CN113422995A - Video processing method based on AI model and portable electronic device - Google Patents

Abstract

The present application provides a video processing method and a portable electronic device based on an AI model. The method includes: acquiring at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and /or air pressure data; obtain at least one kind of data of the target video clip, at least one kind of data of the target video clip includes: sound data, and/or image data, and/or subtitle data; the target video clip is the video to be played by the electronic device segment; input at least one type of environmental data and at least one type of data of the target video segment into the first model to obtain the first processing strategy of the target video segment, and the first model is used to analyze the processing strategy of the video segment; play according to the first processing strategy target video clip. The present application can automatically adjust the processing strategy during the video playing process, reduce the power consumption of the electronic device to play the video, and achieve the purpose of saving power.

Description

Video processing method and portable electronic device based on AI model

technical field

The present application relates to the technical field of intelligent terminals, and in particular, to an AI model-based video processing method and a portable electronic device.

Background technique

At present, if a user moves from indoors to outdoors when using an electronic device, in order to enable the user to clearly see the content displayed on the display screen, the electronic device increases the brightness of the display screen, thereby increasing the power consumption of the electronic device. If the electronic device is playing a video when the environment in which the electronic device is located changes from indoors to outdoors, the power consumption of the electronic device will increase more seriously, resulting in excessive power consumption of the electronic device.

SUMMARY OF THE INVENTION

The present application provides a video processing method and a portable electronic device based on an AI model, which can make the power consumed by the electronic device to play a video more reasonable.

In a first aspect, an embodiment of the present application provides a video processing method based on an AI model, including:

Acquiring at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

Acquire at least one kind of data of the target video clip, where the at least one kind of data of the target video clip includes: sound data, and/or image data, and/or subtitle data; the target video clip is to be played by the electronic device video clips;

Inputting the at least one kind of environmental data and at least one kind of data of the target video clip into a first model to obtain a first processing strategy of the target video clip, and the first model is used to analyze the processing strategy of the video clip;

Play the target video segment according to the first processing strategy.

In a possible implementation manner, the first processing strategy includes: a processing strategy of the image processor for the target video clip, and/or a processing strategy of the data processor for the target video clip, and /or, display the processing strategy of the driver for the target video segment.

In a possible implementation manner, the first processing strategy includes: a processing strategy of the data processor for the target video clip, and the playing the target video clip according to the first processing strategy includes:

For the target video clip, according to the processing strategy of the data processor for the target video clip in the first processing strategy, the code stream of the target video clip is decoded to obtain decoded data.

In a possible implementation manner, the first processing strategy includes: a processing strategy of the image processor for the target video clip, and the playing the target video clip according to the first processing strategy includes:

For each video frame in the target video clip, the image processor performs rendering processing on the video frame according to the processing strategy of the image processor for the target video clip in the first processing strategy.

In a possible implementation manner, the first processing strategy includes: a processing strategy of a display driver for the target video clip, and the playing the target video clip according to the first processing strategy includes:

For each video frame in the target video clip, display the video frame according to the processing strategy of the display driver for the target video clip in the first processing strategy.

In a possible implementation manner, the processing strategy of the image processor for the target video segment includes: an image rendering resolution, and/or a switch state of an image sharpening algorithm, and/or a contrast enhancement algorithm the switch state;

and / or,

The processing strategy of the data processor for the target video clip includes: decoding accuracy, and/or, frame skipping, and/or, the frame rate of the target video clip, and/or, the video encapsulation format of the target video clip, and/or, the bit rate stream of the target video clip, and/or, the resolution of the target video clip;

and / or,

The processing strategy of the display driver for the target video segment includes: screen refresh rate and/or screen resolution.

In a possible implementation manner, the first model is obtained by pre-training, and the training method includes:

Acquiring training samples marked with processing strategies; each of the training samples includes: samples of each environmental data in the at least one type of environmental data, and samples of each type of data in the at least one type of data;

The training samples are input into a preset model for training to obtain the first model.

In a possible implementation manner, the first model is an AI perception neural network composed of an AI perception neural network accelerator and a recurrent neural network.

In a second aspect, an embodiment of the present application provides a video processing method, which is applied to an electronic device, including:

Acquiring at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

determining a first environment type based on the at least one environment data;

Determine the first processing strategy of the target video clip according to the first environment type; the target video clip is the video clip to be played by the electronic device;

Play the target video segment according to the first processing strategy.

In a possible implementation manner, if one type of environmental data is acquired, the determining of the first type of environment according to the at least one type of environmental data includes:

For the type of environmental data, according to the corresponding relationship between the data interval preset for the type of environmental data and the second type of environment, determine the second type of environment corresponding to the acquired type of environmental data, as the first type of environment type of environment;

or,

If at least two kinds of environmental data are obtained, the determining of the first environmental type according to the at least one kind of environmental data includes:

For each kind of environmental data, according to the corresponding relationship between the data interval preset for the environmental data and the second environmental type, determine the second environmental type corresponding to the acquired environmental data;

The first environment type is determined according to the second environment type corresponding to each acquired environment data.

In a possible implementation manner, the determining of the first environment type according to the second environment type corresponding to each acquired environment data includes:

Calculate the first numerical value according to the obtained preset weight of each environmental data and the numerical value corresponding to the second environmental type;

The third environment type corresponding to the first value is determined according to the correspondence between the preset value interval and the third environment type, and the first environment type is obtained.

In another possible implementation manner, if one type of environmental data is acquired, the determining of the first type of environment according to the at least one type of environmental data may also be performed by inputting the at least one type of environmental data into a pre-trained second model to determine the first environment type. At this point, include:

Inputting the above at least one kind of environmental data into a preset second model, obtaining the environment type output by the second model, and obtaining the first environment type.

Optionally, the second model may be an AI-aware neural network composed of an AI-aware neural network accelerator and a recurrent neural network (RNN).

The specific training method of the second model may include: acquiring training samples, each training sample including: samples of each environmental data in at least two kinds of environmental data, and the environment type of the training sample; inputting the training samples into a preset model for training, Get the second model.

In a possible implementation manner, the determining the first processing strategy of the target video according to the first environment type includes:

According to the preset correspondence between the environment type and the processing strategy, the processing strategy corresponding to the first environment type is determined as the first processing strategy; the first processing strategy includes: an image processor for the The processing strategy of the target video clip, and/or the processing strategy of the data processor for the target video clip, and/or the processing strategy of the display driver for the target video clip.

