[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2023024927A1 - 视频播放方法、装置、设备及存储介质 - Google Patents

视频播放方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023024927A1
WO2023024927A1 PCT/CN2022/111942 CN2022111942W WO2023024927A1 WO 2023024927 A1 WO2023024927 A1 WO 2023024927A1 CN 2022111942 W CN2022111942 W CN 2022111942W WO 2023024927 A1 WO2023024927 A1 WO 2023024927A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
background
preset
recommendation model
application program
Prior art date
Application number
PCT/CN2022/111942
Other languages
English (en)
French (fr)
Inventor
阮闻涛
郑炜明
蒋泽帆
张炯衍
Original Assignee
北京字跳网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Priority to JP2023579296A priority Critical patent/JP2024528475A/ja
Priority to EP22860273.6A priority patent/EP4344223A4/en
Publication of WO2023024927A1 publication Critical patent/WO2023024927A1/zh
Priority to US18/395,142 priority patent/US20240129587A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47217—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for controlling playback functions for recorded or on-demand content, e.g. using progress bars, mode or play-point indicators or bookmarks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/443—OS processes, e.g. booting an STB, implementing a Java virtual machine in an STB or power management in an STB
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508—Management of client data or end-user data
    • H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections

Definitions

  • Embodiments of the present disclosure relate to the technical field of the Internet, for example, to a video playing method, device, device, and storage medium.
  • applications can provide users with more and more network information, and the video recommendation function of applications is favored by more and more users.
  • applications usually recommend videos to users by pushing video streams. Users may not be able to continue watching the video during watching videos, such as the terminal screen goes out, switching to other applications or switching to the terminal desktop, etc. , in this case, the push effect of the video stream of the related solution is not ideal and needs to be improved.
  • Embodiments of the present disclosure provide a video playing method, device, storage medium, and equipment, which can optimize existing video playing schemes.
  • an embodiment of the present disclosure provides a video playback method, including:
  • the preset application program is switched from the non-background running state to the background running state during the process of playing the first video, wherein the preset application program is used to play the video stream;
  • Video wherein, the preset background video recommendation model is used to determine the background playback video to be recommended, and the second video candidate set is used to screen videos in the background playback mode, and the second video candidate set is the same as the first video candidate set
  • the preset background video recommendation model is used to determine the background playback video to be recommended
  • the second video candidate set is used to screen videos in the background playback mode
  • the second video candidate set is the same as the first video candidate set
  • the video candidate sets are different, and the first video candidate set is used for screening videos when in non-background play mode
  • the second video is played in the background through the preset application program.
  • an embodiment of the present disclosure provides a video playback device, including:
  • the state detection module is configured to detect whether the preset application program is switched from the non-background running state to the background running state during the process of playing the first video, wherein the preset application program is used to play the video stream;
  • the video determination module is configured to continue playing the first video in the background through the preset application after detecting that the preset application switches from the non-background running state to the background running state during the playing of the first video.
  • video and according to the historical operation information of the current user for the preset application program and the preset background video recommendation model, determine the second video from the second video candidate set, wherein the preset background video recommendation model is used to determine The background playback video to be recommended, the second video candidate set is used to screen videos in the background playback mode, the second video candidate set is different from the first video candidate set, and the first video candidate set is used for Filter videos from it when it is not in background playback mode;
  • the playback switching module is configured to play the second video in the background through the preset application program when a preset video switching event is detected.
  • an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the video playback provided by the embodiment of the present disclosure is realized. method.
  • an embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • the processor executes the computer program, the following is implemented: The video playing method provided by the embodiment of the present disclosure.
  • FIG. 1 is a schematic flowchart of a video playing method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of another video playback method provided by an embodiment of the present disclosure
  • FIG. 3 is a structural block diagram of a video playback device provided by an embodiment of the present disclosure.
  • Fig. 4 is a structural block diagram of an electronic device provided by an embodiment of the present disclosure.
  • the term “comprise” and its variations are open-ended, ie “including but not limited to”.
  • the term “based on” is “based at least in part on”.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one further embodiment”; the term “some embodiments” means “at least some embodiments.” Relevant definitions of other terms will be given in the description below.
  • FIG. 1 is a schematic flowchart of a video playback method provided by an embodiment of the present disclosure.
  • the method can be executed by a video playback device, wherein the device can be implemented by at least one of software and hardware, and can generally be integrated into an electronic device.
  • the electronic device may be a server, or other devices such as a mobile phone or a tablet computer. As shown in Figure 1, the method includes:
  • Step 101 detecting that a preset application is switched from a non-background running state to a background running state during playing a first video, wherein the preset application is used to play a video stream.
  • the type of the preset application program may be a short video application program, or other types of application programs.
  • the preset application can provide the video stream push function, and the source of the video stream can be set by the preset application according to actual needs. For example, it can include videos uploaded to the server by the user as the video author, and can also include the corresponding Videos produced by the platform party, etc.
  • the preset application program can generally be installed as a client in the terminal used by the user, and cooperate with the corresponding server to provide the user with a video streaming push service.
  • the running state generally includes a non-background running state and a background running state.
  • the preset application When the preset application is not running in the background, it generally occupies the entire terminal screen and can display the video playback page. At this time, the user can view the video screen content by watching the screen, and can also input related playback control operations or other based on the video playback page. Operation; when the default application program is running in the background, the terminal may be in a state such as off or locked, or other applications are running in the non-background, that is, the interface of other applications is displayed on the screen at this time, or the terminal When displaying the desktop, at this time, the default application may run in the form of a background service or a background process. Generally, the normal page of the default application cannot be displayed on the screen, and the relevant content of the default application may not be displayed. Default applications are displayed as movable controls such as floating windows or floating control bars that take up a small amount of screen display space.
  • the preset application program can play the first video in a non-background running state, and at this time, the screen content of the video can be seen on the screen.
  • the user may need to use other application programs, and the preset application program may be switched to run in the background.
  • the running state information of the preset application program can be obtained from the system information of the terminal to which the application program belongs , and then determine whether it is detected that the running state of the preset application program is switched from the non-background running state to the background running state.
  • switching from the non-background running state to the background running state is generally performed in response to user operations.
  • the user can trigger the switching by triggering a control for switching to the background. In this case, it can be detected whether the control is triggered to determine whether it is detected that the running state of the preset application program is switched from the non-background running state to the background running state.
  • Step 102 Continue to play the first video in the background through the preset application program, and select from the second video candidate set according to the current user's historical operation information for the preset application program and the preset background video recommendation model Determine the second video, wherein the preset background video recommendation model is used to determine the background playback video to be recommended, and the second video candidate set is used to screen videos in the background playback mode, and the second video candidate set Different from the first video candidate set, the first video candidate set is used to filter videos from it when not playing in the background mode.
  • the non-background play video when switching from the non-background play state to the background play state, can be played continuously in the background, so that the user can obtain relevant information of the video more completely and ensure the video consumption experience.
  • Continue playing can be understood as determining the time point corresponding to the current playback progress in the first video according to the moment of switching from the non-background running state to the background running state, and continuing to play the audio corresponding to the first video from the determined time point.
  • a video suitable for playing in the background is also determined as the next video of the first video in the video stream.
  • the preset application generally selects from a video candidate set (also can be understood as a video candidate pool) when performing video recommendation.
  • a video candidate set also can be understood as a video candidate pool
  • when some applications are not running in the background they select a video from the video candidate set to play, and after switching from the non-background running state to the background running state, they will stop playing and will not continue to recommend videos.
  • the background playback mode is set, and the second video candidate set is configured for the background playback mode, which is used to select from the video when running in the background. Select a video to play in the background.
  • corresponding video recommendation models may be set respectively for non-background video playback and background video playback, that is, a preset non-background video recommendation model and a preset background video recommendation model.
  • the preset non-background video recommendation model corresponds to the first video candidate set, and the first video candidate set is used to filter videos from it in the non-background playback mode.
  • the preset non-background video recommendation model is used to select from the first video candidate Determine the non-background playback videos to be recommended in the set;
  • the preset background video recommendation model corresponds to the second video candidate set, and the second video candidate set is used to filter videos in the background playback mode.
  • the default background video recommendation The model is used to determine the background playing video to be recommended from the second video candidate set.
  • the manner of determining the preset non-background video recommendation model and the first video candidate set may be the same as or different from the implementation manner in the related art.
  • the preset background video recommendation model can be a neural network model, and the actual model structure, parameters, and training process can be set according to the actual situation.
  • For video it generally includes image content and audio content.
  • the user obtains picture information and sound information at the same time, he can have a better understanding of the video as a whole.
  • the default application program is running in the background, the user cannot obtain the screen information, that is, the image content is missing.
  • the videos in the second video candidate set can be set in a targeted manner according to the characteristics of background playback to include videos that are more suitable for listening to.
  • the videos in the second video candidate set satisfy a preset condition
  • the preset condition may be set according to whether the video is suitable for the user to listen to, that is, the preset condition may include being suitable for the user to listen to.
