WO2022204991A1 - 实时音视频推荐方法、装置、设备以及计算机存储介质 - Google Patents
实时音视频推荐方法、装置、设备以及计算机存储介质 Download PDFInfo
- Publication number
- WO2022204991A1 WO2022204991A1 PCT/CN2021/084114 CN2021084114W WO2022204991A1 WO 2022204991 A1 WO2022204991 A1 WO 2022204991A1 CN 2021084114 W CN2021084114 W CN 2021084114W WO 2022204991 A1 WO2022204991 A1 WO 2022204991A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- real
- time audio
- data
- user
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000012216 screening Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000003058 natural language processing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
- H04N21/4223—Cameras
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4882—Data services, e.g. news ticker for displaying messages, e.g. warnings, reminders
Definitions
- the present application relates to the field of Internet technologies, and in particular, to a real-time audio and video recommendation method, apparatus, device, and computer storage medium.
- Real-time audio and video is a common way of communication and entertainment in various fields at present, which can include webcasting and web conferences. It has played an important role in enriching the spiritual and cultural life of the people.
- Embodiments of the present application provide a real-time audio and video recommendation method, apparatus, device, and computer storage medium.
- the technical solution is as follows:
- a real-time audio and video recommendation method includes:
- Acquire content data of the alternative real-time audio and video based on at least one audio and video data of the alternative real-time audio and video;
- the target candidate real-time audio and video in the at least one candidate real-time audio and video is displayed on the user interface.
- the method further includes:
- the quantity of the alternative real-time audio and video is at least two, and after obtaining the degree of association between the content data of the alternative real-time audio and video and the user data, the method further includes:
- the recommendation information of the first alternative real-time audio and video in at least two of the alternative real-time audio and video is the target device in the at least two alternative real-time audio and video.
- the degree of association between the content data and the user data is greater than the second specified value.
- the alternative real-time audio and video, and the recommended information includes one or more of pictures and text. kind;
- the candidate real-time audio and video corresponding to the recommendation information is displayed on the user interface.
- the method further includes:
- the text data is displayed on the user interface.
- the displaying the text data on the user interface includes:
- a prompt box is displayed on the user interface, the text data is displayed in the prompt box, and the size of the prompt box in the user interface is smaller than the size of the candidate real-time audio and video displayed in the user interface.
- the obtaining user data includes:
- the user data includes face data of at least one user:
- the determining of at least one target user viewing the user interface includes:
- Face recognition is performed on the image to determine at least one target user viewing the user interface.
- the acquiring the user data of the at least one target user includes:
- User data of the at least one target user is acquired according to the input information.
- the method also includes:
- the user interface displays the real-time audio and video with the largest number of viewers among the plurality of real-time audio and video.
- the method also includes:
- the candidate real-time audio and video with the highest degree of correlation between the content data and the user input data.
- the obtaining of the degree of association between the content data of at least one of the alternative real-time audio and video content data and the user data includes:
- Semantic analysis is performed on the content data to obtain the semantics of the content data
- Semantic analysis is performed on the user data to obtain the semantics of the user data
- the degree of similarity between the semantics of the content data and the semantics of the user data is determined as the degree of association between the content data and the user data.
- the target alternative real-time audio and video in at least one of the alternative real-time audio and video is displayed on the user interface, include:
- the target candidate real-time audio and video with the highest degree of correlation between the content data and the user data.
- a real-time audio and video recommendation device includes:
- Description data acquisition module used to obtain multiple real-time audio and video description data
- User data acquisition module used to acquire user data
- a determination module configured to determine at least one candidate real-time audio and video of the plurality of real-time audio and video that indicates that the degree of association between the data and the user data is greater than the first specified value
- An audio and video data acquisition module configured to acquire audio and video data of the alternative real-time audio and video after at least one of the alternative real-time audio and video is turned on;
- a content data acquisition module configured to acquire the content data of the alternative real-time audio and video based on at least one audio and video data of the alternative real-time audio and video;
- an association degree obtaining module used to obtain the association degree of at least one of the alternative real-time audio and video content data and the user data
- the first display module is used to display the target candidate real-time audio and video in at least one of the candidate real-time audio and video in the user interface based on the degree of association between the content data of at least one of the candidate real-time audio and video and the user data .
- the number of the alternative real-time audio and video is at least two;
- the real-time audio and video recommendation device further includes:
- the recommendation information acquisition module is used to acquire the recommendation information of the first candidate real-time audio and video in at least two of the candidate real-time audio and video, and the first candidate real-time audio and video is at least two of the candidate real-time audio and video.
- the degree of association between the content data and the user data is greater than the alternative real-time audio and video of the second specified value, and the recommended information includes pictures and one or more of the words;
- a recommendation information display module configured to display the recommendation information on the user interface
- the second display module is configured to display the candidate real-time audio and video corresponding to the recommendation information on the user interface after obtaining the operation on the recommendation information.
- the real-time audio and video recommendation device further includes:
- a text data acquisition module configured to acquire text data corresponding to the audio data of the alternative real-time audio and video corresponding to the recommendation information
- the text data display module is configured to display the text data on the user interface after the operation on the recommendation information is not obtained for a specified period of time.
- a real-time audio and video recommendation device includes a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set , the at least one instruction, the at least one piece of program, the code set or the instruction set is loaded and executed by the processor to implement the real-time audio and video recommendation method according to any one of the preceding aspects.
- a computer non-transitory storage medium stores at least one instruction, at least one piece of program, code set or instruction set, the at least one instruction, The at least one piece of program, the code set or the instruction set is loaded and executed by the processor to implement the real-time audio and video recommendation method as described above.
- a real-time audio and video recommendation method is provided.
- the real-time audio and video are screened according to the degree of association between user data and the description data of the real-time audio and video.
- the correlation degree of the content data of audio and video is screened once, and through two screenings, the real-time audio and video that the user may be interested in can be screened out from a large number of real-time audio and video, and displayed to the user, thus ensuring the real-time audio and video displayed to the user.
- the richness of the real-time audio and video displayed to the user is improved, thereby improving the recommendation effect of the real-time audio and video.
- FIG. 1 is a schematic diagram of an implementation environment of a real-time audio and video recommendation method provided by an embodiment of the present application
- FIG. 2 is a flowchart of a real-time audio and video recommendation method provided by an embodiment of the present application
- FIG. 3 is a flowchart of another real-time audio and video recommendation method provided by an embodiment of the present application.
- Fig. 4 is the flow chart of establishing user database in the method shown in Fig. 3;
- Fig. 5 is the flow chart of at least two alternative real-time audio and video videos that determine that the degree of association between description data and user data is greater than the first specified value in the method shown in Fig. 3;
- Fig. 6 is the flow chart that obtains the correlation degree of the content data of at least two alternative real-time audio and video and the user data of target user in the method shown in Fig. 3;
- FIG. 8 is another user interface provided by an embodiment of the present application.
- FIG. 9 is a flowchart of another real-time audio and video recommendation method provided by an embodiment of the present application.
- FIG. 10 is a structural block diagram of a real-time audio and video recommendation device provided by an embodiment of the present application.
- FIG. 11 is a block diagram of another real-time audio and video recommendation apparatus provided by an embodiment of the present application.
- FIG. 12 is a block diagram of another real-time audio and video recommendation apparatus provided by an embodiment of the present application.
- FIG. 13 is a schematic structural diagram of a server provided by an embodiment of the present application.
- the implementation environment may include a server 11 and one or more terminals 12, and the terminals 12 may include a camera 121 and a display 122, and the camera 121 may be located on the display One side of the terminal 122 is convenient for the user to operate on the terminal 12 .
- the server 11 may be a server or a server cluster.
- the server can acquire multiple real-time audio and video content data and user data, and can perform semantic analysis on the content data and user data to obtain corresponding semantics.
- the terminal 12 may be various terminals such as a desktop computer, a mobile phone, a tablet computer, and a notebook computer.
- the terminal 12 can be connected with the server 13 in a wired or wireless manner.
- the embodiments of the present application provide According to the degree of correlation between the preview content of the webcast and the user data, select a part of the webcasts with a high degree of correlation, and then select the degree of correlation according to the degree of correlation between the content data of these webcasts with a high degree of correlation and the user data.
- the highest online live broadcast can be played quickly and accurately, and the online live broadcast that the user is interested in can be quickly and accurately selected, and the user experience is better.
- the web conference can be recommended.
- the multiple web conferences may contain multiple contents that the user wants to know.
- the method provided by the embodiment of the present application can be used when the user participates in the web conference. Before, or when you have participated in one of the online conferences, continue to obtain the degree of association between user data and the content data of multiple conferences. online meeting.
- FIG. 2 is a flowchart of a real-time audio and video recommendation method provided by an embodiment of the present application.
- the real-time audio and video recommendation method may be applied to the server in the embodiment shown in FIG. 1 .
- the method can include the following steps:
- Step 201 Acquire multiple real-time audio and video description data.
- Step 202 Obtain user data.
- Step 203 Determine at least one candidate real-time audio and video of the plurality of real-time audio and video that indicates that the degree of association between the data and the user data is greater than the first specified value.
- Step 204 After at least one candidate real-time audio and video is enabled, acquire audio and video data of the candidate real-time audio and video.
- Step 205 Acquire content data of the candidate real-time audio and video based on the audio and video data of at least one candidate real-time audio and video.
- Step 206 Obtain the degree of association between the content data of at least one candidate real-time audio and video and the user data.
- Step 207 Based on the degree of association between the content data of the at least one candidate real-time audio and video and the user data, display the target candidate real-time audio and video in the at least one candidate real-time audio and video on the user interface.
- the turn-on time of at least one candidate real-time audio and video may not be fixed, and each candidate real-time audio and video may have its own turn-on time, which may After it is turned on, the content data of the candidate real-time audio and video can be obtained.
- the user can be prompted, and after the user's instruction information (such as touch information) is obtained, the alternative real-time audio and video can be obtained.
- Real-time audio and video content data may be fixed, and each candidate real-time audio and video may have its own turn-on time, which may After it is turned on, the content data of the candidate real-time audio and video can be obtained.
- the alternative real-time audio and video starts, the user can be prompted, and after the user's instruction information (such as touch information) is obtained, the alternative real-time audio and video can be obtained.
- Real-time audio and video content data Real-time audio and video content data.
- the start time of webcast A is 9:00
- the start time of webcast B is 9:20
- the server obtains the execution of the audio and video data of the alternative real-time audio and video from the audio and video server to which the alternative real-time audio and video belongs.