In a possible implementation manner, the first processing strategy includes: a processing strategy of the data processor for the target video clip, and the playing the target video clip according to the first processing strategy includes:

For the target video clip, according to the processing strategy of the data processor for the target video clip in the first processing strategy, decode the code stream of the target video clip to obtain decoded data;

and / or,

The first processing strategy includes: a processing strategy of the image processor for the target video clip, and the playing the target video clip according to the first processing strategy includes:

For each video frame in the target video clip, perform rendering processing on the video frame according to the processing strategy of the image processor for the target video clip in the first processing strategy;

and / or,

The first processing strategy includes: a processing strategy of the display driver for the target video clip, and the playing the target video clip according to the first processing strategy includes:

For each video frame in the target video clip, display the video frame according to the processing strategy of the display driver for the target video clip in the first processing strategy.

In a possible implementation manner, the processing strategy of the image processor for the target video segment includes: an image rendering resolution, and/or a switch state of an image sharpening algorithm, and/or a contrast enhancement algorithm the switch state;

and / or,

The processing strategy of the data processor for the target video clip includes: decoding accuracy, and/or, frame skipping, and/or, the frame rate of the target video clip, and/or, the video encapsulation format of the target video clip, and/or, the bit rate stream of the target video clip, and/or, the resolution of the target video clip;

and / or,

The processing strategy of the display driver for the target video segment includes: screen refresh rate and/or screen resolution.

In a third aspect, an embodiment of the present application provides a portable electronic device, including:

a first acquiring unit, configured to acquire at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

The second obtaining unit is configured to obtain at least one kind of data of the target video clip, where the at least one kind of data of the target video clip includes: sound data, and/or image data, and/or subtitle data; the target video clip is the video clip to be played by the electronic device;

a strategy decision unit, configured to input the at least one kind of environmental data and at least one kind of data of the target video clip into a first model to obtain a first processing strategy of the target video clip, and the first model is used for analysis Video clip processing strategy;

A playing unit, configured to play the target video segment according to the first processing strategy.

In a fourth aspect, an embodiment of the present application provides a portable electronic device, including:

an acquisition unit, configured to acquire at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

a first determining unit, configured to determine a first environment type according to the at least one type of environment data;

a second determining unit, configured to determine a first processing strategy of a target video clip according to the first environment type; the target video clip is a video clip to be played by the electronic device;

A playing unit, configured to play the target video segment according to the first processing strategy.

In a fifth aspect, an embodiment of the present application provides an electronic device, including:

a display screen; one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions for When the instruction is executed by the device, the device is caused to execute the method described in any one of the first aspect or the second aspect.

In a sixth aspect, embodiments of the present application provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when it runs on a computer, causes the computer to execute any one of the first aspect or the second aspect method described in item.

In a seventh aspect, the present application provides a computer program for executing the method of the first aspect when the computer program is executed by a computer.

In a possible design, the program in the seventh aspect may be stored in whole or in part on a storage medium packaged with the processor, or may be stored in part or in part in a memory not packaged with the processor.

In the video processing method of the present application, at least one type of environmental data is acquired, and the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data, and at least one of the target video clips is acquired. A kind of data, at least one kind of data of the target video clip includes: sound data, and/or image data, and/or subtitle data, the target video clip is a video clip to be played by the electronic device, and the target video clip is to be played by the electronic device. At least one kind of environmental data and at least one kind of data of the target video clip are input into a first model to obtain a first processing strategy of the target video clip, and the first model is used to analyze the processing strategy of the video clip, according to the The first processing strategy plays the target video clip, so that the processing strategy can be automatically adjusted during the video playback process according to the environmental data and the data of the target video clip, so that the power consumed by the electronic device to play the video is more reasonable, and the power saving is achieved. Purpose.

Description of drawings

1 is a schematic structural diagram of an embodiment of an electronic device of the present application;

2 is a flowchart of an embodiment of a video playback method of the present application;

3 is a flowchart of another embodiment of the video playback method of the present application;

4A is a flowchart of another embodiment of the video playback method of the present application;

4B is a schematic diagram of the training method of the first model of the application;

FIG. 5 is a flowchart of another embodiment of the video playback method of the present application;

6 is a schematic structural diagram of an embodiment of a video playback device of the present application;

7 is a schematic structural diagram of another embodiment of a video playback device of the present application;

8 is a schematic diagram of a video playback process in the prior art;

FIG. 9 is a schematic diagram of a video playback process according to an embodiment of the present application.

Detailed ways

The terms used in the embodiments of the present application are only used to explain specific embodiments of the present application, and are not intended to limit the present application.

First of all, the nouns involved in the embodiments of the present application are described in an exemplary but not restrictive manner:

Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

System on Chip (System on Chip, hereinafter referred to as "SoC"), also known as system on chip, means that it is a product, an integrated circuit with a dedicated target, which contains a complete system and has all the contents of embedded software. At the same time, it is a technology used to realize the whole process from determining the system function, to the software/hardware division, and completing the design.

A digital signal processor (Digital Signal Processor, DSP) is a microprocessor that is particularly suitable for digital signal processing operations, and its main application is to realize various digital signal processing algorithms quickly and in real time.

AI cultivation: AI cultivation in the field of artificial intelligence, using a large number of accelerators such as graphics processing units (Graphics Processing Unit, GPU) or central processing units (Central Processing Unit, CPU) and other devices that can provide computing power, to find a suitable neural network architecture And calculate the optimal structure parameters of the neural network, so that the network can complete specific tasks. In layman's terms, it is to "feed" a large amount of data to the machine and let it learn to recognize and distinguish objects.

The video playback method of the embodiments of the present application may be applicable to electronic devices, such as a mobile phone, a tablet computer (PAD), a personal computer (PC), and the like. Specifically, it can be used as a function in a video playback application (App) in the electronic device, or a video playback control function provided by the operating system of the electronic device. The above function can be set by the user whether it is enabled or not. After the above function is enabled, the video playback method according to the embodiment of the present application can be triggered to achieve the purpose of reasonably consuming the power of the electronic device during the video playback process, thereby saving the power of the electronic device.

First, the possible implementation structure of the electronic device of the present application will be described. As shown in FIG. 1 , the electronic device 100 may include: a processor 110 , a memory 120 , and a display screen 130 . The electronic device 100 may further include: a light sensor 140, a microphone 150, a temperature sensor 160, an air pressure sensor 170, and the like. The above structures can communicate with each other through internal connection paths to transmit control and/or data signals. The memory 120 is used for storing computer programs, and the processor 110 is used for calling and running the computer programs from the memory 120 .

The above-mentioned processor 110 and the memory 120 may be combined into a processing device, more commonly, independent components, and the processor 110 is used to execute the program codes stored in the memory 120 to realize the above-mentioned functions. During specific implementation, the memory 120 may also be integrated in the processor 110 , or be independent of the processor 110 .

