WO2021047181A1

WO2021047181A1 - Video type-based playback control implementation method and apparatus, and computer device

Info

Publication number: WO2021047181A1
Application number: PCT/CN2020/087026
Authority: WO
Inventors: 齐燕
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2019-09-11
Filing date: 2020-04-26
Publication date: 2021-03-18
Also published as: CN110740343B; CN110740343A

Abstract

Disclosed in the present invention are a video type-based playback control implementation method and apparatus, a computer device and a storage medium. Said method comprises: acquiring a video file to be played back currently corresponding to a video selection instruction; if said video file does not comprise a program type tag, inputting a plurality of selected video images into a convolutional neural network to obtain a video program type; according to the video program type corresponding to said video file and a video type playback strategy, acquiring corresponding playback mode information and sending same to a corresponding user terminal; and if a corresponding operation approval instruction is detected, decomposing said video file into a corresponding audio-video file and/or video file, assembling same into corresponding playback data and sending same to the user terminal. Said method achieves acquiring, on the basis of the video type of a video file to be played back currently, playback mode information and corresponding playback data, and achieves power saving control on the user terminal according to the playback mode information.

Description

Method, device and computer equipment for implementing playback control based on video type

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on September 11, 2019, the application number is 201910858320.3, and the invention title is "Video type-based playback control implementation methods, devices, and computer equipment". The entire content is approved The reference is incorporated in this application.

Technical field

This application relates to the field of image recognition technology, and in particular to a method, device, computer equipment, and storage medium for implementing video type-based playback control.

Background technique

At present, more and more users use the video software of smart terminals to watch videos online (that is, the video server sends the streaming data of the video to the local buffer of the smart terminal for playback). Videos can be divided into different video types according to their video content. (Such as news programs, sports programs, variety shows, etc.). The inventor realized that when general video software plays video content, regardless of any video type, it will run on the front end of the smart terminal and perform video playback. The display screen of the smart terminal needs to be bright for playback, resulting in the video server being unable to display the video on the smart terminal. Perform power saving control.

Summary of the invention

The embodiments of the present application provide a method, device, computer equipment and storage medium for implementing playback control based on video types, aiming to solve the problem that the video software of the smart terminal in the prior art will play video content regardless of any video type. When running and playing video at the front end of the smart terminal, the display of the smart terminal needs to be on for a long time to play, which causes the problem that the video server cannot perform power saving control on the smart terminal.

In the first aspect, an embodiment of the present application provides a method for implementing playback control based on a video type, which includes:

If a video selection instruction is detected, obtain the current to-be-played video file corresponding to the video selection instruction;

Judging whether the currently to-be-played video file includes a video program type tag;

If the currently to-be-played video file does not include the program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network network to obtain the video program type;

If the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag;

According to the video program type corresponding to the currently to-be-played video file and the preset video type play strategy, the play mode information corresponding to the currently-to-be-played video file is obtained and sent to the corresponding user terminal; wherein, the video type play strategy Including a variety of video program types, and one-to-one corresponding playback mode information for each video program type; and

If the consent operation instruction corresponding to the playing mode information of the currently to-be-played video file is detected, the currently-to-be-played video file is decomposed into corresponding audio-visual files and/or video files to assemble into corresponding playback data And sent to the user terminal.

In the second aspect, an embodiment of the present application provides a video type-based playback control implementation device, which includes:

The video selection unit is configured to, if a video selection instruction is detected, obtain a current to-be-played video file corresponding to the video selection instruction;

A video tag determining unit, configured to determine whether the currently to-be-played video file includes a video program type tag;

The first program type acquiring unit is configured to, if the currently to-be-played video file does not include a program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network, Get the type of video program;

The second program type acquiring unit is configured to, if the currently to-be-played video file includes a program type tag, acquire the video program type corresponding to the currently-to-be-played video file according to the program type tag;

The playing mode information obtaining unit is configured to obtain the playing mode information corresponding to the current to-be-played video file according to the video program type corresponding to the current to-be-played video file and the preset video type playing strategy, and send it to the corresponding user terminal; Wherein, the video type play strategy includes multiple video program types, and play mode information corresponding to each video program type one-to-one; and

The playback data sending unit is configured to, if an agreed operation instruction corresponding to the playback mode information of the currently to-be-played video file is detected, decompose the currently-to-be-played video file into corresponding audio-visual files and/or video files, It can be assembled into corresponding playback data and sent to the user terminal.

In a third aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and running on the processor, and the processor executes the computer A video type-based playback control implementation method is implemented during the program. The method includes: if a video selection instruction is detected, obtaining a current to-be-played video file corresponding to the video selection instruction; and judging whether the currently-to-be-played video file includes a video Program type tag; if the currently to-be-played video file does not include a program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network to obtain the video program type; If the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag; play according to the video program type corresponding to the current to-be-played video file and the preset video type Strategy, to obtain the playback mode information corresponding to the currently to-be-played video file and send it to the corresponding user terminal; wherein, the video type playback strategy includes multiple video program types and one-to-one playback corresponding to each video program type Mode information; and if an agreed operation instruction corresponding to the playback mode information of the current to-be-played video file is detected, the current to-be-played video file is decomposed into corresponding audio-visual files and/or video files to be assembled into The corresponding playback data is sent to the user terminal.

