WO2024036979A9 - 一种多媒体资源播放方法及相关装置 - Google Patents

一种多媒体资源播放方法及相关装置 Download PDF

Info

Publication number
WO2024036979A9
WO2024036979A9 PCT/CN2023/085834 CN2023085834W WO2024036979A9 WO 2024036979 A9 WO2024036979 A9 WO 2024036979A9 CN 2023085834 W CN2023085834 W CN 2023085834W WO 2024036979 A9 WO2024036979 A9 WO 2024036979A9
Authority
WO
WIPO (PCT)
Prior art keywords
multimedia
multimedia resource
interest
playback
played
Prior art date
Application number
PCT/CN2023/085834
Other languages
English (en)
French (fr)
Other versions
WO2024036979A1 (zh
Inventor
陈小帅
Original Assignee
腾讯科技(深圳)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 腾讯科技(深圳)有限公司 filed Critical 腾讯科技(深圳)有限公司
Publication of WO2024036979A1 publication Critical patent/WO2024036979A1/zh
Publication of WO2024036979A9 publication Critical patent/WO2024036979A9/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/472End-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
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/472End-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
    • H04N21/4722End-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 requesting additional data associated with the content
    • H04N21/4725End-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 requesting additional data associated with the content using interactive regions of the image, e.g. hot spots
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845Structuring of content, e.g. decomposing content into time segments

