CN115150668B - Video prompt method, device, equipment and computer storage medium - Google Patents

Abstract

The embodiment of the present invention relates to the technical field of computer data processing, and discloses a video prompt method, which includes: determining the behavior heat of each time point according to user behavior data at multiple time points of the video; the behavior heat is used to characterize the user's interest in interactive behavior for the video; determining a target prompt point from the time point according to the behavior heat; the target prompt point includes the time point where the change in the behavior heat meets a preset condition; inserting prompt information at the target prompt point to obtain a processed video; and displaying the processed video. In the above manner, the embodiment of the present invention improves the user experience of video prompts.

Description

Video prompt method, device, equipment and computer storage medium

Technical Field

The embodiments of the present invention relate to the technical field of computer data processing, and in particular to a video prompt method, device, equipment and computer storage medium.

Background technique

When displaying content, reasonable prompts can encourage users to interact, thereby improving user interaction rate and user experience.

The inventors of the present invention discovered during the process of implementing the embodiments of the present invention that the existing video prompt method has the problem of disturbing the user's current viewing behavior and destroying the user's immersive experience.

Summary of the invention

In view of the above problems, an embodiment of the present invention provides a video prompt method, which is used to solve the problem of poor user experience of video prompts in the prior art.

According to one aspect of an embodiment of the present invention, a video prompt method is provided, the method comprising:

Determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video;

Determining a target prompt point from the time points according to the behavior heat; the target prompt point includes the time point at which the change in the behavior heat meets a preset condition;

Inserting prompt information at the target prompt point to obtain a processed video;

The processed video is displayed.

In an optional manner, the method further includes:

Determining an optional prompt point and a corresponding heat change smoothness from the time point according to the behavior heat; the heat change smoothness is used to characterize the severity of the change in the user's behavior heat;

The optional prompt point located at a front preset position after the heat change smoothness is sorted in ascending order is determined as the target prompt point.

In an optional manner, the method further includes:

The time points are arranged in descending order of the heat of the behavior, and the time points preset before arrangement are determined as the optional prompt points.

In an optional manner, the method further includes:

Determining the predicted behavior heat of the optional prompt point;

Determine the relative smoothness error and the absolute smoothness error corresponding to the optional prompt point according to the behavior heat and the predicted behavior heat;

The thermal variation smoothness is determined according to the smoothness relative error and the smoothness absolute error.

In an optional manner, the method further includes:

The predicted behavior heat is obtained by performing a weighted summation process on the actual behavior data volume and the predicted behavior data volume at the previous time point adjacent to the optional prompt point.

In an optional manner, the number of the optional prompt points is multiple; the method further includes:

Determining the difference in the behavior heat between each of the optional prompt points;

When the difference is less than a first threshold, determining the target prompt point from the optional prompt points according to the heat change smoothness;

When the difference is greater than or equal to a second threshold, the target prompt point is determined from the optional prompt points according to the behavior heat at the time point.

In an optional manner, the method further includes:

When the difference is greater than the second threshold, determining the optional prompt point with the largest behavior heat as the heat center point;

The time point adjacent to the heat center point is determined as the target prompt point.

According to another aspect of an embodiment of the present invention, a video prompting device is provided, comprising:

A first determination module is used to determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video;

A second determination module is used to determine a target prompt point from the time points according to the behavior heat; the target prompt point includes the time point when the change of the behavior heat meets a preset condition;

An inserting module, used for inserting prompt information at the target prompt point to obtain a processed video;

A display module is used to display the processed video.

According to another aspect of an embodiment of the present invention, a video prompting device is provided, comprising:

A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of any one of the video prompt methods.

According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a video prompting device to perform the operation of any one of the video prompting methods.

The embodiment of the present invention determines the behavior heat of each time point according to the user behavior data at multiple time points of the video, and characterizes the atmosphere environment of the user watching the video by obtaining the behavior heat of other users when the video is playing, and then determines the change of the behavior heat at each time point according to the behavior heat. The change can be the severity of the change. The more drastic the change of behavior heat, the greater the degree of change of the user's behavior pattern, and there may be a gap in attention, such as from watching the video to posting comments or forwarding and sharing. On the contrary, the less drastic the change of heat, the less the change of the user's behavior amount, that is, the user is more likely to be in immersive viewing; thereby, according to the behavior heat and the change of behavior heat, it is determined from the time point that the change meets the preset conditions. A target prompt point, wherein the preset condition may be that the intensity of the characterization change is less than a certain threshold; finally, the prompt information is inserted at the target prompt point to obtain a processed video; and the processed video is displayed, which is different from the prior art in which prompts are directly given according to the playback progress or playback time, which may interrupt the user's immersive viewing experience, and the prompt time may not best encourage the user to interact according to the prompt. The embodiment of the present invention determines the target prompt point according to the smoothness of the heat change, thereby ensuring that the user's viewing experience is not disturbed, and at the same time reflects the viewing atmosphere of the video through the behavioral heat, and reminds the user in a timely manner according to the atmosphere, thereby increasing the user's enthusiasm for interaction through the herd mentality, thereby improving the overall user experience during video viewing.

