screened from the suspected incomplete element group in the video to be detected, including the first element group, and the integrity of the incomplete element group is incomplete. 26. The electronic device according to any one of claims 14 to 25, wherein the element group attribute of the first element group further comprises a second incomplete parameter value, and the second incomplete parameter value is used to represent At least one of the defect type, duration, importance level, surrounding element group, and period type of the first element group. 27. A chip system applied to an electronic device, the chip system comprising one or more processors for invoking computer instructions to cause the electronic device to perform as in claims 1-13 The method of any one. 28. A computer program product comprising instructions, which, when executed on an electronic device, causes the electronic device to perform the method of any one of claims 1-13. 29. A computer-readable storage medium comprising instructions that, when executed on an electronic device, cause the electronic device to perform the method of any one of claims 1-13.

Images