Definitions

  • the present application relates to the field of computer technology, and in particular to multimedia resource playback technology.
  • a playback progress bar of the multimedia resource can be displayed on the playback page of the multimedia resource.
  • the user can adjust the playback progress of the multimedia resource by dragging the slider on the playback progress bar and changing the position of the slider on the playback progress bar, so that the user can choose to watch any multimedia resource segment in the multimedia resource.
  • the present application provides a multimedia resource playback method and related devices, which can intuitively find the location of interest based on the playback progress bar. Without multiple repeated drag operations, the location of interest can be quickly and accurately located, thereby improving the accuracy and efficiency of jumping to the location of interest and improving the user experience.
  • an embodiment of the present application provides a multimedia resource playback method, the method being executed by a computer device, the method comprising:
  • Play the multimedia resource to be played and when playing the multimedia resource to be played, display the playback progress bar on the playback page of the multimedia resource to be played, wherein the playback progress bar is used to indicate the playback progress of the multimedia resource to be played and the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • an embodiment of the present application provides a multimedia resource playback device, which is deployed on a computer device and includes an acquisition unit, a generation unit, a playback unit, and a display unit:
  • the acquisition unit is used to acquire a play request for a multimedia resource to be played, wherein the play request carries an object identifier of a multimedia playback object and a multimedia identifier of the multimedia resource to be played;
  • the acquisition unit is further used to acquire, based on the object identifier and the multimedia identifier, the interest degree of the multimedia playback object in the multimedia resource segments in different time intervals of the multimedia resource to be played;
  • the generating unit is used to generate a playback progress bar according to the interest of the multimedia playback object in the multimedia resource segments in different time intervals of the multimedia resource to be played, wherein the sliding granularity of the playback progress bar matches the granularity of the division of the time interval;
  • the playing unit is used to play the multimedia resource to be played
  • the display unit is used to display the playback progress bar on the playback page of the multimedia resource to be played when playing the multimedia resource to be played.
  • the playback progress bar is used to indicate the playback progress of the multimedia resource to be played and the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • an embodiment of the present application provides a computer device, the computer device comprising a processor and a memory:
  • the memory is used to store a computer program and transmit the computer program to the processor
  • the processor is configured to execute the method described in any one of the preceding aspects according to instructions in the computer program.
  • an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.
  • an embodiment of the present application provides a computer program product, including a computer program, which, when executed on a computer device, enables the computer device to implement the method described in any of the above aspects.
  • a playback request can be generated based on the playback operation, thereby obtaining a playback request for the multimedia resource to be played. Since the playback request carries the object identifier of the multimedia playback object and the multimedia identifier of the multimedia resource to be played, the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played can be obtained based on the object identifier and the multimedia identifier.
  • a playback progress bar is generated, the multimedia resource to be played is played, and when the multimedia resource to be played is played, the playback progress bar is displayed on the playback page of the multimedia resource to be played.
  • the multimedia playback object can understand the interest in the multimedia resource segments of different time intervals based on the playback progress bar, thereby quickly and intuitively finding the interested position (i.e., the time interval), and the sliding granularity of the playback progress bar matches the division granularity of the time interval, so the multimedia playback object can control the playback progress bar to reach the position of interest.
  • the present application can intuitively find the position of interest based on the playback progress bar, thereby eliminating the need for repeated dragging operations, and can quickly and accurately locate the position of interest, thereby improving the accuracy and efficiency of jumping to the position of interest and improving the user experience.
  • FIG. 1 is an example diagram of a playback progress bar provided by the related art
  • FIG2 is a schematic diagram of a system architecture of a multimedia resource playback method provided in an embodiment of the present application
  • FIG3 is a flowchart of a multimedia resource playback method provided in an embodiment of the present application.
  • FIG4 is an example diagram of a playback page of a multimedia resource to be played provided in an embodiment of the present application.
  • FIG5 is a schematic diagram of the structure of an interest prediction model provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of the structure of another interest prediction model provided in an embodiment of the present application.
  • FIG7 is a schematic diagram of a structure describing a prediction model provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of the overall process of a multimedia resource playback method provided in an embodiment of the present application.
  • FIG9 is a schematic diagram of a process architecture of a multimedia resource playback method provided in an embodiment of the present application.
  • FIG10 is a structural diagram of a multimedia resource playback device provided in an embodiment of the present application.
  • FIG11 is a structural diagram of a terminal provided in an embodiment of the present application.
  • FIG. 12 is a structural diagram of a server provided in an embodiment of the present application.
  • the playback progress bar provided in the related art can be a control used by the user to reflect the playback progress of multimedia resources while the user is watching or listening to the multimedia resources, and the user can quickly jump to the location of interest for watching or listening by dragging the playback progress bar.
  • the current playback progress bar only displays time information, that is, it only displays the playback progress of the multimedia resource. Taking the multimedia resource as a video as an example, the playback progress bar can be shown in Figure 1.
  • the playback progress bar shows the total duration of the entire video "2:09:37” and the duration of the currently played video portion "1:18:17", thereby reflecting the playback progress through the ratio between the two durations and the position of the slider in the playback progress bar (such as shown by the black circle on the playback progress bar in Figure 1).
  • the embodiment of the present application provides a multimedia resource playback method, which can mine the interest of the multimedia playback object (such as the user) in the multimedia resource segments of different time intervals in the multimedia resource to be played, so as to generate a playback progress bar according to the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played.
  • the interesting position can be intuitively found according to the playback progress bar, and the interesting position can be quickly and accurately located without repeated dragging operations, thereby improving the accuracy and efficiency of jumping to the interesting position and improving the user experience.
  • the system architecture includes a terminal 200 and a server 300.
  • the terminal 200 can install a multimedia platform or access the multimedia platform through a browser, so that the multimedia playback object can access the multimedia playback platform through the terminal 200 to watch or listen to the multimedia resources.
  • the terminal 200 includes but is not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc., but is not limited thereto.
  • the server 300 can provide the terminal 200 with a service for accessing multimedia resources, wherein the server 300 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.
  • the terminal 200 and the server 300 can be directly or indirectly connected via wired or wireless communication, which is not limited in this application.
  • the terminal 200 and the server 300 can be connected via a network, which can be a wired or wireless network.
  • the multimedia playback object may be an object that selects a certain multimedia resource (e.g., a multimedia resource to be played) to play in order to watch or listen to the multimedia resource, such as a user.
  • the multimedia resource to be played may be a multimedia resource that is triggered by a play operation and is waiting to be played.
  • the multimedia resources may include multiple types, such as videos (e.g., short videos, movies, TV series, etc.), audio (e.g., music, audio novels, radio dramas, etc.).
  • the terminal 200 may perform a playback operation on the multimedia resource to be played, and then obtain a playback request generated based on the playback operation.
  • the playback operations performed on the multimedia resources to be played may be different. If the multimedia resource to be played is a short video, the playback operation may be to open the multimedia platform of the short video, or to switch the short video, or to select a short video from all short videos under a certain account; if the multimedia resource to be played is a movie, the playback operation may be to select a movie for playback; if the multimedia resource to be played is an episode of a TV series, the playback operation may be to select an episode from multiple episodes for playback; if the multimedia resource to be played is audio, the playback operation may be to select an audio for playback, and so on.
  • the embodiments of the present application do not limit this.
  • the embodiment of the present application is mainly introduced by taking the multimedia to be played as a video, which may be an episode of a TV series as an example.
  • the multimedia playback object opens a TV series and enters an episode selection page, such as 201 shown in Figure 2, including multiple episodes, namely Episode 1, Episode 2, Episode 3, ..., and then selects Episode 3 from the multiple episodes on the episode selection page for playback.
  • the play request carries an object identifier of a multimedia play object and a multimedia identifier of a multimedia resource to be played, wherein the object identifier is used to indicate an object that plays the multimedia resource to be played, and the multimedia identifier is used to indicate the multimedia resource to be played. Since different objects may have different interests in multimedia resource segments in different time intervals in different multimedia resources, the terminal 200 can obtain the interests of the multimedia play object in multimedia resource segments in different time intervals in the multimedia resource to be played based on the object identifier and the multimedia identifier.
  • the terminal 200 generates a playback progress bar based on the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played. Then the terminal 200 plays the multimedia resource to be played, and displays the playback progress bar on the playback page of the multimedia resource to be played when playing the multimedia resource to be played.
  • the playback page can refer to 202 shown in FIG. 2, and the playback progress bar can be shown in 2021.
  • the playback progress bar can include different display forms, and the display form can include, for example, a heartbeat curve, a bar graph, a straight line combined with an interest value (wherein the straight line reflects the playback progress, and the value reflects the interest), etc.
  • the playback progress bar shown in 2021 takes the display form of the heartbeat curve as an example, wherein the horizontal coordinate of the heartbeat curve is the time interval, and the vertical coordinate (i.e., the height of the heartbeat curve) is the interest.
  • the playback progress bar provided in the embodiment of the present application combines the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played with the progress bar, which can be used to indicate the playback progress of the multimedia resource to be played and the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • the playback progress bar provided in the embodiment of the present application can be called a cardiogram-type progress bar.
  • the multimedia playback object can understand the interest in the multimedia resource segments in different time intervals based on the playback progress bar, so as to quickly and intuitively find the position of interest (i.e., the time interval), and the sliding granularity of the playback progress bar matches the granularity of the division of the time interval, so the multimedia playback object can control the playback progress bar to reach the position of interest.
  • the multimedia playback object can directly control the playback progress bar to reach the position to achieve fast and accurate positioning.
  • the present application can intuitively find the position of interest based on the playback progress bar, thereby eliminating the need for repeated dragging operations, and can quickly and accurately locate the position of interest, thereby improving the accuracy and efficiency of jumping to the position of interest and improving the user experience.
  • the computer device may be a server or a terminal
  • the method provided in the embodiments of the present application may be executed by the terminal or the server alone, or by the terminal and the server in cooperation.
  • the embodiment corresponding to FIG. 2 is mainly introduced by taking the terminal executing the method provided in the embodiment of the present application as an example.
  • the method provided in the embodiment of the present application is executed by the server alone, its execution method is similar to the embodiment corresponding to FIG. 2, mainly replacing the terminal with a server.
  • the steps that need to be reflected on the front-end interface can be executed by the terminal, such as displaying a playback progress bar; and some steps that require background calculations and do not need to be reflected on the front-end interface can be executed by the server, such as obtaining the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resources to be played, generating a playback progress bar, etc.
  • user-related data may be involved in the process of determining the interest level.
  • the user's separate permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.
  • FIG. 3 shows a flowchart of a method for playing multimedia resources, the method comprising:
  • S301 Obtain a play request for a multimedia resource to be played.
  • the terminal may perform a playback operation on the multimedia resource to be played, and then obtain a playback request generated based on the playback operation.
  • the type of the multimedia resource to be played may be video, audio, etc., and video and audio may include multiple possible situations.
  • the multimedia playback object may perform a playback operation on a certain episode on the multimedia platform, thereby triggering a playback request so that the terminal obtains the playback request. For example, after opening the TV series, the multimedia playback object selects a certain episode of the TV series from the episode list for playback.
  • the play request may be generated by the terminal based on the play operation.
  • S301 may be implemented by the terminal sending the play request to the server.
  • the purpose of the embodiment of the present application is to combine the multimedia playback object's interest in multimedia resource segments in different time intervals in the multimedia resource to be played with the progress bar, so that the playback progress bar can reflect the multimedia playback object's interest in multimedia resource segments in different time intervals, thereby facilitating positioning to jump to the location of interest.
  • Different objects may have different interests in multimedia resource segments in different time intervals in different multimedia resources.
  • the terminal it is necessary to enable the terminal to determine which object and which multimedia resource it is, so the playback request obtained by the terminal may include an object identifier and a multimedia identifier.
  • the object identifier is used to indicate the object that plays the multimedia resource to be played, so as to determine the identity of the multimedia playback object.
  • the object identifier can be, for example, an account number used by the multimedia playback object to log in or access the multimedia platform, or can be the terminal identifier used.
  • the multimedia identifier is used to indicate the multimedia resource to be played, so as to determine the multimedia resource to be played.
  • the multimedia identifier can be, for example, the name, number, etc. of the multimedia resource to be played.
  • S302 Based on the object identifier and the multimedia identifier, obtain the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • the terminal can obtain the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • the division granularity of the time interval can be configured according to actual needs, or it can be determined according to the sliding granularity of the playback progress bar.
  • the sliding granularity can represent the minimum time unit that the multimedia resource to be played can jump to when the slider on the playback progress bar moves once.
  • the sliding granularity can be pre-configured to generate a playback progress bar that can jump according to the sliding granularity. For example, if the sliding granularity of the playback progress bar is S seconds, the multimedia resource to be played can be divided into time intervals with S seconds as the division granularity.
  • S303 Generate a playback progress bar according to the multimedia playback object's interest in multimedia resource segments in different time intervals in the multimedia resource to be played.
  • the terminal draws a playback progress bar according to the multimedia playback object's interest in multimedia resource segments in different time intervals, and the sliding granularity of the playback progress bar matches the granularity of the time interval division.
  • the playback progress bar may include different display forms, such as a heartbeat curve, a bar graph, a straight line combined with an interest value (where the straight line reflects the playback progress and the value reflects the interest), etc.
  • the embodiment of the present application mainly takes the display form of the heartbeat curve as an example.
  • the terminal can draw a heartbeat curve with the horizontal axis as the time interval and the vertical axis as the interest, and the obtained playback progress bar can be called a heartbeat graph progress bar.
  • the sliding granularity of the play progress bar can also be configured according to the actual needs, so that the sliding granularity of the play progress bar matches the division granularity of the time interval; if the division granularity of the time interval is determined according to the sliding granularity of the play progress bar, then when generating the play progress bar, a play progress bar with the above sliding granularity is generated, so that the sliding granularity of the play progress bar matches the division granularity of the time interval.
  • the matching here can mean that the sliding granularity of the play progress bar is consistent with the division granularity of the time interval, for example, the sliding granularity of the play progress bar is S seconds, and the division granularity of the time interval is S seconds.
  • the multimedia playback object can know the interest of each multimedia resource segment in the time interval that can be jumped to, so as to complete fast and accurate positioning and jumping according to the interest.
  • S304 Play the multimedia resource to be played, and display the play progress bar on the play page of the multimedia resource to be played while playing the multimedia resource to be played.
  • the terminal plays the multimedia resource to be played, and when playing the multimedia resource to be played, a play progress bar is displayed on the play page of the multimedia resource to be played. Since the play progress bar is generated according to the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played, the play progress bar can indicate the play progress of the multimedia resource to be played and the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played. In this way, the multimedia playback object can understand the interest in the multimedia resource segments in different time intervals based on the play progress bar, which enhances the richness of the information displayed on the play progress bar, so as to quickly and intuitively find the location of interest (i.e., the time interval).
  • FIG. 4 shows an example diagram of a play page of a multimedia resource to be played, in which a play progress bar may be displayed, as shown in 401 in FIG. 4 .
  • a playback request can be generated based on the playback operation, thereby obtaining a playback request for the multimedia resource to be played. Since the playback request carries the object identifier of the multimedia playback object and the multimedia identifier of the multimedia resource to be played, the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played can be obtained based on the object identifier and the multimedia identifier.
  • a playback progress bar is generated, the multimedia resource to be played is played, and when the multimedia resource to be played is played, the playback progress bar is displayed on the playback page of the multimedia resource to be played.
  • the multimedia playback object can understand the interest in the multimedia resource segments of different time intervals based on the playback progress bar, so as to quickly and intuitively find the interested position (i.e., the time interval), and the sliding granularity of the playback progress bar matches the division granularity of the time interval, so the multimedia playback object can control the playback progress bar to reach the position of interest.
  • the present application can intuitively find the position of interest based on the playback progress bar, thereby eliminating the need for repeated dragging operations, and can quickly and accurately locate the position of interest, thereby improving the accuracy and efficiency of jumping to the position of interest and improving the user experience.
  • the most critical issue is how to obtain the interest of the multimedia playback object in the multimedia resource segments of different time intervals.
  • multiple acquisition methods are provided.
  • One acquisition method is to pre-calculate the interest of the multimedia playback object in the multimedia resource segments of different time intervals and store it in an interest storage space (such as a database, hard disk, etc.). When it is needed, it can be directly searched from the interest storage space.
  • the interest storage space may store the interest of multiple objects in multimedia resource segments of different time intervals in different multimedia resources, and the multiple objects include multimedia playback objects.
  • the interest storage space stores the interest of object 1 in multimedia resource segments of different time intervals in multimedia resource 1, the interest of object 2 in multimedia resource segments of different time intervals in multimedia resource 1, the interest of object 2 in multimedia resource segments of different time intervals in multimedia resource 2, ..., the interest of object N in multimedia resource segments of different time intervals in multimedia resource 1, and the interest of object N in multimedia resource segments of different time intervals in multimedia resource N.
  • object 1, object 2, ..., object N have corresponding object identifiers respectively
  • multimedia resource 1, multimedia resource 2, ..., multimedia resource N have corresponding multimedia identifiers respectively.
  • the implementation method of S302 can be that the terminal searches the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played from the interest storage space according to the object identifier and the multimedia identifier.
  • the object identifier obtained by the terminal is consistent with the object identifier of object 1
  • the multimedia identifier obtained by the terminal is consistent with the multimedia identifier of multimedia resource 1.
  • the interest of object 1 in multimedia resource segments in different time intervals in multimedia resource 1 can be obtained from the interest storage space, that is, object 1 is a multimedia playback object, and multimedia resource 1 is a multimedia resource to be played.
  • the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played is calculated in advance.
  • it can be directly searched from the interest storage space, which reduces the amount of calculation and improves the playback and display efficiency.
  • the interest stored in the interest storage space can be updated regularly, or when a significant change in interest is detected, the interest stored in the interest storage space can be updated.
  • the embodiment of the present application does not limit the updating method.
  • multimedia resources on a multimedia platform there may be a large number of multimedia resources on a multimedia platform, and the number of commonly used objects on the multimedia platform may also be very large.
  • some objects may have a relatively high activity, for example, multimedia resources are often played through the multimedia platform, so it may be necessary to frequently obtain their interest in multimedia resource segments of different time intervals in the multimedia resources; while some objects may have a relatively low activity, for example, the multimedia platform is only used occasionally, so it may take a long time to obtain their interest in multimedia resource segments of different time intervals in the multimedia resources.
  • the interest of the object with high activity in the multimedia resource segments of different time intervals in the multimedia resources can be pre-calculated and stored in the interest storage space, so that for the object with high activity, the interest in the multimedia resource segments of different time intervals can be obtained by searching from the interest storage space.
  • the terminal before executing S302, the terminal can obtain the interactive data of the multimedia playback object based on the object identifier, and then determine the activity of the multimedia playback object according to the interactive data.
  • the activity of the multimedia playback object is higher than the first threshold, it means that it is an object with relatively high activity, and its interest in the multimedia resource segments of different time intervals of different multimedia resources is stored in the interest storage space, so the steps shown in S302 can be executed.
  • the interactive data can be the data of the multimedia playback object interacting on the multimedia platform, for example, it can include playing multimedia resources, posting comments, barrage content, etc.
  • Another acquisition method may be to calculate the interest of the multimedia playback object in different time intervals of the multimedia resource segments in the multimedia resource to be played in real time when the multimedia resource to be played needs to be played.
  • the real-time calculation method is similar to the pre-calculation method, mainly the calculation timing is different.
  • the implementation of this application will take the real-time calculation method as an example to introduce the calculation method of interest in detail.
  • a possible calculation method provided by the embodiment of the present application may be that the terminal obtains the first object interest tag of the multimedia playback object according to the object identifier, and obtains the multimedia resource information of the multimedia resource segments in different time intervals in the multimedia resource to be played according to the multimedia identifier, and then determines the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resource to be played based on the first object interest tag and the multimedia resource information of the multimedia resource segments in different time intervals.
  • the first object interest tag can be determined based on the historical playback data of the multimedia playback object, which can reflect the content that the multimedia playback object is interested in.
  • the first object interest tag may include the type of multimedia resource, the main creative members, etc.
  • the first object tag may include the type of multimedia resource and the main creative members, such as ancient costume, family, campus, etc., and the main creative members are actor A, film and television company B, etc.
  • the first object tag may include the type of multimedia resource and the main creative members, such as sad, light music, rock, ancient style, etc., and the main creative members are singer C, etc.
  • real-time calculation can be used for objects with low activity.
  • the terminal before executing S302, the terminal can obtain the interactive data of the multimedia playback object based on the object identifier, and then determine the activity of the multimedia playback object based on the interactive data. If the activity of the multimedia playback object is lower than the first threshold, it means that it is an object with relatively low activity, and its interest in multimedia resource segments of different time intervals of different multimedia resources is not stored in the interest storage space, and real-time calculation is required, so the steps shown in S302 can be executed.
  • the multimedia resource information may include at least one of multimedia resource content and bullet-screen content.
  • the multimedia resource content directly reflects the content of different multimedia resource segments, while the bullet-screen content is usually the content (e.g., text, emoticons) published by the object viewing the multimedia resource to be played for the multimedia resource segment.
  • the bullet-screen content may include “Thanks for the gift”, “Showmanship mode is on”, “Imitate the plot of Xiao Ming”, “Xiao Hong is the real master”, “Send it handsomely”, etc.
  • the bullet-screen content can reflect the content of the multimedia resource segment to a certain extent.
  • the interest of the multimedia playback object in the bullet-screen content in the multimedia resource segment can reflect the interest of the multimedia playback object in the multimedia resource segment, thereby helping to determine the interest of the multimedia playback object in the multimedia resource segment.
  • the barrage content can be directly obtained by extracting the barrage on the playback interface, and the acquisition method is simple and convenient. Therefore, in a possible implementation method of the embodiment of the present application, the multimedia resource information includes at least one barrage content of the multimedia resource segment, so as to determine the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played.
  • the method of determining the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played can be for any time interval of the multimedia resource segment, according to the first object interest tag and any barrage content in the multimedia resource segment, respectively calculate the interest of the multimedia playback object in any barrage content, and perform weighted summation on the interest of any barrage content to obtain the interest of the multimedia playback object in the multimedia resource segment.
  • the weight used for the weighted summation can be the heat of the barrage content, which can be expressed by the ratio of the number of likes of the barrage content to the sum of the number of likes of all barrage contents of the multimedia resource to be played.
  • the above method is used to calculate all time intervals respectively, so as to obtain the interest of the multimedia playback object in the multimedia resource segments in different time intervals of the multimedia resource to be played.