- the action can be triggered based on the real-time audio and video activation; or, it can also be triggered after the server obtains the operation performed by the user on the user interface, and the operation can include the user clicking, long pressing or sliding on the user interface.
- the list of description data may include description data of at least one candidate real-time audio and video whose degree of association with the user data is greater than the first specified value.
- the method provided by the embodiment of the present application may also be applied to the terminal in the implementation environment shown in FIG. 1 , which is not limited by the embodiment of the present application.
- the embodiments of the present application provide a method for recommending real-time audio and video.
- a user watches real-time audio and video
- the viewing real-time audio and video is screened once, and then the real-time audio and video are screened.
- one screening is performed according to the degree of association between the user data and the content data of the real-time audio and video.
- the real-time audio and video that the user may be interested in can be screened from a large number of real-time audio and video, and displayed to the user.
- the richness of the real-time audio and video displayed to the user is improved, thereby improving the recommendation effect of the real-time audio and video.
- a recommendation method of a real-time audio and video recommendation method a user is determined according to the user's browsing history to watch in the history. The most frequent real-time audio and video, and when the real-time audio and video is turned on again, the real-time audio and video is displayed to the user for the user to watch. However, the repetition of the real-time audio and video recommended to the user by this method is high, and the recommendation effect is poor.
- the method provided by this embodiment of the present application can screen out real-time audio and video that may be of interest to the user from a large number of real-time audio and video.
- the richness of the real-time audio and video displayed is high, and the recommendation effect is better.
- FIG. 3 is a flowchart of another real-time audio and video recommendation method provided by an embodiment of the present application.
- the real-time audio and video recommendation method may be applied to the server in the embodiment shown in FIG. 1 .
- the method can include the following steps:
- Step 301 Acquire multiple real-time audio and video description data.
- the real-time audio and video may include real-time video, real-time audio, and real-time data including audio and video.
- the description data may include the preview content, themes, and main topics of multiple real-time audio and video, and the description data may play a role in summarizing the content of the real-time audio and video.
- the multiple real-time audio and video may include live programs or online conferences.
- the server may obtain multiple live preview contents before the real-time audio and video is enabled, or obtain the main topics of the online conference according to the meeting notice of the online conference.
- the descriptive data may include "new product launch conference of xxx”, "thematic conference about holding xxx”, “seminar about the development prospect of xxx”, and "audio and video clips of live broadcast announcement”, etc.
- Step 302 Obtain user data.
- multiple users may use the same terminal to watch real-time audio and video, and the corresponding user data may also include user data of multiple users.
- the server can get user data from the user database.
- the user data may include face data of at least one user.
- the server can construct a user database by collecting user data of multiple users in advance, and the user data can be obtained by processing the user's input information by the server.
- the user can send the user input information to the server through a terminal.
- step 302 may include:
- the server can obtain the The image of the user who is watching the user interface, through face recognition, it is determined that the user who is watching the user interface at this time is the target user, that is, the most relevant real-time audio and video can be recommended according to the target user who is watching the real-time audio and video, so as to avoid The data of users who did not participate in the viewing are compared together to further improve the accuracy of the recommendation.
- the above step 1) can include:
- the server may acquire an image of the user uploaded by the terminal from the terminal, where the user may include a user viewing the user interface, and the image may be captured by the camera of the terminal.
- the server may obtain face data of multiple users in advance (the face data of the multiple users may also be located in the user database and correspond one-to-one with the user data in the user database), and each face data corresponds to a user. And in this step, the server can perform face recognition on the image through the steps of face image detection, face image preprocessing, and face image feature extraction, so as to obtain the face data of the user viewing the user interface, and classify the human face.
- the face data obtained by face recognition is compared with the pre-obtained face data to determine the target user viewing the user interface.
- the server can match and recognize the face image, search and match the face data of the user viewing the user interface and the face data of multiple users obtained in advance, and set a threshold, when the similarity exceeds this threshold.
- a threshold value, output the result obtained by matching, and the output result is the target user.
- the above step 2) can include:
- the user database may include user data of multiple users pre-obtained by the server.
- it may be determined whether the user database includes the user data of the target user, and if so, it may be obtained from the user database.
- User data of the target user it may be determined whether the user database includes the user data of the target user, and if so, it may be obtained from the user database.
- the target user viewing the user interface may also be a new user, and the user data of the new user is not included in the user database, so the server can acquire the user data of the new user on the spot.
- the input information may include input data of at least one user viewing the user interface, and the input data may be sent to the server by the new user through the terminal.
- the server may acquire the user data of the target user according to the input information of the target user.
- the server can add the user data and face data of the target user to the user database, so that the user can watch real-time audio and video later.
- the establishment process of the user database can include the following four sub-steps:
- Sub-step 3021 obtain the input information of the user.
- the input information may include personal related information input by multiple users through the terminal, and the personal related information may include the industry engaged in, professional background, hobbies and the like.
- Sub-step 3022 Acquire a plurality of user data according to the input information.
- the server may obtain input information from the terminal, and extract keywords in the input information.
- the keywords may include, for example, “food”, “digital”, “computer technology”, “home improvement” and so on.
- Sub-step 3023 Obtain face data of the user.
- the face data of the user may be collected by the camera of the terminal, and the server may obtain the face data of the user uploaded by the terminal from the terminal.
- the camera is used to capture images of the user viewing the user interface.
- the camera may further include a flash.
- the flash can be a single color temperature flash or a dual color temperature flash. Dual color temperature flash refers to the combination of warm light flash and cold light flash, which can be used for light compensation under different color temperatures to improve image clarity.
- the server obtains face data of multiple users through steps such as face image detection, face image preprocessing, and face image feature extraction.
- Sub-step 3024 associate the user data of the user with the face data of the user.
- the server can associate the user's face data collected by the camera of the terminal with the user's user data, so that the face data of multiple users can be in one-to-one correspondence with the user data, which can be used for multiple users to use the same terminal
- the corresponding user data is retrieved through face recognition.
- the server may acquire user data of multiple users through the above steps 3021 to 3024 to form a user database.
- Step 303 Determine at least two candidate real-time audios and videos in which the correlation degree between the description data and the user data is greater than the first specified value among the plurality of real-time audios and videos.
- the server may determine the degree of association between the description data of each real-time audio and video and the user data, and determine at least two candidate real-time audios and videos that are greater than the first specified value.
- step 303 may include the following four sub-steps:
- Sub-step 3031 perform semantic analysis on the description data to obtain the semantics of the description data.
- the server can perform semantic analysis on the description data and user data in the form of text to obtain semantic information.
- the server may apply a natural language processing (Natural Language Processing, NLP) technology to perform semantic analysis on the chat information in the form of text to obtain semantic information.
- NLP Natural Language Processing
- the server can perform semantic analysis on "Seminar on the Development Prospect of Computer Technology” and "Computer Technology” in the above-mentioned description data and user data, and learn that the real-time audio and video may be related to computer technology. Conference, the user's interests include semantic information of computer technology.
- natural language processing is an important direction in the field of computer science and artificial intelligence.
- This technology can realize various theories and methods for effective communication between humans and computers using natural language.
- the server may first obtain text information based on the video and audio in it (such as obtaining text information through image recognition, and obtaining text information through speech recognition), and then perform semantic analysis on the obtained text information, Get the semantics of the description data.
- Sub-step 3032 Perform semantic analysis on the user data to obtain the semantics of the user data.
- the server may analyze and obtain the user's preference for watching real-time audio and video included in the user data according to the acquired user data.
- Sub-step 3033 Determine the similarity between the semantics of the description data and the semantics of the user data as the degree of association between the description data and the user data.
- the similarity between the semantics of the description data and the semantics of the user data can be judged by the method of calculating the semantic distance of words by the classification system.
- This method is also called a tree-based semantic similarity research method.
- the algorithm may include: calculating the similarity using a semantic dictionary, which is a cognitive linguistics-based dictionary that organizes all words in one or several tree-like hierarchical structures. In a tree graph, there is only one path between any two nodes, so the length of this path can be used as a measure of the semantic distance between the two word concepts. The closer the distance is, the more similar higher degree.
- Sub-step 3034 Determine at least two candidate real-time audio and video in the real-time audio and video that indicate that the degree of association between the data and the user data is greater than the first specified value.
- the first specified value may be related to the degree of association between the description data and the user data.
- a plurality of real-time audio and video may be sorted according to the degree of association between the description data of the real-time audio and video and the user data, and the ranking will be ranked tenth.
- Subsequent determinations are candidate real-time audio and video recordings whose degree of association between the data and the user data is less than or equal to the first specified value.
- the degree of association between the description data of the real-time audio and video and the user data is less than or equal to the first specified value, it can be indicated that the real-time audio and video is not the real-time audio and video that the user is interested in, and can be removed by the server, so as to facilitate the following according to the opened
- the alternative real-time audio and video are compared again for the degree of correlation, which can more accurately screen out the real-time audio and video that meets the needs of the user, and can also reduce the comparison time of the correlation degree and relieve the pressure on the server.
- Step 304 After the at least two candidate real-time audio and video are enabled, acquire audio and video data of the candidate real-time audio and video.
- the server may acquire the audio and video data of at least two candidate real-time audio and video from the audio and video server to which the alternate real-time audio and video belongs (for example, the server of the live broadcast platform, or the server of the web conference),
- the audio and video data may include video data and audio data, and may also include picture data, document data, and the like.
- the alternative real-time audio and video is an online conference.
- the real-time audio and video data can be acquired at the conference site by means of recording, camera shooting, PPT sharing, etc. and uploaded to the audio and video server.
- Step 305 Acquire content data of the candidate real-time audio and video based on the audio and video data of the at least two candidate real-time audio and video.
- the content data may include data that can reflect the actual content of real-time audio and video, for example, the content data may include text data extracted from video images of real-time audio and video, or text data converted from real-time audio and video sound data, The content of the document data, etc.
- the content data may include the bullet screen content of the live program, the data displayed on the screen of the live conference, the content of the banner on the site of the online conference, and the content of the PPT of the online conference.
- Step 306 Obtain the degree of association between the content data of the at least two candidate real-time audio and video and the user data of the target user.
- the degree of association can be determined according to the similarity between the semantics of the content data and the semantics of the user data.
- step 306 may include the following three sub-steps:
- Sub-step 3061 perform semantic analysis on the content data to obtain the semantics of the content data.
- the server may perform semantic analysis on the content data in the form of text to obtain the semantics of the content data.