The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

FIG1 is a schematic diagram showing a flow chart of a video prompting method provided by an embodiment of the present invention;

FIG2 is a schematic diagram showing a flow chart of a video prompting method provided by yet another embodiment of the present invention;

FIG3 is a schematic diagram showing the relationship between the amount of data and the time point in a video prompt method provided by yet another embodiment of the present invention;

FIG4 is a schematic diagram showing prompt types in a video prompt method provided by yet another embodiment of the present invention;

FIG5 shows a schematic diagram of the structure of a video prompting device provided by an embodiment of the present invention;

FIG. 6 shows a schematic diagram of the structure of a video prompt device provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

FIG1 shows a flow chart of a video prompt method provided by an embodiment of the present invention, and the method is executed by a computer processing device. The computer processing device may include a mobile phone, a laptop computer, etc. As shown in FIG1 , the method includes the following steps:

Step 10: Determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video.

In one embodiment of the present invention, user behavior data corresponds to historical users who watched the video. User behavior data may include data corresponding to various types of behaviors such as user comments, barrage, sharing, liking, forwarding, and @. Behavior heat is used to characterize the user's interest in interactive behaviors at various time points. Specifically, the greater the interest in interactive behaviors, the greater the user's participation in interacting with the video, that is, when the user's interest in interacting is higher, the greater the probability of user behavior, that is, the greater the data volume or frequency of user behavior data.

Therefore, the behavior heat can be determined according to the quantity and/or frequency of user behavior data, such as the number of user comments or the number of bullet comments sent by the user. The behavior heat can also be determined according to the total quantity or average frequency of behavior data of at least two of the aforementioned multiple behavior types.

Step 20: Determine a target prompt point from the time points according to the behavior heat; the target prompt point includes the time point at which the change in the behavior heat meets a preset condition.

In one embodiment of the present invention, in order to ensure that the prompt action at the target prompt point does not interrupt the user's immersive experience, the change in the user's attention can be determined based on the change in the behavior heat. Specifically, the change in the behavior heat can include heat change smoothness, and the heat change smoothness is used to characterize the severity of the change in behavior heat. The greater the heat change smoothness, the less drastic the change in the user's behavior heat, so the user is more likely to be in an immersive viewing process, and the smaller the heat change smoothness, the more likely the user has a shift in interactive interest, that is, switching from one interactive behavior mode to another interactive behavior mode, such as a change in the user's attention. Specifically, the heat change smoothness can be determined based on the changes in the behavioral heat corresponding to each adjacent time point.

Then, the time points are screened according to the smoothness of the heat change, and the time points with relatively small heat change smoothness are determined as the target prompt points. This is because a smaller heat change smoothness indicates that the user has a change in the interactive behavior mode, and his or her attention may be interrupted, so there is a small probability that the user is in an immersive experience. If the user is reminded at this time, it will not interrupt the user's viewing experience, so the user experience is better.

Step 201: Determine an optional prompt point and a corresponding heat change smoothness from the time point according to the behavior heat. The heat change smoothness is used to characterize the severity of the change in the user's behavior heat.

In one embodiment of the present invention, considering that time points with lower behavior heat generally correspond to video frames with lower user attention and interaction interest, prompting at such time points may not effectively promote user interaction. Therefore, time points with behavior heat greater than a preset threshold among all time points may be screened out as optional prompt points, thereby further determining the target time point for actual interaction based on the optional prompt points.

Heat change smoothness is used to characterize the severity of changes in behavior heat. The greater the heat change smoothness, the less drastic the change in user behavior heat, so the user is more likely to be in an immersed viewing process, while the smaller the heat change smoothness, the more likely the user has a shift in interactive interest, that is, from one interactive behavior mode to another, such as a change in user attention. Therefore, the heat change smoothness can be determined based on the changes in behavioral heat corresponding to each adjacent time point.

Step 202: After the heat change smoothness is sorted in ascending order, the optional prompt point located at the front preset position is determined as the target prompt point.

In one embodiment of the present invention, as mentioned above, a smaller heat change smoothness indicates that the user has changed his interactive behavior mode, and his attention may be interrupted, so he is less likely to be in an immersive experience. At this time, if the user is reminded, the user's viewing experience will not be interrupted, so the user experience is better. Therefore, the optional time point before the minimum preset position of the heat change smoothness can be determined as the target prompt point.