  • the preset condition includes at least one of matching a preset video category, a ratio of a duration containing voice content to a total video duration greater than a preset ratio threshold, and a total video duration greater than a preset duration threshold.
  • the division method and division granularity of video categories can be set according to the actual situation, for example, it can include cross talk, talk show, sketch, singing, dancing, scenic travel, daily life sharing and so on.
  • cross talk, talk show, and singing may contain more sound performances, and the lack of picture information may have little impact on understanding the entire video, which can be set as the default video category; dance may Contains more physical performances, landscape tourism may contain more scenery, etc., the lack of picture information may have a greater impact on understanding the entire video, therefore, similar categories can be excluded from the default video categories; small categories and life
  • the daily sharing category may include more picture information and sound information at the same time. It can be determined whether to set it as a preset video category according to actual needs, or it can be combined with other factors to determine whether it can be included in the second video candidate set.
  • the duration containing speech content may refer to the sum of the duration of one or more components (understood as segments) containing speech content in the video, and speech recognition technology may be used to identify the speech components, and then determine the duration containing speech content .
  • a Voice Activity Detection (VAD) model can be used to identify a video.
  • the role of the VAD model can include identifying voice segments and non-voice segments from a voice signal, and using the VAD model to identify One or more speech segments are recognized, and the sum of the durations of the recognized speech segments is calculated, that is, the duration containing the speech content is obtained.
  • the preset ratio threshold can be set according to actual needs, such as 60%.
  • the preset condition can be set according to the total video duration, for example, when the total video duration is greater than the preset duration threshold, the preset condition is satisfied.
  • the preset duration threshold may be determined according to the range of video length allowed to be played in the preset application program, for example, it may be the median of the range.
  • preset conditions may be set in combination with at least two of the above conditions or in combination with other conditions.
  • the current user can be understood as the user who is using the preset application program
  • the current user's historical operation information for the preset application program can be understood as the current user's operation of the preset application program within the preset time period before the current moment.
  • Information about various operations performed by the application can be set according to actual needs, for example, starting from the current moment and going back one month.
  • the operations performed by the user may include, for example, clicking, liking, commenting, bookmarking, forwarding, pausing, switching to the next, switching to the previous, and viewing the video author's homepage, etc.; the relevant information of the operation may include, for example, operation frequency, operation time (can be Include specific time, such as 8 o'clock in the morning; it can also include relative time, such as the time of switching operation relative to the starting point of video playback, for example, switch to the next one when the current video is playing for 1 minute, so as to determine the playing time of the video) and The operation object (for example, which video or which type of video to operate on), etc.
  • operation frequency can be Include specific time, such as 8 o'clock in the morning
  • relative time such as the time of switching operation relative to the starting point of video playback, for example, switch to the next one when the current video is playing for 1 minute, so as to determine the playing time of the video
  • the operation object for example, which video or which type of video to operate on
  • the relevant information of the operation can also include a state that the preset application enters because the user does not perform an operation, such as the user does not switch to the next one during the current video playback. One, make the current video play completely, enter the loop playback state or automatically switch to play the next video, etc.
  • the historical operation information may include non-background historical operation information and background historical operation information.
  • Non-background historical operation information can be understood as information related to various operations performed in the non-background
  • background historical operation information can be understood as information related to various operations performed in the background.
  • there are relatively few background operations for example, it may include pausing, switching to the next, switching to the previous, and bookmarking, etc.
  • Related information may include whether the video is completely played and the duration of the video.
  • the historical operation information of the current user for the preset application program can reflect some preferences of the current user for different videos, and the embodiments of the present disclosure can apply the historical operation information to the video recommendation under the condition of obtaining the user's permission, so that it can be based on
  • the historical operation information and the preset background video recommendation model can more personally determine the video to be played in the background for the current user.
  • historical operation information and feature information of each candidate video in the second video candidate set (for example, may include related information such as video tag, video author, video duration, video popularity, video image information, and video audio information) ) is input into the preset background video recommendation model as input data, and the second video is determined according to the output result of the preset background video recommendation model.
  • Step 103 when a preset video switching event is detected, play the second video in the background through the preset application program.
  • the second video in the process of continuing to play the first video in the background, when a preset video switch event is detected, can be played in the background through the preset application program. Exemplarily, it can be to play the corresponding Audio, so as to realize video switching in background playback mode.
  • the preset video switching event can be understood as an event that triggers background video switching, which can be automatically triggered by the system, or actively triggered by the user, and can also be set according to actual needs.
  • the video playing method provided in the embodiment of the present disclosure detects that the preset application program switches from the non-background running state to the background running state during the process of playing the first video, and continues to play the first video in the background through the preset application program, And according to the historical operation information of the current user for the preset application program and the preset background video recommendation model, determine the second video from the second video candidate set. Play the second video.
  • the second video in the background through the preset application program after starting to play the second video in the background through the preset application program, it further includes: when a preset video switching event is detected, playing the third video in the background through the preset application program video, wherein the third video is determined from the second video candidate set according to historical operation information of the current user for the preset application program and a preset background video recommendation model.
  • the advantage of this setting is that it can support switching and playing among multiple videos determined by the preset background video recommendation model.
  • the historical operation information used when determining the third video may be the same as or different from the historical operation information used when determining the second video.
  • the historical operation information on which the third video is determined is the same as the historical operation information on which the second video is determined, it can be understood that multiple video recommendations to be recommended can be determined at one time according to the historical operation information and the preset background video recommendation model
  • the video played in the background can be a video queue. When a preset video switching event is detected, the next video in the video queue is played to ensure push efficiency.
  • the historical operation information on which the third video is determined is different from the historical operation information on which the second video is determined, it can be understood that the historical operation information is updated according to the operation information in the process of playing the second video, and according to the update
  • the final historical operation information and the preset background video recommendation model determine the third video, making the recommendation results more accurate.
  • the detecting the preset video switching event may include: detecting that the current video is played completely.
  • the advantage of this setting is that after the current video is played, the next video can be played automatically. Since the preset application is running in the background, it may be inconvenient for the user to operate the preset application at this time, and the automatic playback can be reduced. Help users acquire new video content while operating, improve the efficiency of video push and the utilization of platform resources.
  • the detecting a preset video switching event may include: receiving a video switching instruction input by the current user.
  • the video switching instruction input by the current user may be received based on the floating control bar.
  • the floating control bar may contain a "next" button, and the user may pass Click this button to enter a video switching command.
  • the video switching command can also be input by voice. At this time, there is no need to display the floating control bar, which saves the screen display space. It is also applicable to the situation where the user needs to switch when the user is far away from the terminal, such as putting down the mobile phone to do it. other things.
  • the historical operation information includes non-background historical operation information and background historical operation information.
  • the determining the second video from the second video candidate set according to the historical operation information of the current user for the preset application program and the preset background video recommendation model includes: inputting the non-background historical operation information into In the preset non-background video recommendation model, an intermediate output result in the preset non-background video recommendation model is obtained, wherein the preset non-background video recommendation model is used to determine the non-background playback video to be recommended,
  • the intermediate output result includes user characteristic information of the current user; according to the user characteristic information of the current user, the background historical operation information and the preset background video recommendation model, determine the second video from the second video candidate set .
  • the intermediate output result can be understood as the output result of the intermediate layer of the preset non-background video recommendation model.
  • user characteristic information can be understood as user portrait information, which can exist in the form of feature vectors, etc., and can reflect user preference information in some aspects, such as liking to listen to an actor's talk show, etc. This preference information can be understood as the current Generally, the user's personalized information will not change in a short period of time due to the change of the running state of the preset application program.
  • the intermediate output result may also contain other information that is beneficial to the preset background video recommendation model to accurately determine the video to be recommended.
  • the advantage of this setting here is that the non-background historical operation information is more abundant than the background historical operation information, and can quickly and accurately determine user characteristic information, while the background historical operation information is more in line with the background playback scene.
  • the input of the preset background video recommendation model can more accurately determine the recommended background playback video that matches the current user.
  • it is conducive to simplifying the preset background video recommendation model and avoiding excessive occupation of background resources.
  • the determining the second video from the second video candidate set according to the historical operation information of the current user for the preset application program and the preset background video recommendation model includes: according to the non-background history Operation information and the preset non-background video recommendation model, determining a second video candidate subset from the second video candidate set corresponding to the preset background video recommendation model; according to the background historical operation information and the preset The background video recommendation model determines the second video from the second video candidate subset.