- semantic analysis method reference may be made to the foregoing step 3031, which will not be repeated in this embodiment of the present application.
- Sub-step 3062 Perform semantic analysis on the target user data to obtain the semantics of the target user data.
- the server performs semantic analysis on the data of the selected target users, and can obtain the interest preferences of the target users who are watching the alternative real-time audio and video on the user interface.
- Sub-step 3063 Determine the degree of similarity between the semantics of the content data and the semantics of the target user data as the degree of association between the content data and the target user data.
- the at least two candidate real-time audio and video can be prioritized according to the degree of association, the highest degree of association is the first priority, the second degree of association is the second priority, and so on, for at least two candidates Real-time audio and video sorting.
- at least two webcasts can be prioritized according to the degree of association, where the degree of association ranges from 0 to 10, and the larger the number, the higher the degree of association, and the sorting results are shown in Table 1:
- Webcast name degree of association priority Webcast A 9.6 1 Webcast B 9.3 2 Webcast C 9.1 3 webcast D 8 4 Webcast E 7.3 5 Webcast F 6.9 6
- Table 1 shows the degree of association and the priority order of the webcasts A to F.
- the degree of association of the webcast E is 7.3
- the priority is 5.
- Step 307 among the at least two candidate real-time audio and video displayed on the user interface, the target candidate real-time audio and video with the highest degree of association between the content data and the user data of the target user.
- the target candidate real-time audio and video with the highest degree of association can be displayed on the user interface, that is, the target candidate real-time audio and video ranked as the first priority.
- Step 308 Obtain recommendation information of the first candidate real-time audio and video among the at least two candidate real-time audio and video.
- the first candidate real-time audio and video is one of the at least two candidate real-time audio and video, except the target candidate real-time audio and video other candidate real-time audio and video, the degree of association between content data and user data is greater than the second specified value.
- the recommended information includes one or more of pictures, text, and small window video images.
- the first candidate real-time audio and video may be the real-time audio and video that the user is more interested in.
- Video data at this time, the user may select the first candidate real-time audio and video to watch.
- Recommendation information corresponding to the candidate real-time audio and video that is ranked as the second priority among the at least two candidate real-time audio and video may also be acquired.
- the recommended information may include one or more of video screenshots, text converted from voice data, and small window video images.
- Step 309 Display the recommendation information on the user interface.
- This embodiment of the present application does not limit the display order of the target candidate real-time audio and video with the highest degree of association and the recommendation information. , and then display the target candidate real-time audio and video, that is, while displaying the target candidate real-time audio and video on the user interface, the recommendation information can be displayed on the user interface.
- FIG. 7 is a user interface provided by an embodiment of the present application.
- the display 122 of the user interface displays a display frame 1221 of the target candidate real-time audio and video with the highest degree of correlation, and at the same time, the display frame 1221 is displayed on the display.
- a recommendation information box 1222 is displayed in 122, the recommendation information box 1222 contains recommendation information, and the recommendation information box 1222 is smaller than the display box 1221 of the target candidate real-time audio and video with the highest degree of association.
- the recommendation information may include one or more recommendation information corresponding to one or more candidate real-time audio and video with a degree of association greater than the second specified value, or may include recommendation information corresponding to the candidate real-time audio and video sorted as the second priority .
- the user can learn the recommendation information of one or more candidate real-time audio data with a higher degree of correlation while watching the target candidate real-time audio and video with the highest degree of correlation. Continue to watch the target candidate real-time audio and video with the highest degree of correlation, or switch the display frame of the user interface according to the recommended information, so that the user can have more choices during the viewing process and improve the user experience.
- Step 310 Acquire text data corresponding to the audio data of the candidate real-time audio and video corresponding to the recommendation information.
- the server can convert the audio data in the real-time audio data into corresponding text data.
- the audio data of the candidate real-time audio and video corresponding to the recommendation information has a high degree of correlation with the target user data, and the user's attention to it may also be high.
- the user can choose to watch one of the alternative real-time After the audio and video, the text data of the remaining real-time audio and video data is displayed, so that the user can grasp more information.
- Step 311 Display the candidate real-time audio, video or text data corresponding to the recommendation information on the user interface.
- step 311 Implementations of step 311 include the following two:
- Manner 1 After obtaining the operation on the recommendation information, an alternative real-time audio and video corresponding to the recommendation information is displayed on the user interface.
- an alternative real-time audio and video corresponding to the recommendation information can be displayed on the user interface.
- the operation may include one of clicking, long pressing or sliding. If the alternative real-time audio and video with the degree of association greater than the second specified value includes an alternative real-time audio and video, the video will be played; if the degree of association is greater than the second specified value
- the candidate real-time audio and video includes at least two candidate real-time audio and video, and one of the candidate real-time audio and video corresponding to the user's operation is played.
- Method 2 Display text data on the user interface after the operation on the recommendation information is not obtained for a specified period of time.
- the specified duration can be 5 seconds to 10 seconds. After 5 seconds to 10 seconds of no operation on the recommended information, the target candidate real-time audio and video with the highest degree of relevance can be played on the display interface, and the text data can be displayed on the user interface at the same time.
- FIG. 8 is another user interface provided by an embodiment of the present application.
- the user interface 21 may include a prompt box 211 displayed on the user interface 21 , and text data is displayed in the prompt box 211 .
- the size of the interface 21 is smaller than the size of the target candidate real-time audio and video 212 displayed in the user interface 21, and the prompt box 211 can be in a corner far from the center of the target candidate real-time audio and video 212, which can avoid the need for the target candidate real-time audio and video 212. Important content is blocked.
- the display interface can also display conference topics, information of participants, etc.
- users can use electronic table cards to input text or voice to interact with the conference room and participants in different sessions or click to select, which can realize user Information exchange with participants in different venues can improve user experience.
- Step 312 After receiving the switching instruction, obtain the number of viewers of multiple real-time audio and video.
- the server may also filter multiple real-time audio and video according to the number of viewers of the real-time audio and video.
- the server When the server receives the switching instruction for filtering the real-time audio and video by the number of viewers, it obtains the number of viewers of multiple real-time audio and video from the audio and video server.
- the instruction may be displayed on the operation interface for the user to operate.
- the instruction may be a button control on the user interface, and the button control may include content such as "the most popular live broadcast" or "the most popular currently”.
- Step 313 Display the real-time audio and video with the largest number of viewers among the plurality of real-time audio and video on the user interface.
- the server sorts multiple real-time audio data according to the number of viewers of multiple real-time audio and video, and selects the real-time audio and video with the most viewers for display.
- Step 314 After receiving the user input data, obtain the degree of association between the content data of the multiple candidate real-time audio and video content and the user input data.
- multiple real-time audio and video can also be filtered according to the user input data.
- the user input data may include keywords input by the user according to the content that the user wants to watch.
- the server may perform semantic analysis on the content data of the multiple candidate real-time audio and video and the user input data, and obtain the degree of association between the content data of the multiple candidate real-time audio and video and the user input data according to the obtained semantic information.
- Step 315 displaying the candidate real-time audio and video on the user interface, the candidate real-time audio and video with the highest degree of correlation between the content data and the user input data.
- steps 312, 313, 314, and 315 are implemented is not limited. That is, steps 312 and 313 may be implemented first, followed by steps 314 and 315, or steps 314 and 315 may be implemented first. 315, then implement steps 312 and 313, or only implement steps 312 and 313, or only implement steps 314 and 315, when the user is watching the screened video, there is no switching instruction operation on the display interface or For input data operation, step 312 and step 313 or step 314 and step 315 may not be performed.
- the embodiments of the present application provide a method for recommending real-time audio and video.
- a user watches real-time audio and video
- the viewing real-time audio and video is screened once, and then the real-time audio and video are screened.
- one screening is performed according to the degree of association between the user data and the content data of the real-time audio and video.
- the real-time audio and video that the user may be interested in can be screened from a large number of real-time audio and video, and displayed to the user.
- the richness of the real-time audio and video displayed to the user is improved, thereby improving the recommendation effect of the real-time audio and video.
- the real-time audio and video recommendation apparatus 1200 includes:
- the description data acquisition module 1201 is used to obtain multiple real-time audio and video description data
- User data acquisition module 1202 for acquiring user data
- the determining module 1203 is used to determine at least one candidate real-time audio and video whose correlation degree between the description data and the user data is greater than the first specified value among the plurality of real-time audio and video;
- the content data acquisition module 1205 is used for acquiring the content data of the alternative real-time audio and video based on the audio and video data of at least one alternative real-time audio and video;
- the degree of association acquisition module 1206 is used to acquire the degree of association between the content data of at least one candidate real-time audio and video and the user data;
- the first display module 1207 is configured to display the target candidate real-time audio and video in the at least one candidate real-time audio and video on the user interface based on the degree of association between the content data of the at least one candidate real-time audio and video and the user data.
- FIG. 11 is a block diagram of another real-time audio and video recommendation apparatus provided by an embodiment of the present application.
- the real-time audio and video recommendation apparatus 1200 further includes:
- the recommendation information acquisition module 1208 is used to acquire the recommendation information of the first candidate real-time audio and video in the at least two candidate real-time audio and video.
- the degree of association between the content data and the user data is greater than the second specified value of the alternative real-time audio and video, and the recommended information includes one or more of pictures and text;
- the recommendation information display module 1209 is used to display the recommendation information on the user interface
- the second display module 1210 is configured to display the candidate real-time audio and video corresponding to the recommendation information on the user interface after obtaining the operation on the recommendation information.
- Figure 13 is a block diagram of another real-time audio and video recommendation device provided by the embodiment of the present application, and the real-time audio and video recommendation device also includes:
- the text data acquisition module 1211 is used to acquire text data corresponding to the audio data of the candidate real-time audio and video corresponding to the recommendation information;
- the text data display module 1212 is configured to display text data on the user interface after the operation for the recommendation information is not obtained for a specified period of time.
- the real-time audio and video recommendation device performs a screening of the viewing real-time audio and video according to the correlation degree between the user data and the description data of the real-time audio and video, and then after the broadcast starts, according to the user data and the real-time audio and video
- the correlation degree of the content data is screened once, and through two screenings, the real-time audio and video that the user may be interested in can be screened out from a large number of real-time audio and video, and displayed to the user, thus ensuring that the real-time audio and video displayed to the user is consistent with the Based on the matching degree of user interests, the richness of the real-time audio and video displayed to the user is improved, thereby improving the recommendation effect of the real-time audio and video.