It should be understood that the processor 110 in the electronic device 100 shown in FIG. 1 may be a system-on-chip SoC, and the processor 110 may include an application processor (application processor, AP), a modem processor, and a graphics processor (graphics processor). unit, GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, and/or neural network processor (neural) -network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

The electronic device 100 implements a display function through a GPU, a display screen 130, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display screen 130 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.

A digital signal processor is used to process digital signals, in addition to processing digital image signals, it can also process other digital signals.

The light sensor 140 is used to sense ambient light brightness.

The temperature sensor 160 is used to detect the ambient temperature.

The air pressure sensor 170 is used to measure air pressure.

The microphone 150 is used to collect sound signals and convert the sound signals into electrical signals.

It should be understood that the electronic device 100 shown in FIG. 1 can implement various processes of the methods provided by the embodiments of the present application. The operations and/or functions of each module in the electronic device 100 are respectively to implement the corresponding processes in the foregoing method embodiments. For details, reference may be made to the descriptions in the method embodiments of the present application. To avoid repetition, the detailed descriptions are appropriately omitted here.

The video playback method of the present application will be described in detail below with reference to the structure of the electronic device.

The video clip referred to in the following embodiments of the present application may be a video clip among several video clips obtained by dividing a video file according to the duration. If the video file is not divided into video clips, it can also be considered that a video file is a video Fragment. The length of the video segment is not limited in this embodiment of the present application.

FIG. 2 is a flowchart of an embodiment of a video playback method of the present application. As shown in FIG. 1 , the method may include:

Step 201: The electronic device acquires at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data.

The light data can be detected by the light sensor in the electronic device; the sound data can be detected by the microphone in the electronic device; the air temperature data can be detected by the temperature sensor in the electronic device; the air pressure data can be detected by the air pressure sensor in the electronic device. .

Step 202: The electronic device determines a first environment type according to at least one kind of environment data.

The first environment type is used to describe the type of environment in which the electronic device is located.

Hereinafter, the implementation of this step will be described in two possible scenarios.

Scenario 1: In step 201, a kind of environment data is obtained. Correspondingly, in this step, the first environment type is determined according to a kind of environment data. In this case, this step may include:

According to the corresponding relationship between the data interval and the environmental type preset for the above-mentioned environmental data, the environmental type corresponding to the data interval in which the environmental data is located is determined as the first environmental type.

The method for classifying environment types is not limited in the embodiment of the present application. For example, environment types may be divided into: indoor and outdoor according to physical space; or, environment types may be divided into: noisy environment and quiet environment according to the degree of quietness; Quietness is divided into: noisy environment, quiet environment, quiet environment; and so on.

for example:

If the environment data is light data, it can be preset that the environment type corresponding to the first light intensity interval (0, a) is indoor, and the environment type corresponding to the second light intensity interval (a, +∞) is outdoor; the unit of light intensity can be Then, if the light intensity obtained by the electronic device is located in the first light intensity interval, determine that the first environment type is indoor, otherwise, determine that the first environment type is outdoor. In other possible instances, The light data can also be light intensity. For example, the first light intensity interval can be (0, 300lx], the corresponding environment type is indoor, the second light intensity interval can be (300lx, +∞), and the corresponding environment type is outdoor.

If the environmental data is sound data, it can be preset that the environment type corresponding to the first volume interval (0, b) is indoor, and the environment type corresponding to the second volume interval (b, +∞) is outdoor; the unit of volume can be decibel ( dB); then, if the volume of the sound obtained by the electronic device is located in the first volume interval, determine that the first environment type is indoor, otherwise, determine that the first environment type is outdoor. The value of B is not limited in this application, for example, it can be 50db.

If the environmental data is air temperature data, it can be preset that the environment type corresponding to the first temperature interval (-∞, c) is outdoor, and the environment type corresponding to the second temperature interval (c, +∞) is indoor; the unit of temperature can be Celsius (°C); then, if the temperature obtained by the electronic device is in the first temperature range, the first environment type is determined to be outdoor, otherwise, the first environment type is determined to be indoor.

If the environmental data is air pressure data, it can be preset that the environment type corresponding to the first air pressure interval (-∞, c) is outdoor, and the environment type corresponding to the second air pressure interval (c, +∞) is indoor; the unit of air pressure can be hundreds Pascal (hPa); then, if the air pressure obtained by the electronic device is in the first air pressure interval, the first environment type is determined to be outdoor, otherwise, the first environment type is determined to be indoor.

Scenario 2: At least two kinds of environmental data are obtained in step 201. Correspondingly, in this step, the first environment type is determined according to the at least two kinds of environmental data. In this case, this step may include:

For each kind of environmental data, according to the corresponding relationship between the data interval preset for this kind of environmental data and the second environmental type, determine the second environmental type corresponding to this kind of environmental data;

The first environment type is determined according to the second environment type corresponding to the at least two types of environment data.

In this scenario, to determine the second environment type corresponding to each kind of environment data, reference may be made to the corresponding description in scenario 1, which will not be repeated here. The division manner of the second environment type corresponding to each kind of environment data may be the same or different. An example of the same division method: assuming that at least two types of environment data are light data and sound data, the second environment type corresponding to the light data is divided into indoor and outdoor, and the second environment type corresponding to the sound data is also divided into indoor and outdoor. Examples of different division methods: Assuming that at least two types of environment data are light data and sound data, the second environment types corresponding to the light data are divided into indoor and outdoor, and the second environment types corresponding to the sound data are: noisy and quiet.

The above-mentioned determination of the first environment type according to the second environment types corresponding to at least two types of environment data may include:

Calculate the first value according to the preset weight of each environmental data and the second environmental type corresponding to the environmental data;

According to the corresponding relationship between the preset value interval and the third environment type, the third environment type corresponding to the first value is determined to obtain the first environment type.

For example, different corresponding values may be set for different second environment types in advance, and weights may be preset for each kind of environment data. If the environment data 1 and environment data 2 are obtained in step 201, the first environment data can be calculated by the following formula Value A: A=a1B1+a2B2, a1 is the weight of environmental data 1, B1 is the value corresponding to the second environmental type corresponding to environmental data 1, a2 is the weight of environmental data 2, and B2 is the second corresponding to environmental data 2. The value corresponding to the environment type. The numerical value corresponding to each second environment type may be the same or different, and the specific numerical value is not limited in this embodiment of the present application. The specific value of the weight corresponding to each environment type is not limited in this embodiment of the present application. After calculating the first value A, look up the correspondence between the preset value interval and the third environment type, obtain the third environment type corresponding to the value interval where the first value A is located, and use the obtained third environment type as the first Environment type. The division of the third environment type may be the same as or different from the second environment type, which is not limited in this embodiment of the present application.