  • This method can reduce the calculation complexity of the interest, simplify the calculation of the interest, and improve the calculation efficiency.
  • the multimedia resource segment of time interval t may include multiple bullet-screen contents, wherein any bullet-screen content is bullet-screen content b, firstly, the interest of the multimedia playback object in the bullet-screen content b is calculated, expressed as p_in_u[b].
  • the interest of the multimedia playback object in multimedia resource segments in different time intervals in the multimedia resources to be played can be determined through an interest prediction model, that is, the first object interest tag and multimedia resource information of the multimedia resource segments in different time intervals are input into the interest prediction model, thereby outputting the multimedia playback object's interest in the multimedia resource segments in different time intervals in the multimedia resources to be played.
  • the method of calculating the interest of the multimedia playback object in any barrage content according to the first object interest tag and any barrage content in the multimedia resource segment can be to encode the first object interest tag to obtain the first object interest feature vector, and to encode any barrage content in the multimedia resource segment to obtain the barrage feature vector of any barrage content. Then, the first object interest feature vector and the barrage feature vector of any barrage content are interacted with each other to obtain the first fused feature vector of any barrage content, and then the interest degree is predicted according to the first fused feature vector of any barrage content to obtain the interest degree of the multimedia playback object in any barrage content.
  • FIG5 shows a schematic diagram of the structure of an interest prediction model, which may include an encoding module, a first fusion module and a prediction module.
  • the first object interest tag and the bullet content are used as inputs of the interest prediction model.
  • the first object interest tag is encoded by the encoding module to obtain a first object interest feature vector
  • the bullet content is encoded by the encoding module to obtain a bullet feature vector.
  • the first fusion module performs attention interaction on the first object interest feature vector and the bullet feature vector to obtain a first fusion feature vector.
  • the prediction module performs interest prediction on the first fusion feature vector to obtain the interest of the multimedia playback object in the bullet content.
  • the weight of the first object interest tag can also be used as the input of the interest prediction model, so as to combine the weight of the first object interest tag and the first object interest tag to obtain the first object interest feature vector.
  • the encoding module can be a Transformer-Encoder.
  • each barrage content has a corresponding publishing object
  • the publishing object can be the object that publishes the barrage content, such as the user who plays the multimedia resource to be played and expresses his opinion on the multimedia resource segment.
  • the barrage content published by different publishing objects can reflect their interest in the multimedia resource segment. If the multimedia playback object has similar interests to the publishing object, the multimedia playback object's interest in the multimedia resource segment may also be similar to that of the publishing object. Therefore, in the embodiment of the present application, the second object interest tag of the publishing object can be used to assist in determining the multimedia playback object's interest in the barrage content.
  • the interest prediction is performed based on the first fused feature vector of any barrage content
  • the method for obtaining the multimedia playback object's interest in any barrage content can be that the terminal obtains the second object interest tag of the publishing object of any barrage content, encodes the second object interest tag to obtain the second object interest feature vector, and then performs attention interaction between the first object interest feature vector and the second object interest feature vector to obtain the second fused feature vector.
  • the second fused feature vector can reflect the consistency of interest between the multimedia playback object and the publishing object. The more consistent the interest, the higher the interest of the multimedia playback object in the barrage content published by the publishing object may be, thereby assisting in predicting the multimedia playback object's interest in the barrage content.
  • the first fused feature vector and the second fused feature vector are feature concatenated to obtain a concatenated feature vector, so as to perform interest prediction based on the concatenated feature vector to obtain the interest of the multimedia playback object in any bullet screen content.
  • FIG6 shows a schematic diagram of the structure of another interest prediction model, which may include an encoding module, a first fusion module, a second fusion module, a splicing module and a prediction module.
  • the first object interest tag, the second object interest tag and the barrage content are used as inputs of the interest prediction model.
  • the first object interest tag is encoded by the encoding module to obtain a first object interest feature vector
  • the second object interest tag is encoded by the encoding module to obtain a second object interest feature vector
  • the barrage content is encoded by the encoding module to obtain a barrage feature vector.
  • the first fusion module performs attention interaction on the first object interest feature vector and the barrage feature vector to obtain a first fused feature vector
  • the second fusion module performs object feature interest vector on the first object feature interest vector and the second object feature interest vector.
  • the splicing module performs feature splicing on the first fused feature vector and the second fused feature vector to obtain a spliced feature vector, so that the prediction module performs interest prediction based on the spliced feature vector to obtain the interest of the multimedia playback object in any barrage content.
  • the weight of the first object interest tag and the weight of the second object interest tag can also be used as inputs of the interest prediction model, thereby combining the weight of the first object interest tag and the first object interest tag to obtain the first object interest feature vector, and combining the weight of the second object interest tag and the second object interest tag to obtain the second object interest feature vector.
  • the interest prediction model used in the embodiment of the present application can be obtained by pre-training, and the training data used for training can be the interactive behavior data of likes for the sample barrage content. If the user (for example, the sample multimedia playback object) likes the sample barrage content, it means that the user is interested in the sample barrage content, which is the positive sample data, otherwise it is a negative sample. According to the above-mentioned interactive behavior data of likes, the first sample object interest tag of the sample multimedia playback object, the second sample object interest tag of the sample publishing object, and the sample barrage content can be obtained.
  • the first sample object interest tag and the sample barrage content are used as input, and then the processing method described in the corresponding embodiment of Figure 5 is used to process the input data to achieve model training; or the first sample object interest tag, the second sample object interest tag, and the sample barrage content are used as input, and then the processing method described in the corresponding embodiment of Figure 6 is used to process the input data to achieve model training.
  • the model training converges, the interest prediction model is obtained, and the interest of the multimedia playback object in the barrage content can be output for the multimedia resource to be played.
  • the bullet screen content whose interest reaches a second threshold can also be recorded, so that when the slider of the playback progress bar moves to the first time interval, that is, when the multimedia playback object uses the playback progress bar to switch to the first time interval, the terminal responds to the slider of the playback progress bar moving to the first time interval.
  • the target barrage content is preferentially displayed on the playback page of the multimedia resource to be played.
  • the target barrage content is the barrage content whose interest reaches the second threshold, and the target barrage content belongs to at least one barrage content of the multimedia resource segment in the first time interval.
  • the multimedia playback object when the multimedia playback object determines the time interval of interest according to the heartbeat reflected on the playback progress bar, the multimedia playback object can use the playback progress bar to switch to this time interval.
  • description information of multimedia resource segments of different time intervals can also be generated, so that in the process of playing the multimedia resource to be played, the terminal can respond to the control operation of the slider on the playback progress bar, control the slider to move to the second time interval, and display the description information of the multimedia resource segment of the second time interval.
  • the description information can be used to summarize the main content of the multimedia resource segment of the time interval, so that the multimedia playback object can understand the content of the multimedia resource segment to be played in the time interval according to the description information, so as to assist the multimedia playback object to confirm the point of interest.
  • the control operation can be various operations to control the slider to move to the second time interval, such as dragging operation, clicking operation, etc.
  • the dragging operation is to drag the slider to the second time interval
  • the clicking operation can be to click a certain position to move the slider to the time interval corresponding to the position.
  • the multimedia playback object is more interested in various yo-yo fancy playing methods, cool actions, etc.
  • the multimedia playback object drags the slider (shown in the black circle in FIG4 ) to the second time interval according to the interest level on the playback progress bar, the description information “fancy skills reappearance” shown in 402 can be displayed.
  • the multimedia playback object can know that the multimedia resource segment in the second time interval may play yo-yo fancy playing methods and cool actions, thereby assisting the multimedia playback object to determine that the multimedia resource segment in this time interval is of interest to it.
  • the description information may be obtained by prediction through a description prediction model. Since the description information is a personalized description of a multimedia playback object, the description information may be generated based on the first object interest tag of the multimedia playback object, that is, a possible implementation method for generating description information of multimedia resource segments of different time intervals is to obtain the first object interest tag of the multimedia playback object according to the object identifier, and obtain multimedia resource information of multimedia resource segments of different time intervals in the multimedia resource to be played according to the multimedia identifier, and then for the multimedia resource segments of any time interval, based on the first object interest tag and the multimedia resource information of the multimedia resource segments, generate description information of the multimedia resource segments through a description prediction model.
  • the multimedia resource information here is similar to the aforementioned multimedia resource information, and the multimedia resource information may include at least one of multimedia resource content and barrage content.
  • the embodiment of the present application is mainly introduced by taking at least one barrage content including a multimedia resource fragment in the multimedia resource information as an example. Since the barrage content may include a lot, some barrage content has a high degree of interaction, which is conducive to generating description information, and some barrage content has a low degree of interaction, which is not conducive to generating description information. Therefore, in order to improve the accuracy of the description information generation, the first object interest tag and the barrage content with the top m interaction heat in the time interval can be used as the input of the description prediction model to generate description information.
  • the method of processing the first object interest tag to generate the corresponding first object interest feature vector is similar to the method shown in Figure 5 or Figure 6.
  • This vector can enhance the user personalization of the generated description information.
  • a combination of pre-training and fine-tuning can be used when training the description prediction model, that is, first obtain the first sample object interest tag of the multimedia playback sample object, and obtain the multimedia resource information of the sample multimedia resource, so as to pre-train the initial network model based on the first sample object interest tag and the multimedia resource information, and use the title information of the sample multimedia resource as the training target to obtain a pre-trained model.
  • the second sample object can be a sample publishing object, which is an object that publishes barrage content for a sample multimedia resource segment, and the interest tag corresponding to the second sample object is called a second sample object interest tag.
  • the description prediction model can adopt various network structures, and this application does not limit this.
  • the embodiment of this application mainly introduces the initial network model, pre-training model, and description prediction model using the unified coding (Unified-Transformer) model as the basic model structure.
  • the Unified-Transformer model includes a unified coding layer (Unified-Transformer Layer) 1, a unified coding layer 2, and a unified coding layer N.
  • pre-training is performed on a large number of sample multimedia resources (such as short videos) with title information on the multimedia platform.
  • the object whose completion degree of the short video meets a certain threshold is regarded as an interested user of the short video (i.e., a multimedia playback sample object), and the first sample object interest tag of the multimedia playback sample object is input into the encoding module, and the barrage content with the top m interactive heat of the short video is input into the encoding module, thereby obtaining the first sample object interest feature vector, and the initial network model calculates the input first sample object interest feature vector through full attention (Fully-Attention) (i.e., bidirectional self-attention (Self-Attention)).
  • the title information of the short video is taken as the target, and prefix attention is used. That is, when each step is generated, only the attention from this step to the previous position can be calculated.
  • the initial network model shown in Figure 7 can be initialized to a better state to obtain a pre-trained model.
  • the interest tag of the sample publishing object that is, the interest tag of the second sample object
  • the barrage content with top m interactive heat in the time interval that is, the multimedia resource information of the sample multimedia resource fragment
  • the training target in the fine-tuning stage is the manually constructed descriptive information.
  • the barrage content can be segmented into words to obtain multiple input words, namely input word 1, input word 2, input word 3, ..., input word k, and then the multiple input words are interpolated through the lookup table module, and the results are sent to the input part, and then the description information is generated based on the multiple input words through the generation part.
  • the description information is composed of multiple description words (such as description word 1, description word 2, ..., description word n-1, description word n). At each step of generation, only the attention from this step to the previous position can be calculated.
  • the start mark in Figure 7 indicates the start of predicting the description information.
  • the first step calculates description word 1, and the second step is based on the attention from this step to the previous position (including description word 1) to obtain description word 2.
  • the n-1 step is based on the attention from this step to the previous position (including description word n-2) to obtain description word n-1
  • the nth step is based on the attention from this step to the previous position (including description word n-1) to obtain description word n.
  • the embodiment of the present application jointly models the multimedia resource information of the multimedia resource to be played and the interest tag of the first object, constructs the heartbeat degree of the multimedia playback object to the multimedia resource segments of the multimedia resource in different time intervals, and replaces the playback progress bar shown in Figure 1 with the cardiogram-style progress bar shown in Figure 4.
  • the height of the heartbeat curve in the cardiogram-style progress bar indicates the possible interest of the multimedia playback object in this time interval, which is convenient for users to intuitively find the part of interest.
  • the multimedia playback object drags the cardiogram-style progress bar, as the dragging position changes, the description information of the position is dynamically displayed, and the barrage content of interest is selected for priority display, so that the multimedia playback object can quickly realize the positioning jump of the interested position through the cardiogram-style progress bar, improve the use experience of the playback progress bar, and further improve the user experience.
  • the multimedia playback object can be a user, then the multimedia playback object can be called a viewing user, the multimedia resource to be played can be a video to be played, the multimedia resource segment can be a video segment, and the multimedia resource information can be the barrage content.
  • the overall process of the multimedia resource playback method can be shown in Figure 8, and the method can be executed by the terminal, including the following steps:
  • S801 The terminal obtains a playback operation performed on a video to be played.
  • the terminal In response to the playback operation, the terminal obtains the first object interest tag of the viewing user and the bullet screen content of the video segments in different time intervals in the video to be played.
  • the process architecture of the multimedia resource playback method can be shown in FIG9 , wherein other users who have watched the video to be played may publish corresponding bullet screen content for different video clips when watching the video to be played (as shown in 901 ), and the bullet screen content can be stored in a bullet screen content database (as shown in 902 ).
  • the bullet screen content can be obtained from the bullet screen content database.
  • the terminal calculates the viewing user's interest in the video segments in different time intervals based on the first object interest tag and the bullet screen contents of the video segments in different time intervals in the video to be played.
  • the first object interest tag can reflect the interest of the viewing user, so step S803 can be called interest degree calculation based on the viewing user's interest, referring to step 1 in FIG9 .
  • S804 The terminal generates description information of video clips in different time intervals.
  • the description information may be generated based on the first object interest tag of the viewing object, meeting the personalized needs of the viewing object, so step S804 may be referred to as generation of personalized description information, see step 2 in FIG9 .
  • S805 The terminal plays the video to be played and displays a playback progress bar.
  • S805 can refer to step 3 shown in FIG. 9 , and the play progress bar is generated based on the viewing user's interest in the video clips in different time intervals.
  • the terminal plays the video clip corresponding to the second time interval and displays the description information and bullet comment content corresponding to the second time interval.
  • Viewing users can switch locations based on the interest estimate.
  • a time interval such as the second time interval
  • the playback progress bar can be dragged to the second time interval to switch to the video clip corresponding to the second time interval for playback, and display the description information and barrage content corresponding to the second time interval, so that viewing users can more intuitively find the viewing location of interest.
  • the embodiment of the present application further provides a multimedia resource playback device 1000, which includes an acquisition unit 1001, a generation unit 1002, a playback unit 1003, and a display unit 1004:
  • the acquisition unit 1001 is used to acquire a play request for a multimedia resource to be played, wherein the play request carries an object identifier of a multimedia playback object and a multimedia identifier of the multimedia resource to be played;
  • the acquisition unit 1001 is further configured to acquire, based on the object identifier and the multimedia identifier, the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played;
  • the generating unit 1002 is used to generate a playback progress bar according to the interest of the multimedia playback object in the multimedia resource segments in different time intervals of the multimedia resource to be played, and the sliding granularity of the playback progress bar matches the granularity of the division of the time interval;
  • the playing unit 1003 is used to play the multimedia resource to be played
  • the display unit 1004 is used to display the playback progress bar on the playback page of the multimedia resource to be played when playing the multimedia resource to be played.
  • the playback progress bar is used to indicate the playback progress of the multimedia resource to be played and the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • the obtaining unit 1001 is specifically configured to:
  • the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played is searched from the interest storage space, the interest storage space stores the interest of multiple objects in the multimedia resource segments in different time intervals in different multimedia resources, and the multiple objects include the multimedia playback object.
  • the device further includes a determining unit:
  • the determining unit is used to obtain the interactive data of the multimedia playback object based on the object identifier
  • the determination unit determines that the activity of the multimedia playback object is higher than the first threshold, it triggers the acquisition unit 1001 to execute the step of searching the interest storage space for the multimedia playback object's interest in multimedia resource segments in different time intervals in the multimedia resources to be played based on the object identifier and the multimedia identifier.
  • the obtaining unit 1001 is specifically configured to:
  • the interest degree of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played is determined.
  • the device further includes a determining unit:
  • the determining unit is used to obtain the interactive data of the multimedia playback object based on the object identifier
  • the acquisition unit 1001 is triggered to execute the steps of acquiring the first object interest tag of the multimedia playback object according to the object identifier, and acquiring the multimedia resource information of the multimedia resource fragments in different time intervals in the multimedia resource to be played according to the multimedia identifier.
  • the multimedia resource information includes at least one bullet screen content of the multimedia resource segment, and the obtaining unit 1001 is specifically configured to:
  • the interest level of any barrage content is weighted and summed to obtain the interest level of the multimedia playback object in the multimedia resource segment.
  • the obtaining unit 1001 is specifically configured to:
  • the interest level is predicted based on the first fused feature vector of any barrage content to obtain the interest level of the multimedia playback object in the any barrage content.
  • the obtaining unit 1001 is specifically configured to:
  • the interest level of the multimedia playback object in any of the bullet screen contents is obtained by performing interest level prediction based on the spliced feature vector.
  • the device further includes a recording unit:
  • the recording unit is used to record the bullet comment content whose interest reaches a second threshold
  • the display unit 1004 is also used to preferentially display target barrage content on the playback page of the multimedia resource to be played in response to the slider of the playback progress bar moving to the first time interval, wherein the target barrage content is barrage content whose interest reaches the second threshold, and the target barrage content belongs to at least one barrage content of the multimedia resource segment in the first time interval.
  • the device further includes a control unit:
  • the generating unit 1002 is further configured to generate description information of multimedia resource segments in different time intervals;
  • the control unit is used to control the slider to move to a second time interval in response to a control operation on the slider on the playback progress bar during the process of playing the multimedia resource to be played;
  • the display unit 1004 is further configured to display description information of the multimedia resource segment in the second time interval.
  • the generating unit 1002 is specifically configured to:
  • description information of the multimedia resource segment is generated through a description prediction model.
  • the training method of the description prediction model includes:
  • the pre-trained model is trained to obtain the description prediction model.
  • the multimedia resource information includes at least one of multimedia resource content and barrage content.
  • a playback request can be generated based on the playback operation, thereby obtaining a playback request for the multimedia resource to be played. Since the playback request carries the object identifier of the multimedia playback object and the multimedia identifier of the multimedia resource to be played, the interest of the multimedia playback object in the multimedia resource segments of different time intervals in the multimedia resource to be played can be obtained based on the object identifier and the multimedia identifier.
  • a playback progress bar is generated, the multimedia resource to be played is played, and when the multimedia resource to be played is played, the playback progress bar is displayed on the playback page of the multimedia resource to be played.
  • the multimedia playback object can understand the interest in the multimedia resource segments of different time intervals based on the playback progress bar, thereby quickly and intuitively finding the interested position (i.e., the time interval), and the sliding granularity of the playback progress bar matches the division granularity of the time interval, so the multimedia playback object can control the playback progress bar to reach the position of interest.
  • the present application can intuitively find the position of interest based on the playback progress bar, thereby eliminating the need for repeated dragging operations, and can quickly and accurately locate the position of interest, thereby improving the accuracy and efficiency of jumping to the position of interest and improving the user experience.
  • the embodiment of the present application further provides a computer device, which may be a terminal.
  • the terminal is a smart phone:
  • FIG11 is a block diagram showing a partial structure of a smartphone provided in an embodiment of the present application.
  • the smartphone includes: a radio frequency (full name in English: Radio Frequency, English abbreviation: RF) circuit 1110, a memory 1120, an input unit 1130, a display unit 1140, a sensor 1150, an audio circuit 1160, a wireless fidelity (English abbreviation: WiFi) module 1170, a processor 1180, and a power supply 1190 and other components.
  • the input unit 1130 may include a touch panel 1131 and other input devices 1132
  • the display unit 1140 may include a display panel 1141
  • the audio circuit 1160 may include a speaker 1161 and a microphone 1162.
  • the smartphone structure shown in FIG11 does not constitute a limitation on the smartphone, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.
  • the memory 1120 can be used to store software programs and modules.
  • the processor 1180 executes various functional applications and data processing of the smartphone by running the software programs and modules stored in the memory 1120.
  • the memory 1120 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the smartphone (such as audio data, a phone book, etc.), etc.
  • the memory 1120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the processor 1180 is the control center of the smartphone, which uses various interfaces and lines to connect various parts of the entire smartphone, and executes various functions of the smartphone and processes data by running or executing software programs and/or modules stored in the memory 1120, and calling data stored in the memory 1120.
  • the processor 1180 may include one or more processing units; preferably, the processor 1180 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1180.
  • the processor 1180 in the smart phone may perform the following steps:
  • Play the multimedia resource to be played and when playing the multimedia resource to be played, display the playback progress bar on the playback page of the multimedia resource to be played, wherein the playback progress bar is used to indicate the playback progress of the multimedia resource to be played and the interest of the multimedia playback object in the multimedia resource segments in different time intervals in the multimedia resource to be played.
  • the computer device provided in the embodiment of the present application can also be a server, as shown in Figure 12,
  • Figure 12 is a structural diagram of the server 1200 provided in the embodiment of the present application, and the server 1200 may have relatively large differences due to different configurations or performances, and may include one or more processors, such as a central processing unit (CPU) 1222, and a memory 1232, one or more storage media 1230 (such as one or more mass storage devices) storing application programs 1242 or data 1244.
  • the memory 1232 and the storage medium 1230 can be short-term storage or permanent storage.
  • the program stored in the storage medium 1230 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server.
  • the central processing unit 1222 can be configured to communicate with the storage medium 1230, and execute a series of instruction operations in the storage medium 1230 on the server 1200.
  • the server 1200 may further include one or more power supplies 1226, one or more wired or wireless network interfaces 1250, one or more input and output interfaces 1258, and/or one or more operating systems 1241, such as Windows Server TM , Mac OS X TM , Unix TM , Linux TM , FreeBSD TM , etc.
  • operating systems 1241 such as Windows Server TM , Mac OS X TM , Unix TM , Linux TM , FreeBSD TM , etc.
  • the steps performed by the central processor 1222 in the server 1200 can be implemented based on the structure shown in FIG. 12 .
  • a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the multimedia resource playback method described in the above-mentioned embodiments is implemented.
  • a computer program product comprising a computer program, the computer program being stored in a computer-readable storage medium.
  • a processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the method provided in various optional implementations of the above-mentioned embodiments.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the computer software product is stored in a storage medium, including several instructions for a computer device to execute all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store computer programs.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Indexing, Searching, Synchronizing, And The Amount Of Synchronization Travel Of Record Carriers (AREA)
  • Management Or Editing Of Information On Record Carriers (AREA)