- FIG. 13 is a schematic structural diagram of a server provided by an embodiment of the present application.
- the server 1600 includes a Central Processing Unit (CPU) 1601, a system memory 1604 including a random access memory (RAM) 1602 and a read only memory (ROM) 1603, and a connection system memory 1604 And the system bus 1605 of the central processing unit 1601.
- the server 1600 also includes a basic input/output system (I/O system) 1606 that facilitates the transfer of information between various devices within the computer, and a mass storage device 1607 for storing the operating system 1613, application programs 1614, and other program modules 1615 .
- I/O system basic input/output system
- Basic input/output system 1606 includes a display 1608 for displaying information and input devices 1609 such as a mouse, keyboard, etc., for user input of information. Both the display 1608 and the input device 1609 are connected to the central processing unit 1601 through the input and output controller 1610 connected to the system bus 1605.
- the basic input/output system 1606 may also include an input output controller 1610 for receiving and processing input from a number of other devices such as a keyboard, mouse, or electronic stylus.
- input output controller 1610 also provides output to a display screen, printer, or other type of output device.
- Mass storage device 1607 is connected to central processing unit 1601 through a mass storage controller (not shown) connected to system bus 1605 .
- Mass storage device 1607 and its associated computer-readable media provide non-volatile storage for server 1600. That is, the mass storage device 1607 may include a computer-readable medium (not shown) such as a hard disk or a Compact Disc Read-Only Memory (CD-ROM) drive.
- a computer-readable medium such as a hard disk or a Compact Disc Read-Only Memory (CD-ROM) drive.
- Computer non-transitory readable media can include computer storage media and communication media.
- Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.
- Computer storage media include RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other solid state Storage medium, CD-ROM, Digital Versatile Disc (DVD) or other optical storage, cassette, magnetic tape, magnetic disk storage or other magnetic storage device.
- RAM random access memory
- ROM Erasable Programmable Read-Only Memory
- EEPROM Electrically Erasable Programmable Read Only Memory
- flash memory or other solid state Storage medium
- CD-ROM Compact Disc
- DVD Digital Versatile Disc
- the server 1600 may also operate on a remote computer connected to a network through a network such as the Internet. That is, the server 1600 can be connected to the network 1612 through the network interface unit 1611 connected to the system bus 1605, or can also use the network interface unit 1611 to connect to other types of networks or remote computer systems (not shown).
- the memory also includes one or more programs, one or more programs are stored in the memory, and the central processing unit 1601 implements any one of the real-time audio and video recommendation methods provided in the above embodiments by executing the one or more programs.
- an embodiment of the present application also provides a real-time audio and video recommendation device, the real-time audio and video recommendation device includes a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, and at least one instruction , At least one piece of program, code set or instruction set is loaded and executed by the processor to implement any of the real-time audio and video recommendation methods provided by the foregoing embodiments.
- an embodiment of the present application also provides a computer non-transitory storage medium, in which at least one instruction, at least one program, code set or instruction set, at least one instruction, at least one program, The code set or the instruction set is loaded and executed by the processor to implement any of the real-time audio and video recommendation methods provided by the foregoing embodiments.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本申请公开了一种实时音视频推荐方法、装置、设备以及计算机存储介质，属于互联网技术领域。所述方法包括：根据用户数据与实时音视频的说明数据关联程度对观看实时音视频进行一次筛选，再在开播后，根据用户数据与实时音视频的内容数据的关联程度进行一次筛选，通过两次筛选，可以从大量的实时音视频中筛选出用户可能感兴趣的实时音视频，并向用户展示。
Description
本申请涉及互联网技术领域，特别涉及一种实时音视频推荐方法、装置、设备以及计算机存储介质。
实时音视频是目前一种各个领域常用的交流以及娱乐的方式，其可以包括网络直播以及网络会议等，实时音视频以其内容和形式的直观性、即时性和互动性，在促进经济社会发展、丰富人民群众精神文化生活等方面发挥了重要作用。
目前，在观看实时音视频的过程中，可能会存在多个用户感兴趣的网络直播同时进行，用户需要不停切换直播画面，甚至切换直播的应用程序，如此，用户就会错过很多自己最感兴趣的直播内容。
发明内容
本申请实施例提供了一种实时音视频推荐方法、装置、设备和计算机存储介质。所述技术方案如下：
根据本申请的第一方面，提供了一种实时音视频推荐方法，所述方法包括：
获取多个实时音视频的说明数据；
获取用户数据；
确定所述多个实时音视频中，说明数据与所述用户数据的关联程度大于第一指定值的至少一个备选实时音视频；
在至少一个所述备选实时音视频开启后，获取所述备选实时音视频的音视频数据；
基于至少一个所述备选实时音视频的音视频数据，获取所述备选实时音视频的内容数据；
获取至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度；
基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度， 在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频。
可选地，所述获取所述至少一个备选实时音视频的内容数据与所述用户数据的关联程度之后，所述方法还包括：
所述备选实时音视频的数量为至少两个，所述获取所述备选实时音视频的内容数据与所述用户数据的关联程度之后，所述方法还包括：
获取至少两个所述备选实时音视频中的第一备选实时音视频的推荐信息，所述第一备选实时音视频是所述至少两个备选实时音视频中除所述目标备选实时音视频外的其他备选实时音视频中，内容数据与所述用户数据的关联程度大于第二指定值的备选实时音视频，所述推荐信息包括图片和文字中的一种或多种；
在所述用户界面展示所述推荐信息；
在获取对于所述推荐信息的操作后，在所述用户界面展示所述推荐信息对应的备选实时音视频。
可选地，在所述用户界面展示所述推荐信息之后，所述方法还包括：
获取所述推荐信息对应的备选实时音视频的音频数据对应的文字数据；
在指定时长未获取对于所述推荐信息的操作后，在所述用户界面展示所述文字数据。
可选地，所述在所述用户界面展示所述文字数据，包括：
在所述用户界面展示提示框，所述提示框中显示有所述文字数据，所述提示框在所述用户界面的尺寸小于所述用户界面中展示的备选实时音视频的尺寸。
可选地，所述获取用户数据，包括：
确定观看所述用户界面的至少一个目标用户；
获取所述至少一个目标用户的用户数据。
可选地，所述用户数据包括至少一个用户的人脸数据：