In a fourth aspect, the embodiments of the present application also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes a video-based Type of playback control implementation method, the method includes: if a video selection instruction is detected, obtaining a current to-be-played video file corresponding to the video selection instruction; judging whether the current to-be-played video file includes a video program type tag; if If the currently to-be-played video file does not include the program type tag, the selected multi-frame video image in the currently-to-be-played video file is input to a pre-trained convolutional neural network network to obtain the video program type; The video file to be played includes a program type tag, and the video program type corresponding to the current to-be-played video file is obtained according to the program type tag; according to the video program type corresponding to the currently-to-be-played video file and the preset video type playback strategy, the data is obtained The playing mode information corresponding to the current video file to be played is sent to the corresponding user terminal; wherein, the video type playing strategy includes multiple video program types, and the playing mode information corresponding to each video program type one-to-one; and if The consent operation instruction corresponding to the playing mode information of the currently to-be-played video file is detected, and the currently-to-be-played video file is decomposed into corresponding audio-visual files and/or video files to assemble into corresponding playback data and Send to the user terminal.

The embodiments of the present application provide a method, a device, a computer device, and a storage medium for implementing playback control based on a video type. The method realizes that based on the video type of the current to-be-played video file, the playing mode information and the corresponding playing data are obtained, and the power saving control of the user terminal is realized according to the playing mode information.

Description of the drawings

FIG. 1 is a schematic diagram of an application scenario of a method for implementing playback control based on a video type provided by an embodiment of the application;

2 is a schematic flowchart of a method for implementing video type-based playback control provided by an embodiment of the application;

3 is a schematic diagram of a sub-flow of a method for implementing video type-based playback control provided by an embodiment of the application;

4 is a schematic diagram of another sub-flow of the method for implementing video type-based playback control according to an embodiment of the application;

FIG. 5 is a schematic block diagram of a device for implementing playback control based on video types according to an embodiment of the application;

6 is a schematic block diagram of subunits of the device for implementing video type-based playback control according to an embodiment of the application;

FIG. 7 is a schematic block diagram of another subunit of the device for implementing video type-based playback control according to an embodiment of the application; FIG.

FIG. 8 is a schematic block diagram of a computer device provided by an embodiment of the application.

detailed description

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Please refer to Figures 1 and 2. Figure 1 is a schematic diagram of an application scenario of a method for implementing video type-based playback control provided by an embodiment of this application; Figure 2 is a schematic flowchart of a method for implementing video type-based playback control provided by an embodiment of this application The method for implementing playback control based on video types is applied to a server, and the method is executed by application software installed in the server.

As shown in Figure 2, the method includes steps S110 to S160.

S110: If a video selection instruction is detected, obtain a current to-be-played video file corresponding to the video selection instruction.

In this embodiment, when the user opens the user interaction interface of the video software on the user terminal (such as a smart phone, a tablet computer, etc.), a video file to be played needs to be selected. Once the video file to be played is selected, the user terminal will This video selection instruction is sent to the video server. The video server obtains the video selection instruction, and correspondingly obtains the current to-be-played video file. Among them, the video file to be played can be a video file with a limited duration (such as a movie, a short video, etc., and the video file with a limited duration can be a video file that includes a single video program type, or it can include multiple video programs. Types of video files), or live video (for example, the online program of TV A, the live video broadcasts different types of video programs in different time periods).

S120: Determine whether the currently to-be-played video file includes a video program type tag.

In this embodiment, since the currently to-be-played video file selected by the user may have been set with a video program type tag, or it may not have been set, in order to determine the playback of the currently-to-be-played video file in the subsequent steps Method, you need to determine the video program type first according to the video program type tag or video content recognition.

S130: If the currently to-be-played video file does not include the program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network network to obtain the video program type.

In this embodiment, if the currently to-be-played video file does not include the program type tag, it means that the video server is required to identify the video program type of the currently-to-be-played video file. After the video server obtains the currently to-be-played video file, in order to determine the type of its video program (such as news programs, real-time review programs, recitation programs, sports programs, variety shows, movie programs, etc.), it is necessary to set the currently-to-be-played video files The video file is split into video to obtain multiple frames of video images. Then, according to the pre-trained convolutional neural network network, the multi-frame video images obtained by the split can be identified, so as to obtain the corresponding video program type.

In an embodiment, as shown in FIG. 3, step S130 includes:

S131: Acquire multiple frames of video images in the video image set corresponding to the currently to-be-played video file at a preset interval number, as a target image set;

S132. Input the target image set to the convolutional neural network to obtain the program type corresponding to each frame of video image in the target image set;

S133. If the total number of types is greater than 1, sequentially obtain the program type corresponding to each frame of video image in the target image set to form a program type sequence, and divide two adjacent program types in the program type sequence into different programs Insert a separator between the types;

S134: Locate the separation time point corresponding to each separator inserted in the program type sequence, and divide the current to-be-played video file into corresponding play segments through each separation time point;

S135. Obtain video program types corresponding to each playback segment in the currently to-be-played video file in sequence.