  • the background video recommendation model which determines the second video from the second video candidate subset, can make full use of the user's historical operation information in the non-background and background, and combine the characteristics of the two video recommendation models to quickly and accurately determine the suitable video that meets the user's preferences. Play recommended videos in the background.
  • the training data used by the preset background video recommendation model in the training phase includes at least one of user samples and user characteristic information corresponding to the preset non-background video recommendation model.
  • the advantage of this setting is that since the non-background recommended videos are richer and the user operation information is also richer, at least one of the user samples and user feature information corresponding to the preset non-background video recommendation model can more fully and accurately reflect the user's personalization Features, using at least one of the user samples and user feature information corresponding to the preset non-background video recommendation model as training data can enable the trained preset background video recommendation model to more accurately identify user features, and then determine the relationship with the user. Background recommended videos with matching features.
  • the determining the second video from the second video candidate set according to the historical operation information of the current user for the preset application program and the preset background video recommendation model includes: determining the background history When the data volume of the operation information is less than the preset data volume threshold corresponding to the preset background video recommendation model, according to the non-background historical operation information and the preset non-background video recommendation model, select from the second video candidate set Determine the second video in .
  • the advantage of this setting is that when using the preset background video recommendation model for video recommendation, it generally requires the accumulation of user operation information. Relatively few will affect the accuracy of the recommendation results. At this time, you can first use the non-background historical operation information and the preset non-background video recommendation model to determine the second video from the second video candidate set. In the cold start stage, you can also Provide users with personalized background video recommendation function.
  • the second video candidate set includes videos of the first type and videos of the second type, and the amount of image information in the videos of the first type is less than or equal to a first preset information amount threshold, The amount of image information in the second type of video is greater than a second preset information amount threshold, and the second preset information amount threshold is greater than or equal to the first preset information amount threshold.
  • the input data when using the preset background video recommendation model includes audio information in the first type of video
  • for the second type of video using the preset
  • the input data when setting the background video recommendation model includes image information and audio information in the first type of video.
  • the configured pictures may be a small number of one or several static pictures, Picture information is relatively scarce, and picture content may also be less useful for understanding audio content.
  • This kind of video is closer to audio. Therefore, this type of video can be classified as the first type of video.
  • the amount of image information in the video can be determined according to the sum of the amount of image information of each video frame (excluding repeated video frames), and the amount of image information can be obtained by calculating, for example, information entropy.
  • the image information can be ignored when using the preset background video recommendation model for video recommendation; while for the second type of video with a large amount of image information, when using the preset background video recommendation model
  • the video recommendation model can consider both image information and audio information when making video recommendations. In this way, background recommendations can be made more accurately for different types of videos.
  • different background video recommendation models can be set for the first type of video and the second type of video, such as the first preset background video recommendation model and the second background video recommendation model, two The models are trained and used separately.
  • the first number of first videos to be recommended can be determined according to the historical operation information and the first preset background video recommendation model
  • the second number can be determined according to the historical operation information and the second preset background video recommendation model
  • the first video to be recommended and the second video to be recommended are mixed and sorted to obtain a queue of videos to be recommended, and then the next video to be played in the background is sequentially determined from the queue of videos to be recommended.
  • the first type of video it may not be suitable for playing in the non-background.
  • Background operation information at this time, corresponding cold start processing can be performed on the first type of video, for example, the first type of video with a higher popularity ranking can be determined as the first video to be recommended.
  • Fig. 2 is a schematic flow chart of another video playback method provided by the embodiment of the present disclosure.
  • the embodiment of the present disclosure makes changes based on multiple optional solutions in the above embodiments, and the method includes the following steps:
  • Step 201 detecting that the preset application switches from a non-background running state to a background running state during playing the first video.
  • the preset application program is a short video application program
  • the user can switch the preset application program to the background when there is a need to operate other application programs during the process of using the short video application program to browse short video streams run.
  • short video A when short video A is currently playing, the user can swipe from the bottom of the screen to enter the desktop of the terminal.
  • a floating control bar can be displayed on the desktop interface.
  • the floating control bar can include sub-controls such as a pause button and a next button. , the user can also launch other applications.
  • Step 202 continue to play the first video in the background through the preset application program.
  • the short video A can continue to be played in the background.
  • the user switches the short video app to run in the background when short video A plays for 1 minute.
  • the time point of 1 minute can be recorded and started from 1 minute Continue to play the audio corresponding to short video A backwards.
  • Step 203 Input the current user's non-background historical operation information for the preset application program into the preset non-background video recommendation model, and obtain the intermediate output results of the preset non-background video recommendation model, wherein the intermediate output results include the current The user profile information of the user.
  • the non-background historical operation information may include the operation information of the current user when using the short video application in the non-background to browse the short video stream in the past month, and the non-background historical operation information is input into the preset non-background video recommendation
  • the preset non-background video recommendation model it should be noted that when using the preset non-background video recommendation model, other data may also need to be input.
  • the user characteristic information of the current user is obtained from the output result of the middle layer of the preset non-background video recommendation model.
  • Step 204 Determine the second video from the second video candidate set according to the user characteristic information, the background historical operation information and the preset background video recommendation model.
  • the current user's user feature information, background historical operation information and feature information of each candidate video in the second video candidate set can be input into the preset background video recommendation model as input data, and according to the default background video recommendation model The output determines the second video.
  • the videos in the second video candidate set meet the preset conditions;
  • the preset conditions include matching the preset video category, the ratio of the duration containing voice content to the total duration of the video is greater than a preset ratio threshold, and the total duration of the video The duration is greater than at least one of the preset duration thresholds.
  • Step 205 When it is detected that the first video is finished playing, start playing the second video in the background.
  • the second video may also start playing in the background after receiving a video switching command input by the current user.
  • Step 206 When the video switching instruction input by the current user is received, start playing the third video in the background, wherein the third video is selected from the second video according to the historical operation information of the current user for the preset application program and the preset background video recommendation model. identified in the candidate set.
  • the third video may also be automatically played in the background.
  • the user switches the preset application program to run in the background, then the background playback of the audio form of the current video can be continued, combined with
  • the user's non-background historical operation information and the preset non-background video recommendation model determine the user characteristic information, and then use the user characteristic information, the background historical operation information and the preset background video recommendation model to continuously recommend video streams suitable for background playback to the user , in the process of playing in the background, it can realize continuous automatic playback, and can also support users to input video switching instructions, provide users with a new form of content consumption, improve user experience, improve the performance of applications, and also increase the exposure of videos on the platform rate and improve the utilization of platform resources.
  • FIG. 3 is a structural block diagram of a video playback device provided by an embodiment of the present disclosure.
  • the device can be implemented by software and/or hardware, and generally can be integrated into an electronic device, and can perform video playback by executing a video playback method. As shown in Figure 3, the device includes:
  • the state detection module 301 is configured to detect whether a preset application is switched from a non-background running state to a background running state during playing the first video, wherein the preset application is used to play a video stream;
  • the video determination module 302 is configured to continue playing the second video in the background through the preset application after detecting that the preset application switches from the non-background running state to the background running state during the process of playing the first video.
  • a video and according to the historical operation information of the current user for the preset application program and the preset background video recommendation model, determine the second video from the second video candidate set, wherein the preset background video recommendation model is used for Determine the background playback video to be recommended, the second video candidate set is used to screen videos in the background playback mode, the second video candidate set is different from the first video candidate set, and the first video candidate set is used for Filter videos from it when not in background playback mode;
  • the play switch module 303 is configured to play the second video in the background through the preset application program when a preset video switch event is detected.
  • the video playback device distinguishes the video recommendations of the preset application programs in the non-background running state and the background running state, and continues to play in the background after switching from the non-background running state to the background running state
  • the video that is being played uses a video recommendation model and a video candidate set that are different from those that are not running in the background. Refer to the historical operation information of the current user to determine a video suitable for background playback, and play it when a preset video switching event is detected. It can ensure the continuity of the user's access to video information, and more accurately perform personalized video recommendations while running in the background to improve the performance of the application.
  • the videos in the second video candidate set meet a preset condition;
  • the preset condition includes matching a preset video category, the ratio of the duration containing voice content to the total duration of the video is greater than a preset ratio threshold, and The total duration of the video is greater than at least one of the preset duration thresholds.
  • the playback switching module is further configured to: after the preset application program starts playing the second video in the background, when a preset video switching event is detected, the preset application program The third video is played in the background, wherein the third video is determined from the second video candidate set according to historical operation information of the current user on the preset application program and a preset background video recommendation model.
  • the detecting the preset video switching event includes: detecting that the current video is played completely; or receiving a video switching instruction input by the current user.