所述确定观看所述用户界面的至少一个目标用户，包括：
获取具有至少一个用户的图像；
对所述图像进行人脸识别，以确定观看所述用户界面的至少一个目标用户。
可选地，所述获取所述至少一个目标用户的用户数据，包括：
在用户数据库中包括所述至少一个目标用户的用户数据时，从所述用户数据库中获取所述至少一个目标用户的用户数据；或者，
在所述用户数据库中包括所述至少一个目标用户的用户数据时，获取输入 信息；
根据所述输入信息获取所述至少一个目标用户的用户数据。
可选地，基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频之后，所述方法还包括：
在接收到切换指令后，获取所述多个实时音视频的观看人数；
在所述用户界面展示所述多个实时音视频中，观看人数最多的实时音视频。
可选地，基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频之后，所述方法还包括：
在接收到用户输入数据后，获取至少一个所述备选实时音视频的内容数据与所述用户输入数据的关联程度；
在所述用户界面展示至少一个所述备选实时音视频中，内容数据与所述用户输入数据的关联程度最高的备选实时音视频。
可选地，所述获取至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，包括：
对所述内容数据进行语义分析，得到所述内容数据的语义；
对所述用户数据进行语义分析，得到所述用户数据的语义；
将所述内容数据的语义和所述用户数据的语义的相似度确定为所述内容数据与所述用户数据的关联程度。
可选地，所述基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频，包括：
在用户界面展示至少一个所述备选实时音视频中，内容数据与所述用户数据的关联程度最高的所述目标备选实时音视频。
根据本申请的另一方面，提供了一种实时音视频推荐装置，该实时音视频推荐装置包括：
说明数据获取模块，用于获取多个实时音视频的说明数据；
用户数据获取模块，用于获取用户数据；
确定模块，用于确定所述多个实时音视频中，说明数据与所述用户数据的关联程度大于第一指定值的至少一个备选实时音视频；
音视频数据获取模块，用于在至少一个所述备选实时音视频开启后，获取所述备选实时音视频的音视频数据；
内容数据获取模块，用于基于至少一个所述备选实时音视频的音视频数据，获取所述备选实时音视频的内容数据；
关联程度获取模块，用于获取至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度；
第一展示模块，用于基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频。
可选地，所述备选实时音视频的数量为至少两个；
所述实时音视频推荐装置，还包括：
推荐信息获取模块，用于获取至少两个所述备选实时音视频中的第一备选实时音视频的推荐信息，所述第一备选实时音视频是至少两个所述备选实时音视频中除所述目标备选实时音视频外的其他备选实时音视频中，内容数据与所述用户数据的关联程度大于第二指定值的备选实时音视频，所述推荐信息包括图片和文字中的一种或多种；
推荐信息展示模块，用于在所述用户界面展示所述推荐信息；
第二展示模块，用于在获取对于所述推荐信息的操作后，在所述用户界面展示所述推荐信息对应的备选实时音视频。
可选地，所述实时音视频推荐装置，还包括：
文字数据获取模块，用于获取所述推荐信息对应的备选实时音视频的音频数据对应的文字数据；
文字数据展示模块，用于在指定时长未获取对于所述推荐信息的操作后，在所述用户界面展示所述文字数据。
根据本申请的另一方面，提供了一种实时音视频推荐设备，所述实时音视频推荐设备包括处理器和存储器，所述存储器中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如上述一方面任一所述的实时音视频推荐方法。
根据本申请的另一方面，提供了一种计算机非瞬态存储介质，所述计算机非瞬态存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所 述至少一条指令、所述至少一段程序、所述代码集或指令集由处理器加载并执行以实现如上述任一所述的实时音视频推荐方法。
本申请实施例提供的技术方案带来的有益效果至少包括：
提供了一种实时音视频推荐方法，通过在用户观看实时音视频时，根据用户数据与实时音视频的说明数据关联程度对观看实时音视频进行一次筛选，再在开播后，根据用户数据与实时音视频的内容数据的关联程度进行一次筛选，通过两次筛选，可以从大量的实时音视频中筛选出用户可能感兴趣的实时音视频，并向用户展示，如此保证了向用户展示的实时音视频与用户兴趣的匹配程度的基础上，提高了向用户展示的实时音视频的丰富程度，进而提高了实时音视频的推荐效果。
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例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人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的实时音视频推荐方法的实施环境的示意图；
图2是本申请实施例提供的一种实时音视频推荐方法流程图；
图3是本申请实施例提供的另一种实时音视频推荐方法流程图；
图4是图3所示的方法中建立用户数据库的流程图；
图5是图3所示的方法中确定说明数据与用户数据的关联程度大于第一指定值的至少两个备选实时音视频的流程图；
图6是图3所示的方法中获取至少两个备选实时音视频的内容数据与目标用户的用户数据的关联程度的流程图；
图7是本申请实施例提供的一种用户界面；
图8是本申请实施例提供的另一种用户界面；
图9是本申请实施例提供的另一种实时音视频推荐方法流程图；
图10是本申请实施例提供的一种实时音视频推荐装置的结构框图；
图11是本申请实施例提供的另一种实时音视频推荐装置的框图；
图12是本申请实施例提供的另一种实时音视频推荐装置的框图；
图13是本申请实施例提供的一种服务器的结构示意图。
通过上述附图，已示出本申请明确的实施例，后文中将有更详细的描述。这些附图和文字描述并不是为了通过任何方式限制本申请构思的范围，而是通过参考特定实施例为本领域技术人员说明本申请的概念。
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
图1是本申请实施例提供的实时音视频推荐方法的实施环境的示意图，该实施环境可以包括服务器11和一个或多个终端12，终端12可以包括摄像头121以及显示器122，摄像头121可以位于显示器122的一侧，可以方便用户在终端12进行操作。
服务器11可以为一个服务器或服务器集群。该服务器可以获取多个实时音视频的内容数据和用户数据，并且可以对内容数据和用户数据进行语义分析，得到相对应的语义。
终端12可以为台式电脑、手机、平板电脑、笔记本电脑等各种终端。
终端12可以通过有线或无线的方式与服务器13连接。
本申请实施例的应用场景可以包括：
1)在多个网络直播同时播放时进行网络直播的实时音视频的推荐，多个网络直播在同一时间播出，且各个网络直播可能都包含了用户想要观看的内容，本申请实施例提供的方法可以根据网络直播的预告内容和用户数据的关联程度，挑选一部分关联程度较高的网络直播，再根据这些关联程度较高的网络直播的内容数据与用户数据的关联程度，挑选出关联度最高的网络直播，进行播放，可以快速、准确的挑选出用户感兴趣的网络直播，用户体验较好。
2)有多个网络会议的时间段存在冲突时，可以进行网络会议的推荐，多个网络会议中可能包含了用户要了解的多个内容，本申请实施例提供的方法可以在用户参加网络会议前，或者已经参加了其中一场网络会议时，持续获取用户数据与多个会议的内容数据的关联程度，在获取到此刻关联程度最高的会议的实时音视频内容时，可以为用户推荐相应的网络会议。
图2是本申请实施例提供的一种实时音视频推荐方法流程图，该实时音视频推荐方法可以应用于图1所示实施例中的服务器中。该方法可以包括下面几个步骤：
步骤201、获取多个实时音视频的说明数据。
步骤202、获取用户数据。
步骤203、确定多个实时音视频中，说明数据与用户数据的关联程度大于第一指定值的至少一个备选实时音视频。
步骤204、在至少一个备选实时音视频开启后，获取备选实时音视频的音视频数据。
步骤205、基于至少一个备选实时音视频的音视频数据，获取备选实时音视频的内容数据。
步骤206、获取至少一个备选实时音视频的内容数据与用户数据的关联程度。
步骤207、基于至少一个备选实时音视频的内容数据与用户数据的关联程度，在用户界面展示至少一个备选实时音视频中的目标备选实时音视频。
可以理解的是，本申请实施例中，至少一个备选实时音视频的开启时间可以是不固定的，每个备选实时音视频都可以有各自的开启时间，可以在一个备选实时音视频开启后，获取该备选实时音视频的内容数据，也可以在一个备选实时音视频开始后，向用户提示，并在获取用户的指示信息(如触控信息)后，开始获取该备选实时音视频的内容数据。
示例性的，网络直播A的开启时间是9点，网络直播B的开启时间是9点20分，服务器从备选实时音视频所属的音视频服务器获取备选实时音视频的音视频数据的执行动作，可以是基于实时音视频开启而触发的；或者，也可以是在服务器获取了用户在用户界面进行的操作后触发的，该操作可以包括用户在用户界面上点击、长按或者滑动说明数据的列表，该说明数据的列表可以包括与用户数据的关联程度大于第一指定值的至少一个备选实时音视频的说明数据。此外，本申请实施例提供的方法也可以应用于图1所示实施环境中的终端中，本申请实施例对此不进行限制。
综上所述，本申请实施例提供了一种实时音视频推荐方法，通过在用户观看实时音视频时，根据用户数据与实时音视频的说明数据关联程度对观看实时音视频进行一次筛选，再在开播后，根据用户数据与实时音视频的内容数据的关联程度进行一次筛选，通过两次筛选，可以从大量的实时音视频中筛选出用 户可能感兴趣的实时音视频，并向用户展示，如此保证了向用户展示的实时音视频与用户兴趣的匹配程度的基础上，提高了向用户展示的实时音视频的丰富程度，进而提高了实时音视频的推荐效果。
目前，在观看实时音视频的过程中，可能会存在多个用户感兴趣的网络直播同时进行，一种实时音视频推荐方法的推荐方法中，会根据用户的浏览历史确定一个用户在历史中观看次数最多的实时音视频，并在该实时音视频再次开启时，向用户展示该实时音视频，以便用户观看。但是，该方法向用户推荐的实时音视频的重复度较高，推荐效果较差。
而本申请实施例提供的方法，可以从大量的实时音视频中筛选出用户可能感兴趣的实时音视频，如此保证了向用户展示的实时音视频与用户兴趣的匹配程度的基础上，向用户展示的实时音视频的丰富程度较高，推荐效果较好。
图3是本申请实施例提供的另一种实时音视频推荐方法流程图，该实时音视频推荐方法可以应用于图1所示实施例中的服务器中。该方法可以包括下面几个步骤：
步骤301、获取多个实时音视频的说明数据。
其中，实时音视频可以包括实时视频、实时音频以及实时的包括音频和视频的数据。
该说明数据可以包括多个实时音视频的预告内容、主题以及主要议题等，说明数据可以对实时音视频的内容起到概括的作用。
多个实时音视频可以包括直播节目或者在线会议，服务器可以在实时音视频开启之前，获取多个直播的预告内容，或者根据在线会议的会议通知，获取在线会议的主要议题。示例性的，说明数据可以包括“xxx新品发布会”、“关于召开xxx的主题会议”、“关于xxx发展前景的研讨会”以及“直播预告的音视频片段”等。
步骤302、获取用户数据。
本申请实施例中，多个用户可以使用同一终端观看实时音视频，对应的用户数据也可以包括多个用户的用户数据。服务器可以从用户数据库中获取用户数据。该用户数据可以包括至少一个用户的人脸数据。
服务器可以通过预先收集多个用户的用户数据以构建用户数据库，用户数据可以通过服务器对用户的输入信息进行处理而得到，示例性的，用户可以通 过终端向服务器发送用户输入信息。
可选地，步骤302可以包括：
1)确定观看用户界面的至少一个目标用户。
在实时音视频推荐方法的应用过程中，某一段时间可以是多个用户中的一部分用户在观看用户界面播放的实时音视频，目标用户可以包括该部分用户，这种情况下，服务器可以通过获取正在观看用户界面的用户的图像，通过人脸识别，确定此时观看用户界面的用户，即为目标用户，即可以根据正在观看实时音视频的目标用户推荐关联度最高的实时音视频，避免将没有参加观看的用户的数据一起比对，以便于进一步提高推荐的准确性。
上述步骤1)可以包括：
1.1、获取具有至少一个用户的图像。
服务器可以从终端处获取终端上传的用户的图像，该用户可以包括观看用户界面的用户，该图像可以由终端的摄像头来采集。
1.2、对图像进行人脸识别，以确定观看用户界面的至少一个目标用户。