Abstract

本申请公开一种多媒体资源播放方法及相关装置,获取针对待播放多媒体资源的播放请求,播放请求中携带有对象标识和多媒体标识,基于对象标识和多媒体标识,获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。依据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,从而在播放待播放多媒体资源时,在待播放多媒体资源的播放页面上显示播放进度条。播放进度条可以指示多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,多媒体播放对象可以依据播放进度条快速直观发现感兴趣位置(即时间区间),提升跳转到感兴趣位置的准确度与效率,提升用户体验。

Description

一种多媒体资源播放方法及相关装置
本申请要求于2022年8月19日提交中国专利局、申请号202210998870.7、申请名称为“一种多媒体资源播放方法及相关装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域,特别是涉及多媒体资源播放技术。
背景技术
随着计算机技术的发展,播放多媒体资源成为了人们日常生活中常见的娱乐方式。通常在多媒体资源播放过程中,可以在多媒体资源的播放页面上显示该多媒体资源的播放进度条,用户可以通过拖拽播放进度条上的滑块,改变滑块在播放进度条上的位置,来调整多媒体资源的播放进度,便于用户选择观看多媒体资源中的任一多媒体资源片段。
但是,通过拖拽播放进度条上的滑块,通常只能确定将多媒体资源切换至滑块所处位置对应的时刻,对于用户来说,可能需要多次重复的拖拽操作,才能确定在滑块所处位置对应的时刻播放的是自己感兴趣的部分。因此,操作不够便捷,难以一次准确定位,不仅效率低下,进一步会导致用户错过或定位不到感兴趣的精彩内容,给用户的体验较差。
发明内容
为了解决上述技术问题,本申请提供了一种多媒体资源播放方法及相关装置,可以根据播放进度条直观的发现感兴趣位置,无需多次重复的拖拽操作,可以快速、准确地定位到感兴趣位置,提升跳转到感兴趣位置的准确度与效率,提升用户体验。
本申请实施例公开了如下技术方案:
一方面,本申请实施例提供一种多媒体资源播放方法,所述方法由计算机设备执行,所述方法包括:
获取针对待播放多媒体资源的播放请求,所述播放请求中携带有多媒体播放对象的对象标识和所述待播放多媒体资源的多媒体标识;
基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度;
依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,所述播放进度条的滑动粒度与所述时间区间的划分粒度相匹配;
播放所述待播放多媒体资源,并在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条,所述播放进度条用于指示所述待播放多媒体资源的播放进度和所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
又一方面,本申请实施例提供一种多媒体资源播放装置,所述装置部署在计算机设备上,所述装置包括获取单元、生成单元、播放单元和显示单元:
所述获取单元,用于获取针对待播放多媒体资源的播放请求,所述播放请求中携带有多媒体播放对象的对象标识和所述待播放多媒体资源的多媒体标识;
所述获取单元,还用于基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度;
所述生成单元,用于依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,所述播放进度条的滑动粒度与所述时间区间的划分粒度相匹配;
所述播放单元,用于播放所述待播放多媒体资源;
所述显示单元,用于在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条,所述播放进度条用于指示所述待播放多媒体资源的播放进度和所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
另一方面,本申请实施例提供一种计算机设备,所述计算机设备包括处理器以及存储器:
所述存储器用于存储计算机程序,并将所述计算机程序传输给所述处理器;
所述处理器用于根据所述计算机程序中的指令执行前述任一方面所述的方法。
另一方面,本申请实施例提供一种计算机可读存储介质,所述计算机可读存储介质用于存储计算机程序,所述计算机程序被处理器执行时实现前述任一方面所述的方法。
另一方面,本申请实施例提供一种计算机程序产品,包括计算机程序,当其在计算机设备上运行时,使得所述计算机设备执行时实现前述任一方面所述的方法。
由上述技术方案可以看出,当多媒体播放对象对待播放多媒体资源执行播放操作后,可以基于该播放操作生成播放请求,从而获取针对待播放多媒体资源的播放请求。由于播放请求中携带有多媒体播放对象的对象标识和待播放多媒体资源的多媒体标识,故可以基于对象标识和多媒体标识,获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。依据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,播放待播放多媒体资源,并在播放待播放多媒体资源时,在待播放多媒体资源的播放页面上显示播放进度条。由于播放进度条用于指示待播放多媒体资源的播放进度和多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,故多媒体播放对象可以依据播放进度条了解对不同时间区间的多媒体资源片段的兴趣度,从而快速直观发现感兴趣位置(即时间区间),而播放进度条的滑动粒度与时间区间的划分粒度相匹配,因此多媒体播放对象可以控制播放进度条到达自己感兴趣的位置。也就是说,本申请可以根据播放进度条直观的发现感兴趣位置,从而无需多次重复的拖拽操作,可以快速、准确地定位到感兴趣位置,提升跳转到感兴趣位置的准确度与效率,提升用户体验。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术成员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为相关技术提供的一种播放进度条的示例图;
图2为本申请实施例提供的一种多媒体资源播放方法的系统架构示意图;
图3为本申请实施例提供的一种多媒体资源播放方法的流程图;
图4为本申请实施例提供的一种待播放多媒体资源的播放页面示例图;
图5为本申请实施例提供的一种兴趣度预测模型的结构示意图;
图6为本申请实施例提供的另一种兴趣度预测模型的结构示意图;
图7为本申请实施例提供的一种描述预测模型的结构示意图;
图8为本申请实施例提供的一种多媒体资源播放方法的整体流程示意图;
图9为本申请实施例提供的一种多媒体资源播放方法的流程架构示意图;
图10为本申请实施例提供的一种多媒体资源播放装置的结构图;
图11为本申请实施例提供的一种终端的结构图;
图12为本申请实施例提供的一种服务器的结构图。
具体实施方式
下面结合附图,对本申请的实施例进行描述。
相关技术中提供的播放进度条可以是用户在观看或收听多媒体资源的过程中,用来体现多媒体资源播放进度的控件,且可以通过拖动播放进度条来快速跳转到感兴趣的位置进行观看或收听。目前的播放进度条只展示时间信息,即只展示多媒体资源的播放进度,以多媒体资源是视频为例,播放进度条可以参见图1所示。在图1中,播放进度条展示了整个视频的总时长“2:09:37”,以及当前播放完的视频部分的时长“1:18:17”,从而通过两个时长之间的比例以及播放进度条中滑块(例如图1中播放进度条上的黑色圆圈所示)的位置来体现播放进度。
基于此播放进度条,用户只能左右拖动播放进度条,去凭感觉定位感兴趣的位置。这种方式未能结合播放视频的用户的个性化兴趣需求,造成用户定位感兴趣位置时需要来回多次左右拖动,难以一次准确定位,不仅效率低下,进一步会导致用户错过或定位不到感兴趣的精彩内容,给用户的体验较差。
为了解决上述技术问题,本申请实施例提供一种多媒体资源播放方法,该方法可以挖掘多媒体播放对象(例如用户)对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,从而根据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度生成播放进度条。这样,便可以根据播放进度条直观的发现感兴趣位置,无需多次重复的拖拽操作,可以快速、准确地定位到感兴趣位置,提升跳转到感兴趣位置的准确度与效率,提升用户体验。
接下来,将对多媒体资源播放方法的系统架构进行介绍。参见图2所示,该系统架构中包括终端200和服务器300,终端200可以安装多媒体平台或者通过浏览器访问该多媒体平台,这样,多媒体播放对象可以通过终端200访问多媒体播放平台,从而观看或收听多媒体资源。其中,终端200包括但不限于智能手机、平板电脑、笔记本电脑、台式计算机、智能语音交互设备、智能家电、车载终端等,但并不局限于此。
服务器300可以为终端200提供访问多媒体资源的服务,其中,服务器300可以是独立的物理服务器,也可以是多个物理服务器构成的服务器集群或者分布式系统,还可以是提供云计算服务的云服务器。终端200以及服务器300可以通过有线或无线通信方式进行直接或间接地连接,本申请在此不做限制。例如终端200以及服务器300可以通过网络连接,该网络可以是有线或无线网络。
多媒体播放对象可以是选择某个多媒体资源(例如待播放多媒体资源)进行播放,以观看或收听该多媒体资源的对象,例如可以是用户。待播放多媒体资源可以是被播放操作触发,以等待进行播放的多媒体资源。其中,多媒体资源可以包括多种类型,例如可以是视频(例如短视频、电影、电视剧的剧集等等)、音频(例如可以是音乐、有声小说、广播剧等等)。
当多媒体播放对象希望对待播放多媒体资源进行播放时,可以对待播放多媒体资源执行播放操作后,终端200获取基于该播放操作生成的播放请求。
需要说明的是,由于待播放多媒体资源的类型不同,则对待播放多媒体资源执行的播放操作可能有所不同,若待播放多媒体资源是短视频,则播放操作可以是打开短视频的多媒体平台,或者切换短视频,或者从某个账号下所有短视频中选择某个短视频;若待播放多媒体资源是电影,则播放操作可以是选中某部电影进行播放;若待播放多媒体资源是电视剧的剧集,则播放操作可以是从多个剧集中选择某个剧集进行播放;若待播放多媒体资源是音频时,则可以是选择某个音频进行播放,等等,本申请实施例对此不做限定。
本申请实施例主要以待播放多媒体为视频,该视频可能是某个电视剧的某个剧集为例进行介绍,多媒体播放对象打开某部电视剧,进入剧集选择页面,例如图2中201所示,包括多个剧集,分别是剧集1、剧集2、剧集3、……,进而在剧集选择页面选择多个剧集中的剧集3进行播放。
播放请求中携带有多媒体播放对象的对象标识和待播放多媒体资源的多媒体标识,对象标识用于指示播放该待播放多媒体资源的对象,多媒体标识用于指示播放的待播放多媒体资源。由于不同对象对不同多媒体资源中不同时间区间的多媒体资源片段的兴趣度可能不同,故终端200可以基于对象标识和多媒体标识,获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
进而终端200依据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条。接着终端200播放待播放多媒体资源,并在播放待播放多媒体资源时,在待播放多媒体资源的播放页面上显示播放进度条。其中,播放页面可以参见图2中202所示,播放进度条可以如2021所示,播放进度条可以包括不同的展示形式,展示形式例如可以包括心动曲线的方式、条形图的方式、直线结合兴趣度数值的方式(其中直线体现播放进度,数值体现兴趣度)等,2021所示的播放进度条以心动曲线的展示形式为例,其中心动曲线的横坐标是时间区间,纵坐标(即心动曲线的高度)是兴趣度。
本申请实施例提供的播放进度条将多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度与进度条相结合,可以用于指示待播放多媒体资源的播放进度和多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,本申请实施例提供的播放进度条可以称为心动图式进度条。多媒体播放对象可以依据播放进度条了解对不同时间区间的多媒体资源片段的兴趣度,从而快速直观发现感兴趣位置(即时间区间),而播放进度条的滑动粒度与时间区间的划分粒度相匹配,因此多媒体播放对象可以控制播放进度条到达自己感兴趣的位置。
例如,通过播放进度条可以看出2022所示的位置对应的兴趣度较高,表示该位置可能是多媒体播放对象比较感兴趣的位置,故多媒体播放对象可以直接控制播放进度条到达该位置,实现快速精准定位。
也就是说,本申请可以根据播放进度条直观的发现感兴趣位置,从而无需多次重复的拖拽操作,可以快速、准确地定位到感兴趣位置,提升跳转到感兴趣位置的准确度与效率,提升用户体验。
需要说明的是,在本申请实施例中,计算机设备可以是服务器或终端,本申请实施例提供的方法可以由终端或服务器单独执行,也可以由终端和服务器配合执行。其中,图2对应的实施例主要以终端执行本申请实施例提供的方法为例进行介绍。当本申请实施例提供的方法由服务器单独执行时,其执行方法与图2对应的实施例类似,主要是将终端换成服务器。
当由终端和服务器配合执行本申请实施例提供的方法时,需要体现在前端界面上的步骤可以由终端执行,例如显示播放进度条;而一些需要后台计算、无需体现在前端界面上的步骤可以由服务器执行,例如获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条等等。
需要说明的是,在本申请的具体实施方式中,确定兴趣度的过程中有可能会涉及到用户相关的数据,当本申请以上实施例运用到具体产品或技术中时,需要获得用户单独许可或者单独同意,且相关数据的收集、使用和处理需要遵守相关国家和地区的相关法律法规和标准。
接下来,将以终端执行本申请实施例提供的方法为例、结合附图对本申请实施例提供的多媒体资源播放方法进行详细介绍。参见图3,图3示出了一种多媒体资源播放方法的流程图,所述方法包括:
S301、获取针对待播放多媒体资源的播放请求。
当多媒体播放对象希望对待播放多媒体资源进行播放时,可以对待播放多媒体资源执行播放操作后,终端可以获取基于该播放操作生成的播放请求。
在本申请实施例中,待播放多媒体资源的类型可以是视频、音频等,视频和音频又分别可以包括多种可能情况,以待播放多媒体资源是视频,且为电视剧的剧集时,多媒体播放对象可以在多媒体平台上对某个剧集执行播放操作,从而触发播放请求,以便终端获取该播放请求。例如,多媒体播放对象在打开该电视剧后,从剧集列表中选择该电视剧的某个剧集进行播放。
其中,该播放请求可以是终端基于播放操作生成的。当本申请实施例提供的方法由服务器执行时,S301的实现方式可以是终端向服务器发送该播放请求。
可以理解的是,本申请实施例的目的是将多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度与进度条相结合,使得播放进度条能够体现多媒体播放对象对不同时间区间的多媒体资源片段的兴趣度,从而便于定位到其感兴趣的位置进行跳转。为此,需要获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。而不同对象对不同多媒体资源中不同时间区间的多媒体资源片段的兴趣度可能不同,为此,需要使得终端能够确定是哪个对象和哪个多媒体资源,故终端获取的播放请求中可以包括对象标识和多媒体标识。
对象标识用于指示播放该待播放多媒体资源的对象,以确定多媒体播放对象的身份。对象标识例如可以是多媒体播放对象登录或访问多媒体平台的账号,也可以是所使用的终端标识。多媒体标识用于指示播放的待播放多媒体资源,以确定待播放多媒体资源。多媒体标识例如可以是待播放多媒体资源的名称、编号等。
S302、基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
终端根据对象标识和多媒体标识,可以获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。时间区间的划分粒度可以是根据实际需求配置的,也可以是根据播放进度条的滑动粒度确定的,滑动粒度可以表示播放进度条上的滑块移动一次时,待播放多媒体资源所能跳转的最小时间单位。其中,滑动粒度可以是预先配置的,以用于生成能够按照该滑动粒度进行跳转的播放进度条。例如播放进度条的滑动粒度为S秒,则可以将待播多媒体资源以S秒为划分粒度切分为时间区间。
S303、依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条。
终端根据依据多媒体播放对象对不同时间区间的多媒体资源片段的兴趣度,绘制播放进度条,播放进度条的滑动粒度与时间区间的划分粒度相匹配。播放进度条可以包括不同的展示形式,展示形式例如可以包括心动曲线的方式、条形图的方式、直线结合兴趣度数值的方式(其中直线体现播放进度,数值体现兴趣度)等,本申请实施例主要以心动曲线的展示形式为例。在心动曲线的展示形式下,终端可以将兴趣度按横坐标为时间区间、纵坐标为兴趣度绘制心动曲线,得到的播放进度条可以称为心动图式进度条。
需要说明的是,若时间区间的划分粒度是根据实际需求配置的,那么播放进度条的滑动粒度也可以根据该实际需求进行配置,从而使得播放进度条的滑动粒度与时间区间的划分粒度相匹配;若时间区间的划分粒度是根据播放进度条的滑动粒度确定的,则生成播放进度条时,生成具有上述滑动粒度的播放进度条,从而使得播放进度条的滑动粒度与时间区间的划分粒度相匹配。在一种可能的实现方式中,这里的相匹配可以是指播放进度条的滑动粒度与时间区间的划分粒度一致,例如播放进度条的滑动粒度为S秒,时间区间的划分粒度是S秒。
由于播放进度条的滑动粒度与时间区间的划分粒度相匹配,从而保证多媒体播放对象可以知晓每个可以跳转到的时间区间的多媒体资源片段的兴趣度,从而根据兴趣度完成快速、精准的定位及跳转。
S304、播放所述待播放多媒体资源,并在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条。
接着终端播放播放待播放多媒体资源,并在播放待播放多媒体资源时,在待播放多媒体资源的播放页面上显示播放进度条。由于播放进度条是根据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度生成的,故该播放进度条可以指示待播放多媒体资源的播放进度和多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。这样,多媒体播放对象可以依据播放进度条了解对不同时间区间的多媒体资源片段的兴趣度,增强了播放进度条上信息展示丰富度,从而快速直观发现感兴趣位置(即时间区间)。