  • the historical operation information includes non-background historical operation information and background historical operation information.
  • the video determination module includes a continuation playing unit, which is configured to switch from the non-background running state to the background running state after detecting that the preset application program is playing the first video in the process of playing the first video, through the preset application program in the background Continue to play the first video; the video determination unit is configured to: input the non-background historical operation information into the preset non-background video recommendation model, and obtain the intermediate output result of the preset non-background video recommendation model , wherein, the preset non-background video recommendation model is used to determine the non-background playback video to be recommended, and the intermediate output result includes user characteristic information of the current user; according to the user characteristic information of the current user, the background history The operation information and the preset background video recommendation model determine the second video from the second video candidate set.
  • the training data used by the preset background video recommendation model in the training phase includes at least one of user samples and user feature information corresponding to the preset non-background video recommendation model.
  • the video determining unit is configured to: when it is determined that the data volume of the background historical operation information is less than the preset data volume threshold corresponding to the preset background video recommendation model, according to the non-background history The operation information and the preset non-background video recommendation model determine the second video from the second video candidate set.
  • the second video candidate set includes videos of the first type and videos of the second type, the amount of image information in the videos of the first type is less than or equal to a first preset information amount threshold, the The amount of image information in the second type of video is greater than a second preset information amount threshold, and the second preset information amount threshold is greater than or equal to the first preset information amount threshold.
  • the input data when using the preset background video recommendation model includes audio information in the first type of video; for the second type of video, use the preset background
  • the input data for the video recommendation model includes image information and audio information in the first type of video.
  • FIG. 4 it shows a schematic structural diagram of an electronic device 400 suitable for implementing an embodiment of the present disclosure.
  • Electronic devices in the embodiments of the present disclosure may include mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (Personal Digital Assistant, PDA), tablet computers (Portable Android Device, PAD), portable multimedia players (Portable Media Player, PMP), mobile terminals such as vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, and the like.
  • PDA Personal Digital Assistant
  • PAD Portable Android Device
  • PMP portable multimedia players
  • mobile terminals such as vehicle-mounted terminals (such as vehicle-mounted navigation terminals)
  • fixed terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 4 is just an example.
  • an electronic device 400 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 401, which may be stored in a read-only memory (Read-Only Memory, ROM) 402 according to a program 408 is loaded into the program in the random access memory (Random Access Memory, RAM) 403 to execute various appropriate actions and processes.
  • a processing device such as a central processing unit, a graphics processing unit, etc.
  • ROM read-only memory
  • RAM Random Access Memory
  • various programs and data necessary for the operation of the electronic device 400 are also stored.
  • the processing device 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404.
  • An input/output (I/O) interface 405 is also connected to bus 404 .
  • an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; including, for example, a liquid crystal display (Liquid Crystal Display, LCD) , an output device 407 such as a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409.
  • the communication means 409 may allow the electronic device 400 to perform wireless or wired communication with other devices to exchange data. While FIG. 4 shows electronic device 400 having various means, it should be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, where the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network via communication means 409, or from storage means 408, or from ROM 402.
  • the processing device 401 When the computer program is executed by the processing device 401, the above-mentioned functions in the methods of the embodiments of the present disclosure are executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof.
  • Computer-readable storage media may include: electrical connections having one or more conductors, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory) -Only Memory, EPROM or flash memory), optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • the program code contained on the computer readable medium can be transmitted by any appropriate medium, including: electric wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any appropriate combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: detects that the preset application program is in the process of playing the first video, from the non-background The running state is switched to the background running state, wherein the preset application program is used to play the video stream; the first video is continued to be played in the background through the preset application program, and the preset application program is used according to the current user
  • the historical operation information and the preset background video recommendation model determine the second video from the second video candidate set, wherein the preset background video recommendation model is used to determine the background playback video to be recommended, and the second video candidate The set is used to screen videos when in the background play mode, the second video candidate set is different from the first video candidate set, and the first video candidate set is used to screen videos when the non-background play mode is used; When a video switching event is set, the second video is played in the background through the preset application program.
  • Computer program code for carrying out the operations of the present disclosure can be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer ( For example, use an Internet service provider to connect via the Internet).
  • LAN Local Area Network
  • WAN Wide Area Network
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware.
  • the name of the module does not constitute a limitation on the module itself in one case, for example, the playback switching module can also be described as "when a preset video switching event is detected, the A module that plays said second video".
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Parts
  • SOC System on Chip
  • CPLD Complex Programmable logic device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may comprise an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.
  • a machine-readable storage medium may include one or more wire-based electrical connections, a portable computer disk, a hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash flash memory), optical fiber, compact disc read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash flash memory erasable programmable read only memory
  • CD-ROM compact disc read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • Example 1 provides a video playback method, including:
  • the preset application program is switched from the non-background running state to the background running state during the process of playing the first video, wherein the preset application program is used to play the video stream;
  • Video wherein, the preset background video recommendation model is used to determine the background playback video to be recommended, and the second video candidate set is used to screen videos in the background playback mode, and the second video candidate set is the same as the first video candidate set
  • the preset background video recommendation model is used to determine the background playback video to be recommended
  • the second video candidate set is used to screen videos in the background playback mode
  • the second video candidate set is the same as the first video candidate set
  • the video candidate sets are different, and the first video candidate set is used for screening videos when in non-background play mode
  • the second video is played in the background through the preset application program.
  • Example 2 in Example 2, according to the method described in Example 1, the videos in the second video candidate set meet preset conditions; the preset conditions include matching to a preset video category, including At least one of the ratio of the duration of the voice content to the total duration of the video is greater than a preset ratio threshold, and the total duration of the video is greater than a preset duration threshold.
  • Example 3 according to the method described in Example 1, after starting to play the second video in the background through the preset application program, further includes:
  • a third video is played in the background through the preset application program, wherein the third video is based on historical operation information of the current user for the preset application program and the preset background video
  • a recommendation model is determined from the second video candidate set.
  • example 4 is according to the method described in example 1, and the detection of a preset video switching event includes:
  • a video switching instruction input by the current user is received.
  • example 5 is according to the method described in any one of examples 1-4, the historical operation information includes non-background historical operation information and background historical operation information;
  • the determining the second video from the second video candidate set according to the historical operation information of the current user for the preset application program and the preset background video recommendation model includes:
  • the second video is determined from the second video candidate set according to the user feature information of the current user, the background historical operation information and the preset background video recommendation model.
  • example 6 is according to the method described in example 5, the training data used by the preset background video recommendation model in the training phase includes user samples corresponding to the preset non-background video recommendation model and at least one of user characteristic information.
  • Example 7 is based on the method described in Example 5, according to the historical operation information of the current user for the preset application program and the preset background video recommendation model, from the second video candidate Identify the second video in the collection, including:
  • a second video is determined from the second video candidate set.
  • example 8 is according to the method described in example 1, the second video candidate set includes videos of the first type and videos of the second type, and the videos of the first type
  • the amount of image information in the video of the second type is less than or equal to the first preset information amount threshold, the image information amount in the second type of video is greater than the second preset information amount threshold, and the second preset information amount threshold is greater than or equal to the a first preset information volume threshold;
  • the input data when using the preset background video recommendation model includes audio information in the first type of video
  • the input data when using the preset background video recommendation model includes image information and audio information in the first type of video.
  • Example 9 provides a video playback device, including:
  • the state detection module is configured to detect whether the preset application program is switched from the non-background running state to the background running state during the process of playing the first video, wherein the preset application program is used to play the video stream;
  • the video determination module is configured to continue playing the first video in the background through the preset application after detecting that the preset application switches from the non-background running state to the background running state during the playing of the first video.
  • video and according to the historical operation information of the current user for the preset application program and the preset background video recommendation model, determine the second video from the second video candidate set, wherein the preset background video recommendation model is used to determine The background playback video to be recommended, the second video candidate set is used to screen videos in the background playback mode, the second video candidate set is different from the first video candidate set, and the first video candidate set is used for Filter videos from it when it is not in background playback mode;
  • the playback switching module is configured to play the second video in the background through the preset application program when a preset video switching event is detected.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Human Computer Interaction (AREA)
  • Software Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本公开实施例公开了视频播放方法、装置、设备及存储介质。该方法包括：检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，通过预设应用程序在后台继续播放第一视频，并根据当前用户针对预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，在检测到预设视频切换事件时，通过预设应用程序在后台播放第二视频。