In yet another embodiment of the present invention, step 20 further includes:

Step 203: Arrange the time points in descending order of the behavior heat, and determine the time points preset before arrangement as the optional prompt points.

In one embodiment of the present invention, the behavior heat reflects the user's interest in interaction, and the greater the behavior heat, the more enthusiastic the atmosphere of interaction among the user group at that point in time. Therefore, reminding at that point in time can enable the current user to join the public's interactive behavior trend, thereby increasing the user's interaction probability. Driven by joining the interactive behavior trend, the user interaction has a greater probability of receiving feedback from other users, and the user experience is better.

In one embodiment of the present invention, step 20 further includes:

Step 202: Determine the predicted behavior heat of the optional prompt point.

In one embodiment of the present invention, the predicted behavior heat is used to characterize the behavior heat in the ideal case of the optional prompt point, that is, the behavior heat when the behavior heat does not change. The predicted behavior heat can be a preset value or can be determined based on the average value of the behavior heat at all time points.

Therefore, in yet another embodiment of the present invention, step 202 further includes:

Step 2021: Perform weighted sum processing on the actual behavior data volume and the predicted behavior data volume at the previous time point adjacent to the optional prompt point to obtain the predicted behavior heat.

In one embodiment of the present invention, the preset initial smoothness can be used as a weight value for weighted summation. Specifically, for each optional prompt point t, its corresponding predicted behavior heat y _t can be expressed as: y _t =ax _t +(1-a)y _t-1 , where a is the initial smoothness and x _t is the actual behavior data volume at time t.

Step 203: Determine the relative smoothness error and the absolute smoothness error corresponding to the optional prompt point according to the behavior heat and the predicted behavior heat.

In one embodiment of the present invention, the smoothness absolute error is used to characterize the sum of the prediction errors of all optional prompt points, where the prediction error of a single optional prompt point can be the difference between the predicted behavior heat and the behavior heat. The smoothness relative error is used to characterize the sum of the prediction errors of all optional prompt points after the prediction errors of the behavior heat between adjacent optional prompt points are offset.

Specifically, the difference between the prediction errors of adjacent optional prompt points in the relative error of smoothness can offset each other in the calculation of the overall error. In order to make the difference between the prediction errors of adjacent optional prompt points in the absolute error of smoothness unable to offset each other in the calculation of the overall error, the absolute value of the difference between the prediction errors of every two optional prompt points can be taken and then summed up for calculation.

Therefore, in yet another embodiment of the present invention, the absolute error Mt of smoothness at time _t can be expressed as:

Wherein, β is a preset adjustment parameter, which can be 0.1 to 0.2; e _t represents the prediction error at time t, e _t = x _t -y _t .

The relative error of smoothness E t at time _t can be expressed as:

E _t = βe _t + β(1-β)e _t-1 + β(1-β) ² e _t-2 + … + β(1-β) ^t-1 e ₁

That is, E _t = βe _t + (1-β)E _t-1 ; M _t = βe _t+1 + (1-β)M _t-1 ;

Here, t is a natural number greater than 1; y ₁ =x ₁ ; y ₂ =x ₁ ; e ₁ =0; E ₁ =0.

Step 204: Determine the thermal variation smoothness according to the smoothness relative error and the smoothness absolute error.

In one embodiment of the present invention, the thermal variation smoothness may be determined based on the ratio between the absolute value of the smoothness absolute error and the smoothness relative error.

That is, the heat change smoothness at time _t can be expressed as:

The larger the ratio value a _t is, the larger the absolute smoothness error is relative to the relative smoothness error, that is, the greater the mutual offset of the prediction errors between the optional prompt points is. Therefore, overall, the heat change between the optional prompt points is smoother, that is, the heat change is smoother.

Step 30: Determine a target prompt point from the optional prompt points according to the heat change smoothness.

In one embodiment of the present invention, there are multiple optional prompt points. In order not to interrupt the user's immersive viewing experience, optional prompt points with smaller heat change smoothness can be selected as target prompt points, that is, timely reminders are given when the user's interactive behavior pattern changes, which can attract the user's attention and increase the probability of interaction.

Therefore, step 30 also includes: step 301: determining the difference in the behavior heat between each of the optional prompt points.

In one embodiment of the present invention, in addition to considering the change in the user's interactive interest represented by the smoothness of the heat change, thereby avoiding interrupting the user's immersive experience due to reminders, the interactive behavior trend of most users can also be considered, that is, when most users are performing interactive behaviors, interactive prompts are given to users, prompting users to follow the herd mentality and also perform interactive behaviors.