参见图4所示,图4示出了一种待播放多媒体资源的播放页面示例图,在该播放页面中可以显示播放进度条,如图4中401所示。
由上述技术方案可以看出,当多媒体播放对象对待播放多媒体资源执行播放操作后,可以基于该播放操作生成播放请求,从而获取针对待播放多媒体资源的播放请求。由于播放请求中携带有多媒体播放对象的对象标识和待播放多媒体资源的多媒体标识,故可以基于对象标识和多媒体标识,获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。依据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,播放待播放多媒体资源,并在播放待播放多媒体资源时,在待播放多媒体资源的播放页面上显示播放进度条。由于播放进度条用于指示待播放多媒体资源的播放进度和多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,故多媒体播放对象可以依据播放进度条了解对不同时间区间的多媒体资源片段的兴趣度,从而快速直观发现感兴趣位置(即时间区间),而播放进度条的滑动粒度与时间区间的划分粒度相匹配,因此多媒体播放对象可以控制播放进度条到达自己感兴趣的位置。也就是说,本申请可以根据播放进度条直观的发现感兴趣位置,从而无需多次重复的拖拽操作,可以快速、准确地定位到感兴趣位置,提升跳转到感兴趣位置的准确度与效率,提升用户体验。
需要说明的是,在本申请实施例中,最为关键的是如何获取多媒体播放对象对不同时间区间的多媒体资源片段的兴趣度。在本申请实施例提供多种获取方式,一种获取方式是预先计算出多媒体播放对象对不同时间区间的多媒体资源片段的兴趣度,并存储在兴趣度存储空间(例如数据库、硬盘等等),当需要获取时便可以直接从兴趣度存储空间查找。
在一种可能的实现方式汇总,兴趣度存储空间中可以存储有多个对象分别对不同多媒体资源中不同时间区间的多媒体资源片段的兴趣度,多个对象中包括多媒体播放对象。例如,兴趣度存储空间中存储有对象1对多媒体资源1中不同时间区间的多媒体资源片段的兴趣度,对象2对多媒体资源1中不同时间区间的多媒体资源片段的兴趣度,对象2对多媒体资源2中不同时间区间的多媒体资源片段的兴趣度,……,对象N对多媒体资源1中不同时间区间的多媒体资源片段的兴趣度,对象N对多媒体资源N中不同时间区间的多媒体资源片段的兴趣度。其中,对象1、对象2、……、对象N分别具有对应的对象标识,多媒体资源1、多媒体资源2、……、多媒体资源N分别具有对应的多媒体标识。此时,S302的实现方式可以是终端根据对象标识和多媒体标识,从兴趣度存储空间中查找多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。例如,终端获取的对象标识与对象1的对象标识一致,终端获取的多媒体标识与多媒体资源1的多媒体标识,则可以从兴趣度存储空间中获取对象1对多媒体资源1中不同时间区间的多媒体资源片段的兴趣度,即对象1为多媒体播放对象,多媒体资源1为待播放多媒体资源。
预先计算出多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,当播放待播放多媒体资源时,便可以直接从兴趣度存储空间中查找即可,减少计算量,提高播放显示效率。
需要说明的是,兴趣度存储空间中存储的兴趣度可以定期进行更新,或者在检测出兴趣度发生比较大的变化时,可以对兴趣度存储空间中存储的兴趣度进行更新,本申请实施例对其更新方式不做限定。
在一种可能的实现方式中,多媒体平台上可能有大量的多媒体资源,并且该多媒体平台的常用对象的数量也可能非常庞大。而这些对象中,有些对象的活跃度可能比较高,例如经常通过多媒体平台播放多媒体资源,从而可能需要频繁获取其对多媒体资源中不同时间区间的多媒体资源片段的兴趣度;而有些对象的活跃度可能比较低,例如偶尔才会使用多媒体平台,从而很久才可能获取一次其对多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
基于上述特性,考虑到存储成本和兴趣度获取效率之间的平衡,在兴趣度存储空间中,可以将活跃度较高的对象对多媒体资源中不同时间区间的多媒体资源片段的兴趣度进行预先计算并存储在兴趣度存储空间,从而针对活跃度较高的对象,可以采用从兴趣度存储空间中查找的方式获取对不同时间区间的多媒体资源片段的兴趣度。在这种情况下,在执行S302之前,终端可以基于对象标识获取多媒体播放对象的互动数据,进而根据互动数据确定多媒体播放对象的活跃度,若多媒体播放对象的活跃度高于第一阈值,则说明其是活跃度比较高的对象,其对不同多媒体资源的不同时间区间的多媒体资源片段的兴趣度存储在兴趣度存储空间,故可以执行S302所示的步骤。其中,互动数据可以是多媒体播放对象在多媒体平台上互动的数据,例如可以包括播放多媒体资源、发表评论、弹幕内容等。
通过将活跃度较高的对象对不同多媒体资源的不同时间区间的多媒体资源片段的兴趣度存储在兴趣度存储空间,不仅可以提高播放显示效率,还可以在一定程度上节省存储空间,降低存储压力。
另一种获取方式可以是在需要播放待播放多媒体资源时,实时计算多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。可以理解的是,实时计算的方式与预先计算的方式类似,主要是计算时机有所不同,本申请实施将以实时计算的方式为例,对兴趣度的计算方式进行详细介绍。
本申请实施例提供的一种可能的计算方式可以是终端根据对象标识获取多媒体播放对象的第一对象兴趣标签,以及根据多媒体标识获取待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息,进而基于第一对象兴趣标签和不同时间区间的多媒体资源片段的多媒体资源信息,确定多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。其中,第一对象兴趣标签可以是根据多媒体播放对象的历史播放数据确定的,能够反映多媒体播放对象感兴趣的内容,第一对象兴趣标签可以包括多媒体资源的类型、主创成员等。
以多媒体资源是电视剧的剧集为例,第一对象标签可以包括多媒体资源的类型和主创成员,多媒体资源的类型例如古装、家庭、校园等,主创成员例如演员A、影视公司B等。以多媒体资源是音乐为例,第一对象标签可以包括多媒体资源的类型和主创成员,多媒体资源的类型例如伤感、轻音乐、摇滚、古风等,主创成员例如歌手C等。
在一种可能的实现方式中,基于前述对多媒体平台上大量对象的特性分析,考虑到存储成本和兴趣度获取效率之间的平衡,为了降低频繁计算带来的计算资源的消耗,可以针对活跃度较低的对象采用实时计算。在这种情况下,在执行S302之前,终端可以基于对象标识获取多媒体播放对象的互动数据,进而根据互动数据确定多媒体播放对象的活跃度,若多媒体播放对象的活跃度低于第一阈值,说明其是活跃度比较低的对象,其对不同多媒体资源的不同时间区间的多媒体资源片段的兴趣度未存储在兴趣度存储空间,需要实时计算,故可以执行S302所示的步骤。
通过将活跃度较低的对象对不同多媒体资源的不同时间区间的多媒体资源片段的兴趣度进行实时计算,可以降低频繁计算带来的计算资源的消耗,降低计算压力。
在一种可能的实现方式中,多媒体资源信息可以包括多媒体资源内容和弹幕内容中至少一种,多媒体资源内容直接反映不同多媒体资源片段的内容,而弹幕内容通常是观看该待播放多媒体资源的对象针对多媒体资源片段发布的内容(例如文字、表情),例如图4所示,弹幕内容可以包括“感谢送的礼物”、“炫技模式已开启”、“模仿小明的那个剧情”、“小红才是真正的高手”、“发个好帅”等。弹幕内容在一定程度上可以反映该多媒体资源片段的内容,多媒体播放对象对多媒体资源片段中弹幕内容的兴趣度可以体现多媒体播放对象对多媒体资源片段的兴趣度,从而帮助确定多媒体播放对象对该多媒体资源片段的兴趣度。
通常情况下,弹幕内容可以直接通过提取播放界面上的弹幕获取,获取方式简单、方便。故在本申请实施例的一种可能的实现方式中,多媒体资源信息中包括多媒体资源片段的至少一个弹幕内容,从而确定多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。在这种情况下,基于第一对象兴趣标签和不同时间区间的多媒体资源片段的多媒体资源信息,确定多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度的方式可以是针对任一时间区间的多媒体资源片段,根据第一对象兴趣标签和多媒体资源片段中的任一弹幕内容分别计算多媒体播放对象对任一弹幕内容的兴趣度,对任一弹幕内容的兴趣度进行加权求和,得到多媒体播放对象对多媒体资源片段的兴趣度。其中,加权求和所使用的权重可以为弹幕内容的热度,可以用弹幕内容的点赞次数与待播放多媒体资源所有弹幕内容的点赞次数之和的比值表示。
对所有时间区间分别采用上述方式进行计算,从而得到多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,通过这种方式可以降低兴趣度的计算复杂度,简化兴趣度的计算,提高计算效率。
例如任一时间区间为时间区间t,时间区间t的多媒体资源片段中可能包括多个弹幕内容,其中,任一弹幕内容为弹幕内容b,首先计算多媒体播放对象对弹幕内容b的兴趣度,表示为p_in_u[b]。权重可以表示为wb,则多媒体播放对象对时间区间t的多媒体资源片段的兴趣度=sum_b(p_in_u[b]*wb),其中wb为弹幕内容b的热度,wb=弹幕内容b的点赞次数/待播放多媒体资源所有弹幕内容的点赞次数之和。
在一种可能的实现方式中,可以是通过兴趣度预测模型确定多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,即将第一对象兴趣标签和不同时间区间的多媒体资源片段的多媒体资源信息输入至兴趣度预测模型,从而输出多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
在这种情况下,根据第一对象兴趣标签和多媒体资源片段中的任一弹幕内容分别计算多媒体播放对象对任一弹幕内容的兴趣度的方式可以是对第一对象兴趣标签进行编码得到第一对象兴趣特征向量,以及对多媒体资源片段中的任一弹幕内容进行编码得到任一弹幕内容的弹幕特征向量。然后将第一对象兴趣特征向量和任一弹幕内容的弹幕特征向量进行注意力交互,得到任一弹幕内容的第一融合特征向量,接着根据任一弹幕内容的第一融合特征向量进行兴趣度预测,得到多媒体播放对象对任一弹幕内容的兴趣度。
图5示出了一种兴趣度预测模型的结构示意图,该兴趣度预测模型可以包括编码模块、第一融合模块和预测模块,将第一对象兴趣标签和弹幕内容作为兴趣度预测模型的输入,通过编码模块对第一对象兴趣标签进行编码得到第一对象兴趣特征向量,并通过编码模块对弹幕内容进行编码得到弹幕特征向量。通过第一融合模块对第一对象兴趣特征向量和弹幕特征向量进行注意力交互,得到第一融合特征向量。接着通过预测模块对第一融合特征向量,通过进行兴趣度预测得到多媒体播放对象对弹幕内容的兴趣度。需要说明的是,由于第一对象兴趣标签可能包括多个,不同第一对象兴趣标签对于兴趣度预测的重要程度可能不同,故还可以将第一对象兴趣标签的权重作为兴趣度预测模型的输入,从而结合第一对象兴趣标签的权重和第一对象兴趣标签得到第一对象兴趣特征向量。其中,编码模块可以是Transformer-Encoder。
可以理解的是,每个弹幕内容有对应的发布对象,发布对象可以是发布弹幕内容的对象,例如播放该待播放多媒体资源的、且对多媒体资源片段发表看法的用户。不同发布对象发布的弹幕内容可以反映其对多媒体资源片段的兴趣度,若多媒体播放对象与发布对象的兴趣类似,则多媒体播放对象对多媒体资源片段的兴趣度也可能与发布对象类似,因此在本申请实施例中,可以利用发布对象的第二对象兴趣标签辅助确定多媒体播放对象对弹幕内容的兴趣度。为此,根据任一弹幕内容的第一融合特征向量进行兴趣度预测,得到多媒体播放对象对任一弹幕内容的兴趣度的方式可以是终端获取任一弹幕内容的发布对象的第二对象兴趣标签,对第二对象兴趣标签进行编码得到第二对象兴趣特征向量,进而将第一对象兴趣特征向量与第二对象兴趣特征向量进行注意力交互,得到第二融合特征向量,第二融合特征向量可以体现多媒体播放对象和发布对象之间的兴趣一致情况,兴趣越一致,多媒体播放对象对发布对象发布的弹幕内容的兴趣度可能越高,从而辅助预测多媒体播放对象对弹幕内容的兴趣度。然后将第一融合特征向量与第二融合特征向量进行特征拼接得到拼接特征向量,以便根据拼接特征向量进行兴趣度预测得到多媒体播放对象对任一弹幕内容的兴趣度。
图6示出了另一种兴趣度预测模型的结构示意图,该兴趣度预测模型可以包括编码模块、第一融合模块、第二融合模块、拼接模块和预测模块,将第一对象兴趣标签、第二对象兴趣标签和弹幕内容作为兴趣度预测模型的输入,通过编码模块对第一对象兴趣标签进行编码得到第一对象兴趣特征向量,通过编码模块对第二对象兴趣标签进行编码得到第二对象兴趣特征向量,并通过编码模块对弹幕内容进行编码得到弹幕特征向量。通过第一融合模块对第一对象兴趣特征向量和弹幕特征向量进行注意力交互,得到第一融合特征向量,并通过第二融合模块对第一对象特征兴趣向量和第二对象特征兴趣向量进行对象特征兴趣向量。接着通过拼接模块将第一融合特征向量与第二融合特征向量进行特征拼接得到拼接特征向量,以便预测模块根据拼接特征向量进行兴趣度预测得到多媒体播放对象对任一弹幕内容的兴趣度。
需要说明的是,由于第一对象兴趣标签和第二对象兴趣标签分别可能包括多个,不同第一对象兴趣标签或第二对象兴趣标签对于兴趣度预测的重要程度可能不同,故还可以将第一对象兴趣标签的权重、第二对象兴趣标签的权重作为兴趣度预测模型的输入,从而结合第一对象兴趣标签的权重和第一对象兴趣标签得到第一对象兴趣特征向量,以及结合第二对象兴趣标签的权重和第二对象兴趣标签得到第二对象兴趣特征向量。
需要说明的是,兴趣度预测模型可以采用各种网络结构,故5和图6仅是一种示例,并不构成对本申请的限定。
应理解,本申请实施例采用的兴趣度预测模型可以是预先训练得到的,训练所使用的训练数据可以是针对样本弹幕内容的点赞互动行为数据,如果用户(例如样本多媒体播放对象)对样本弹幕内容进行点赞,表示用户对此样本弹幕内容感兴趣,即为正样本数据,否则为负样本。依据上述点赞互动行为数据可以得到样本多媒体播放对象的第一样本对象兴趣标签、样本发布对象的第二样本对象兴趣标签、样本弹幕内容,将第一样本对象兴趣标签、样本弹幕内容作为输入,进而采用类似图5对应实施例介绍的处理方法对输入的数据进行处理,实现模型训练;或者将第一样本对象兴趣标签、第二样本对象兴趣标签、样本弹幕内容作为输入,进而采用类似图6对应实施例介绍的处理方法对输入的数据进行处理,实现模型训练。待模型训练收敛后,得到兴趣度预测模型,即可实现针对待播放多媒体资源输出多媒体播放对象对弹幕内容的兴趣度。
在得到多媒体播放对象对任一弹幕内容的兴趣度之后,还可以记录兴趣度达到第二阈值的弹幕内容,以便在播放进度条的滑块移动至第一时间区间时,即多媒体播放对象使用播放进度条切换到第一时间区间时,终端响应于播放进度条的滑块移动至第一时间区间, 在待播放多媒体资源的播放页面上优先展示目标弹幕内容,目标弹幕内容为兴趣度达到第二阈值的弹幕内容,且目标弹幕内容属于第一时间区间的多媒体资源片段的至少一个弹幕内容。
在一种可能的实现方式中,当多媒体播放对象根据播放进度条上体现的心动度确定感兴趣的时间区间时,多媒体播放对象可以使用播放进度条切换到此时间区间。为了辅助多媒体播放对象确定该时间区间的确是其感兴趣的位置,在本申请实施例中,还可以生成不同时间区间的多媒体资源片段的描述信息,从而在播放待播放多媒体资源的过程中,终端可以响应于针对播放进度条上滑块的控制操作,控制滑块移动至第二时间区间,并展示第二时间区间的多媒体资源片段的描述信息。描述信息可以用于概括该时间区间的多媒体资源片段的主要内容,从而使得多媒体播放对象可以根据描述信息了解该时间区间的多媒体资源片段将要播放的内容,以辅助多媒体播放对象确认兴趣点。其中,控制操作可以是各种控制滑块移动到第二时间区间的操作,例如可以是拖动操作、点击操作等等,拖动操作即拖动滑块移动到第二时间区间,点击操作可以是点击某个位置使得滑块移动到该位置对应的时间区间。
例如图4所示,若图4中的待播放多媒体资源是关于玩悠悠球的电视剧的剧集,而在这种剧集中多媒体播放对象比较感兴趣的是各种悠悠球的花式玩法、酷炫的动作等。当多媒体播放对象根据播放进度条上的兴趣度将滑块(图4中黑色圆圈所示)拖动至第二时间区间时,可以展示402所示的描述信息“花式技巧重现”,通过该描述信息,多媒体播放对象可以知晓该第二时间区间的多媒体资源片段可能要播放悠悠球的花式玩法、酷炫的动作,从而辅助多媒体播放对象确定此时间区间的多媒体资源片段是其感兴趣的。
在一种可能的实现方式中,描述信息可以是通过描述预测模型预测得到的。由于该描述信息是针对多媒体播放对象的个性化描述,故生成该描述信息可以依据多媒体播放对象的第一对象兴趣标签,即生成不同时间区间的多媒体资源片段的描述信息的可能实现方式为根据对象标识获取多媒体播放对象的第一对象兴趣标签,以及根据多媒体标识获取待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息,进而针对任一时间区间的多媒体资源片段,基于第一对象兴趣标签和多媒体资源片段的多媒体资源信息,通过描述预测模型生成多媒体资源片段的描述信息。
其中,此处的多媒体资源信息与前述的多媒体资源信息类似,多媒体资源信息可以包括多媒体资源内容和弹幕内容中至少一种,本申请实施例主要以多媒体资源信息中包括多媒体资源片段的至少一个弹幕内容为例进行介绍。由于弹幕内容可能包括很多,有些弹幕内容的互动热度比较高,有利于生成描述信息,有些弹幕内容的互动热度比较低,不利于生成描述信息。因此,为了提高描述信息生成的准确性,可以将第一对象兴趣标签与时间区间内互动热度为top m的弹幕内容作为描述预测模型的输入,以生成描述信息。
在生成描述信息的过程中,对第一对象兴趣标签进行处理以生成对应的第一对象兴趣特征向量的方式与图5或图6所示的方式类似,例如可以参见图5或图6最左侧对第一对象兴趣标签进行处理的模块,输入第一对象兴趣标签与第一对象兴趣标签的权重,输出第一对象兴趣特征向量,此向量可以提升生成描述信息的用户个性化。
需要说明的是,在本申请实施例中,由于描述预测模型的规模较为庞大,而人工构建的描述信息有限,因此为了提高描述预测模型的训练精度和收敛速度,在对描述预测模型进行训练时可以采用预训练和精调结合的方式,即先获取多媒体播放样本对象的第一样本对象兴趣标签,以及获取样本多媒体资源的多媒体资源信息,从而基于第一样本对象兴趣标签和多媒体资源信息,以样本多媒体资源的标题信息作为训练目标对初始网络模型进行预训练,得到预训练模型。由于带有标题信息的样本多媒体资源的数量比较多,且可以直接获取,无需人为标注,例如多媒体平台上的短视频,故使用带有标题信息的样本多媒体资源进行预训练,可以得到一个具有较优状态的预训练模型。然后获取第二样本对象兴趣标签,以及从样本多媒体资源中获取样本多媒体资源片段,基于第二样本对象兴趣标签和样本多媒体资源片段的多媒体资源信息,对预训练模型进行训练(即精调(finetune)),从而得到描述预测模型。其中,第二样本对象可以是样本发布对象,样本发布对象是针对样本多媒体资源片段发布弹幕内容的对象,第二样本对象对应的兴趣标签称为第二样本对象兴趣标签。