Description

视频播放方法、装置、设备及存储介质
本申请要求在2021年08月27日提交中国专利局、申请号为202110996241.6的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开实施例涉及互联网技术领域，例如涉及视频播放方法、装置、设备及存储介质。
背景技术
随着信息技术的快速发展以及移动互联网的普及，应用程序能够为用户提供的网络信息越来越多，其中，应用程序的视频推荐功能受到越来越多用户的喜爱。
目前，应用程序通常以推送视频流的方式向用户推荐视频，用户在观看视频过程中可能会存在无法继续观看视频画面的情况，如终端屏幕熄灭、切换到其他应用程序或切换至终端的桌面等，这种情况下，相关方案的视频流的推送效果不理想，需要改进。
发明内容
本公开实施例提供了视频播放方法、装置、存储介质及设备，可以优化现有的视频播放方案。
第一方面，本公开实施例提供了一种视频播放方法，包括：
检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第 二视频。
第二方面，本公开实施例提供了一种视频播放装置，包括：
状态检测模块，被设置为检测预设应用程序在播放第一视频的过程中，是否从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
视频确定模块，被设置为在检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态后，通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
播放切换模块，被设置为在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
第三方面，本公开实施例提供了一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如本公开实施例提供的视频播放方法。
第四方面，本公开实施例提供了一种电子设备，包括存储器、处理器及存储在所述存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如本公开实施例提供的视频播放方法。
附图说明
图1为本公开实施例提供的一种视频播放方法的流程示意图；
图2为本公开实施例提供的又一种视频播放方法的流程示意图；
图3为本公开实施例提供的一种视频播放装置的结构框图；
图4为本公开实施例提供的一种电子设备的结构框图。
具体实施方式
下面将参照附图描述本公开的实施例。虽然附图中显示了本公开的一些实 施例，然而应当理解的是，本公开可以通过各种形式来实现。应当理解的是，本公开的附图及实施例仅用于示例性作用。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
下述各实施例中，每个实施例中同时提供了可选特征和示例，实施例中记载的各个特征可进行组合，形成多个可选方案，不应将每个编号的实施例仅视为一个技术方案。
图1为本公开实施例提供的一种视频播放方法的流程示意图，该方法可以由视频播放装置执行，其中该装置可由软件和硬件中的至少一个实现，一般可集成在电子设备中。所述电子设备可以为服务器，也可以为手机或平板电脑等其他设备。如图1所示，该方法包括：
步骤101、检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流。
本公开实施例中，预设应用程序的类型可以是短视频应用程序，还可以是其他类型的应用程序。预设应用程序可提供视频流推送功能，视频流的来源等可以由预设应用程序根据实际需求设定，例如可以包括作为视频作者的用户上传至服务端的视频，还可以包括预设应用程序对应的平台方制作的视频等。预设应用程序一般可作为客户端安装于用户所使用的终端中，与对应的服务端相配合来为用户提供视频流推送服务。
示例性的，应用程序在所属终端中运行时，运行状态一般包括非后台运行状态和后台运行状态。预设应用程序处于非后台运行状态时，一般占据整个终端屏幕，可以显示视频播放页面，此时用户通过观看屏幕可以查看视频的画面内容，还可以基于视频播放页面输入相关的播放控制操作或其他操作；预设应 用程序处于后台运行状态时，终端可能处于熄屏或锁屏等状态，或者在非后台运行其他应用程序，也即此时屏幕上显示的是其他应用程序的界面，或者，终端在显示桌面，此时，预设应用程序可能以后台服务或后台进程的形式运行，一般无法在屏幕上显示预设应用程序的正常页面，可能不显示预设应用程序的相关内容，也可能以悬浮窗或悬浮控制条等占用少量屏幕显示空间的可移动控件的方式显示预设应用程序。
示例性的，预设应用程序可以在非后台运行状态播放第一视频，此时可以从屏幕上看到视频的画面内容。在第一视频的播放过程中，用户可能存在使用其他应用程序的需求，可以将预设应用程序切换至后台运行。
本公开实施例中，对于检测预设应用程序是否从非后台运行状态切换为后台运行状态的检测方式，示例性的，可以从应用程序所属终端的系统信息中获取预设应用程序的运行状态信息，进而确定是否检测到预设应用程序的运行状态由非后台运行状态切换为后台运行状态。此外，从非后台运行状态到后台运行状态的切换一般是响应于用户操作来执行的，例如，用户可以通过触发用于切换至后台的控件来触发切换，这种情况下，可以检测该控件是否被触发，进而确定是否检测到预设应用程序的运行状态由非后台运行状态切换为后台运行状态。
步骤102、通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频。
本公开实施例中，在从非后台播放状态切换为后台播放状态时，可以在后台对非后台播放的视频进行继续播放，使用户可以更加完整地获取该视频的相关信息，保证视频消费体验。继续播放可以理解为根据从非后台运行状态切换为后台运行状态的时刻确定第一视频中当前播放进度对应的时间点，从所确定的时间点开始继续播放第一视频对应的音频。
本公开实施例中，在继续播放第一视频的基础上，还会确定适合后台播放的视频，作为视频流中第一视频的下一个视频。示例性的，预设应用程序在进行视频推荐时，一般从视频候选集合(也可以理解为视频候选池)中进行选取。相关技术中，一些应用程序在非后台运行时，从视频候选集合中选择视频进行播放，在从非后台运行状态切换至后台运行状态后，会停止播放，也不会继续推荐视频。而本公开实施例中，为了保证预设应用程序在后台可以实现持续地 视频推荐，设置了后台播放模式，并为后台播放模式配置了第二视频候选集合，用于在后台运行的情况下从中选取视频进行后台播放。
本公开实施例中，可以针对非后台视频播放和后台视频播放分别设置对应的视频推荐模型，即预设非后台视频推荐模型和预设后台视频推荐模型。预设非后台视频推荐模型对应于第一视频候选集合，第一视频候选集合用于在非后台播放模式时从中筛选视频，一般情况下，预设非后台视频推荐模型用于从第一视频候选集合中确定待推荐的非后台播放视频；预设后台视频推荐模型对应于第二视频候选集合，第二视频候选集合用于在后台播放模式时从中筛选视频，一般情况下，预设后台视频推荐模型用于从第二视频候选集合中确定待推荐的后台播放视频。预设非后台视频推荐模型和第一视频候选集合的确定方式可以与相关技术中的实现方式相同或不同。预设后台视频推荐模型可以是神经网络模型，实际的模型结构、参数以及训练过程等，可以根据实际情况设置。
对于视频来说，一般包括图像内容和音频内容，当用户同时获取到画面信息和声音信息时，可以对视频整体有更好的理解。然而，当预设应用程序处于后台运行状态时，用户无法获取到画面信息，也即缺失了图像内容，对于图像内容丰富的视频来说，单纯依靠音频内容难以有效理解视频内容。视频流中的不同视频通常存在一定的差异，本公开实施例中，可以根据后台播放的特点来有针对性地设置第二视频候选集合中的视频包括更加适合听的视频。
示例性的，所述第二视频候选集合中的视频满足预设条件，预设条件可以根据视频是否适合用户收听来设定，也即预设条件可包括适合用户收听。可选的，所述预设条件包括匹配于预设视频类别、包含语音内容的时长占视频总时长的比例大于预设比例阈值、以及视频总时长大于预设时长阈值中的至少一个。
示例性的，视频类别的划分方式以及划分粒度等可以根据实际情况设置，例如可包括相声类、脱口秀类、小品类、歌唱类、跳舞类、风景旅游类以及生活日常分享类等等。其中，相声类、脱口秀类以及歌唱类等，可能会包含较多的声音方面的表演，画面信息的缺失可能对理解整个视频来说影响较小，可设置为预设视频类别；跳舞类可能包含较多的肢体表演，风景旅游类可能包含较多的景物等，画面信息的缺失可能对理解整个视频来说影响较大，因此，可将类似类别排除于预设视频类别；小品类以及生活日常分享类，可能会同时包括较多的画面信息和声音信息，可以根据实际需求确定是否设置为预设视频类别，也可结合其他因素来确定是否可以放入第二视频候选集合中。
示例性的，视频中包含语音内容较多时，声音信息较丰富，即使缺失画面信息，对于用户来说，也是存在一定的收听价值的，因此，可以将包含语音内容的时长占视频总时长的比例大于预设比例阈值的视频放入第二视频候选集合 中。其中，包含语音内容的时长可以指视频中包含语音内容的一个或多个组成部分(可理解为片段)的时长总和，可以采用语音识别技术来对语音成分进行识别，进而确定包含语音内容的时长。例如，可以利用语音激活监测(Voice Activity Detection，VAD)模型对视频进行识别，VAD模型的作用可以包括从一段语音信号中标识出语音片段与非语音片段，利用VAD模型从视频对应的音频数据中识别出一个或多个语音片段，计算识别到的语音片段的时长总和，即得到包含语音内容的时长。预设比例阈值可以根据实际需求设置，例如60％等。
示例性的，由于画面信息的表达能力更强，在进行视频创作或制作过程中，在预期视频总时长较短的情况下，为了吸引其他用户浏览该视频，通常会将期望向用户展现的信息尽量体现于画面中，因此，这类视频的画面内容也会较为丰富，相反的，在预期视频总时长较长的情况下，那么可能画面内容不需要很丰富。本公开实施例中，可以基于上述考量，根据视频总时长来设定预设条件，例如视频总时长大于预设时长阈值时，满足预设条件。其中，预设时长阈值可以根据预设应用程序中允许播放的视频长度的范围来确定，例如可以是该范围的中位数等。
可选的，为了更加准确地筛选适合听的视频加入到第二视频候选集合中，可以结合上述条件中的至少两种或结合其他条件来设置预设条件。
本公开实施例中，当前用户可以理解为正在使用预设应用程序的用户，当前用户针对预设应用程序的历史操作信息，可以理解为当前用户在当前时刻之前的预设时间段内对预设应用程序进行各种操作的相关信息。其中，预设时间段可以根据实际需求设置，例如当前时刻开始向前追溯一个月。用户进行的操作例如可包括点击、点赞、评论、收藏、转发、暂停、切换至下一个、切换至上一个以及查看视频作者主页等等；操作的相关信息例如可包括操作频次、操作时间(可包括具体的时间，如早上8点；还可包括相对时间，如切换操作相对于视频播放起点的时间，例如，当前视频播放1分钟时切换至下一个，由此可确定视频的播放时长)以及操作对象(例如针对哪个视频或哪类视频进行操作)等，操作的相关信息还可包括因用户未进行操作使得预设应用程序进入的一种状态，如当前视频播放过程中用户未切换至下一个，使得当前视频完整播放，进入循环播放状态或自动切换至播放下一个视频等。
示例性的，历史操作信息可包括非后台历史操作信息和后台历史操作信息。非后台历史操作信息可理解为在非后台进行各种操作的相关信息，后台历史操作信息可理解为在后台进行各种操作的相关信息。一般的，后台操作相对少一些，例如，可能包括暂停、切换至下一个、切换至上一个以及收藏等，相关信息可包括如视频是否完整播放以及视频播放时长等等。
当前用户针对所述预设应用程序的历史操作信息可以反映出当前用户针对不同视频的一些偏好，本公开实施例可以在征得用户允许的情况下将历史操作信息应用于视频推荐，从而可以根据历史操作信息和预设后台视频推荐模型针对当前用户更加个性化地确定待后台播放的视频。
示例性的，可以将历史操作信息和第二视频候选集合中各候选视频的特征信息(例如可包括视频标签、视频作者、视频时长、视频热度、视频的图像信息和视频的音频信息等相关信息)作为输入数据输入到预设后台视频推荐模型，根据预设后台视频推荐模型的输出结果确定第二视频。