Therefore, we can first determine whether the difference in the behavior heat corresponding to each optional prompt point is large, that is, whether there is an optional time point with a relatively stronger interactive atmosphere and most users perform interactive behaviors. If so, a reminder is given at this time point.

Step 302: When the difference is less than a first threshold, the target prompt point is determined from the optional prompt points according to the heat change smoothness.

In one embodiment of the present invention, when the difference is less than the first threshold, it means that the behavior heat of the optional prompt points is relatively close, that is, the interactive interest corresponding to the optional prompt points is similar, and there is no time point with a relatively stronger interactive atmosphere to prompt the user, so it can be selected according to the smoothness of the behavior heat change, so as to avoid interference with the user's immersive viewing experience. Specifically, after the heat change smoothness is arranged in ascending order, the optional prompt points preset before the arrangement are determined as the target prompt points. Optionally, the optional prompt point with the smallest heat change smoothness can be selected as the target prompt point.

Therefore, in one embodiment of the present invention, step 302 further includes:

Step 3021: When the difference is less than the first threshold, the optional prompt points are arranged in ascending order of the smoothness of the heat change, and the optional prompt point preset before arrangement is determined as the target prompt point.

In one embodiment of the present invention, after all optional cue points are arranged in ascending order of heat change smoothness, the optional cue points that are pre-positioned in ascending order are determined as target cue points, thereby avoiding interference with the user's immersive viewing experience. Optionally, the optional cue point with the smallest heat change smoothness can also be determined as the target cue point.

Step 303: When the difference is greater than or equal to a second threshold, the target prompt point is determined from the optional prompt points according to the behavior heat at the time point.

In one embodiment of the present invention, the second threshold value may be the same as the first threshold value. When the difference is greater than or equal to the second threshold value, it indicates that the behavior heat between the optional prompt points is greatly different, that is, there are some optional prompt points corresponding to higher interactive interest than other optional prompt points, and these optional prompt points with higher interactive interest can reflect the climax atmosphere of a user's participation in the interaction. Therefore, the optional time point with the greatest interactive interest of a user can be selected as the target prompt point, thereby encouraging users to interact through the interactive climax atmosphere of most users.

Therefore, in yet another embodiment of the present invention, step 303 further includes:

Step 3031: When the difference is greater than the second threshold, the optional prompt point with the maximum behavior heat is determined as the heat center point.

In one embodiment of the present invention, the optional prompt point with the largest behavior heat represents the climax of the interaction behavior of most users, and thus it can be used as the heat center point.

Step 3032: Determine the time point adjacent to the heat center point as the target prompt point.

In one embodiment of the present invention, the heat center point represents the center of the climax of the user's participation in the interactive activity, so that the user can be prompted at a time point near the climax center to remind the user that the majority of other users are about to or are interacting, thereby utilizing the herd mentality to encourage the user to participate in the interactive climax.

Step 40: inserting prompt information at the target prompt point to obtain a processed video.

In one embodiment of the present invention, the prompt information is inserted into the video frame corresponding to the target prompt point to obtain the processed video. First, the number of prompt information, prompt type, priority, etc. are determined. The number of prompt information is generally not too much, and can be set to 1-3. The trigger types include comment, like, coin and share, and the priority can be determined according to business needs.

Specifically, the process of determining the prompt type can be as follows: determine the time point and behavior content corresponding to each type of behavior in the user behavior data, where the behavior content can include the text content of comments and barrages, or video information, such as video tags, video lines, etc. Perform cluster analysis based on the behavior content and the corresponding behavior type to obtain the behavior content class corresponding to each behavior type, and finally determine the corresponding behavior type as the prompt type based on the behavior content at the target prompt point.

In another embodiment of the present invention, natural language processing and semantic analysis can be performed on the user behavior data corresponding to the target prompt point to obtain a semantic analysis result, which may include the barrage and comment semantics corresponding to the target prompt point; when the semantics include semantic information corresponding to a preset interaction type such as like, forward/share, one-click triple-click, etc., the interaction type corresponding to the included semantic information is determined as the prompt type of the prompt information.

Step 50: Display the processed video.

In one embodiment of the present invention, an interactive control or logo may be displayed at the target prompt point in the processed video, thereby prompting the user to interact at that point.

Specifically, when the same behavior is triggered, the prompt cannot be triggered again in this video. When the prompt contact is triggered, the icon that needs to be prompted will display the prompt effect, which can be a GIF, animation or sound, etc. Among them, the prompt effect can be a fixed duration, or it can be adjusted according to the amount of data corresponding to the contact. The greater the difference between the amount of data and the average amount of data at all time points, the longer the duration of the prompt for this point. If the original prompt effect duration is T, the corrected duration T _is T＝(MAX(x)-AVER(x))/AVER(x)*(1+T); wherein x is the amount of data corresponding to a time point, MAX(x) is the maximum value of the average of the amount of data corresponding to all time points, and AVER(x) is the average of the amount of data corresponding to all time points.