需要说明的是,描述预测模型可以采用各种网络结构,本申请对此不做限定。本申请实施例主要以初始网络模型、预训练模型、描述预测模型使用联合编码(Unified-Transformer)模型作为基础模型结构为例进行介绍。如图7所示,Unified-Transformer模型包括联合编码层(Unified-Transformer Layer)1、联合编码层2、联合编码层N。首先在多媒体平台大量的带有标题信息的样本多媒体资源(例如短视频)上进行预训练。将对该短视频完成度满足一定阈值的对象作为短视频的感兴趣用户(即多媒体播放样本对象),将多媒体播放样本对象的第一样本对象兴趣标签输入编码模块,同时将短视频的互动热度为top m的弹幕内容输入编码模块,从而得到第一样本对象兴趣特征向量,初始网络模型对输入的第一样本对象兴趣特征向量通过全注意力(Fully-Attention)计算(即双向自注意力(Self-Attention))。
在生成部分对将短视频的标题信息作为目标,生成部分采用前缀注意力(Prefix-Attention),即每一步生成时,只能计算该步到以前位置的Attention,通过这样大规模的预训练,可使图7所示的初始网络模型初始化到一个较优状态,得到预训练模型。
待上述大规模预训练完毕后,再在用户感兴趣的时间区间上进行精调,,将样本发布对象的兴趣标签即第二样本对象兴趣标签、时间区间内互动热度为top m的弹幕内容(即样本多媒体资源片段的多媒体资源信息)作为模型输入特征,精调阶段训练目标为人工构建的描述信息。
在图7中,针对输入的时间区间内互动热度为top m的弹幕内容,可以对弹幕内容进行词语切分,得到多个输入词,分别是输入词1、输入词2、输入词3、……、输入词k,然后通过查找表(Lookup Table)模块对多个输入词进行插值计算,将结果送入输入部分,然后基于多个输入词通过生成部分生成描述信息,该描述信息是由多个描述词(例如描述词1、描述词2、……、描述词n-1、描述词n)组成,每一步生成时,只能计算该步到以前位置的Attention。图7中的起始标记表示开始预测描述信息,第一步计算得到描述词1,第二步基于该步到以前位置(包括描述词1)的Attention得到描述词2,依次类推,第n-1步基于该步到以前位置(包括描述词n-2)的Attention得到描述词n-1,第n步基于该步到以前位置(包括描述词n-1)的Attention得到描述词n。
本申请实施例通过对待播放多媒体资源的多媒体资源信息与第一对象兴趣标签联合建模,构建出多媒体播放对象对待播放多媒体资源不同时间区间的多媒体资源片段的心动度,将图1所示的播放进度条替换为图4所示的心动图式进度条,心动图式进度条中心动曲线的高度表示了多媒体播放对象对此时间区间可能的兴趣度,便于用户直观发现感兴趣部分。并且当多媒体播放对象拖动心动图式进度条时,随着拖动位置的变化,动态展示该位置的描述信息,同时选取感兴趣的弹幕内容优先展示,使得多媒体播放对象可快速通过心动图式进度条实现感兴趣位置的定位跳转,提升播放进度条的使用体验,进一步提升用户体验。
基于前述介绍,下面将结合实际应用场景,对本申请实施例提供的多媒体资源播放方法的整体流程进行介绍。在该应用场景中多媒体播放对象可以是用户,则多媒体播放对象可以称为观看用户,待播放多媒体资源可以是待播放视频,多媒体资源片段可以是视频片段,多媒体资源信息可以是弹幕内容。此时,多媒体资源播放方法的整体流程可以参见图8所示,该方法可以由终端执行,包括以下步骤:
S801、终端获取针对待播放视频执行的播放操作。
S802、终端响应于该播放操作,获取观看用户的第一对象兴趣标签以及待播放视频中不同时间区间的视频片段的弹幕内容。
多媒体资源播放方法的流程架构可以参见图9所示,其中,已观看过该待播放视频的其他用户可能在观看该待播放视频(如901所示)时,针对不同的视频片段发布对应的弹幕内容,弹幕内容可以存储在弹幕内容数据库(如902所示)中。当终端接收到针对待播放视频的播放操作时,可以从弹幕内容数据库中获取弹幕内容。
S803、终端基于第一对象兴趣标签以及待播放视频中不同时间区间的视频片段的弹幕内容计算观看用户对不同时间区间的视频片段的兴趣度。
第一对象兴趣标签可以反映观看用户的兴趣,故S803的步骤可以称为基于观看用户兴趣的兴趣度计算,参见图9中①所示的步骤。
S804、终端生成不同时间区间的视频片段的描述信息。
该描述信息可以是根据观看对象的第一对象兴趣标签生成的,符合观看对象的个性化需求,故S804的步骤可以称为个性化描述信息的生成,参见图9中②所示的步骤。
S805、终端播放待播放视频,并展示播放进度条。
其中,S805可以参见图9中③所示的步骤,该播放进度条是基于观看用户对不同时间区间的视频片段的兴趣度生成的。
S806、终端响应于播放进度条被拖动到待播放视频的第二时间区间,播放第二时间区间对应的视频片段,并展示第二时间区间对应的描述信息和弹幕内容。
观看用户可以参照兴趣度预估进行定位切换,当根据播放进度条上体现的兴趣度确定某个时间区间例如第二时间区间是感兴趣位置时,可以将播放进度条拖动到该第二时间区间,从而切换到第二时间区间对应的视频片段进行播放,并展示第二时间区间对应的描述信息和弹幕内容,便于观看用户更加直观的发现感兴趣的观看位置。
需要说明的是,本申请在上述各方面提供的实现方式的基础上,还可以进行进一步组合以提供更多实现方式。
基于图3对应实施例提供的多媒体资源播放方法,本申请实施例还提供一种多媒体资源播放装置1000,该多媒体资源播放装置1000包括获取单元1001、生成单元1002、播放单元1003和显示单元1004:
所述获取单元1001,用于获取针对待播放多媒体资源的播放请求,所述播放请求中携带有多媒体播放对象的对象标识和所述待播放多媒体资源的多媒体标识;
所述获取单元1001,还用于基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度;
所述生成单元1002,用于依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,所述播放进度条的滑动粒度与所述时间区间的划分粒度相匹配;
所述播放单元1003,用于播放所述待播放多媒体资源;
所述显示单元1004,用于在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条,所述播放进度条用于指示所述待播放多媒体资源的播放进度和所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
在一种可能的实现方式中,所述获取单元1001,具体用于:
根据所述对象标识和所述多媒体标识,从兴趣度存储空间中查找所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,所述兴趣度存储空间中存储有多个对象分别对不同多媒体资源中不同时间区间的多媒体资源片段的兴趣度,所述多个对象中包括所述多媒体播放对象。
在一种可能的实现方式中,所述装置还包括确定单元:
所述确定单元,用于基于所述对象标识获取所述多媒体播放对象的互动数据;
根据所述互动数据确定所述多媒体播放对象的活跃度;
若所述确定单元确定所述多媒体播放对象的活跃度高于第一阈值,触发所述获取单元1001执行根据所述对象标识和所述多媒体标识,从兴趣度存储空间中查找所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度的步骤。
在一种可能的实现方式中,所述获取单元1001,具体用于:
根据所述对象标识获取所述多媒体播放对象的第一对象兴趣标签,以及根据所述多媒体标识获取所述待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息;
基于所述第一对象兴趣标签和不同时间区间的多媒体资源片段的多媒体资源信息,确定所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
在一种可能的实现方式中,所述装置还包括确定单元:
所述确定单元,用于基于所述对象标识获取所述多媒体播放对象的互动数据;
根据所述互动数据确定所述多媒体播放对象的活跃度;
若所述确定单元确定所述多媒体播放对象的活跃度低于第一阈值,触发所述获取单元1001执行根据所述对象标识获取所述多媒体播放对象的第一对象兴趣标签,以及根据所述多媒体标识获取所述待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息的步骤。
在一种可能的实现方式中,所述多媒体资源信息中包括所述多媒体资源片段的至少一个弹幕内容,所述获取单元1001,具体用于:
针对任一时间区间的多媒体资源片段,根据所述第一对象兴趣标签和所述多媒体资源片段中的任一弹幕内容分别计算所述多媒体播放对象对所述任一弹幕内容的兴趣度;
对所述任一弹幕内容的兴趣度进行加权求和,得到所述多媒体播放对象对所述多媒体资源片段的兴趣度。
在一种可能的实现方式中,所述获取单元1001,具体用于:
对所述第一对象兴趣标签进行编码得到第一对象兴趣特征向量,以及对所述多媒体资源片段中的任一弹幕内容进行编码得到所述任一弹幕内容的弹幕特征向量;
将所述第一对象兴趣特征向量和所述任一弹幕内容的弹幕特征向量进行注意力交互,得到所述任一弹幕内容的第一融合特征向量;
根据所述任一弹幕内容的第一融合特征向量进行兴趣度预测,得到所述多媒体播放对象对所述任一弹幕内容的兴趣度。
在一种可能的实现方式中,所述获取单元1001,具体用于:
获取所述任一弹幕内容的发布对象的第二对象兴趣标签;
对所述第二对象兴趣标签进行编码得到第二对象兴趣特征向量;
将所述第一对象兴趣特征向量与所述第二对象兴趣特征向量进行注意力交互,得到第二融合特征向量;
将所述第一融合特征向量与所述第二融合特征向量进行特征拼接得到拼接特征向量;
根据所述拼接特征向量进行兴趣度预测得到所述多媒体播放对象对所述任一弹幕内容的兴趣度。
在一种可能的实现方式中,所述装置还包括记录单元:
所述记录单元,用于记录兴趣度达到第二阈值的弹幕内容;
所述显示单元1004,还用于响应于所述播放进度条的滑块移动至第一时间区间,在所述待播放多媒体资源的播放页面上优先展示目标弹幕内容,所述目标弹幕内容为兴趣度达到所述第二阈值的弹幕内容,且所述目标弹幕内容属于所述第一时间区间的多媒体资源片段的至少一个弹幕内容。
在一种可能的实现方式中,所述装置还包括控制单元:
所述生成单元1002,还用于生成不同时间区间的多媒体资源片段的描述信息;
所述控制单元,用于在播放所述待播放多媒体资源的过程中,响应于针对所述播放进度条上滑块的控制操作,控制所述滑块移动至第二时间区间;
所述显示单元1004,还用于展示所述第二时间区间的多媒体资源片段的描述信息。
在一种可能的实现方式中,所述生成单元1002,具体用于:
根据所述对象标识获取所述多媒体播放对象的第一对象兴趣标签,以及根据所述多媒体标识获取所述待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息;
针对任一时间区间的多媒体资源片段,基于所述第一对象兴趣标签和所述多媒体资源片段的多媒体资源信息,通过描述预测模型生成所述多媒体资源片段的描述信息。
在一种可能的实现方式中,所述描述预测模型的训练方式包括:
获取多媒体播放样本对象的第一样本对象兴趣标签,以及获取样本多媒体资源的多媒体资源信息;
基于所述第一样本对象兴趣标签和所述多媒体资源信息,以所述样本多媒体资源的标题信息作为训练目标对初始网络模型进行预训练,得到预训练模型;
获取第二样本对象兴趣标签,以及从所述样本多媒体资源中获取样本多媒体资源片段;
基于所述第二样本对象兴趣标签和所述样本多媒体资源片段的多媒体资源信息,对所述预训练模型进行训练,得到所述描述预测模型。
在一种可能的实现方式中,所述多媒体资源信息包括多媒体资源内容和弹幕内容中至少一种。
由上述技术方案可以看出,当多媒体播放对象对待播放多媒体资源执行播放操作后,可以基于该播放操作生成播放请求,从而获取针对待播放多媒体资源的播放请求。由于播放请求中携带有多媒体播放对象的对象标识和待播放多媒体资源的多媒体标识,故可以基于对象标识和多媒体标识,获取多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。依据多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,播放待播放多媒体资源,并在播放待播放多媒体资源时,在待播放多媒体资源的播放页面上显示播放进度条。由于播放进度条用于指示待播放多媒体资源的播放进度和多媒体播放对象对待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,故多媒体播放对象可以依据播放进度条了解对不同时间区间的多媒体资源片段的兴趣度,从而快速直观发现感兴趣位置(即时间区间),而播放进度条的滑动粒度与时间区间的划分粒度相匹配,因此多媒体播放对象可以控制播放进度条到达自己感兴趣的位置。也就是说,本申请可以根据播放进度条直观的发现感兴趣位置,从而无需多次重复的拖拽操作,可以快速、准确地定位到感兴趣位置,提升跳转到感兴趣位置的准确度与效率,提升用户体验。
本申请实施例还提供了一种计算机设备,该计算机设备可以是终端,以终端为智能手机为例:
图11示出的是与本申请实施例提供的智能手机的部分结构的框图。参考图11,智能手机包括:射频(英文全称:Radio Frequency,英文缩写:RF)电路1110、存储器1120、输入单元1130、显示单元1140、传感器1150、音频电路1160、无线保真(英文缩写:WiFi)模块1170、处理器1180、以及电源1190等部件。输入单元1130可包括触控面板1131以及其他输入设备1132,显示单元1140可包括显示面板1141,音频电路1160可以包括扬声器1161和传声器1162。本领域技术人员可以理解,图11中示出的智能手机结构并不构成对智能手机的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
存储器1120可用于存储软件程序以及模块,处理器1180通过运行存储在存储器1120的软件程序以及模块,从而执行智能手机的各种功能应用以及数据处理。存储器1120可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等;存储数据区可存储根据智能手机的使用所创建的数据(比如音频数据、电话本等)等。此外,存储器1120可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
处理器1180是智能手机的控制中心,利用各种接口和线路连接整个智能手机的各个部分,通过运行或执行存储在存储器1120内的软件程序和/或模块,以及调用存储在存储器1120内的数据,执行智能手机的各种功能和处理数据。可选的,处理器1180可包括一个或多个处理单元;优选的,处理器1180可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序等,调制解调处理器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器1180中。
在本实施例中,智能手机中的处理器1180可以执行以下步骤:
获取针对待播放多媒体资源的播放请求,所述播放请求中携带有多媒体播放对象的对象标识和所述待播放多媒体资源的多媒体标识;
基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度;
依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,所述播放进度条的滑动粒度与所述时间区间的划分粒度相匹配;
播放所述待播放多媒体资源,并在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条,所述播放进度条用于指示所述待播放多媒体资源的播放进度和所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
本申请实施例提供的计算机设备还可以是服务器,请参见图12所示,图12为本申请实施例提供的服务器1200的结构图,服务器1200可因配置或性能不同而产生比较大的差异,可以包括一个或一个以上处理器,例如中央处理器(Central Processing Units,简称CPU)1222,以及存储器1232,一个或一个以上存储应用程序1242或数据1244的存储介质1230(例如一个或一个以上海量存储设备)。其中,存储器1232和存储介质1230可以是短暂存储或持久存储。存储在存储介质1230的程序可以包括一个或一个以上模块(图示没标出),每个模块可以包括对服务器中的一系列指令操作。更进一步地,中央处理器1222可以设置为与存储介质1230通信,在服务器1200上执行存储介质1230中的一系列指令操作。
服务器1200还可以包括一个或一个以上电源1226,一个或一个以上有线或无线网络接口1250,一个或一个以上输入输出接口1258,和/或,一个或一个以上操作系统1241,例如Windows ServerTM,Mac OS XTM,UnixTM,LinuxTM,FreeBSDTM等等。
在本实施例中,由服务器1200中的中央处理器1222执行的步骤可以基于图12所示的结构实现。
根据本申请的一个方面,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用于存储计算机程序,所述计算机程序被处理器执行时实现前述各个实施例所述的多媒体资源播放方法。
根据本申请的一个方面,提供了一种计算机程序产品,该计算机程序产品包括计算机程序,该计算机程序存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机程序,处理器执行该计算机程序,使得该计算机设备执行上述实施例各种可选实现方式中提供的方法。
上述各个附图对应的流程或结构的描述各有侧重,某个流程或结构中没有详述的部分,可以参见其他流程或结构的相关描述。
本申请的说明书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,简称ROM)、随机存取存储器(Random Access Memory,简称RAM)、磁碟或者光盘等各种可以存储计算机程序的介质。
以上所述,以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术成员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (17)