In another possible implementation manner, in this step, the first environment type may also be determined by inputting the above-mentioned at least one kind of environment data into a pre-trained second model. At this point, this step can include:

Inputting the above at least one kind of environmental data into a preset second model, obtaining the environment type output by the second model, and obtaining the first environment type.

The second model is used to analyze the environmental types corresponding to the at least two types of environmental data. The second model can be obtained by AI model cultivation through AI cultivation. Specifically, a large number of training samples, such as more than a thousand training samples, can be "fed" to the AI machine. The network architecture and the neural network structure parameters are used to obtain the above-mentioned second model.

Optionally, the second model may be an AI-aware neural network composed of an AI-aware neural network accelerator and a recurrent neural network (RNN).

The specific training method of the second model may include: acquiring training samples, each training sample including: samples of each environmental data in at least two kinds of environmental data, and the environment type of the training sample; inputting the training samples into a preset model for training, Get the second model.

For example, assuming that the electronic device only acquires one type of environmental data, and the environmental data is sound data, the following AI basic model can be used as the initial model of the first model: P(X|V)=γ1X1, where X1 is the environment The sound data in , γ1 is the weighting parameter to be calculated in the AI cultivation process, P(X|V) is the environment type; wherein, if the environment data is light data, X1 in the above initial model can represent the light data in the environment . In the same way, the above initial model can also be extended to the case where the electronic device obtains at least two kinds of environmental data. Taking the electronic device to obtain two kinds of environmental data, and the two kinds of environmental data are sound data and light data, for example, the following can be used: The AI basic model is used as the initial model of the first model: P(X|V)=γ1X1+γ2X2, where X1 is the sound data in the environment, X2 is the light data in the environment, and γ1 and γ2 are to be calculated during the AI cultivation process. The weighting parameter of , P(X|V) is the environment type.

Step 203: The electronic device determines a first processing strategy of the target video clip according to the first environment type; the target video clip is a video clip to be played by the electronic device.

The target video clip and the video clip currently being played by the electronic device may be video clips of the same video file, or may be video clips of different video files. For example, if video file 1 is currently playing, video file 1 includes video clip 11 and video clip 12, after video file 1 is played, the next preset video file is automatically played, such as video file 2, video file 2 includes video clips 21 and video clip 22, then if the currently playing video clip is video clip 11, the target video clip can be video clip 12, and if the currently playing video clip is video clip 12, the target video clip can be video clip 12 twenty one. It should be noted that the above example takes the target video clip being the next video clip of the currently playing video clip as an example, and does not limit the positional relationship between the target video clip and the currently playing video clip, such as the target video clip. It may also be the second video clip after the currently playing video clip, etc., which is not limited in this application.

The corresponding relationship between the environment type and the processing strategy can be preset, and in this step, the corresponding relationship can be searched according to the first environment type to obtain the processing strategy corresponding to the first environment type as the first processing strategy.

When setting the processing policy corresponding to the environment type, it can be set based on whether the environment is suitable for watching videos when the user is in different environments, and the user's attention to the video being played. For example, if the environment type includes indoor and outdoor, the user When the light is too strong outdoors, it is not suitable for watching videos, and users generally pay less attention to the video being played by the electronic device. Therefore, the corresponding outdoor processing strategy can be more inclined to save the power of the electronic device. When the user is indoors Because the light is relatively soft and suitable for watching videos, users generally pay more attention to the video being played by the electronic device, and the corresponding indoor processing strategy can be more inclined to make the video played have better visual effects for the user.

The first processing strategy may include: the processing strategy of the image processor for the target video clip, and/or the processing strategy of the data processor for the target video clip, and/or the processing strategy of the display driver for the target video clip Strategy.

The processing strategy of the image processor may include, but is not limited to: the image rendering resolution, and/or the on/off state of the image sharpening algorithm, and/or the on/off state of the contrast enhancement algorithm;

The processing strategy of the data processor may include, but is not limited to: decoding accuracy, and/or, frame skipping, and/or, the frame rate of the target video clip, and/or, the video encapsulation format of the target video clip, and/or, the target video clip The bitrate stream of the video clip, and/or the resolution of the target video clip;

The processing strategy of the display driver may include, but is not limited to, the screen refresh rate, and/or the screen resolution.

Wherein, the above-mentioned image processor may be the GPU or Accelerated Processing Units (APU) described in FIG. 1 ; the data processor may be the DSP described in FIG. 1 . The high-power APU or GPU is in a deep sleep state most of the time, while the low-power SoC with AI processing capability is in a listening or monitoring state. When the AI accelerator running with low power consumption on the SoC detects a wake-up factor , the SoC is responsible for waking up the APU, while the APU executes more complex speech recognition algorithms and completes corresponding operations, such as playing music, or making voice calls. In such a system, the intelligent SoC and the APU are responsible for their respective responsibilities. Since the APU is in a deep sleep state most of the time, the overall power consumption can be controlled to a low level.

The image rendering resolution refers to the resolution of the video image output by the image processor. Generally speaking, the higher the image rendering resolution is, the more power is consumed by the electronic device to play the target video clip. On the contrary, the lower the image rendering resolution is, the more power is consumed by the electronic device to play the target video clip.

The image sharpening algorithm is an image processing method used in the image processor to make the edge of the video image clearer. Generally speaking, when the image sharpening algorithm is on, the electronic device consumes relatively more power to play the target video clip, and when the image sharpening algorithm is off, the electronic device consumes relatively less power to play the target video clip.

The contrast enhancement algorithm is an image processing method used in image processors to adjust the grayscale of pixels in a video image, which can improve the visual effect of the video image. Generally speaking, when the contrast enhancement algorithm is turned on, the electronic device consumes relatively more power to play the target video clip, and when the contrast enhancement algorithm is turned off, the electronic device consumes relatively less power to play the target video clip.

The decoding accuracy may be the decoding accuracy with which the data processor decodes the target video segment. Generally speaking, the higher the decoding accuracy is, the more power the electronic device consumes to play the target video clip, and the lower the decoding accuracy is, the less power the electronic device consumes to play the target video clip.

Frame skipping is a way to reduce the number of video frames displayed per second. You can set a number to identify the number of frames skipped each time. For example, the parameter value of frame skipping is 1, which means that one continuous frame of image is skipped, and the parameter of skipping frame A value of 2 indicates that 2 consecutive frames of images are skipped. The larger the number of skipped frames, the relatively greater the power consumed by the electronic device to play the target video clip, and the smaller the number of skipped frames, the less power consumed by the electronic device to play the target video clip.

The screen refresh rate refers to the number of times the screen is refreshed in a unit time, and the unit time may be, for example, 1 second. Generally speaking, the higher the screen refresh frequency is, the more power the electronic device consumes to play the target video clip, and the lower the screen refresh frequency is, the less power the electronic device consumes to play the target video clip.