服务器可以预先获取多个用户的人脸数据(该多个用户的人脸数据也可以位于用户数据库中，并与用户数据库中的用户数据一一对应)，每个人脸数据对应一个用户。并在本步骤中，服务器可以通过人脸图像检测、人脸图像预处理以及人脸图像特征提取等步骤来对图像进行人脸识别，以获取观看用户界面的用户的人脸数据，并将人脸识别得到的人脸数据与预先得到的人脸数据进行比对，以确定观看用户界面的目标用户。示例性的，服务器可以通过人脸图像匹配与识别，根据观看用户界面的用户的人脸数据与预先获取的多个用户的人脸数据进行搜索匹配，通过设定一个阈值，当相似度超过这一阈值，将匹配得到的结果输出，该输出的结果即为目标用户。
2)获取至少一个目标用户的用户数据。
上述步骤2)可以包括：
2.1在用户数据库中包括至少一个目标用户的用户数据时，从用户数据库中获取至少一个目标用户的用户数据。
该用户数据库中可以包括服务器预先获取的多个用户的用户数据，在获取观看用户界面的用户数据时，可以确定用户数据库中是否包括目标用户的用户数据，若包括，则可以从用户数据库中获取目标用户的用户数据。
2.2在用户数据库中不包括至少一个目标用户的用户数据时，获取输入信息。
观看用户界面的目标用户还可以为新用户，用户数据库中不包括该新用户的用户数据，因而服务器可以现场获取该新用户的用户数据。
其中，该输入信息可以包括至少一个观看用户界面的用户的输入数据，该输入数据可以由该新用户通过终端发送至服务器。
2.3根据输入信息获取至少一个目标用户的用户数据。
服务器可以根据该目标用户的输入信息，获取该用户的用户数据。
同时，服务器可以将该目标用户的用户数据和人脸数据增加到用户数据库，以便于之后该用户观看实时音视频。
如图4所示，用户数据库的建立过程可以包括以下四个子步骤：
子步骤3021、获取用户的输入信息。
输入信息可以包括多个用户通过终端输入的个人相关信息，该个人相关信息可以包括从事的行业、专业背景以及兴趣爱好等。
子步骤3022、根据输入信息获取多个用户数据。
服务器可以从终端处获取输入信息，提取出输入信息中的关键字，作为用户数据，示例性的，关键字可以包括“美食”、“数码”、“计算机技术”、“家装”等。
子步骤3023、获取用户的人脸数据。
该用户的人脸数据可以由终端的摄像头来采集，服务器可以从终端处获取终端上传的用户的人脸数据。
摄像头用于采集观看用户界面的用户的图像。示例性的，摄像头还可以包括闪光灯。闪光灯可以是单色温闪光灯，也可以是双色温闪光灯。双色温闪光灯是指暖光闪光灯和冷光闪光灯的组合，可以用于不同色温下的光线补偿，提高图像的清晰度。
服务器通过人脸图像检测、人脸图像预处理以及人脸图像特征提取等步骤，获取多个用户的人脸数据。
子步骤3024、将用户的用户数据与用户的人脸数据进行关联。
服务器可以将终端的摄像头采集的用户的人脸数据与该用户的用户数据进行关联，如此便可以将多个用户的人脸数据与用户数据一一对应，可以用于多个用户使用同一个终端观看实时视频时，通过人脸识别调取相对应的用户数据。
服务器可以通过上述步骤3021至3024获取多个用户的用户数据，组建用户数据库。
步骤303、确定多个实时音视频中，说明数据与用户数据的关联程度大于第一指定值的至少两个备选实时音视频。
服务器在获取了说明数据后，可以确定每个实时音视频的说明数据与用户数据的关联程度，并确定其中大于第一指定值的至少两个备选实时音视频。
如图5所示，步骤303可以包括以下四个子步骤：
子步骤3031、对说明数据进行语义分析，得到说明数据的语义。
服务器可以对文字形式的说明数据与用户数据进行语义分析，得到语义信息。
可选地，服务器可以应用自然语言处理(Natural Language Processing，NLP)技术来对文字形式的聊天信息进行语义分析，得到语义信息。例如，服务器应用自然语言处理技术，可以对上述说明数据与用户数据中的“关于计算机技术发展前景的研讨会”与“计算机技术”进行语义分析，得知该实时音视频可能是有关计算机技术的会议，该用户的兴趣爱好包括计算机技术的语义信息。
其中，自然语言处理是计算机科学领域与人工智能领域中的一个重要方向。该项技术可以实现人与计算机之间用自然语言进行有效通信的各种理论和方法。
在说明数据为音视频片段时，服务器可以先基于其中的视频以及音频得到文字信息(如通过图像识别得到文字信息，以及通过语音识别得到文字信息)，在对该得到的文字信息进行语义分析，得到说明数据的语义。
子步骤3032、对用户数据进行语义分析，得到用户数据的语义。
服务器可以根据获取的用户数据，分析得到用户数据所包括的用户观看实时音视频的偏好。
子步骤3033、将说明数据的语义和用户数据的语义的相似度确定为说明数据与用户数据的关联程度。
可选地，可以通过分类体系计算词语语义距离的方法来判断说明数据的语义和用户数据的语义的相似度，该方法又称基于树的语义相似度研究方法，基于树的语义相似度计算的算法可以包括：利用一部语义词典计算相似度，语义词典是将所有的词组织在一棵或几棵树状的层次结构中一种基于认知语言学的词典。在一棵树状图中，任何两个结点之间有且只有一条路径，于是，这条路径的长度就可以作为这两个词语概念间语义距离的一种度量，距离越近，则相似度越高。
说明数据的语义和用户数据的语义的相似度越高，既可以说明用户对于实 时音视频数据的偏好与说明数据的重叠度较高，即可以表明实时音视频与用户数据的关联程度越高。
子步骤3034、确定实时音视频中，说明数据与用户数据的关联程度大于第一指定值的至少两个备选实时音视频。
该第一指定值可以和说明数据与用户数据的关联程度有关，示例性的，可以根据实时音视频的说明数据与用户数据的关联程度对多个实时音视频进行排序，将排名在第十名以后的确定为说明数据与用户数据的关联程度小于或等于第一指定值的备选实时音视频。
当实时音视频的说明数据与用户数据的关联程度小于或等于第一指定值时，可以说明该实时音视频不是用户感兴趣的实时音视频，可以被服务器去除，以便于接下来根据开启后的备选实时音视频再次进行关联程度的比对，可以更精准地筛选出符合用户需求的实时音视频，同时也能减少关联程度的比对时间，缓解服务器的压力。
步骤304、在至少两个备选实时音视频开启后，获取备选实时音视频的音视频数据。
在网络直播或网络会议开始之后，服务器可以从备选实时音视频所属的音视频服务器(例如直播平台的服务器，或者网络会议的服务器)上获取至少两个备选实时音视频的音视频数据，音视频数据可以包括视频数据以及音频数据，此外还可以包括图片数据以及文档数据等。
示例性的，备选实时音视频为在线会议，在线会议系统中，会议现场可采用录音、摄像头拍摄、PPT分享等形式获取实时音视频数据并上传至音视频服务器。
步骤305、基于至少两个备选实时音视频的音视频数据，获取备选实时音视频的内容数据。
该内容数据可以包括能够反映实时音视频的实际内容的数据，例如，该内容数据可以包括从实时音视频的视频图像中提取的文字数据，或者包括从实时音视频的声音数据转化的文字数据，文档数据包含的内容等。
示例性的，内容数据可以包括直播节目的弹幕内容，直播发布会的屏幕上显示的数据、在线会议现场的横幅的内容、在线会议的PPT的内容。
步骤306、获取至少两个备选实时音视频的内容数据与目标用户的用户数据的关联程度。
在本申请实施例示出的实时音视频推荐方法中，可以根据内容数据的语义与用户数据的语义的相似度确定其关联程度。
如图6所示，步骤306可以包括以下三个子步骤：
子步骤3061、对内容数据进行语义分析，得到内容数据的语义。
服务器可以对文字形式的内容数据进行语义分析，以得到内容数据的语义，语义分析的方式可以参考上述步骤3031，本申请实施例在此不再赘述。
子步骤3062、对目标用户数据进行语义分析，得到目标用户数据的语义。
服务器对筛选出来的目标用户的数据进行语义分析，可以得到正在用户界面观看备选实时音视频的目标用户的兴趣偏好。
子步骤3063、将内容数据的语义和目标用户数据的语义的相似度确定为内容数据与目标用户数据的关联程度。
内容数据的语义和目标用户数据的语义的相似度越高，即可以说明用户对于实时音视频数据的偏好与内容数据的重叠度越高，即可以表明备选实时音视频与目标用户数据的关联程度越高。
可以根据关联程度的高低对至少两个备选实时音视频做优先级排序，关联程度最高的为第一优先级，关联程度第二的为第二优先级，依次类推，对至少两个备选实时音视频进行排序。示例性的，可以根据关联程度的高低对至少两个网络直播做优先级排序，其中关联程度的范围为0～10，数字越大表示关联度越高，排序结果如表1所示：
表1 网络直播的优先级排序
| 网络直播名称 | 关联程度 | 优先级 |
| 网络直播A | 9.6 | 1 |
| 网络直播B | 9.3 | 2 |
| 网络直播C | 9.1 | 3 |
| 网络直播D | 8 | 4 |
| 网络直播E | 7.3 | 5 |
| 网络直播F | 6.9 | 6 |
其中，表1中示出了网络直播A～F的关联程度以及优先级排序，示例性的，网络直播E的关联程度为7.3，优先级为5。
步骤307、在用户界面展示至少两个备选实时音视频中，内容数据与目标用 户的用户数据的关联程度最高的目标备选实时音视频。
根据内容数据与目标用户的用户数据的关联程度的比对，可以在用户界面展示关联程度最高的目标备选实时音视频，即排序为第一优先级的目标备选实时音视频。
步骤308、获取至少两个备选实时音视频中的第一备选实时音视频的推荐信息。其中，第一备选实时音视频是至少两个备选实时音视频中除目标备选实时音视频外的其他备选实时音视频中，内容数据与用户数据的关联程度大于第二指定值的备选实时音视频。推荐信息包括图片、文字、小窗口视频画面中的一种或多种。
当除目标备选实时音视频外的第一备选实时音视频的内容数据与用户数据的关联程度大于第二指定值时，该第一备选实时音视频可以为用户较为感兴趣的实时音视频数据，此时，用户有可能会选择该第一备选实时音视频进行观看。
也可以获取至少两个备选实时音视频中，排序为第二优先级的备选实时音视频对应的推荐信息。
推荐信息可以包括视频截图，语音数据转换的文字，小窗口视频画面中的一种或多种。
步骤309、在用户界面展示推荐信息。
本申请实施例对关联程度最高的目标备选实时音视频和推荐信息的展示顺序不做限定，可以先展示关联程度最高的目标备选实时音视频，再展示推荐信息，也可以先展示推荐信息，再展示目标备选实时音视频，即可以在用户界面展示目标备选实时音视频的同时，在用户界面展示推荐信息。
示例性的，如图7所示，图7是本申请实施例提供的一种用户界面，用户界面的显示器122中展示了关联程度最高的目标备选实时音视频的展示框1221，同时在显示器122中显示推荐信息框1222，推荐信息框1222包含推荐信息，该推荐信息框1222小于关联程度最高的目标备选实时音视频的展示框1221。该推荐信息可以包括关联程度大于第二指定值的一个或者多个备选实时音视频对应的一个或者多个推荐信息，也可以包括排序为第二优先级的备选实时音视频对应的推荐信息。此时，用户可以在观看关联程度最高的目标备选实时音视频的同时，了解到关联程度较高的一个或者多个备选实时音频数据的推荐信息，用户在接下来的观看过程中可以选择继续观看关联程度最高的目标备选实时音视频，也可以根据推荐信息切换用户界面的展示框，如此可以使得用户在观看的 过程中有更多的选择，提高用户的使用体验。
步骤310、获取推荐信息对应的备选实时音视频的音频数据对应的文字数据。
服务器可以将实时音频数据中的音频数据转换为对应的文字数据。
推荐信息对应的备选实时音视频的音频数据与目标用户数据的关联度较高，用户对其的关注度可能也较高，获取对应的文字数据，可以在用户选择观看了其中一个备选实时音视频后，展示其余实时音视频数据的文字数据，以便于用户可以掌握较多的信息。
步骤311、在用户界面展示推荐信息对应的备选实时音视频或者文字数据。
步骤311的实施方式包括以下两种：
方式一、在获取对于推荐信息的操作后，在用户界面展示推荐信息对应的一个备选实时音视频。
在服务器获取了用于在展示界面对于推荐信息的操作后，即可以在用户界面展示推荐信息对应的一个备选实时音视频。该操作可以包括点击、长按或者滑动中的一种，若关联程度大于第二指定值的备选实时音视频包括一个备选实时音视频，则播放该视频；若关联程度大于第二指定值的备选实时音视频包括至少两个备选实时音视频，则播放用户的操作对应的其中一个备选实时音视频。
方式二、在指定时长未获取对于推荐信息的操作后，在用户界面展示文字数据。
指定时长可以为5秒～10秒。可以在5秒～10秒未获取对于推荐信息的操作后，在展示界面播放关联程度最高的目标备选实时音视频，同时在用户界面展示文字数据。
如图8所示，图8是本申请实施例提供的另一种用户界面，用户界面21可以包括在用户界面21展示的提示框211，提示框211中显示有文字数据，提示框211在用户界面21的尺寸小于用户界面21中展示的目标备选实时音视频212的尺寸，提示框211可以在目标备选实时音视频212的远离中心的一角，可以避免对目标备选实时音视频中的重要内容造成遮挡。