In yet another embodiment of the present invention, the process of video prompting may refer to FIG. 2 .

As shown in FIG2 , step A: determining the best prompt point based on user comments, bullet comments and other data.

At fixed time intervals, obtain the data on the number of user comments and bullet screens at each time point of the video playback progress. Optionally, it can also be user behavior data such as sharing, forwarding, @, etc., but comments and bullet screens are more representative, so these two types of behavior data are used as examples. Among them, the number of bullet screens and comments can be calculated together or separately. Among them, the corresponding relationship between the time point and the amount of data obtained by merging the number of bullet screen and comment behavior data can be referred to Figure 3.

The number of data in Figure 3 is used as the behavior heat, and the behavior heat is sorted from high to low to obtain the top n data and the corresponding time points. When n is 3, the top 3 data and the corresponding time points are obtained as follows:

01:40 corresponds to 38 data, 01:30 corresponds to 37 data, and 01:00 corresponds to 33 data.

Then, for the top n time points of the behavior heat ranking, the corresponding heat change smoothness is determined respectively, wherein the heat change smoothness calculation process can be as follows:

First, the time series composed of various time points are numbered in chronological order to obtain the time series t, where t is a natural number.

Suppose the total number of bullet comments and comments is x, and x is the actual behavior data volume corresponding to the time point;

Let the initial smoothing index be a;

Assume the predicted behavior heat is y, then y _t = ax _t +(1-a)y _t-1 ;

Assume that the initial parameter value is β, and the value range of β is (0.1–0.2);

Assume that the prediction error of the heat change smoothness at time t is e _t , then e _t = x _t -y _t , and take the weighted average of the prediction errors at each time point t to obtain:

The absolute error of smoothness at time t, Mt _, can be expressed as

The relative error of smoothness E t at time _t can be expressed as:

E _t = βe _t + β(1-β)e _t-1 + β(1-β) ² e _t-2 + … + β(1-β) ^t-1 e ₁

That is, E _t = βe _t + (1-β)E _t-1 ; M _t = βe _t+1 + (1-β)M _t-1 ;

Here, t is a natural number greater than 1; y ₁ =x ₁ ; y ₂ =x ₁ ; e ₁ =0; E ₁ =0.

That is, the heat change smoothness at time _t can be expressed as:

For example, the time point 01:40 corresponds to 38 data items, and the corresponding t=10, so its heat change smoothness is a ₁₀ =|E ₁₀ |/M ₁₀ =|βe ₁₀ +(1-β)E ₉ |/β|e ₁₀ |+(1-β)M ₉ .

Determine whether the data difference between the top n data in terms of data quantity is less than N%, if so, take the time point corresponding to the data pair with the minimum value of heat change smoothness as the best prompt point. If the heat change smoothness values of the top n data are the same, select them in order from left to right on the time axis.

Table 1

As shown in Table 1, the order of data size is t10>t9>t6, and the corresponding data size relationship is: 38>37>33. The difference in the number of data between the three is <10%. Here, 10% is used as the threshold for example, and the corresponding heat change smoothness of the three is 0.9, 0.1, and 0.1 respectively.

There are two minimum values, namely: 0.1 corresponding to t9 and 0.1 corresponding to t6, so t9 is determined as the best prompt point in order from left to right.

Optionally, the time point with the largest amount of data among the adjacent time points may be determined as the best prompt point.

For example, the adjacent points of t10 are t9 and t11, and the corresponding data quantities are 37 and 27 respectively;

The adjacent points of t9 are t8 and t10, and the corresponding data numbers are 17 and 38 respectively;

The adjacent points of t6 are t5 and t7, and the corresponding data numbers are 27 and 9 respectively;

It can be seen that the number of data of the neighboring points of t9 is the largest, which is 38, so t9 is the best prompt point.

In addition to the above methods, the time point corresponding to the largest amount of data can also be directly used as the best prompt point, such as t10.

It should be noted that there may be multiple optimal prompt points or only one optimal prompt point, depending on how many different prompts need to be provided to the user.

Step B: Determine the prompt content and prompt type corresponding to the best prompt point.

Through step A, three optimal contact points are confirmed, namely t9, t10, and t6.

Insert prompt information into the video frame corresponding to the target prompt point to obtain the processed video. First, determine the number of prompt information, prompt type, priority, etc. The number of prompt information should not be too many, and can be set to 1-3. The trigger types include comment, like, coin and share, and the priority can be determined according to business needs.