Screen resolution refers to the number of pixels displayed on the screen vertically and horizontally, and the unit is px. The higher the screen resolution is set, the clearer the displayed video image, otherwise, the more blurred the displayed video image. Generally speaking, the higher the screen refresh frequency is, the more power the electronic device consumes to play the target video clip, and the higher the screen refresh frequency is, the less power the electronic device consumes to play the target video clip.

The frame rate of the video clip can be set to different values according to the different levels of the decoding bit rate. Continuing the above example, a relatively high frame rate can be set for the "indoor" environment type, which consumes a relatively large amount of power for electronic devices, which is The "outdoor" environment type sets a relatively low frame rate and consumes relatively little power on electronic devices.

Similar to the frame rate, the video encapsulation format can be set to different values according to the different levels of the decoding bit rate. Continuing the above example, a video encapsulation format with relatively good visual effects can be set for the "indoor" environment type, which can be "indoor". "This environment type sets a video package format with relatively poor visual effects. Taking the current mainstream MPEG2, VC-1 and H.264 package formats as examples, the general visual effect sequence is H.264>VC-1> MPEG2, you can set the video encapsulation format to H.264 for the "indoor" environment type, which consumes a relatively large amount of power for electronic devices. Setting MPEG2 for the "outdoor" environment type has relatively low power consumption for electronic devices. Small,.

Similar to the frame rate and video encapsulation format, the bit rate stream can be set to different values according to the different levels of the decoding bit rate. The power consumption of the device is relatively small.

Similarly, the resolution can be set to different values according to different levels of the decoding bit rate. The higher the decoding bit rate is, the higher the resolution is, and the lower the decoding bit rate is, the lower the resolution is. Continuing the previous example, you can set a relatively high resolution for the "indoor" environment type, such as 3840*2048, which consumes a relatively large amount of power for electronic devices, and set a relatively low resolution for the "outdoor" environment type rate, such as 1280*720, the power consumption of electronic equipment is relatively small.

Step 204: Play the target video segment according to the first processing strategy.

This step can include:

Receive the playback instruction for the target video clip, decode the code stream of the target video clip, render each frame of the target video clip according to the decoded data, and display each frame of the target video clip on the screen in turn video frame.

If the first processing strategy includes: the processing strategy of the data processor for the target video clip, then the electronic device can use the data processor to process the code stream of the target video clip according to the processing strategy of the data processor for the target video clip. decoding.

If the first processing strategy includes: the processing strategy of the image processor for the target video clip, then the electronic device can use the image processor to perform processing on each of the target video clips according to the above-mentioned processing strategy of the image processor for the target video clip. frame video frames for rendering.

If the first processing strategy includes: the processing strategy of the display driver for the target video clip, then the electronic device can use the display driver to process each frame of the video frame in the target video clip according to the above-mentioned processing strategy of the display driver for the target video clip. to display.

In the method shown in FIG. 2, the processing strategy of the target video segment is adjusted according to the environmental data, so that a processing strategy with relatively better visual effect can be provided in an environment where the user pays high attention to the video played by the electronic device. Provide a processing strategy that saves the power of the electronic device in an environment with low attention to the played video, so as to dynamically adjust the processing strategy of the video clip, so that the electronic device can meet the user's viewing needs when playing the video, and use the electronic device more reasonably. The power of the device to achieve the purpose of saving power.

Optionally, referring to FIG. 3, before step 201, it may further include:

Step 301: The electronic device receives a playback instruction for the target video file, divides the target video file into video segments, and determines the target video segment.

Among them, the user can instruct to play the video file by selecting a video file and selecting the "play" control for the video file. Correspondingly, the electronic device can receive the playback instruction for the target video file, and the target video file also That is, the video file selected by the user.

When the target video file is divided, the lengths of the divided video segments may be the same or different, and the number of video segments divided by the target video file is not limited in this embodiment of the present application, and may be any natural number. It should be noted that the minimum unit in the general target video file may be a video frame, and the minimum video segment may be a video frame.

Wherein, in step 201, the video clips obtained by dividing the target video file may be sequentially regarded as the target video clips according to the playing order. Optionally, for the timeliness of playing the target video file, a certain number of video clips at the front of the target video file can be played directly according to the preset processing strategy, and the video clips after the above-mentioned certain number of video clips can be sequentially used as target video clip. The specific value of the above-mentioned certain number is not limited in the embodiments of the present application, and is related to the length of the video clip, the processing speed of the electronic device, etc., and can be specifically set based on the angle that the electronic device can provide users with a smooth video playback effect; Considering power saving, the above-mentioned processing strategy used by the above-mentioned certain number of video clips may be a processing strategy that makes the visual effect of video playback relatively poor, or, based on the user's viewing effect, the above-mentioned preset processing strategy may be to make the video A processing strategy with relatively good visual effects of playback is not limited in this embodiment of the present application.

FIG. 4A is a flowchart of another embodiment of the video playback method of the present application. As shown in FIG. 4A , the method may include:

Step 401: The electronic device acquires at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data.

For the implementation of this step, reference may be made to the description in step 201, which is not repeated here.

Step 402: The electronic device obtains at least one kind of data of the target video clip, and the at least one kind of data of the target video clip includes: sound data, and/or image data, and/or subtitle data; the target video clip is the video to be played by the electronic device Fragment.

The execution order between step 401 and step 402 is not limited.

For the realization of the target video segment in this step, reference may be made to the corresponding description in step 202, which is not repeated here.

Step 403: The electronic device inputs at least one kind of environmental data and at least one kind of data of the target video clip into the first model to obtain a first processing strategy of the target video clip, and the first model is used to output the processing strategy of the video clip.

Optionally, the first model can be obtained by cultivating an AI model by means of AI cultivating. Specifically, a large number of training samples, such as more than 1,000 training samples, can be "fed" to the AI machine. The network architecture and neural network structure parameters of the processing strategy are obtained to obtain the above-mentioned first model.

Optionally, the first model may be an AI-sensing neural network composed of an AI-sensing neural network accelerator and a recurrent neural network (RNN).

The specific training method of the first model may include: acquiring training samples marked with processing strategies; each of the training samples includes: samples of each environmental data in the at least one type of environmental data, at least one type of data of the video clip Samples of each kind of data in; input the training samples into a preset model for training to obtain the first model. Referring to FIG. 4B , a schematic diagram of a training method of the first model is shown by taking the preset model as an AI basic model as an example.