  1. 一种多媒体资源播放方法,所述方法由计算机设备执行,所述方法包括:
    获取针对待播放多媒体资源的播放请求,所述播放请求中携带有多媒体播放对象的对象标识和所述待播放多媒体资源的多媒体标识;
    基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度;
    依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,所述播放进度条的滑动粒度与所述时间区间的划分粒度相匹配;
    播放所述待播放多媒体资源,并在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条,所述播放进度条用于指示所述待播放多媒体资源的播放进度和所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
  2. 根据权利要求1所述的方法,所述基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,包括:
    根据所述对象标识和所述多媒体标识,从兴趣度存储空间中查找所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,所述兴趣度存储空间中存储有多个对象分别对不同多媒体资源中不同时间区间的多媒体资源片段的兴趣度,所述多个对象中包括所述多媒体播放对象。
  3. 根据权利要求2所述的方法,所述方法还包括:
    基于所述对象标识获取所述多媒体播放对象的互动数据;
    根据所述互动数据确定所述多媒体播放对象的活跃度;
    若所述多媒体播放对象的活跃度高于第一阈值,执行根据所述对象标识和所述多媒体标识,从兴趣度存储空间中查找所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度的步骤。
  4. 根据权利要求1所述的方法,所述基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,包括:
    根据所述对象标识获取所述多媒体播放对象的第一对象兴趣标签,以及根据所述多媒体标识获取所述待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息;
    基于所述第一对象兴趣标签和不同时间区间的多媒体资源片段的多媒体资源信息,确定所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
  5. 根据权利要求4所述的方法,所述方法还包括:
    基于所述对象标识获取所述多媒体播放对象的互动数据;
    根据所述互动数据确定所述多媒体播放对象的活跃度;
    若所述多媒体播放对象的活跃度低于第一阈值,执行根据所述对象标识获取所述多媒体播放对象的第一对象兴趣标签,以及根据所述多媒体标识获取所述待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息的步骤。
  6. 根据权利要求4所述的方法,所述多媒体资源信息中包括所述多媒体资源片段的至少一个弹幕内容,所述基于所述第一对象兴趣标签和不同时间区间的多媒体资源片段的多媒体资源信息,确定所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,包括:
    针对任一时间区间的多媒体资源片段,根据所述第一对象兴趣标签和所述多媒体资源片段中的任一弹幕内容分别计算所述多媒体播放对象对所述任一弹幕内容的兴趣度;
    对所述任一弹幕内容的兴趣度进行加权求和,得到所述多媒体播放对象对所述多媒体资源片段的兴趣度。
  7. 根据权利要求6所述的方法,所述根据所述第一对象兴趣标签和所述多媒体资源片段中的任一弹幕内容分别计算所述多媒体播放对象对所述任一弹幕内容的兴趣度,包括:
    对所述第一对象兴趣标签进行编码得到第一对象兴趣特征向量,以及对所述多媒体资源片段中的任一弹幕内容进行编码得到所述任一弹幕内容的弹幕特征向量;
    将所述第一对象兴趣特征向量和所述任一弹幕内容的弹幕特征向量进行注意力交互,得到所述任一弹幕内容的第一融合特征向量;
    根据所述任一弹幕内容的第一融合特征向量进行兴趣度预测,得到所述多媒体播放对象对所述任一弹幕内容的兴趣度。
  8. 根据权利要求7所述的方法,其特征在于,所述根据所述任一弹幕内容的第一融合特征向量进行兴趣度预测,得到所述多媒体播放对象对所述任一弹幕内容的兴趣度,包括:
    获取所述任一弹幕内容的发布对象的第二对象兴趣标签;
    对所述第二对象兴趣标签进行编码得到第二对象兴趣特征向量;
    将所述第一对象兴趣特征向量与所述第二对象兴趣特征向量进行注意力交互,得到第二融合特征向量;
    将所述第一融合特征向量与所述第二融合特征向量进行特征拼接得到拼接特征向量;
    根据所述拼接特征向量进行兴趣度预测得到所述多媒体播放对象对所述任一弹幕内容的兴趣度。
  9. 根据权利要求6所述的方法,所述根据所述第一对象兴趣标签和所述多媒体资源片段中的任一弹幕内容分别计算所述多媒体播放对象对所述任一弹幕内容的兴趣度之后,所述方法还包括:
    记录兴趣度达到第二阈值的弹幕内容;
    响应于所述播放进度条的滑块移动至第一时间区间,在所述待播放多媒体资源的播放页面上优先展示目标弹幕内容,所述目标弹幕内容为兴趣度达到所述第二阈值的弹幕内容,且所述目标弹幕内容属于所述第一时间区间的多媒体资源片段的至少一个弹幕内容。
  10. 根据权利要求1-9任一项所述的方法,所述方法还包括:
    生成不同时间区间的多媒体资源片段的描述信息;
    在播放所述待播放多媒体资源的过程中,响应于针对所述播放进度条上滑块的控制操作,控制所述滑块移动至第二时间区间,并展示所述第二时间区间的多媒体资源片段的描述信息。
  11. 根据权利要求10所述的方法,所述生成不同时间区间的多媒体资源片段的描述信息,包括:
    根据所述对象标识获取所述多媒体播放对象的第一对象兴趣标签,以及根据所述多媒体标识获取所述待播放多媒体资源中不同时间区间的多媒体资源片段的多媒体资源信息;
    针对任一时间区间的多媒体资源片段,基于所述第一对象兴趣标签和所述多媒体资源片段的多媒体资源信息,通过描述预测模型生成所述多媒体资源片段的描述信息。
  12. 根据权利要求11所述的方法,所述描述预测模型的训练方式包括:
    获取多媒体播放样本对象的第一样本对象兴趣标签,以及获取样本多媒体资源的多媒体资源信息;
    基于所述第一样本对象兴趣标签和所述多媒体资源信息,以所述样本多媒体资源的标题信息作为训练目标对初始网络模型进行预训练,得到预训练模型;
    获取第二样本对象兴趣标签,以及从所述样本多媒体资源中获取样本多媒体资源片段;
    基于所述第二样本对象兴趣标签和所述样本多媒体资源片段的多媒体资源信息,对所述预训练模型进行训练,得到所述描述预测模型。
  13. 根据权利要求11或12所述的方法,所述多媒体资源信息包括多媒体资源内容和弹幕内容中至少一种。
  14. 一种多媒体资源播放装置,所述装置部署在计算机设备上,所述装置包括获取单元、生成单元、播放单元和显示单元:
    所述获取单元,用于获取针对待播放多媒体资源的播放请求,所述播放请求中携带有多媒体播放对象的对象标识和所述待播放多媒体资源的多媒体标识;
    所述获取单元,还用于基于所述对象标识和所述多媒体标识,获取所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度;
    所述生成单元,用于依据所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度,生成播放进度条,所述播放进度条的滑动粒度与所述时间区间的划分粒度相匹配;
    所述播放单元,用于播放所述待播放多媒体资源;
    所述显示单元,用于在播放所述待播放多媒体资源时,在所述待播放多媒体资源的播放页面上显示所述播放进度条,所述播放进度条用于指示所述待播放多媒体资源的播放进度和所述多媒体播放对象对所述待播放多媒体资源中不同时间区间的多媒体资源片段的兴趣度。
  15. 一种计算机设备,所述计算机设备包括处理器以及存储器:
    所述存储器用于存储计算机程序,并将所述计算机程序传输给所述处理器;
    所述处理器用于根据所述计算机程序中的指令执行权利要求1-13任一项所述的方法。
  16. 一种计算机可读存储介质,所述计算机可读存储介质用于存储计算机程序,所述计算机程序被处理器执行时实现权利要求1-13任一项所述的方法。
  17. 一种计算机程序产品,包括计算机程序,当其在计算机设备上运行时,使得所述计算机设备执行权利要求1-13任一项所述的方法。
PCT/CN2023/085834 2022-08-19 2023-04-03 一种多媒体资源播放方法及相关装置 WO2024036979A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210998870.7A CN117641054A (zh) 2022-08-19 2022-08-19 一种多媒体资源播放方法及相关装置
CN202210998870.7 2022-08-19