In this embodiment, when acquiring multiple frames of video images in the video image set corresponding to the currently to-be-played video file according to a preset number of intervals, the preset number of intervals may be set to 12. Generally, a 1 second video can be split into 24 frames of images, and the current video file to be played with a duration of N minutes can be split into 24N video images. At this time, the first frame of video image can be used as the starting point, and the 13th frame can also be selected. 25,..., 1+12n (where 1+12n≤24N) frames of video images form the target image set. In the specific implementation of step S131, another implementation manner may be adopted, that is, multiple frames of video images in the video image set corresponding to the current to-be-played video file are randomly obtained as the target image set.

After that, the target image set is input to the convolutional neural network, the program type corresponding to each frame of the video image in the target image set can be obtained through the convolutional neural network, and then the convolutional neural network obtains all The total number of types in the program types corresponding to each frame of video image in the target image set.

When the total number of types is greater than 1, it means that there are two or more program types in the current to-be-played video file. At this time, in order to effectively divide the current to-be-played video file, you can locate the program type sequence at this time For the separation time point corresponding to each of the inserted separators, the current to-be-played video file is divided into corresponding play segments through each separation time point;

For example, the program type sequence is [News Program News Program News Program News Program Sports Program Sports Program Sports Program Sports Program Variety Program Variety Program Variety Program Variety Program Variety Program Variety Program...Variety Program]

The program type sequence after inserting the separator is [News Program News Program News Program News Program|Sports Program Sports Program Sports Program Sports Program|Variety Program Variety Program Variety Program Variety Program Variety Program Variety Program Variety Program...Variety Program].

In the above program type sequence, the first separator is between the news program in the fourth place and the sports program in the fifth place, and the second separator is between the sports program in the eighth place and the variety show in the ninth place. Obtain the first separation time point corresponding to the first separator and the second separation time point corresponding to the second separator (where the first separation time point is recorded as the start time corresponding to the fifth place sports program, where the The two separate time points are recorded as the start time corresponding to the ninth variety show). Then the time between the start time point corresponding to the first news program and the first separation time point is recorded as the first play segment, and the time between the first separation time point and the second separation time point is recorded as the second play segment, and the second The interval between the separation time point and the end time point corresponding to the last variety show is recorded as the third play segment. After the above division is completed, the video program types corresponding to each playback segment in the current to-be-played video file are sequentially acquired. The convolutional neural network can effectively identify the video program type included in the currently to-be-played video file, so as to facilitate subsequent control of the video file playback mode according to the video program type.

In an embodiment, as shown in FIG. 4, before step S130 or step S110, the method further includes:

S1101: Divide the video program into multiple video program types;

S1102: Obtain video samples of each video program type;

S1103: Extract image feature data of each frame of image in the video sample as a training set;

S1104. Input the training set to the convolutional neural network to be trained for training to obtain the convolutional neural network.

In this embodiment, when the convolutional neural network is trained in advance, for example, the image feature of the movie program is that the image feature in the movie scene is the upper and lower or left and right black borders in the movie scene, so the right of the image in the image can be increased. The upper and lower or left and right black borders are used as image feature data; the image characteristics of news programs are the upper left corner of the station logo and the lower subtitles in the news scene, so the station logo and subtitles can be extracted as image feature data. After the convolutional neural network is trained in the above manner, it can be used to identify the video program type corresponding to the video image.

In an embodiment, after step S132, the method further includes:

S136: If the total number of types is equal to 1, obtain the video program type corresponding to the currently to-be-played video file.

In this embodiment, if the total number of types is equal to 1, it means that there is only one program type in the current to-be-played video file, and there is no need to divide the current to-be-played video file to identify the corresponding video program type. , Directly use the current program type of the currently to-be-played video file as the corresponding video program type.

S140: If the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag.

In this embodiment, that is, if the program type tag of the current video file to be played has been set, the corresponding video program type can be directly extracted, without the need to use the convolutional neural network as a recognition model to obtain the current to be played The program type corresponding to each picture in the target image set in the video file.

S150. According to the video program type corresponding to the currently to-be-played video file and the preset video type playback strategy, obtain the playback mode information corresponding to the currently-to-be-played video file and send it to the corresponding user terminal; wherein, the video type The play strategy includes a variety of video program types, and the play mode information corresponding to each video program type one-to-one.

In this embodiment, the video type play strategy can be preset as the following Table 1:

Table 1

As another implementation manner, the video type playback strategy can be preset as the following Table 2:

序号Serial number	视频节目类型Video program type	播放方式信息Play mode information
11	新闻节目News program	音频播放+后台运行Audio playback + background operation
22	实时点评节目Real-time comment on the show	音频播放+后台运行Audio playback + background operation
33	朗诵节目Recitation program	音频播放+后台运行Audio playback + background operation
44	体育节目Sports programs	视频播放Video playback
55	综艺节目variety show	视频播放Video playback
66	电影节目Movie show	视频播放Video playback
……...	……...	……...