For example, assuming that the electronic device only obtains one type of environmental data, and the environmental data is sound data, and obtains the image data and sound data of the target video clip, the following AI basic model can be used as the initial model of the first model: P(X |V)=α1X1+α2Y1+α3Y2=β1Z1+β2Z2, where X1 is the sound data in the environment, Y1 is the sound data of the target video clip, Y2 is the image data of the target video clip, and Z1 represents the processing strategy of the image processor , Z2 represents the processing strategy of the display driver, α1, α2, α3, β1, and β2 are the weighting parameters to be calculated during the AI cultivation process, and P(X|V) is the first processing strategy of the target video clip; is light data, then X1 in the above initial model can represent light data in the environment. Similarly, the above-mentioned initial model can also be extended to the situation of several kinds of environmental data and the situation of data of several kinds of target video clips, which will not be listed one by one here.

Further, the sound data in the above-mentioned initial model can also be further subdivided into data such as volume, timbre, audio frequency, and spatial distribution of sound. The weighting parameters of each kind of sound data are calculated through training, so that the first model can distinguish the environment more accurately. Similarly, if the above initial model includes light data, the light data can also be subdivided into data such as light intensity, light band, and illuminance change. , the weighting parameters of each light data are calculated by means of sample training, so that the first model can distinguish the environment more accurately.

Wherein, when annotating the processing strategy for the training sample, it can be set based on whether the user is suitable for watching the video in the scene corresponding to the training sample, and the user's attention to the video being played. For example, if the environment type includes indoor and outdoor, and the data of the video clip is image data, then the user is not suitable for watching the video because the light is too strong outdoors, and the image data played by the video clip is a landscape picture, then the user The attention to the video being played by the electronic device is relatively small. Therefore, the processing strategy annotated for this training sample can be more inclined to save the power of the electronic device. When the user is indoors, the light is softer and is suitable for watching the video. Moreover, the video The image data played by the clip is a character fighting scene, and the user pays relatively more attention to the video being played by the electronic device. The processing strategy marked for the training sample can be more inclined to make the played video more attractive to the user. Visual effects.

Step 404: The electronic device plays the target video clip according to the first processing strategy.

For the implementation of this step, reference may be made to the description in step 201, which is not repeated here.

Optionally, referring to FIG. 5, before step 401, it may further include:

Step 501: The electronic device receives a playback instruction for the target video file, divides the target video file into video segments, and determines the target video segment.

For the implementation of this step, reference may be made to the description in step 301, which is not repeated here.

In the methods shown in FIGS. 4A and 5 , the processing strategy of the video is dynamically adjusted according to the environmental data and the data included in the target video segment, so that the processing strategy can be automatically adjusted during the video playback process, so that the electronic device consumes more power to play the video. In order to be reasonable and achieve the purpose of saving electricity.

It can be understood that, some or all of the steps or operations in the foregoing embodiments are only examples, and other operations or variations of various operations may also be performed in the embodiments of the present application. Furthermore, the various steps may be performed in a different order presented in the above-described embodiments, and may not perform all operations in the above-described embodiments.

FIG. 6 is a structural diagram of an embodiment of a video playback device of the present application. As shown in FIG. 6 , the device 600 may include:

The first acquiring unit 610 is configured to acquire at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

The second obtaining unit 620 is configured to obtain at least one kind of data of the target video clip, where the at least one kind of data of the target video clip includes: sound data, and/or image data, and/or subtitle data; the target video clip is the video clip to be played by the electronic device;

A strategy decision unit 630, configured to input the at least one kind of environmental data and at least one kind of data of the target video clip into a first model to obtain a first processing strategy of the target video clip, and the first model is used for Analyze the processing strategy of video clips;

The playing unit 640 is configured to play the target video segment according to the first processing strategy.

Optionally, the first processing strategy includes: a processing strategy of an image processor for the target video clip, and/or a processing strategy of a data processor for the target video clip, and/or a display driver The processing strategy for the target video segment.

Optionally, the first processing strategy includes: a processing strategy of the data processor for the target video clip, and the playing unit 640 may be specifically configured to: for the target video clip, perform according to the first processing strategy. According to the processing strategy of the target video clip, the data processor performs decoding processing on the code stream of the target video clip to obtain decoded data.

Optionally, the first processing strategy includes: a processing strategy of the image processor for the target video clip, and the playing unit 640 may be specifically configured to: for each video frame in the target video clip, according to the In the first processing strategy, the image processor performs rendering processing on the video frame according to the processing strategy of the target video segment.

Optionally, the first processing strategy includes: a processing strategy of the display driver for the target video clip, and the playing unit 640 may be specifically configured to: for each video frame in the target video clip, according to the first In a processing strategy, the display driver displays the video frame according to the processing strategy of the target video segment.

Optionally, the processing strategy of the image processor for the target video segment includes: an image rendering resolution, and/or an on-off state of an image sharpening algorithm, and/or a on-off state of an enhanced contrast algorithm;

and / or,

The processing strategy of the data processor for the target video clip includes: decoding accuracy, and/or, frame skipping, and/or, the frame rate of the target video clip, and/or, the video encapsulation format of the target video clip, and/or, the bit rate stream of the target video clip, and/or, the resolution of the target video clip;

and / or,

The processing strategy of the display driver for the target video segment includes: screen refresh rate and/or screen resolution.

Optionally, it also includes: a model training unit, configured to obtain training samples marked with processing strategies; each of the training samples includes: samples of each environmental data in the at least one type of environmental data, the at least one type of data Samples of each kind of data in; input the training samples into a preset model for training to obtain the first model.

Optionally, the first model is an AI perception neural network composed of an AI perception neural network accelerator and a recurrent neural network.

FIG. 7 is a structural diagram of an embodiment of a video playback apparatus of the present application. As shown in FIG. 7 , the apparatus 700 may include:

an acquisition unit 710, configured to acquire at least one type of environmental data; the at least one type of environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

a first determining unit 720, configured to determine a first environment type according to the at least one type of environment data;

a second determining unit 730, configured to determine a first processing strategy of a target video clip according to the first environment type; the target video clip is a video clip to be played by the electronic device;

The playing unit 740 is configured to play the target video segment according to the first processing strategy.

Optionally, if a type of environmental data is acquired, the first determining unit 720 may be specifically configured to: for the type of environmental data, according to the corresponding relationship between the data interval preset for this type of environmental data and the second environmental type , and determine the second environment type corresponding to the acquired environment data as the first environment type.

Optionally, if at least two types of environmental data are acquired, the first determining unit 720 may be specifically configured to: for each type of environmental data, according to the corresponding relationship between the data interval preset for this type of environmental data and the second environmental type , determine the second environment type corresponding to the obtained environment data; determine the first environment type according to the second environment type corresponding to each obtained environment data.