Specifically, the process of determining the prompt type can be as follows: determine the time point and behavior content corresponding to each type of behavior in the user behavior data, where the behavior content can include the text content of comments and barrages, or video information, such as video tags, video lines, etc. Perform cluster analysis based on the behavior content and the corresponding behavior type to obtain the behavior content class corresponding to each behavior type, and finally determine the corresponding behavior type as the prompt type based on the behavior content at the target prompt point.

It is also possible to perform natural language processing and semantic analysis on the user behavior data corresponding to the target prompt point to obtain a semantic analysis result, which may include the barrage and comment semantics corresponding to the target prompt point; when the semantics include semantic information corresponding to a preset interaction type such as likes, forwarding/sharing, and one-click triple-click, the interaction type corresponding to the included semantic information is determined as the prompt type of the prompt information.

Step C: Prompt at the target prompt point according to the prompt content and prompt type.

An interactive control or logo may be displayed at the target prompt point in the processed video, thereby prompting the user to interact at that point. The target prompt point is the optimal prompt point mentioned in steps A and B.

Specifically, when the same behavior is triggered, the prompt cannot be triggered again in this video. When the prompt contact is triggered, the icon that needs to be prompted will display the prompt effect, which can be a GIF, animation or sound, etc. Among them, the prompt effect can be a fixed duration, or it can be adjusted according to the amount of data corresponding to the contact. The greater the difference between the amount of data and the average amount of data at all time points, the longer the duration of the prompt for this point. If the original prompt effect duration is T, the corrected duration T _is T＝(MAX(x)-AVER(x))/AVER(x)*(1+T); wherein x is the amount of data corresponding to a time point, MAX(x) is the maximum value of the average of the amount of data corresponding to all time points, and AVER(x) is the average of the amount of data corresponding to all time points.

The embodiment of the present invention determines the behavior heat of each time point according to the user behavior data at multiple time points of the video, and characterizes the atmosphere environment of the user watching the video by obtaining the behavior heat of other users when the video is playing, and then determines the change of the behavior heat at each time point according to the behavior heat. The change can be the severity of the change. The more drastic the change of behavior heat, the greater the degree of change of the user's behavior pattern, and there may be a gap in attention, such as from watching the video to posting comments or forwarding and sharing. Conversely, the less drastic the heat change, the less the change of the user's behavior amount, that is, the user is more likely to be in immersive viewing; thereby, according to the behavior heat and the change of behavior heat, it is determined from the time point that the change meets the preset condition. Mark prompt points, wherein the preset condition may be that the intensity of the change is less than a certain threshold; finally, insert prompt information at the target prompt point to obtain a processed video; and display the processed video, thereby being different from the prior art in which prompts are directly given according to the playback progress or playback time, which may interrupt the user's immersive viewing experience, and the prompt time may not best encourage the user to interact according to the prompt. The embodiment of the present invention determines the target prompt point according to the smoothness of the heat change, thereby ensuring that the user's viewing experience is not disturbed, and at the same time reflects the viewing atmosphere of the video through the behavioral heat, and reminds the user in a timely manner according to the atmosphere, thereby increasing the user's enthusiasm for interaction through the herd mentality, thereby improving the overall user experience during video viewing.

Fig. 5 shows a schematic diagram of the structure of a video prompting device provided by an embodiment of the present invention. As shown in Fig. 5 , the device 60 includes: a first determination module 601 , a second determination module 602 , an insertion module 603 and a display module 604 .

The first determination module 601 is used to determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in the interactive behavior for the video;

A second determination module 602 is used to determine a target prompt point from the time points according to the behavior heat; the target prompt point includes the time point when the change of the behavior heat meets a preset condition;

Insertion module 603, used for inserting prompt information at the target prompt point to obtain a processed video;

The display module 604 is used to display the processed video.

The operation process performed by the video prompting device provided in the embodiment of the present invention is substantially the same as that of the aforementioned method embodiment, and will not be described in detail.