Table 2

The difference between the above two specific embodiments of the video playback strategy is that the audio playback type video program shown in Table 1 is played when the user terminal screen is turned off to save power. The audio playback type video program is as follows: The second method in Table 2 is to suspend playback in the background of the user terminal so that the user can operate the user terminal to perform other operations (such as browsing web pages).

S160. If the consent operation instruction corresponding to the playing mode information of the currently to-be-played video file is detected, decompose the currently-to-be-played video file into corresponding audio-visual files and/or video files to assemble into corresponding Play the data and send it to the user terminal.

In this embodiment, after the video server sends the information about the play mode of the currently to-be-played video file to the user terminal, if the user chooses to agree to the play mode, the consent operation instruction is triggered, and the consent operation instruction is sent by the user terminal To the video server. If the video server detects the consent operation instruction, it decomposes the currently to-be-played video file into corresponding audio-visual files and/or video files and sends them to the user terminal.

In an embodiment, step S160 includes:

If there is a first playback segment of the audio playback mode in the playback mode corresponding to the playback mode information of the currently to-be-played video file, the audio data of the first playback segment and the corresponding audio playback control parameters are acquired; wherein, the audio playback control parameter is used It is used to control the display screen of the user terminal to turn on or off, or it is used to control the player corresponding to the current video file to be played to run in the front end or hang in the background;

If there is a second play segment of the video play mode in the play mode corresponding to the play mode information of the currently to-be-played video file, acquiring the video data of the second play segment;

The audio data of the first playback segment and the audio playback control parameters, and the video data of the second playback segment are assembled into playback data.

In this embodiment, for example, if the first playback segment of the audio playback mode exists in the playback mode information corresponding to the currently to-be-played video file, the audio data of the first playback segment and the audio playback control parameters (such as controlling the user The display screen of the terminal is turned off or the player is suspended in the background); if the second playback segment of the video playback mode exists in the playback mode information corresponding to the currently to-be-played video file, the video data of the second playback segment is acquired; and finally The audio data of the first playback segment, the audio playback control parameters, and the video data of the second playback segment are assembled into playback data and sent to the user terminal.

Wherein, if the first playback segment of the audio playback mode exists in the playback mode information corresponding to the currently to-be-played video file, the audio data and audio playback control parameters of the first playback segment are not null values; if the currently to-be-played If the first playback segment of the audio playback mode does not exist in the playback mode information corresponding to the video file, the audio data and audio playback control parameters of the first playback segment are null values. Similarly, if the second playback segment of the video playback mode exists in the playback mode information corresponding to the currently to-be-played video file, the video data corresponding to the second playback segment is not a null value; if the currently-to-be-played video file corresponds to If the second playback segment of the video playback mode does not exist in the playback mode information, the video data corresponding to the second playback segment is a null value. In this way, when the audio data of the first playback segment and the audio playback control parameters, and the video data of the second playback segment are assembled into playback data and sent to the user terminal, it can be based on whether there is a second playback mode information corresponding to the current video file to be played. Both the one playback terminal and/or the second playback terminal can combine the playback data corresponding to the currently to-be-played video file, and there is no error.

After that, by importing the playback data into the video player on the user terminal for playback, a smart playback can be realized, which can save power immediately when the display screen is turned off or the background hangs in response to audio playback, without the need to keep on It consumes electricity.

At this point, after sending the playback data to the user terminal for playback, you can also determine whether the video needs to be played (turn off the screen) according to the location of the user terminal. For example, it is detected that the user puts the user terminal in a pocket or a suitcase, and then pauses the video playback. , The initiator of this control method is the user terminal itself, not the video server. In this way, the user terminal can also be effectively controlled to save power.

The method realizes that based on the video type of the current to-be-played video file, the playing mode information and the corresponding playing data are obtained, and the power saving control of the user terminal is realized according to the playing mode information.

The embodiment of the present application also provides a device for implementing playback control based on a video type, and the device for implementing playback control based on a video type is used to execute any embodiment of the foregoing method for implementing playback control based on a video type. Specifically, please refer to FIG. 5, which is a schematic block diagram of a video type-based playback control implementation device provided by an embodiment of the present application. The device 100 for implementing playback control based on video types may be configured in a server.

As shown in FIG. 5, the device 100 for implementing playback control based on video type includes a video selection unit 110, a video tag determination unit 120, a first program type acquisition unit 130, a second program type acquisition unit 140, a playback mode information acquisition unit 150, Play data sending unit 160.

The video selection unit 110 is configured to, if a video selection instruction is detected, obtain a current to-be-played video file corresponding to the video selection instruction.

The video tag determining unit 120 is configured to determine whether the currently to-be-played video file includes a video program type tag.

The first program type acquiring unit 130 is configured to, if the currently to-be-played video file does not include a program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network network , Get the video program type.