Optionally, the first determining unit 720 may be specifically configured to: calculate the first value according to the obtained preset weight of each environmental data and the value corresponding to the second environment type; according to the preset value interval and the first value; The correspondence between the three environment types is determined, and the third environment type corresponding to the first value is determined to obtain the first environment type.

Optionally, the second determining unit 730 may be specifically configured to: determine the processing strategy corresponding to the first environment type according to the preset correspondence between the environment type and the processing strategy, as the first processing strategy; The first processing strategy includes: the processing strategy of the image processor for the target video clip, and/or the processing strategy of the data processor for the target video clip, and/or the display driver for the target The processing strategy for video clips.

Optionally, the first processing strategy includes: a processing strategy of the data processor for the target video clip, and the playing unit 740 may be specifically configured to: for the target video clip, perform according to the first processing strategy. According to the processing strategy of the target video clip, the data processor performs decoding processing on the code stream of the target video clip to obtain decoded data.

Optionally, the first processing strategy includes: a processing strategy of the image processor for the target video clip, and the playing unit 740 may be specifically configured to: for each video frame in the target video clip, according to the In the first processing strategy, the image processor performs rendering processing on the video frame according to the processing strategy of the target video segment.

Optionally, the first processing strategy includes: a processing strategy of the display driver for the target video clip, and the playing unit 740 may be specifically configured to: for each video frame in the target video clip, according to the first In a processing strategy, the display driver displays the video frame according to the processing strategy of the target video segment.

Optionally, the processing strategy of the image processor for the target video segment includes: an image rendering resolution, and/or an on-off state of an image sharpening algorithm, and/or a on-off state of an enhanced contrast algorithm;

and / or,

The processing strategy of the data processor for the target video clip includes: decoding accuracy, and/or, frame skipping, and/or, the frame rate of the target video clip, and/or, the video encapsulation format of the target video clip, and/or, the bit rate stream of the target video clip, and/or, the resolution of the target video clip;

and / or,

The processing strategy of the display driver for the target video segment includes: screen refresh rate and/or screen resolution.

The apparatuses provided by the embodiments shown in FIG. 6 to FIG. 7 can be used to implement the technical solutions of the method embodiments shown in FIG. 2 to FIG. 5 of the present application, and the implementation principles and technical effects may further refer to the relevant descriptions in the method embodiments.

It should be understood that the division of each unit of the apparatus shown in FIG. 6 to FIG. 7 is only a division of logical functions, and may be fully or partially integrated into a physical entity in actual implementation, or may be physically separated. And these units can all be implemented in the form of software calling through processing elements; they can also all be implemented in hardware; some units can also be implemented in the form of software calling through processing elements, and some units can be implemented in hardware. For example, the playback unit may be a separately established processing element, or may be integrated in a certain chip of the electronic device. The implementation of other units is similar. In addition, all or part of these units can be integrated together, and can also be implemented independently. In the implementation process, each step of the above-mentioned method or each of the above-mentioned units may be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software.

For example, the above units may be one or more integrated circuits configured to implement the above method, such as: one or more specific integrated circuits (Application Specific Integrated Circuit; hereinafter referred to as: ASIC), or one or more microprocessors A digital processor (Digital Singnal Processor; hereinafter referred to as: DSP), or, one or more Field Programmable Gate Arrays (Field Programmable Gate Array; hereinafter referred to as: FPGA), etc. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (System-On-a-Chip; hereinafter referred to as: SOC).

As shown in FIG. 8 , the process from detecting a user operation to displaying a video in the prior art includes the following stages:

The user executes an operation instruction for video playback in the UI interface, and accordingly, the electronic device detects the user's operation event;

The operating system of the electronic device is scheduled and configured based on the user's operation events;

The driver layer performs concrete function conversion;

The SOC executes the corresponding assembly instructions;

The GPU/DSP performs graphics operations corresponding to the video data; the graphics operations include decoding the video data.

The display driver performs digital-to-analog conversion on the data obtained after the graphics operation to obtain an analog signal for display;

The monitor displays video based on an analog signal.

Based on the foregoing embodiments of the present application, before the GPU/DSP performs graphics operations on the video data, a processing strategy for the video clip can be obtained based on the environment data and the video data, so that the GPU/DSP and the display driver can perform the video clip based on the processing strategy. processing. After adding the data processing of the embodiment of the present application, as shown in FIG. 9 , the following parts can be added to the process from detecting the user operation to displaying the video:

A receiving interface for environmental data and an AI perception computing module are added to the GPU/DSP. The receiving interface for environmental data is used to receive environmental data output by environmental sensors; a first model can be set in the AI perception computing module to combine at least one environmental data and At least one kind of data of the target video clip is input into the first model to obtain the first processing strategy of the target video clip;

After that, the GPU/DSP can perform subsequent graphics operations according to the first processing strategy, and the graphics operations are graphics operations optimized based on the first processing strategy.

The present application also provides an electronic device, comprising: a display screen; one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, the One or more computer programs include instructions, which, when executed by the device, cause the device to execute the methods provided by the embodiments shown in FIGS. 2 to 5 of the present application.

The present application also provides an electronic device, the device includes a storage medium and a central processing unit, the storage medium may be a non-volatile storage medium, and a computer-executable program is stored in the storage medium, and the central processing unit is connected to the central processing unit. The non-volatile storage medium is connected, and the computer-executable program is executed to implement the method provided by the embodiments shown in FIG. 2 to FIG. 5 of the present application.

Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when it runs on a computer, the computer causes the computer to execute the programs provided by the embodiments shown in FIGS. 2 to 5 of the present application. method.

Embodiments of the present application further provide a computer program product, where the computer program product includes a computer program that, when running on a computer, enables the computer to execute the methods provided by the embodiments shown in FIGS. 2 to 5 of the present application.

In the embodiments of the present application, "at least one" refers to one or more, and "multiple" refers to two or more. "And/or", which describes the association relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can indicate the existence of A alone, the existence of A and B at the same time, and the existence of B alone. where A and B can be singular or plural. The character "/" generally indicates that the associated objects are an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c may be single, or Can be multiple.

Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (Read-Only Memory; hereinafter referred to as: ROM), Random Access Memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk and other various A medium on which program code can be stored.

The above are only specific embodiments of the present application. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application. The protection scope of the present application shall be subject to the protection scope of the claims.

Claims (16)

1. A video processing method based on AI model is characterized by comprising the following steps:

acquiring at least one environmental data; the at least one environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

acquiring at least one data of a target video segment, wherein the at least one data of the target video segment comprises: sound data, and/or image data, and/or subtitle data; the target video clip is a video clip to be played by the electronic equipment;

inputting the at least one environmental data and the at least one data of the target video segment into a first model to obtain a first processing strategy of the target video segment, wherein the first model is used for analyzing the processing strategy of the video segment;

and playing the target video clip according to the first processing strategy.