The video prompt device provided by the embodiment of the present invention determines the behavior heat of each time point according to the user behavior data at multiple time points of the video, and characterizes the atmosphere environment of the user watching the video by obtaining the behavior heat of other users when the video is played, and then determines the change of the behavior heat at each time point according to the behavior heat. The change can be the severity of the change. The more drastic the change of behavior heat, the greater the degree of change of the user's behavior pattern, and there may be a gap in attention, such as from watching the video to commenting or forwarding and sharing. On the contrary, the less drastic the change of heat, the less the change of the user's behavior amount, that is, the user is more likely to be in immersive viewing; thereby, according to the behavior heat and the change of behavior heat, it is determined from the time point that the change meets the expected A conditional target prompt point is set, wherein the preset condition may be a representation that the intensity of the change is less than a certain threshold; finally, prompt information is inserted at the target prompt point to obtain a processed video; and the processed video is displayed, which is different from the prior art in which prompts are directly given according to the playback progress or playback time, which may interrupt the user's immersive viewing experience, and the prompt time may not best encourage the user to interact according to the prompt. The embodiment of the present invention determines the target prompt point according to the smoothness of the heat change, so as to ensure that the user's viewing experience is not disturbed, and at the same time reflects the viewing atmosphere of the video through the behavior heat, and reminds the user in time according to the atmosphere, thereby improving the user's enthusiasm for interaction through the herd mentality, thereby improving the overall user experience during video viewing.

FIG6 shows a schematic diagram of the structure of a video prompt device provided in an embodiment of the present invention. The specific embodiment of the present invention does not limit the specific implementation of the video prompt device.

As shown in FIG. 6 , the video prompting device may include: a processor (processor) 702 , a communications interface (Communications Interface) 704 , a memory (memory) 706 , and a communication bus 708 .

The processor 702, the communication interface 704, and the memory 706 communicate with each other via a communication bus 708. The communication interface 704 is used to communicate with other devices such as a client or other server network elements. The processor 702 is used to execute a program 710, which can specifically execute the relevant steps in the above-mentioned video prompt method embodiment.

Specifically, the program 710 may include program code including computer executable instructions.

The processor 702 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the video prompt device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

The memory 706 is used to store the program 710. The memory 706 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

Program 710 can be specifically called by processor 702 to enable the video prompt device to perform the following operations:

Determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video;

Determining a target prompt point from the time points according to the behavior heat; the target prompt point includes the time point at which the change in the behavior heat meets a preset condition;

Inserting prompt information at the target prompt point to obtain a processed video;

The processed video is displayed.

The operation process performed by the video prompt device provided in the embodiment of the present invention is substantially the same as that of the aforementioned method embodiment, and will not be described in detail.

The video prompt device provided by the embodiment of the present invention determines the behavior heat of each time point according to the user behavior data at multiple time points of the video, and characterizes the atmosphere environment of the user watching the video by obtaining the behavior heat of other users when the video is played, and then determines the change of the behavior heat at each time point according to the behavior heat. The change can be the severity of the change. The more drastic the change of behavior heat, the greater the degree of change of the user's behavior pattern, and there may be a gap in attention, such as from watching the video to commenting or forwarding and sharing. On the contrary, the less drastic the change of heat, the less the change of the user's behavior amount, that is, the user is more likely to be in immersive viewing; thereby, according to the behavior heat and the change of behavior heat, it is determined from the time point that the change meets the expected A conditional target prompt point is set, wherein the preset condition may be a representation that the intensity of the change is less than a certain threshold; finally, prompt information is inserted at the target prompt point to obtain a processed video; and the processed video is displayed, which is different from the prior art in which prompts are directly given according to the playback progress or playback time, which may interrupt the user's immersive viewing experience, and the prompt time may not best encourage the user to interact according to the prompt. The embodiment of the present invention determines the target prompt point according to the smoothness of the heat change, so as to ensure that the user's viewing experience is not disturbed, and at the same time, the viewing atmosphere of the video is reflected through the behavior heat, and the user is reminded in time according to the atmosphere, so as to increase the user's enthusiasm for interaction through the herd mentality, thereby improving the overall user experience during video viewing.

An embodiment of the present invention provides a computer-readable storage medium, wherein the storage medium stores at least one executable instruction. When the executable instruction is executed on a video prompting device, the video prompting device executes the video prompting method in any of the above method embodiments.

The executable instructions can be specifically used to enable the video prompt device to perform the following operations:

Determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video;

Determining a target prompt point from the time points according to the behavior heat; the target prompt point includes the time point at which the change in the behavior heat meets a preset condition;

Inserting prompt information at the target prompt point to obtain a processed video;

The processed video is displayed.

The operation process of the executable instructions stored in the computer storage medium provided in the embodiment of the present invention is substantially the same as that of the aforementioned method embodiment and will not be described in detail.