此外，显示界面还可以显示会议议题、参会人员信息等，同时用户可以利用电子桌牌进行文字或语音的输入来与本会议室及不同场次的参会者进行互动或者点击选择，可以实现用户与不同会场的参会者进行信息交流，进而可以提高用户体验效果。
可选地，如图9所示，上述实施例的步骤311之后，还可以包括下面几个 步骤：
步骤312、在接收到切换指令后，获取多个实时音视频的观看人数。
当用户对推荐的视频不感兴趣或者是无目的性的观看浏览时，服务器还可以根据实时音视频的观看人数对多个实时音视频进行筛选。
服务器接收到使用观看人数对实时音视频进行筛选的切换指令时，从音视频服务器获取多个实时音视频的观看人数。该指令可以在操作界面展示，以供用户操作，示例性的，该指令可以是用户界面的一个按钮控件，该按钮控件上可以包括“最热门直播”或者“当前热度最高”等内容。
步骤313、在用户界面展示多个实时音视频中，观看人数最多的实时音视频。
服务器根据多个实时音视频的观看人数，对多个实时音频数据进行排序，挑选出观看人数最多的实时音视频进行展示。
步骤314、在接收到用户输入数据后，获取多个备选实时音视频的内容数据与用户输入数据的关联程度。
当用户对推荐的视频不感兴趣时，还可以根据用户输入数据对多个实时音视频进行筛选。
用户输入数据可以包括用户根据想要观看的内容输入的关键字。
服务器可以对多个备选实时音视频的内容数据与用户输入数据进行语义分析，根据得到的语义信息，获取多个备选实时音视频的内容数据与用户输入数据的关联程度。
步骤315、在用户界面展示多个备选实时音视频中，内容数据与用户输入数据的关联程度最高的备选实时音视频。
如此便可以根据用户的意愿来展示实时音视频，以提高用户体验。
本申请实施例中，上述步骤312、步骤313、步骤314和步骤315的实施顺序不限定，即可以先实施步骤312和步骤313，再实施步骤314和步骤315，也可以先实施步骤314和步骤315，再实施步骤312和步骤313，或者只实施步骤312和步骤313，或者步只实施骤314和步骤315，当户用在观看筛选出的视频时，没有在展示界面做出切换指令操作或者输入数据操作，也可以不执行步骤312和步骤313或步骤314和步骤315。
综上所述，本申请实施例提供了一种实时音视频推荐方法，通过在用户观看实时音视频时，根据用户数据与实时音视频的说明数据关联程度对观看实时音视频进行一次筛选，再在开播后，根据用户数据与实时音视频的内容数据的 关联程度进行一次筛选，通过两次筛选，可以从大量的实时音视频中筛选出用户可能感兴趣的实时音视频，并向用户展示，如此保证了向用户展示的实时音视频与用户兴趣的匹配程度的基础上，提高了向用户展示的实时音视频的丰富程度，进而提高了实时音视频的推荐效果。
图10是本申请实施例提供的一种实时音视频推荐装置的结构框图，该实时音视频推荐装置1200包括：
说明数据获取模块1201，用于获取多个实时音视频的说明数据；
用户数据获取模块1202，用于获取用户数据；
确定模块1203，用于确定多个实时音视频中，说明数据与用户数据的关联程度大于第一指定值的至少一个备选实时音视频；
音视频数据获取模块1204，用于在至少一个备选实时音视频开启后，获取备选实时音视频的音视频数据；
内容数据获取模块1205，用于基于至少一个备选实时音视频的音视频数据，获取备选实时音视频的内容数据；
关联程度获取模块1206，用于获取至少一个备选实时音视频的内容数据与用户数据的关联程度；
第一展示模块1207，用于基于至少一个备选实时音视频的内容数据与用户数据的关联程度，在用户界面展示至少一个备选实时音视频中的目标备选实时音视频。
可选地，如图11所示，图11是本申请实施例提供的另一种实时音视频推荐装置的框图，该实时音视频推荐装置1200还包括：
推荐信息获取模块1208，用于获取至少两个备选实时音视频中的第一备选实时音视频的推荐信息，第一备选实时音视频是至少两个备选实时音视频中除目标备选实时音视频外的其他备选实时音视频中，内容数据与用户数据的关联程度大于第二指定值的备选实时音视频，推荐信息包括图片和文字中的一种或多种；
推荐信息展示模块1209，用于在用户界面展示推荐信息；
第二展示模块1210，用于在获取对于推荐信息的操作后，在用户界面展示推荐信息对应的备选实时音视频。
可选地，如图12所示，图13是本申请实施例提供的另一种实时音视频推 荐装置的框图，该实时音视频推荐装置还包括：
文字数据获取模块1211，用于获取推荐信息对应的备选实时音视频的音频数据对应的文字数据；
文字数据展示模块1212，用于在指定时长未获取对于推荐信息的操作后，在用户界面展示文字数据。
综上所述，本申请实施例提供的实时音视频推荐装置，通过用户数据与实时音视频的说明数据关联程度对观看实时音视频进行一次筛选，再在开播后，根据用户数据与实时音视频的内容数据的关联程度进行一次筛选，通过两次筛选，可以从大量的实时音视频中筛选出用户可能感兴趣的实时音视频，并向用户展示，如此保证了向用户展示的实时音视频与用户兴趣的匹配程度的基础上，提高了向用户展示的实时音视频的丰富程度，进而提高了实时音视频的推荐效果。
图13是本申请实施例提供的一种服务器的结构示意图。服务器1600包括中央处理单元(Central Processing Unit，CPU)1601、包括随机存取存储器(random access memory，RAM)1602和只读存储器(read only memory，ROM)1603的系统存储器1604，以及连接系统存储器1604和中央处理单元1601的系统总线1605。服务器1600还包括帮助计算机内的各个器件之间传输信息的基本输入/输出系统(I/O系统)1606，和用于存储操作系统1613、应用程序1614和其他程序模块1615的大容量存储设备1607。
基本输入/输出系统1606包括有用于显示信息的显示器1608和用于用户输入信息的诸如鼠标、键盘之类的输入设备1609。其中显示器1608和输入设备1609都通过连接到系统总线1605的输入输出控制器1610连接到中央处理单元1601。基本输入/输出系统1606还可以包括输入输出控制器1610以用于接收和处理来自键盘、鼠标、或电子触控笔等多个其他设备的输入。类似地，输入输出控制器1610还提供输出到显示屏、打印机或其他类型的输出设备。
大容量存储设备1607通过连接到系统总线1605的大容量存储控制器(未示出)连接到中央处理单元1601。大容量存储设备1607及其相关联的计算机可读介质为服务器1600提供非易失性存储。也就是说，大容量存储设备1607可以包括诸如硬盘或者只读光盘(Compact Disc Read-Only Memory，CD-ROM)驱动器之类的计算机可读介质(未示出)。
不失一般性，计算机非瞬态可读介质可以包括计算机存储介质和通信介质。计算机存储介质包括以用于存储诸如计算机可读指令、数据结构、程序模块或其他数据等信息的任何方法或技术实现的易失性和非易失性、可移动和不可移动介质。计算机存储介质包括RAM、ROM、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)、带电可擦可编程只读存储器(Electrically Erasable Programmable read only memory，EEPROM)、闪存或其他固态存储介质，CD-ROM、数字通用光盘(Digital Versatile Disc，DVD)或其他光学存储、磁带盒、磁带、磁盘存储或其他磁性存储设备。当然，本领域技术人员可知计算机存储介质不局限于上述几种。上述的系统存储器1604和大容量存储设备1607可以统称为存储器。
根据本申请的各种实施例，服务器1600还可以通过诸如因特网等网络连接到网络上的远程计算机运行。也即服务器1600可以通过连接在系统总线1605上的网络接口单元1611连接到网络1612，或者说，也可以使用网络接口单元1611来连接到其他类型的网络或远程计算机系统(未示出)。
存储器还包括一个或者一个以上的程序，一个或者一个以上程序存储于存储器中，中央处理单元1601通过执行该一个或一个以上程序来实现上述实施例提供的任意一种实时音视频推荐方法。
此外，本申请实施例还提供了一种实时音视频推荐设备，该实时音视频推荐设备包括处理器和存储器，存储器中存储有至少一条指令、至少一段程序、代码集或指令集，至少一条指令、至少一段程序、代码集或指令集由处理器加载并执行以实现上述实施例提供的任一的实时音视频推荐方法。
此外，本申请实施例还提供了一种计算机非瞬态存储介质，该计算机非瞬态存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，至少一条指令、至少一段程序、代码集或指令集由处理器加载并执行以实现上述实施例提供的任一的实时音视频推荐方法。
Claims (15)
- 一种实时音视频推荐方法，其特征在于，所述方法包括：获取多个实时音视频的说明数据；获取用户数据；确定所述多个实时音视频中，说明数据与所述用户数据的关联程度大于第一指定值的至少一个备选实时音视频；在至少一个所述备选实时音视频开启后，获取所述备选实时音视频的音视频数据；基于至少一个所述备选实时音视频的音视频数据，获取所述备选实时音视频的内容数据；获取至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度；基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频。
- 根据权利要求1所述的方法，其特征在于，所述备选实时音视频的数量为至少两个，所述获取所述备选实时音视频的内容数据与所述用户数据的关联程度之后，所述方法还包括：获取至少两个所述备选实时音视频中的第一备选实时音视频的推荐信息，所述第一备选实时音视频是所述至少两个备选实时音视频中除所述目标备选实时音视频外的其他备选实时音视频中，内容数据与所述用户数据的关联程度大于第二指定值的备选实时音视频，所述推荐信息包括图片和文字中的一种或多种；在所述用户界面展示所述推荐信息；在获取对于所述推荐信息的操作后，在所述用户界面展示所述推荐信息对应的备选实时音视频。
- 根据权利要求2所述的方法，其特征在于，在所述用户界面展示所述推荐信息之后，所述方法还包括：获取所述推荐信息对应的备选实时音视频的音频数据对应的文字数据；在指定时长未获取对于所述推荐信息的操作后，在所述用户界面展示所述 文字数据。
- 根据权利要求2所述的方法，其特征在于，所述在所述用户界面展示所述文字数据，包括：在所述用户界面展示提示框，所述提示框中显示有所述文字数据。
- 根据权利要求1所述的方法，其特征在于，所述获取用户数据，包括：确定观看所述用户界面的至少一个目标用户；获取所述至少一个目标用户的用户数据。
- 根据权利要求5所述的方法，其特征在于，所述用户数据包括至少一个用户的人脸数据；所述确定观看所述用户界面的至少一个目标用户，包括：获取具有至少一个用户的图像；对所述图像进行人脸识别，以确定观看所述用户界面的至少一个目标用户。
- 根据权利要求5所述的方法，其特征在于，所述获取所述至少一个目标用户的用户数据，包括：在用户数据库中包括所述至少一个目标用户的用户数据时，从所述用户数据库中获取所述至少一个目标用户的用户数据；或者，在所述用户数据库中不包括所述至少一个目标用户的用户数据时，获取输入信息；根据所述输入信息获取所述至少一个目标用户的用户数据。
- 根据权利要求1-7任一所述的方法，其特征在于，基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频之后，所述方法还包括：在接收到切换指令后，获取所述多个实时音视频的观看人数；在所述用户界面展示所述多个实时音视频中，观看人数最多的实时音视频。
- 根据权利要求1-7任一所述的方法，其特征在于，基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频之后，所述方法还包括：在接收到用户输入数据后，获取至少一个所述备选实时音视频的内容数据与所述用户输入数据的关联程度；在所述用户界面展示至少一个所述备选实时音视频中，内容数据与所述用户输入数据的关联程度最高的备选实时音视频。
- 根据权利要求1-7任一所述的方法，其特征在于，所述获取至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，包括：对所述内容数据进行语义分析，得到所述内容数据的语义；对所述用户数据进行语义分析，得到所述用户数据的语义；将所述内容数据的语义和所述用户数据的语义的相似度确定为所述内容数据与所述用户数据的关联程度。
- 根据权利要求1-7任一所述的方法，其特征在于，所述基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频，包括：在用户界面展示至少一个所述备选实时音视频中，内容数据与所述用户数据的关联程度最高的所述目标备选实时音视频。