2. The method of claim 1, wherein the first processing policy comprises: a processing strategy of the image processor for the target video segment, and/or a processing strategy of the data processor for the target video segment, and/or a processing strategy of the display driver for the target video segment.

3. The method of claim 2, wherein the first processing policy comprises: the data processor, aiming at the processing policy of the target video segment, playing the target video segment according to the first processing policy, includes:

and for the target video clip, decoding the code stream of the target video clip according to the processing strategy of the data processor for the target video clip in the first processing strategy to obtain decoded data.

4. The method of claim 2, wherein the first processing policy comprises: the image processor, aiming at the processing strategy of the target video segment, playing the target video segment according to the first processing strategy, including:

and for each video frame in the target video segment, rendering the video frame according to the processing strategy of the image processor for the target video segment in the first processing strategy.

5. The method of claim 2, wherein the first processing policy comprises: the display driver is used for aiming at the processing strategy of the target video segment, and playing the target video segment according to the first processing strategy comprises the following steps:

for each video frame in the target video segment, displaying the video frame according to the processing strategy of the display driver for the target video segment in the first processing strategy.

6. The method according to any one of claims 2 to 5, wherein the processing strategy of the image processor for the target video segment comprises: an image rendering resolution, and/or an on-off state of an image sharpening algorithm, and/or an on-off state of a contrast enhancement algorithm;

and/or the presence of a gas in the gas,

the processing strategy of the data processor for the target video segment comprises: decoding accuracy, and/or frame skipping, and/or frame rate of the target video segment, and/or video encapsulation format of the target video segment, and/or bitrate streaming of the target video segment, and/or resolution of the target video segment;

and/or the presence of a gas in the gas,

the processing strategy of the display driver for the target video segment comprises: screen refresh frequency, and/or screen resolution.

7. The method according to any one of claims 2 to 5, wherein the first model is trained in advance, and the training method comprises:

acquiring a training sample marked with a processing strategy; each of the training samples comprises: a sample of each of the at least one environmental data, a sample of each of the at least one data;

and inputting the training sample into a preset model for training to obtain the first model.

8. The method of any one of claims 1 to 7, wherein the first model is an Artificial Intelligence (AI) -aware neural network consisting of an AI-aware neural network accelerator and a recurrent neural network.

9. A video processing method applied to an electronic device is characterized by comprising the following steps:

acquiring at least one environmental data; the at least one environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

determining a first environment type according to the at least one environment data;

determining a first processing strategy of a target video clip according to the first environment type; the target video clip is a video clip to be played by the electronic equipment;

and playing the target video clip according to the first processing strategy.

10. The method of claim 9, wherein if one environment data is obtained, said determining a first environment type based on the at least one environment data comprises:

for the environment data, determining a second environment type corresponding to the acquired environment data as the first environment type according to a corresponding relation between a data interval preset for the environment data and the second environment type;

or,

if at least two types of environment data are acquired, the determining a first environment type according to the at least one type of environment data comprises:

for each environment data, determining a second environment type corresponding to the acquired environment data according to a corresponding relation between a data interval preset for the environment data and the second environment type;

and determining the first environment type according to the second environment type corresponding to each acquired environment data.

11. The method according to claim 10, wherein the determining the first environment type according to the second environment type corresponding to each acquired environment data includes:

calculating a first numerical value according to the preset weight of each acquired environment data and the numerical value corresponding to the second environment type;

and determining a third environment type corresponding to the first numerical value according to a corresponding relation between a preset numerical value interval and the third environment type to obtain the first environment type.

12. The method according to any one of claims 9 to 11, wherein the determining a first processing policy for a target video according to the first environment type comprises:

determining a processing strategy corresponding to the first environment type as the first processing strategy according to a corresponding relation between a preset environment type and the processing strategy; the first processing strategy comprises: a processing strategy of the image processor for the target video segment, and/or a processing strategy of the data processor for the target video segment, and/or a processing strategy of the display driver for the target video segment.

13. The method of claim 12, wherein the first processing policy comprises: the data processor, aiming at the processing policy of the target video segment, playing the target video segment according to the first processing policy, includes:

for the target video segment, decoding the code stream of the target video segment according to the processing strategy of the data processor for the target video segment in the first processing strategy to obtain decoded data;

and/or the presence of a gas in the gas,

the first processing strategy comprises: the image processor, aiming at the processing strategy of the target video segment, playing the target video segment according to the first processing strategy, including:

for each video frame in the target video segment, rendering the video frame according to the processing strategy of the image processor for the target video segment in the first processing strategy;

and/or the presence of a gas in the gas,

the first processing strategy comprises: the display driver is used for aiming at the processing strategy of the target video segment, and playing the target video segment according to the first processing strategy comprises the following steps:

for each video frame in the target video segment, displaying the video frame according to the processing strategy of the display driver for the target video segment in the first processing strategy.

14. The method of claim 13, wherein the processing strategy of the image processor for the target video segment comprises: an image rendering resolution, and/or an on-off state of an image sharpening algorithm, and/or an on-off state of a contrast enhancement algorithm;

and/or the presence of a gas in the gas,

the processing strategy of the data processor for the target video segment comprises: decoding accuracy, and/or frame skipping, and/or frame rate of the target video segment, and/or video encapsulation format of the target video segment, and/or bitrate streaming of the target video segment, and/or resolution of the target video segment;

and/or the presence of a gas in the gas,

the processing strategy of the display driver for the target video segment comprises: screen refresh frequency, and/or screen resolution.

15. A portable electronic device, comprising:

a first obtaining unit, configured to obtain at least one environmental data; the at least one environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

a second obtaining unit, configured to obtain at least one type of data of a target video segment, where the at least one type of data of the target video segment includes: sound data, and/or image data, and/or subtitle data; the target video clip is a video clip to be played by the electronic equipment;

a policy decision unit, configured to input the at least one environmental data and the at least one data of the target video segment into a first model, so as to obtain a first processing policy of the target video segment, where the first model is used to analyze a processing policy of a video segment;

and the playing unit is used for playing the target video clip according to the first processing strategy.

16. A portable electronic device, comprising:

an acquisition unit for acquiring at least one environmental data; the at least one environmental data includes: light data, and/or sound data, and/or air temperature data, and/or air pressure data;

a first determining unit, configured to determine a first environment type according to the at least one environment data;

a second determining unit, configured to determine a first processing policy of the target video segment according to the first environment type; the target video clip is a video clip to be played by the electronic equipment;

and the playing unit is used for playing the target video clip according to the first processing strategy.

Images