步骤103、在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
示例性的，在后台继续播放第一视频的过程中，在检测到预设视频切换事件时，可以通过预设应用程序在后台播放第二视频，示例性的，可以是播放第二视频对应的音频，从而实现后台播放模式下的视频切换。预设视频切换事件可以理解为触发后台视频切换的事件，可以由系统自动触发，也可以由用户主动触发，还可根据实际需求设置。
本公开实施例中提供的视频播放方法，检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，通过预设应用程序在后台继续播放第一视频，并根据当前用户针对预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，在检测到预设视频切换事件时，通过预设应用程序在后台播放第二视频。通过采用上述实施方式，可以将预设应用程序分别处于非后台运行状态和后台运行状态下的视频推荐进行区分，在从非后台运行状态切换至后台运行状态后，继续在后台播放正在播放的视频，并采用不同于非后台运行情况下的视频推荐模型以及视频候选集合，参考当前用户的历史操作信息，确定适合后台播放的视频，待检测到预设视频切换事件时进行播放，可以保证用户获取视频信息的连续性，且更加精准地在后台运行状态下进行个性化的视频推荐，提升应用程序的性能。
在一些实施例中，在通过所述预设应用程序在后台开始播放所述第二视频之后，还包括：在检测到预设视频切换事件时，通过所述预设应用程序在后台播放第三视频，其中，所述第三视频根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型从所述第二视频候选集合中确定。这样设置的好处在于，可以支持由预设后台视频推荐模型确定的多个视频之间的切换播放。其中，在确定第三视频时所依据的历史操作信息可以与确定第二视频时所依据的历史操作信息相同或不同。在确定第三视频所依据的历史操作信息与确定第二视频时所依据的历史操作信息相同的情况下，可以理解为根据历史操 作信息和预设后台视频推荐模型可以一次性确定多个待推荐的后台播放视频，可以是一个视频队列，在检测到预设视频切换事件时，播放视频队列中的下一个视频，保证推送效率。在确定第三视频所依据的历史操作信息与确定第二视频时所依据的历史操作信息不同的情况下，可以理解为根据播放第二视频过程中的操作信息对历史操作信息进行更新，根据更新后的历史操作信息和预设后台视频推荐模型确定第三视频，使得推荐结果更加精准。
在一些实施例中，所述检测到预设视频切换事件，可包括：检测到当前视频播放完毕。这样设置的好处在于，在当前视频播放完毕后，可以自动播放下一个视频，由于预设应用程序处于后台运行状态，此时用户可能不太方便对预设应用程序进行操作，自动播放可以在减少用户操作的同时帮助用户获取到新的视频内容，提高视频推送效率以及平台资源的利用率。
在一些实施例中，所述检测到预设视频切换事件，可包括：接收到所述当前用户输入的视频切换指令。这样设置的好处在于，当当前用户对当前播放的视频不感兴趣时，可以快速切换至下一个视频的播放，提升互动效率。可选的，当屏幕上显示有预设应用程序对应的悬浮控制条时，可以基于悬浮控制条接收当前用户输入的视频切换指令，例如，悬浮控制条中可以包含“下一个”按钮，用户通过点击该按钮输入视频切换指令。可选的，视频切换指令还可以通过语音方式输入，此时不需要显示悬浮控制条，节省屏幕显示空间，还可适用于用户在远离终端一定距离时存在切换需求的情况，如放下手机去做其他事情的情况。
在一些实施例中，所述历史操作信息包括非后台历史操作信息和后台历史操作信息。其中，所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，包括：将所述非后台历史操作信息输入至所述预设非后台视频推荐模型中，并获取所述预设非后台视频推荐模型中的中间输出结果，其中，所述预设非后台视频推荐模型用于确定待推荐的非后台播放视频，所述中间输出结果包括当前用户的用户特征信息；根据所述当前用户的用户特征信息、所述后台历史操作信息和所述预设后台视频推荐模型，从第二视频候选集合中确定第二视频。其中，中间输出结果可以理解为预设非后台视频推荐模型的中间层的输出结果。示例性的，用户特征信息可以理解为用户画像信息，可以以特征向量等形式存在，可以体现用户在一些方面的偏好信息，如喜欢听一个演员的脱口秀等，这种偏好信息可以理解为当前用户的个性化信息，一般在短时间内不会因为预设应用程序运行状态的改变而发生变化。中间输出结果中还可能包含其他有利于预设后台视频推荐模型准确确定待推荐视频的信息。此处这样设置的好处在于，非后台历史操作信息相比于后台历史操作信息来说更加丰富，能够快速准确地确定用户特 征信息，而后台历史操作信息更加符合后台播放场景，两者相结合作为预设后台视频推荐模型的输入，可以更加精准地确定符合当前用户的待推荐后台播放视频，此外，有利于简化预设后台视频推荐模型，避免对后台资源的过度占用。
在一些实施例中，所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，包括：根据所述非后台历史操作信息和所述预设非后台视频推荐模型，从所述预设后台视频推荐模型对应的第二视频候选集合中确定第二视频候选子集合；根据所述后台历史操作信息和所述预设后台视频推荐模型，从所述第二视频候选子集合中确定第二视频。这样设置的好处在于，利用非后台历史操作信息和预设非后台视频推荐模型对第二视频候选集合中的视频进行初步筛选，得到第二视频候选子集合，再利用后台历史操作信息和预设后台视频推荐模型，从第二视频候选子集合中确定第二视频，能够充分利用用户在非后台和后台的历史操作信息，结合两个视频推荐模型的特点，快速准确地确定符合用户喜好的适合在后台播放待推荐视频。
在一些实施例中，所述预设后台视频推荐模型在训练阶段使用的训练数据包括所述预设非后台视频推荐模型对应的用户样本和用户特征信息中的至少一个。这样设置的好处在于，由于非后台推荐视频更加丰富，用户操作信息也更丰富，预设非后台视频推荐模型对应的用户样本和用户特征信息中的至少一个能够更加全面准确地体现用户的个性化特征，使用预设非后台视频推荐模型对应的用户样本和用户特征信息中的至少一个作为训练数据，可以使得训练得到的预设后台视频推荐模型能够更准确地识别出用户特征，进而确定与用户特征相匹配的后台推荐视频。
在一些实施例中，所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，包括：在确定所述后台历史操作信息的数据量小于所述预设后台视频推荐模型对应的预设数据量阈值的情况下，根据所述非后台历史操作信息和所述预设非后台视频推荐模型，从第二视频候选集合中确定第二视频。这样设置的好处在于，在使用预设后台视频推荐模型进行视频推荐时，一般需要用户操作信息的积累，对于很少进入后台播放的用户或者后台视频播放功能刚投入使用阶段，往往后台历史操作信息比较少，会影响推荐结果的准确性，此时，可以先利用非后台历史操作信息和预设非后台视频推荐模型从第二视频候选集合中确定第二视频，实现在冷启动阶段，也能够为用户提供个性化的后台视频推荐功能。
在一些实施例中，所述第二视频候选集合中包括第一类型的视频和第二类型的视频，所述第一类型的视频中的图像信息量小于或等于第一预设信息量阈 值，所述第二类型的视频中的图像信息量大于第二预设信息量阈值，所述第二预设信息量阈值大于或等于所述第一预设信息量阈值。其中，针对所述第一类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的音频信息；针对所述第二类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的图像信息和音频信息。这样设置的好处在于，可以从画面信息丰富程度的维度上对视频进行划分，针对不同类型的视频采用不同的输入，使得模型的推荐结果更有针对性。
示例性的，在视频创作过程中，可能存在更注重音频创作的情况，例如讲述自己对一个热点事件的观点或讲故事等，此时，配置的图片可能是少量的一个或几个静态图片，画面信息比较匮乏，且图片内容对理解音频内容可能也用处较小，这种视频更接近于音频，因此，可将此类视频划分为第一类型的视频。视频中的图像信息量可以根据各视频帧(不包含重复的视频帧)图像信息量的总和确定，图像信息量例如可通过信息熵等方式计算得到。
对于图像信息量较小的第一类型的视频，在利用预设后台视频推荐模型进行视频推荐时，可以忽略图像信息；而对于图像信息量较大的第二类型的视频，在利用预设后台视频推荐模型进行视频推荐时，可以同时考虑图像信息和音频信息。这样，可以更加准确地针对不同类型的视频进行后台推荐。
可选的，作为一种实现方式，可以分别针对第一类型的视频和第二类型的视频设置不同的后台视频推荐模型，如第一预设后台视频推荐模型和第二后台视频推荐模型，两个模型分开训练和使用。在需要进行后台视频推荐时，可以根据历史操作信息和第一预设后台视频推荐模型确定第一数量的第一待推荐视频，根据历史操作信息和第二预设后台视频推荐模型确定第二数量的第二待推荐视频，将第一待推荐视频和第二待推荐视频进行混合排序，得到待推荐视频队列，再从待推荐视频队列中依次确定下一个需要进行后台播放的视频。
可选的，对于第一类型的视频，可能不适合在非后台播放，在进行非后台视频推荐时不包含第一类型的视频的情况下，在进入后台运行状态后，可能没有可参考的非后台操作信息，此时，可以针对第一类型的视频进行相应的冷启动处理，如可以将当前热度排名较高的第一类型的视频确定为第一待推荐视频。
图2为本公开实施例提供的又一种视频播放方法的流程示意图，本公开实施例以上述实施例中多个可选方案为基础进行改动，该方法包括如下步骤：
步骤201、检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态。
示例性的，预设应用程序为短视频应用程序，用户在利用短视频应用程序 浏览短视频流的过程中，在存在操作其他应用程序的需求的情况下，可以将预设应用程序切换至后台运行。例如当前在播放短视频A，用户可以从屏幕最底部滑动进入终端的桌面，此时可以在桌面的界面中显示悬浮控制条，悬浮控制条中可以包括暂停按钮和下一个按钮等子控件，此后，用户还可以启动其他应用程序。
步骤202、通过预设应用程序在后台继续播放第一视频。
当短视频应用切换至后台运行后，可以在后台继续播放短视频A。
示例性的，假设短视频A的总时长为3分钟，用户在短视频A播放至1分钟时，将短视频应用切换至后台运行，此时可记录1分钟这个时间点，并从1分钟开始继续向后播放短视频A对应的音频。
步骤203、将当前用户针对预设应用程序的非后台历史操作信息输入至预设非后台视频推荐模型中，并获取预设非后台视频推荐模型中的中间输出结果，其中，中间输出结果包括当前用户的用户特征信息。
示例性的，非后台历史操作信息可以包括当前用户在过去1个月的时间内在非后台使用短视频应用浏览短视频流时的操作信息，将非后台历史操作信息输入至预设非后台视频推荐模型中，需要说明的是，在使用预设非后台视频推荐模型时，可能还需要输入其他数据。随后，从预设非后台视频推荐模型的中间层的输出结果中获取当前用户的用户特征信息。
步骤204、根据用户特征信息、后台历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频。
示例性的，可以将当前用户的用户特征信息、后台历史操作信息和第二视频候选集合中各候选视频的特征信息作为输入数据输入到预设后台视频推荐模型，根据预设后台视频推荐模型的输出结果确定第二视频。
其中，所述第二视频候选集合中的视频满足预设条件；所述预设条件包括匹配于预设视频类别、包含语音内容的时长占视频总时长的比例大于预设比例阈值、以及视频总时长大于预设时长阈值中的至少一个。
步骤205、在检测到第一视频播放完毕时，开始在后台播放第二视频。
需要说明的是，在第一视频播放完毕之前，接收到当前用户输入的视频切换指令，也可开始在后台播放第二视频。
步骤206、接收到当前用户输入的视频切换指令时，开始在后台播放第三视频，其中，第三视频根据当前用户针对预设应用程序的历史操作信息和预设后台视频推荐模型从第二视频候选集合中确定。
示例性的，用户在使用其他非后台应用程序的过程中，如果对当前播放的第二视频的音频内容不感兴趣，则可以通过点击悬浮控制条中的下一个按钮来完成视频切换指令的输入，从而实现切换至下一个视频的后台播放。