The executable instructions stored in the computer storage medium provided by the embodiment of the present invention determine the behavior heat of each time point according to the user behavior data at multiple time points of the video, and characterize the atmosphere environment of the user watching the video by obtaining the behavior heat of other users when the video is played, and then determine the change of the behavior heat at each time point according to the behavior heat. The change can be the severity of the change. The more drastic the change in behavior heat, the greater the degree of change in the user's behavior pattern, and there may be a gap in attention, such as from watching the video to posting comments or forwarding and sharing. Conversely, the less drastic the heat change, the less the change in the user's behavior amount, that is, the user is more likely to be in immersive viewing; thereby determining the change from the time point according to the behavior heat and the change in behavior heat. The preset condition may be a target prompt point where the situation satisfies a preset condition, wherein the preset condition may be a characterization that the intensity of the change is less than a certain threshold; finally, a prompt information is inserted at the target prompt point to obtain a processed video; and the processed video is displayed, thereby being different from the prior art in which prompts are directly given according to the playback progress or playback time, which may interrupt the user's immersive viewing experience, and the prompt time may not best encourage the user to interact according to the prompt. The embodiment of the present invention determines the target prompt point according to the smoothness of the heat change, thereby ensuring that the user's viewing experience is not disturbed, and at the same time reflects the viewing atmosphere of the video through the behavior heat, and reminds the user in a timely manner according to the atmosphere, thereby increasing the user's enthusiasm for interaction through the herd mentality, thereby improving the overall user experience during video viewing.

An embodiment of the present invention provides a video prompting device, which is used to execute the above-mentioned video prompting method.

An embodiment of the present invention provides a computer program, which can be called by a processor to enable a video prompting device to execute the video prompting method in any of the above method embodiments.

An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed on a computer, the computer executes the video prompt method in any of the above method embodiments.

The algorithm or display provided here is not inherently related to any specific computer, virtual system or other equipment. Various general systems can also be used together with the teaching based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages can be utilized to realize the content of the present invention described here, and the description of the above specific language is for disclosing the best mode of the present invention.

In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than those expressly recited in each claim.

Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and/or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim that lists a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims (8)

1. A video prompt method, characterized in that the method comprises: Determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video; Determining an optional prompt point and a corresponding heat change smoothness from the time point according to the behavior heat; the heat change smoothness is used to characterize the severity of the change in the user's behavior heat; Arrange the time points in descending order of the behavior heat, and determine the time points preset before arrangement as optional prompt points; After the heat change smoothness is sorted in ascending order, the optional prompt point located at the front preset position is determined as the target prompt point; Inserting prompt information at the target prompt point to obtain a processed video; The processed video is displayed. 2. The method according to claim 1, characterized in that the step of determining the optional prompt points and the corresponding heat change smoothness from the time points according to the behavior heat comprises: Determining the predicted behavior heat of the optional prompt point; Determine a relative smoothness error and an absolute smoothness error corresponding to the optional prompt point according to the behavior heat and the predicted behavior heat; The thermal variation smoothness is determined according to the smoothness relative error and the smoothness absolute error. 3. The method according to claim 2, characterized in that the step of determining the predicted behavior heat of the optional prompt point comprises: The predicted behavior heat is obtained by performing a weighted summation process on the actual behavior data volume and the predicted behavior data volume at the previous time point adjacent to the optional prompt point. 4. The method according to claim 1, characterized in that the number of the optional prompt points is multiple; before the optional prompt point located at a front preset position after the heat change smoothness is sorted in ascending order is determined as the target prompt point, it comprises: Determining the difference in the behavior heat between each of the optional prompt points; When the difference is less than a first threshold, determining the target prompt point from the optional prompt points according to the heat change smoothness; When the difference is greater than or equal to a second threshold, the target prompt point is determined from the optional prompt points according to the behavior heat at the time point. 5. The method according to claim 4, characterized in that when the difference is greater than or equal to a second threshold, determining the target prompt point from the optional prompt points according to the behavior heat at the time point comprises: When the difference is greater than the second threshold, determining the optional prompt point with the largest behavior heat as the heat center point; The time point adjacent to the heat center point is determined as the target prompt point. 6. A video prompting device, characterized in that the device comprises: A first determination module is used to determine the behavior heat of each time point according to the user behavior data at multiple time points of the video; the behavior heat is used to represent the user's interest in interactive behavior with respect to the video; The second determination module is used to determine the optional prompt point and the corresponding heat change smoothness from the time point according to the behavior heat; the heat change smoothness is used to characterize the severity of the change in the behavior heat of the user; the time points are arranged in descending order of the behavior heat, and the time points at the front preset position are determined as optional prompt points; the optional prompt point at the front preset position after the heat change smoothness is sorted in ascending order is determined as the target prompt point; An inserting module, used for inserting prompt information at the target prompt point to obtain a processed video; A display module is used to display the processed video. 7. A video prompt device, characterized in that it comprises: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the video prompt method as described in any one of claims 1-5. 8. A computer-readable storage medium, characterized in that at least one executable instruction is stored in the storage medium, and when the executable instruction is executed on a video prompting device, the video prompting device executes the operation of the video prompting method as described in any one of claims 1-5.