In this embodiment, if the currently to-be-played video file does not include the program type tag, it means that the video server is required to identify the video program type of the currently-to-be-played video file. After the video server obtains the currently to-be-played video file, in order to determine the type of its video program (such as news programs, real-time review programs, recitation programs, sports programs, variety shows, movie programs, etc.), it is necessary to set the currently-to-be-played video files The video file is split into video to obtain multiple frames of video images. Then, according to the pre-trained convolutional neural network, the split multi-frame video images can be identified, and the corresponding video program type can be obtained.

In an embodiment, as shown in FIG. 6, the first program type acquiring unit 130 includes:

The target image set obtaining unit 131 is configured to obtain multiple frames of video images in the video image set corresponding to the current to-be-played video file according to a preset number of intervals, as a target image set;

The program type identification unit 132 is configured to input the target image set to the convolutional neural network to obtain the program type corresponding to each frame of video image in the target image set;

The separating unit 133 is configured to, if the total number of types is greater than 1, sequentially obtain the program type corresponding to each frame of the video image in the target image set to form a program type sequence, and divide the two adjacent program types in the program type sequence Insert separators between different program types;

The playback segment dividing unit 134 is configured to locate the separation time point corresponding to each separator inserted in the program type sequence, and divide the current to-be-played video file into corresponding playback segments through each separation time point;

The playback segment type acquiring unit 135 is configured to sequentially acquire the video program type corresponding to each playback segment in the currently to-be-played video file.

In an embodiment, as shown in FIG. 7, the device 100 for implementing video type-based playback control further includes:

The video program type dividing unit 1101 is configured to divide the video program into multiple video program types;

The video sample obtaining unit 1102 is used to obtain video samples of each video program type;

The training set obtaining unit 1103 is configured to extract image feature data of each frame of image in the video sample as a training set;

The model training unit 1104 is configured to input the training set to the convolutional neural network to be trained for training to obtain the convolutional neural network.

In an embodiment, the first program type acquiring unit 130 further includes:

The current program type obtaining unit 136 is configured to obtain the video program type corresponding to the current video file to be played if the total number of types is equal to one.

The second program type obtaining unit 140 is configured to, if the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag.

The playing mode information obtaining unit 150 is configured to obtain the playing mode information corresponding to the current to-be-played video file according to the video program type corresponding to the current to-be-played video file and the preset video type playing strategy and send it to the corresponding user terminal ; Wherein, the video type play strategy includes multiple video program types, and play mode information corresponding to each video program type one-to-one.

In this embodiment, the video type play strategy may be preset as shown in Table 1 above: as another implementation manner, the video type play strategy may be preset as shown in Table 2 above.

The play data sending unit 160 is configured to, if an agreed operation instruction corresponding to the play mode information of the currently to-be-played video file is detected, decompose the currently-to-be-played video file into corresponding audio-visual files and/or video files , To assemble the corresponding playback data and send it to the user terminal.

In an embodiment, the play data sending unit 160 includes:

The first acquiring unit is configured to acquire audio data of the first playback segment and corresponding audio playback control parameters if there is a first playback segment of the audio playback mode in the playback mode corresponding to the playback mode information of the currently to-be-played video file; Among them, the audio playback control parameter is used to control the display screen of the user terminal to turn on or off, or to control the player corresponding to the video file currently to be played to run in the front end or hang in the background;

The second obtaining unit is configured to obtain the video data of the second playing section if there is a second playing section of the video playing mode in the playing mode corresponding to the playing mode information of the currently to-be-played video file;

The data combination unit is used to assemble the audio data of the first playback segment, the audio playback control parameters, and the video data of the second playback segment into playback data.

The device realizes that based on the video type of the current to-be-played video file, it obtains its playing mode information and corresponding playing data, and realizes power-saving control of the user terminal according to the playing mode information.

The foregoing device for implementing playback control based on the video type may be implemented in the form of a computer program, and the computer program may run on the computer device as shown in FIG. 8.

Please refer to FIG. 8. FIG. 8 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 is a server. The server can be an independent server or a server cluster composed of multiple servers to implement a video type-based playback control method, where the method includes: if a video selection instruction is detected, acquiring and The current to-be-played video file corresponding to the video selection instruction; determine whether the current to-be-played video file includes a video program type tag; if the current to-be-played video file does not include a program type tag, the current to-be-played video file The selected multi-frame video images are input to the pre-trained convolutional neural network to obtain the video program type; if the currently to-be-played video file includes a program type tag, the video file to be played is obtained according to the program type tag. Corresponding video program type; according to the video program type corresponding to the current to-be-played video file and the preset video type playback strategy, obtain the playback mode information corresponding to the currently-to-be-played video file and send it to the corresponding user terminal; wherein, The video type play strategy includes multiple video program types, and play mode information corresponding to each video program type one-to-one; and if an agreed operation instruction corresponding to the play mode information of the currently to-be-played video file is detected, the The current to-be-played video file is decomposed into corresponding audio-visual files and/or video files to be assembled into corresponding play data and sent to the user terminal.