需要说明的是，在第二视频播放完毕时仍未接收到当前用户输入的视频切换指令的情况下，也可自动开始在后台播放第三视频。
本公开实施例提供的视频播放方法，当预设应用程序在非后台播放视频流的过程中，用户将预设应用程序切换至后台运行，则可以继续当前视频的音频形式的后台播放，并结合用户的非后台历史操作信息和预设非后台视频推荐模型确定用户特征信息，再利用户特征信息、所述后台历史操作信息和预设后台视频推荐模型持续地为用户推荐适合后台播放的视频流，在后台播放过程中，可以实现连续的自动播放，还可以支持用户输入视频切换指令，为用户提供新的内容消费形式，提升用户体验，提升应用程序的性能，也能够提高平台中视频的曝光率，提高平台资源的利用率。
图3为本公开实施例提供的一种视频播放装置的结构框图，该装置可由软件和/或硬件实现，一般可集成在电子设备中，可通过执行视频播放方法来进行视频播放。如图3所示，该装置包括：
状态检测模块301，被设置为检测预设应用程序在播放第一视频的过程中，是否从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
视频确定模块302，被设置为在检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态后，通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
播放切换模块303，被设置为在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
本公开实施例中提供的视频播放装置，将预设应用程序分别处于非后台运行状态和后台运行状态下的视频推荐进行区分，在从非后台运行状态切换至后台运行状态后，继续在后台播放正在播放的视频，并采用不同于非后台运行情况下的视频推荐模型以及视频候选集合，参考当前用户的历史操作信息，确定适合后台播放的视频，待检测到预设视频切换事件时进行播放，可以保证用户 获取视频信息的连续性，且更加精准地在后台运行状态下进行个性化的视频推荐，提升应用程序的性能。
可选的，所述第二视频候选集合中的视频满足预设条件；所述预设条件包括匹配于预设视频类别、包含语音内容的时长占视频总时长的比例大于预设比例阈值、以及视频总时长大于预设时长阈值中的至少一个。
可选的，所述播放切换模块还被设置为：在通过所述预设应用程序在后台开始播放所述第二视频之后，在检测到预设视频切换事件时，通过所述预设应用程序在后台播放第三视频，其中，所述第三视频根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型从所述第二视频候选集合中确定。
可选的，所述检测到预设视频切换事件，包括：检测到当前视频播放完毕；或，接收到所述当前用户输入的视频切换指令。
可选的，所述历史操作信息包括非后台历史操作信息和后台历史操作信息。所述视频确定模块包括继续播放单元，被设置为在检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态后，通过所述预设应用程序在后台继续播放所述第一视频；视频确定单元，被设置为：将所述非后台历史操作信息输入至预设非后台视频推荐模型中，并获取所述预设非后台视频推荐模型的中间输出结果，其中，所述预设非后台视频推荐模型用于确定待推荐的非后台播放视频，所述中间输出结果包括当前用户的用户特征信息；根据所述当前用户的用户特征信息、所述后台历史操作信息和所述预设后台视频推荐模型，从第二视频候选集合中确定第二视频。
可选的，所述预设后台视频推荐模型在训练阶段使用的训练数据包括所述预设非后台视频推荐模型对应的用户样本和用户特征信息中的至少一个。
可选的，所述视频确定单元被设置为：在确定所述后台历史操作信息的数据量小于所述预设后台视频推荐模型对应的预设数据量阈值的情况下，根据所述非后台历史操作信息和所述预设非后台视频推荐模型，从第二视频候选集合中确定第二视频。
可选的，所述第二视频候选集合中包括第一类型的视频和第二类型的视频，所述第一类型的视频中的图像信息量小于或等于第一预设信息量阈值，所述第二类型的视频中的图像信息量大于第二预设信息量阈值，所述第二预设信息量阈值大于或等于所述第一预设信息量阈值。针对所述第一类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的音频信息；针对所述第二类型的视频，使用所述预设后台视频推荐模型时的输入数据 包括所述第一类型的视频中的图像信息和音频信息。
下面参考图4，其示出了适于用来实现本公开实施例的电子设备400的结构示意图。本公开实施例中的电子设备可以包括诸如移动电话、笔记本电脑、数字广播接收器、个人数字助理(Personal Digital Assistant，PDA)、平板电脑(Portable Android Device，PAD)、便携式多媒体播放器(Portable Media Player，PMP)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图4示出的电子设备仅仅是一个示例。
如图4所示，电子设备400可以包括处理装置(例如中央处理器、图形处理器等)401，其可以根据存储在只读存储器(Read-Only Memory，ROM)402中的程序或者从存储装置408加载到随机访问存储器(Random Access Memory，RAM)403中的程序而执行各种适当的动作和处理。在RAM 403中，还存储有电子设备400操作所需的各种程序和数据。处理装置401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。
通常，以下装置可以连接至I/O接口405：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置406；包括例如液晶显示器(Liquid Crystal Display，LCD)、扬声器、振动器等的输出装置407；包括例如磁带、硬盘等的存储装置408；以及通信装置409。通信装置409可以允许电子设备400与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的电子设备400，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置409从网络上被下载和安装，或者从存储装置408被安装，或者从ROM 402被安装。在该计算机程序被处理装置401执行时，执行本公开实施例的方法中上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质可以包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(Compact Disc Read-Only Memory， CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括：电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(Local Area Network，LAN)或广域网(Wide Area Network，WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图 中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块的名称在一种情况下并不构成对该模块本身的限定，例如，播放切换模块还可以被描述为“在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频的模块”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、片上系统(System on Chip，SOC)、复杂可编程逻辑设备(Complex Programmable logic device，CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质可以包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，示例1提供了一种视频播放方法，包括：
检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频， 所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
根据本公开的一个或多个实施例，示例2根据示例1所述的方法，所述第二视频候选集合中的视频满足预设条件；所述预设条件包括匹配于预设视频类别、包含语音内容的时长占视频总时长的比例大于预设比例阈值、以及视频总时长大于预设时长阈值中的至少一个。
根据本公开的一个或多个实施例，示例3根据示例1所述的方法，在通过所述预设应用程序在后台开始播放所述第二视频之后，还包括：
在检测到预设视频切换事件时，通过所述预设应用程序在后台播放第三视频，其中，所述第三视频根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型从所述第二视频候选集合中确定。
根据本公开的一个或多个实施例，示例4根据示例1所述的方法，所述检测到预设视频切换事件，包括：
检测到当前视频播放完毕；或，
接收到所述当前用户输入的视频切换指令。
根据本公开的一个或多个实施例，示例5根据示例1-4任一所述的方法，所述历史操作信息包括非后台历史操作信息和后台历史操作信息；
其中，所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，包括：
将所述非后台历史操作信息输入至预设非后台视频推荐模型中，并获取所述预设非后台视频推荐模型的中间输出结果，其中，所述预设非后台视频推荐模型用于确定待推荐的非后台播放视频，所述中间输出结果包括当前用户的用户特征信息；
根据所述当前用户的用户特征信息、所述后台历史操作信息和所述预设后台视频推荐模型，从第二视频候选集合中确定第二视频。
根据本公开的一个或多个实施例，示例6根据示例5所述的方法，所述预设后台视频推荐模型在训练阶段使用的训练数据包括所述预设非后台视频推荐模型对应的用户样本和用户特征信息中的至少一个。
根据本公开的一个或多个实施例，示例7根据示例5所述的方法，所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型， 从第二视频候选集合中确定第二视频，包括：
在确定所述后台历史操作信息的数据量小于所述预设后台视频推荐模型对应的预设数据量阈值的情况下，根据所述非后台历史操作信息和所述预设非后台视频推荐模型，从第二视频候选集合中确定第二视频。
根据本公开的一个或多个实施例，示例8根据示例1所述的方法，所述第二视频候选集合中包括第一类型的视频和第二类型的视频，所述第一类型的视频中的图像信息量小于或等于第一预设信息量阈值，所述第二类型的视频中的图像信息量大于第二预设信息量阈值，所述第二预设信息量阈值大于或等于所述第一预设信息量阈值；
其中，针对所述第一类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的音频信息；
针对所述第二类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的图像信息和音频信息。
根据本公开的一个或多个实施例，示例9提供了一种视频播放装置，包括：
状态检测模块，被设置为检测预设应用程序在播放第一视频的过程中，是否从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
视频确定模块，被设置为在检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态后，通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
播放切换模块，被设置为在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。