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/596,234 Continuation US20240212721A1 (en) 2022-08-19 2024-03-05 Multimedia resource playing method and related apparatus

Publications (2)

Publication Number Publication Date
WO2024036979A1 WO2024036979A1 (zh) 2024-02-22
WO2024036979A9 true WO2024036979A9 (zh) 2024-05-16

Family

ID=89940517

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/085834 WO2024036979A1 (zh) 2022-08-19 2023-04-03 一种多媒体资源播放方法及相关装置

Country Status (2)

Country Link
CN (1) CN117641054A (zh)
WO (1) WO2024036979A1 (zh)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110446093A (zh) * 2019-08-15 2019-11-12 天脉聚源(杭州)传媒科技有限公司 一种视频进度条显示方法、装置和存储介质
CN112492370A (zh) * 2019-09-12 2021-03-12 上海哔哩哔哩科技有限公司 进度条的展示方法、装置、计算机设备及可读存储介质
CN112287165A (zh) * 2020-10-29 2021-01-29 深圳市艾酷通信软件有限公司 文件处理方法及装置
CN113411680B (zh) * 2021-06-18 2023-03-21 腾讯科技(深圳)有限公司 多媒体资源播放方法、装置、终端及存储介质
CN113259780B (zh) * 2021-07-15 2021-11-05 中国传媒大学 全息多维音视频播放进度条生成、显示和控制播放方法
CN113709566B (zh) * 2021-08-11 2024-03-22 咪咕数字传媒有限公司 多媒体内容的播放方法、装置、设备以及计算机存储介质

Also Published As

Publication number Publication date
WO2024036979A1 (zh) 2024-02-22
CN117641054A (zh) 2024-03-01

Similar Documents

Publication Publication Date Title
US11417341B2 (en) Method and system for processing comment information
US11871063B2 (en) Intelligent multi-device content distribution based on internet protocol addressing
US8799300B2 (en) Bookmarking segments of content
EP3255889B1 (en) System and method for testing and certification of media devices for use within a connected media environment
CN109845283B (zh) 定制在与用户装置配对的替代回放装置上回放的媒体项目
EP3680896B1 (en) Method for controlling terminal by voice, terminal, server and storage medium
CN111050203B (zh) 一种视频处理方法、装置、视频处理设备及存储介质
US20140278993A1 (en) Interactive advertising
CN111556353B (zh) 一种视频播放方法、视频播放管理装置及终端设备
JP2017505949A (ja) インスタント通信において表現情報を処理する方法及び装置
CN102298947A (zh) 一种用于在多媒体播放器间进行播放切换的方法与设备
EP3531707A1 (en) Audio content playback control
US20180014074A1 (en) Method and Apparatus for Playing a Multimedia File From a Re-Positioned Playing Point
JP2021121969A (ja) アプリケーションプログラムの操作ガイダンス方法、装置、機器及び読み取り可能な記憶媒体
US11609738B1 (en) Audio segment recommendation
WO2016150273A1 (zh) 一种视频播放方法、移动终端及系统
JP2023522092A (ja) インタラクション記録生成方法、装置、デバイス及び媒体
KR20150114386A (ko) 컨텐츠 재생 장치 및 방법,및 컨텐츠 제공 장치 및 방법
US20170070784A1 (en) Interactive content generation for thin client applications
US20240103802A1 (en) Method, apparatus, device and medium for multimedia processing
WO2023174073A1 (zh) 视频生成方法、装置、设备、存储介质和程序产品
WO2024036979A9 (zh) 一种多媒体资源播放方法及相关装置
US20190138265A1 (en) Systems and methods for managing displayless portable electronic devices
US20220317968A1 (en) Voice command processing using user interface context
CN113392260B (zh) 界面显示控制方法、装置、介质及电子设备

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: 23853892

Country of ref document: EP

Kind code of ref document: A1