Referring to FIG. 8, the computer device 500 includes a processor 502, a memory, and a network interface 505 connected through a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the method for implementing playback control based on the video type.

The processor 502 is used to provide computing and control capabilities, and support the operation of the entire computer device 500.

The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can make the processor 502 execute a video type-based playback control implementation method.

The network interface 505 is used for network communication, such as providing data information transmission. Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

Wherein, the processor 502 is configured to run a computer program 5032 stored in a memory to implement the video type-based playback control implementation method disclosed in the embodiment of the present application, where the method at least includes:

Those skilled in the art can understand that the embodiment of the computer device shown in FIG. 8 does not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or less components than those shown in the figure. Or some parts are combined, or different parts are arranged. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are consistent with the embodiment shown in FIG. 8 and will not be repeated here.

It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), and special purpose processors. Integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a volatile medium or a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, where the computer program is executed by a processor to implement the video type-based playback control implementation method disclosed in the embodiments of the present application, wherein the method at least includes: if a video selection instruction is detected, Obtain the current to-be-played video file corresponding to the video selection instruction; determine whether the current to-be-played video file includes a video program type tag; if the current to-be-played video file does not include a program type tag, set the currently to be played The selected multi-frame video images in the video file are input to the pre-trained convolutional neural network network to obtain the video program type; if the currently to-be-played video file includes a program type tag, it is obtained according to the program type tag and the current to-be-played The video program type corresponding to the video file; according to the video program type corresponding to the current to-be-played video file and the preset video type play strategy, obtain the play mode information corresponding to the currently-to-be-played video file and send it to the corresponding user terminal; Wherein, the video type play strategy includes multiple video program types, and play mode information corresponding to each video program type one-to-one; and if an agreed operation instruction corresponding to the play mode information of the currently to-be-played video file is detected , Decompose the currently to-be-played video file into corresponding audio-visual files and/or video files to assemble into corresponding play data and send them to the user terminal. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium. It includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or optical disk and other media that can store program codes.

The above are only specific implementations of this application, but the protection scope of this application is not limited thereto. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A method for implementing playback control based on video types, including:

If a video selection instruction is detected, obtain the current to-be-played video file corresponding to the video selection instruction;

Judging whether the currently to-be-played video file includes a video program type tag;

If the currently to-be-played video file does not include the program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network network to obtain the video program type;

If the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag;

According to the video program type corresponding to the currently to-be-played video file and the preset video type play strategy, the play mode information corresponding to the currently-to-be-played video file is obtained and sent to the corresponding user terminal; wherein, the video type play strategy Including a variety of video program types, and one-to-one corresponding playback mode information for each video program type; and

If the consent operation instruction corresponding to the playing mode information of the currently to-be-played video file is detected, the currently-to-be-played video file is decomposed into corresponding audio-visual files and/or video files to assemble into corresponding playback data And sent to the user terminal.
The method for implementing playback control based on video types according to claim 1, wherein said inputting the selected multi-frame video images in the currently to-be-played video file into a pre-trained convolutional neural network network to obtain a video program Types, including:

Acquiring multiple frames of video images in the video image set corresponding to the currently to-be-played video file according to a preset number of intervals, as a target image set;

Inputting the target image set to the convolutional neural network to obtain the program type corresponding to each frame of video image in the target image set;

If the total number of types is greater than 1, the program types corresponding to each frame of the video image in the target image set are sequentially obtained to form a program type sequence, and two adjacent program types in the program type sequence are divided into two different program types. Insert a separator between;

Locate the separation time point corresponding to each separator inserted in the program type sequence, and divide the current to-be-played video file into corresponding play segments through each separation time point;

Obtain the video program type corresponding to each playback segment in the currently to-be-played video file in sequence.
The method for implementing playback control based on video types according to claim 2, wherein said inputting said target image set to said convolutional neural network obtains the program type corresponding to each frame of video image in said target image set After that, it also includes:

If the total number of types is equal to 1, the video program type corresponding to the currently to-be-played video file is acquired.
The method for implementing video type-based playback control according to claim 1, wherein if the current to-be-played video file does not include a program type tag, the selected multi-frame video image in the current to-be-played video file Before inputting to a pre-trained convolutional neural network to obtain the video program type, or if a video selection instruction is detected in real time, before obtaining the current to-be-played video file corresponding to the video selection instruction, it also includes:

Divide multiple video program types into video programs;

Obtain video samples of each video program type;

Extracting image feature data of each frame of image in the video sample as a training set;

The training set is input to the convolutional neural network to be trained for training to obtain the convolutional neural network.
The method for implementing video type-based playback control according to claim 2, wherein the positioning time point corresponding to each separator inserted in the sequence of program types includes:

The first program type sorted after each separator corresponds to the start playback time of the video segment, and the first program type sorted after each separator corresponds to the start playback time of the video segment corresponding to the corresponding separator Separate time points.
The method for implementing playback control based on video types according to claim 1, wherein said decomposing said currently to-be-played video file into corresponding audiovisual files and/or video files to assemble into corresponding playback data, include:

If there is a first playback segment of the audio playback mode in the playback mode corresponding to the playback mode information of the currently to-be-played video file, the audio data of the first playback segment and the corresponding audio playback control parameters are acquired; wherein, the audio playback control parameter is used It is used to control the display screen of the user terminal to turn on or off, or it is used to control the player corresponding to the current video file to be played to run in the front end or hang in the background;

If there is a second play segment of the video play mode in the play mode corresponding to the play mode information of the currently to-be-played video file, acquiring the video data of the second play segment;

The audio data of the first playback segment and the audio playback control parameters, and the video data of the second playback segment are assembled into playback data.
A video type-based playback control implementation device, which includes:

The video selection unit is configured to, if a video selection instruction is detected, obtain a current to-be-played video file corresponding to the video selection instruction;

A video tag determining unit, configured to determine whether the currently to-be-played video file includes a video program type tag;

The first program type acquiring unit is configured to, if the currently to-be-played video file does not include a program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network, Get the type of video program;

The second program type acquiring unit is configured to, if the currently to-be-played video file includes a program type tag, acquire the video program type corresponding to the currently-to-be-played video file according to the program type tag;

The playing mode information obtaining unit is configured to obtain the playing mode information corresponding to the current to-be-played video file according to the video program type corresponding to the current to-be-played video file and the preset video type playing strategy, and send it to the corresponding user terminal; Wherein, the video type play strategy includes multiple video program types, and play mode information corresponding to each video program type one-to-one; and

The playback data sending unit is configured to, if an agreed operation instruction corresponding to the playback mode information of the currently to-be-played video file is detected, decompose the currently-to-be-played video file into corresponding audio-visual files and/or video files, It can be assembled into corresponding playback data and sent to the user terminal.
The device for implementing playback control based on video type according to claim 7, wherein the first program type acquiring unit comprises:

The target image set acquiring unit is configured to acquire multiple frames of video images in the video image set corresponding to the current to-be-played video file according to a preset number of intervals, as a target image set;

A program type identification unit, configured to input the target image set to the convolutional neural network to obtain the program type corresponding to each frame of the video image in the target image set;

The separating unit is used to obtain the program type corresponding to each frame of the video image in the target image set in sequence if the total number of types is greater than 1, to form a program type sequence, and to store two adjacent program types in the program type sequence Insert separators between different program types;

The playback segment dividing unit is used to locate the separation time point corresponding to each separator inserted in the program type sequence, and divide the current to-be-played video file into corresponding playback segments through each separation time point;

The playback segment type acquiring unit is configured to sequentially acquire the video program type corresponding to each playback segment in the currently to-be-played video file.
A computer device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor implements video type-based playback control when the processor executes the computer program Methods, including:

If a video selection instruction is detected, obtain the current to-be-played video file corresponding to the video selection instruction;

Judging whether the currently to-be-played video file includes a video program type tag;

If the currently to-be-played video file does not include the program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network network to obtain the video program type;

If the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag;

According to the video program type corresponding to the currently to-be-played video file and the preset video type play strategy, the play mode information corresponding to the currently-to-be-played video file is obtained and sent to the corresponding user terminal; wherein, the video type play strategy Including a variety of video program types, and one-to-one corresponding playback mode information for each video program type; and

If the consent operation instruction corresponding to the playing mode information of the currently to-be-played video file is detected, the currently-to-be-played video file is decomposed into corresponding audio-visual files and/or video files to assemble into corresponding playback data And sent to the user terminal.
9. The computer device according to claim 9, wherein the inputting the selected multi-frame video images in the currently to-be-played video file to a pre-trained convolutional neural network network to obtain the video program type comprises:

Acquiring multiple frames of video images in the video image set corresponding to the currently to-be-played video file according to a preset number of intervals, as a target image set;

Inputting the target image set to the convolutional neural network to obtain the program type corresponding to each frame of video image in the target image set;

If the total number of types is greater than 1, the program types corresponding to each frame of the video image in the target image set are sequentially obtained to form a program type sequence, and two adjacent program types in the program type sequence are divided into two different program types. Insert a separator between;

Locate the separation time point corresponding to each separator inserted in the program type sequence, and divide the current to-be-played video file into corresponding play segments through each separation time point;

Obtain the video program type corresponding to each playback segment in the currently to-be-played video file in sequence.
The computer device according to claim 10, wherein after the input of the target image set to the convolutional neural network to obtain the program type corresponding to each frame of the video image in the target image set, the method further comprises:

If the total number of types is equal to 1, the video program type corresponding to the currently to-be-played video file is acquired.
The computer device according to claim 9, wherein, if the currently to-be-played video file does not include a program type tag, input the selected multi-frame video image in the currently-to-be-played video file to a pre-trained volume The product neural network network, before obtaining the video program type, or if a video selection instruction is detected in real time, before obtaining the currently to-be-played video file corresponding to the video selection instruction, it also includes:

Divide multiple video program types into video programs;

Obtain video samples of each video program type;

Extracting image feature data of each frame of image in the video sample as a training set;

The training set is input to the convolutional neural network to be trained for training to obtain the convolutional neural network.
The computer device according to claim 10, wherein the separation time point corresponding to each separator inserted in the sequence of positioning program types comprises:

The first program type sorted after each separator corresponds to the start playback time of the video segment, and the first program type sorted after each separator corresponds to the start playback time of the video segment corresponding to the corresponding separator Separate time points.
8. The computer device according to claim 9, wherein the decomposing the currently to-be-played video file into corresponding audio-visual files and/or video files to assemble into corresponding playback data comprises:

If there is a first playback segment of the audio playback mode in the playback mode corresponding to the playback mode information of the currently to-be-played video file, the audio data of the first playback segment and the corresponding audio playback control parameters are acquired; wherein, the audio playback control parameter is used It is used to control the display screen of the user terminal to turn on or off, or it is used to control the player corresponding to the current video file to be played to run in the front end or hang in the background;

If there is a second play segment of the video play mode in the play mode corresponding to the play mode information of the currently to-be-played video file, acquiring the video data of the second play segment;

The audio data of the first playback segment and the audio playback control parameters, and the video data of the second playback segment are assembled into playback data.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to execute a video type-based playback control implementation method, which includes :

If a video selection instruction is detected, obtain the current to-be-played video file corresponding to the video selection instruction;

Judging whether the currently to-be-played video file includes a video program type tag;

If the currently to-be-played video file does not include the program type tag, input the selected multiple frames of video images in the currently-to-be-played video file to a pre-trained convolutional neural network network to obtain the video program type;

If the currently to-be-played video file includes a program type tag, obtain the video program type corresponding to the currently-to-be-played video file according to the program type tag;

According to the video program type corresponding to the currently to-be-played video file and the preset video type play strategy, the play mode information corresponding to the currently-to-be-played video file is obtained and sent to the corresponding user terminal; wherein, the video type play strategy Including a variety of video program types, and one-to-one corresponding playback mode information for each video program type; and

If the consent operation instruction corresponding to the playing mode information of the currently to-be-played video file is detected, the currently-to-be-played video file is decomposed into corresponding audio-visual files and/or video files to assemble into corresponding playback data And sent to the user terminal.
The medium according to claim 15, wherein said inputting the selected multi-frame video images in the currently to-be-played video file into a pre-trained convolutional neural network to obtain the video program type comprises:

Acquiring multiple frames of video images in the video image set corresponding to the currently to-be-played video file according to a preset number of intervals, as a target image set;

Inputting the target image set to the convolutional neural network to obtain the program type corresponding to each frame of video image in the target image set;

If the total number of types is greater than 1, the program types corresponding to each frame of the video image in the target image set are sequentially obtained to form a program type sequence, and two adjacent program types in the program type sequence are divided into two different program types. Insert a separator between;

Locate the separation time point corresponding to each separator inserted in the program type sequence, and divide the current to-be-played video file into corresponding play segments through each separation time point;

Obtain the video program type corresponding to each playback segment in the currently to-be-played video file in sequence.
The medium according to claim 16, wherein said inputting said target image set to said convolutional neural network to obtain the program type corresponding to each frame of video image in said target image set, further comprising:

If the total number of types is equal to 1, the video program type corresponding to the currently to-be-played video file is acquired.
The medium according to claim 15, wherein, if the currently to-be-played video file does not include a program type tag, input the selected multi-frame video image in the currently-to-be-played video file to a pre-trained convolution The neural network network, before obtaining the video program type, or if a video selection instruction is detected in real time, before obtaining the currently to-be-played video file corresponding to the video selection instruction, it also includes:

Divide multiple video program types into video programs;

Obtain video samples of each video program type;

Extracting image feature data of each frame of image in the video sample as a training set;

The training set is input to the convolutional neural network to be trained for training to obtain the convolutional neural network.
The medium according to claim 16, wherein the separation time point corresponding to each separator inserted in the sequence of positioning program types comprises:

The first program type sorted after each separator corresponds to the start playback time of the video segment, and the first program type sorted after each separator corresponds to the start playback time of the video segment corresponding to the corresponding separator Separate time points.
The medium according to claim 15, wherein the decomposing the currently to-be-played video file into corresponding audio-visual files and/or video files to assemble into corresponding playback data comprises:

If there is a first playback segment of the audio playback mode in the playback mode corresponding to the playback mode information of the currently to-be-played video file, the audio data of the first playback segment and the corresponding audio playback control parameters are acquired; wherein, the audio playback control parameter is used It is used to control the display screen of the user terminal to turn on or off, or it is used to control the player corresponding to the current video file to be played to run in the front end or hang in the background;

If there is a second play segment of the video play mode in the play mode corresponding to the play mode information of the currently to-be-played video file, acquiring the video data of the second play segment;

The audio data of the first playback segment and the audio playback control parameters, and the video data of the second playback segment are assembled into playback data.