Claims (11)

  1. 一种视频播放方法，包括：
    检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
    通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
    在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
  2. 根据权利要求1所述的方法，其中，所述第二视频候选集合中的视频满足预设条件；所述预设条件包括匹配于预设视频类别、包含语音内容的时长占视频总时长的比例大于预设比例阈值、以及视频总时长大于预设时长阈值中的至少一个。
  3. 根据权利要求1所述的方法，在通过所述预设应用程序在后台开始播放所述第二视频之后，还包括：
    在检测到预设视频切换事件时，通过所述预设应用程序在后台播放第三视频，其中，所述第三视频根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型从所述第二视频候选集合中确定。
  4. 根据权利要求1所述的方法，其中，所述检测到预设视频切换事件，包括：
    检测到当前视频播放完毕；或，
    接收到所述当前用户输入的视频切换指令。
  5. 根据权利要求1-4任一所述的方法，其中，所述历史操作信息包括非后台历史操作信息和后台历史操作信息；
    所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，包括：
    将所述非后台历史操作信息输入至预设非后台视频推荐模型中，并获取所述预设非后台视频推荐模型的中间输出结果，其中，所述预设非后台视频推荐模型用于确定待推荐的非后台播放视频，所述中间输出结果包括当前用户的用户特征信息；
    根据所述当前用户的用户特征信息、所述后台历史操作信息和所述预设后台视频推荐模型，从第二视频候选集合中确定第二视频。
  6. 根据权利要求5所述的方法，其中，所述预设后台视频推荐模型在训练阶段使用的训练数据包括所述预设非后台视频推荐模型对应的用户样本和用户特征信息中的至少一个。
  7. 根据权利要求5所述的方法，其中，所述根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，包括：
    在确定所述后台历史操作信息的数据量小于所述预设后台视频推荐模型对应的预设数据量阈值的情况下，根据所述非后台历史操作信息和所述预设非后台视频推荐模型，从第二视频候选集合中确定第二视频。
  8. 根据权利要求1所述的方法，其中，所述第二视频候选集合中包括第一类型的视频和第二类型的视频，所述第一类型的视频中的图像信息量小于或等于第一预设信息量阈值，所述第二类型的视频中的图像信息量大于第二预设信息量阈值，所述第二预设信息量阈值大于或等于所述第一预设信息量阈值；
    其中，针对所述第一类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的音频信息；
    针对所述第二类型的视频，使用所述预设后台视频推荐模型时的输入数据包括所述第一类型的视频中的图像信息和音频信息。
  9. 一种视频播放装置，包括：
    状态检测模块，被设置为检测预设应用程序在播放第一视频的过程中，是否从非后台运行状态切换为后台运行状态，其中，所述预设应用程序用于播放视频流；
    视频确定模块，被设置为在检测到预设应用程序在播放第一视频的过程中，从非后台运行状态切换为后台运行状态后，通过所述预设应用程序在后台继续播放所述第一视频，并根据当前用户针对所述预设应用程序的历史操作信息和预设后台视频推荐模型，从第二视频候选集合中确定第二视频，其中，所述预设后台视频推荐模型用于确定待推荐的后台播放视频，所述第二视频候选集合用于在后台播放模式时从中筛选视频，所述第二视频候选集合与第一视频候选集合不同，所述第一视频候选集合用于在非后台播放模式时从中筛选视频；
    播放切换模块，被设置为在检测到预设视频切换事件时，通过所述预设应用程序在后台播放所述第二视频。
  10. 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1-8任一项所述的方法。
  11. 一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-8任一项所述的方法。
PCT/CN2022/111942 2021-08-27 2022-08-12 视频播放方法、装置、设备及存储介质 WO2023024927A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2023579296A JP2024528475A (ja) 2021-08-27 2022-08-12 ビデオ再生方法、装置、機器及び記憶媒体
EP22860273.6A EP4344223A4 (en) 2021-08-27 2022-08-12 VIDEO PLAYBACK METHOD AND DEVICE AND DEVICE AND STORAGE MEDIUM
US18/395,142 US20240129587A1 (en) 2021-08-27 2023-12-22 Video playing method and apparatus, and device and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110996241.6 2021-08-27
CN202110996241.6A CN113727169A (zh) 2021-08-27 2021-08-27 视频播放方法、装置、设备及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/395,142 Continuation US20240129587A1 (en) 2021-08-27 2023-12-22 Video playing method and apparatus, and device and storage medium

Publications (1)

Publication Number Publication Date
WO2023024927A1 true WO2023024927A1 (zh) 2023-03-02

Family

ID=78678572

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/111942 WO2023024927A1 (zh) 2021-08-27 2022-08-12 视频播放方法、装置、设备及存储介质

Country Status (5)

Country Link
US (1) US20240129587A1 (zh)
EP (1) EP4344223A4 (zh)
JP (1) JP2024528475A (zh)
CN (1) CN113727169A (zh)
WO (1) WO2023024927A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113727169A (zh) * 2021-08-27 2021-11-30 北京字跳网络技术有限公司 视频播放方法、装置、设备及存储介质
CN114449328A (zh) * 2022-01-26 2022-05-06 北京百度网讯科技有限公司 视频封面的展示方法、装置、电子设备及可读存储介质
CN114786063B (zh) * 2022-03-11 2023-12-05 北京字跳网络技术有限公司 一种音视频处理方法、装置、设备以及存储介质
CN117707717B (zh) * 2023-06-16 2024-10-11 荣耀终端有限公司 进程调度方法、可读存储介质和电子设备
CN116992073B (zh) * 2023-09-28 2023-12-08 北京小糖科技有限责任公司 视频片段排序方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106792075A (zh) * 2017-01-04 2017-05-31 合网络技术（北京）有限公司 视频播放方法及装置
US20170180805A1 (en) * 2015-12-22 2017-06-22 Le Holdings (Beijing) Co., Ltd. Method and electronic device for video follow-play
CN108012584A (zh) * 2015-08-06 2018-05-08 谷歌有限责任公司 提供适合于仅音频回放的视频内容的方法、系统和介质
CN112685599A (zh) * 2020-12-29 2021-04-20 北京达佳互联信息技术有限公司 视频推荐方法及装置
CN113727169A (zh) * 2021-08-27 2021-11-30 北京字跳网络技术有限公司 视频播放方法、装置、设备及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9665248B2 (en) * 2014-07-15 2017-05-30 Google Inc. Adaptive background playback behavior
US11025976B2 (en) * 2019-03-18 2021-06-01 At&T Intellectual Property I, L.P. System and method for state based content delivery to a client device
CN111079016A (zh) * 2019-12-17 2020-04-28 北京奇艺世纪科技有限公司 一种短视频推荐方法、装置及电子设备
CN111741336B (zh) * 2020-07-20 2021-05-11 杭州翔毅科技有限公司 视频内容推荐方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108012584A (zh) * 2015-08-06 2018-05-08 谷歌有限责任公司 提供适合于仅音频回放的视频内容的方法、系统和介质
US20170180805A1 (en) * 2015-12-22 2017-06-22 Le Holdings (Beijing) Co., Ltd. Method and electronic device for video follow-play
CN106792075A (zh) * 2017-01-04 2017-05-31 合网络技术（北京）有限公司 视频播放方法及装置
CN112685599A (zh) * 2020-12-29 2021-04-20 北京达佳互联信息技术有限公司 视频推荐方法及装置
CN113727169A (zh) * 2021-08-27 2021-11-30 北京字跳网络技术有限公司 视频播放方法、装置、设备及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4344223A4

Also Published As

Publication number Publication date
EP4344223A1 (en) 2024-03-27
EP4344223A4 (en) 2024-08-28
US20240129587A1 (en) 2024-04-18
JP2024528475A (ja) 2024-07-30
CN113727169A (zh) 2021-11-30

Similar Documents

Publication Publication Date Title
WO2023024927A1 (zh) 视频播放方法、装置、设备及存储介质
CN109640188B (zh) 视频预览方法、装置、电子设备及计算机可读存储介质
WO2021052085A1 (zh) 视频推荐方法、装置、电子设备及计算机可读介质
WO2021052141A1 (zh) 列表流的实现方法、装置、电子设备及存储介质
WO2022042593A1 (zh) 字幕编辑方法、装置和电子设备
WO2022143924A1 (zh) 视频生成方法、装置、电子设备和存储介质
JP7572108B2 (ja) 議事録のインタラクション方法、装置、機器及び媒体
US11758228B2 (en) Methods, systems, and media for modifying the presentation of video content on a user device based on a consumption of the user device
CN113852767B (zh) 视频编辑方法、装置、设备及介质
CN111858974B (zh) 信息推送方法、装置、电子设备及存储介质
WO2023024921A1 (zh) 视频交互方法、装置、设备及介质
WO2023061230A1 (zh) 内容展示方法、装置、设备及存储介质
WO2024051715A1 (zh) 媒体内容播放方法、装置、设备、存储介质和程序产品
WO2023005575A1 (zh) 基于兴趣标签的处理方法、装置、设备及存储介质
US11272136B2 (en) Method and device for processing multimedia information, electronic equipment and computer-readable storage medium
WO2023185647A1 (zh) 媒体内容的显示方法、装置、设备、存储介质和程序产品
WO2023216804A1 (zh) 内容推送方法、装置和电子设备
WO2024016902A1 (zh) 多媒体播放方法、设备、存储介质及程序产品
CN111935357A (zh) 多媒体播放方法及设备
WO2024037480A1 (zh) 交互方法、装置、电子设备和存储介质
CN110740373B (zh) 一种音/视频文件的缓冲方法及相关装置
CN114925274A (zh) 媒体内容播放方法、装置、设备、存储介质及产品
WO2024061360A1 (zh) 文本素材获取方法、装置、设备、介质和程序产品
US20240112702A1 (en) Method and apparatus for template recommendation, device, and storage medium
CN112965686A (zh) 音乐播放方法及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22860273

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202327087402

Country of ref document: IN

ENP Entry into the national phase

Ref document number: 2023579296

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2022860273

Country of ref document: EP

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112023027198

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 2022860273

Country of ref document: EP

Effective date: 20231222

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 112023027198

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20231221