- 一种实时音视频推荐装置，其特征在于，所述实时音视频推荐装置包括：说明数据获取模块，用于获取多个实时音视频的说明数据；用户数据获取模块，用于获取用户数据；确定模块，用于确定所述多个实时音视频中，说明数据与所述用户数据的关联程度大于第一指定值的至少一个备选实时音视频；音视频数据获取模块，用于在至少一个所述备选实时音视频开启后，获取所述备选实时音视频的音视频数据；内容数据获取模块，用于基于至少一个所述备选实时音视频的音视频数据，获取所述备选实时音视频的内容数据；关联程度获取模块，用于获取至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度；第一展示模块，用于基于至少一个所述备选实时音视频的内容数据与所述用户数据的关联程度，在用户界面展示至少一个所述备选实时音视频中的目标备选实时音视频。
- 根据权利要求12所述的实时音视频推荐装置，其特征在于，所述备选实时音视频的数量为至少两个；所述实时音视频推荐装置，还包括：推荐信息获取模块，用于获取至少两个所述备选实时音视频中的第一备选实时音视频的推荐信息，所述第一备选实时音视频是至少两个所述备选实时音视频中除所述目标备选实时音视频外的其他备选实时音视频中，内容数据与所述用户数据的关联程度大于第二指定值的备选实时音视频，所述推荐信息包括图片和文字中的一种或多种；推荐信息展示模块，用于在所述用户界面展示所述推荐信息；第二展示模块，用于在获取对于所述推荐信息的操作后，在所述用户界面展示所述推荐信息对应的备选实时音视频。
- 一种实时音视频推荐设备，其特征在于，所述实时音视频推荐设备包括处理器和存储器，所述存储器中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如权利要求1至11任一所述的实时音视频推荐方法。
- 一种计算机非瞬态存储介质，其特征在于，所述计算机非瞬态存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由处理器加载并执行以实现如权利要求1至11任一所述的实时音视频推荐方法。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2021/084114 WO2022204991A1 (zh) | 2021-03-30 | 2021-03-30 | 实时音视频推荐方法、装置、设备以及计算机存储介质 |
| US17/780,700 US20240163515A1 (en) | 2021-03-30 | 2021-03-30 | Method and device for recommending real-time audios and/or videos, and computer storage medium |
| CN202180000653.8A CN115486089B (zh) | 2021-03-30 | 2021-03-30 | 实时音视频推荐方法、装置、设备以及计算机存储介质 |
| EP21933672.4A EP4161085A4 (en) | 2021-03-30 | 2021-03-30 | REAL-TIME AUDIO/VIDEO CONTENT RECOMMENDATION METHOD AND APPARATUS, DEVICE, AND COMPUTER STORAGE MEDIUM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2021/084114 WO2022204991A1 (zh) | 2021-03-30 | 2021-03-30 | 实时音视频推荐方法、装置、设备以及计算机存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022204991A1 true WO2022204991A1 (zh) | 2022-10-06 |
Family
ID=83455424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/084114 WO2022204991A1 (zh) | 2021-03-30 | 2021-03-30 | 实时音视频推荐方法、装置、设备以及计算机存储介质 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20240163515A1 (zh) |
| EP (1) | EP4161085A4 (zh) |
| CN (1) | CN115486089B (zh) |
| WO (1) | WO2022204991A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115988238A (zh) * | 2022-12-19 | 2023-04-18 | 北京奇艺世纪科技有限公司 | 视频信息的显示方法、装置、系统、电子设备及存储介质 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120173502A1 (en) * | 2010-11-09 | 2012-07-05 | Harsha Prem Kumar | System and method for displaying, enabling exploration and discovery, recommending, and playing back media files based on user preferences |
| CN106658086A (zh) * | 2016-09-22 | 2017-05-10 | 广州华多网络科技有限公司 | 一种直播间切换方法及装置 |
| CN109379608A (zh) * | 2018-09-13 | 2019-02-22 | 武汉斗鱼网络科技有限公司 | 一种直播间的推荐方法以及相关设备 |
| CN109388693A (zh) * | 2018-09-13 | 2019-02-26 | 武汉斗鱼网络科技有限公司 | 一种确定分区意图的方法以及相关设备 |
| CN110267067A (zh) * | 2019-06-28 | 2019-09-20 | 广州酷狗计算机科技有限公司 | 直播间推荐的方法、装置、设备及存储介质 |
| CN111163076A (zh) * | 2019-12-25 | 2020-05-15 | 广州华多网络科技有限公司 | 网络直播的开播消息推送方法及相关设备 |
| CN111866528A (zh) * | 2020-04-30 | 2020-10-30 | 火币（广州）区块链科技有限公司 | 一种直播节目推送方法和可读存储介质 |
Family Cites Families (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6434747B1 (en) * | 2000-01-19 | 2002-08-13 | Individual Network, Inc. | Method and system for providing a customized media list |
| US20070255755A1 (en) * | 2006-05-01 | 2007-11-01 | Yahoo! Inc. | Video search engine using joint categorization of video clips and queries based on multiple modalities |
| US20090055373A1 (en) * | 2006-05-09 | 2009-02-26 | Irit Haviv-Segal | System and method for refining search terms |
| US8832742B2 (en) * | 2006-10-06 | 2014-09-09 | United Video Properties, Inc. | Systems and methods for acquiring, categorizing and delivering media in interactive media guidance applications |
| US8959108B2 (en) * | 2008-06-18 | 2015-02-17 | Zeitera, Llc | Distributed and tiered architecture for content search and content monitoring |
| US8364660B2 (en) * | 2008-07-11 | 2013-01-29 | Videosurf, Inc. | Apparatus and software system for and method of performing a visual-relevance-rank subsequent search |
| US8140550B2 (en) * | 2008-08-20 | 2012-03-20 | Satyam Computer Services Limited Of Mayfair Centre | System and method for bounded analysis of multimedia using multiple correlations |
| US8180766B2 (en) * | 2008-09-22 | 2012-05-15 | Microsoft Corporation | Bayesian video search reranking |
| US20130166303A1 (en) * | 2009-11-13 | 2013-06-27 | Adobe Systems Incorporated | Accessing media data using metadata repository |
| US8489589B2 (en) * | 2010-02-05 | 2013-07-16 | Microsoft Corporation | Visual search reranking |
| US8874584B1 (en) * | 2010-02-24 | 2014-10-28 | Hrl Laboratories, Llc | Hierarchical video search and recognition system |
| JP2011217209A (ja) * | 2010-03-31 | 2011-10-27 | Sony Corp | 電子機器、コンテンツ推薦方法及びプログラム |
| US20110320476A1 (en) * | 2010-06-28 | 2011-12-29 | Vizio, Inc. | Television-based search using metadata |
| US8543521B2 (en) * | 2011-03-30 | 2013-09-24 | Microsoft Corporation | Supervised re-ranking for visual search |
| US8260117B1 (en) * | 2011-07-26 | 2012-09-04 | Ooyala, Inc. | Automatically recommending content |
| CN103827856A (zh) * | 2011-09-27 | 2014-05-28 | 惠普发展公司，有限责任合伙企业 | 检索视觉媒体 |
| US9244924B2 (en) * | 2012-04-23 | 2016-01-26 | Sri International | Classification, search, and retrieval of complex video events |
| CN103631823B (zh) * | 2012-08-28 | 2017-01-18 | 腾讯科技（深圳）有限公司 | 一种媒体内容推荐方法及设备 |
| US9292622B2 (en) * | 2012-12-27 | 2016-03-22 | Google Inc. | Systems and methods for providing search suggestions |
| US9363155B1 (en) * | 2013-03-14 | 2016-06-07 | Cox Communications, Inc. | Automated audience recognition for targeted mixed-group content |
| CN103440335B (zh) * | 2013-09-06 | 2016-11-09 | 北京奇虎科技有限公司 | 视频推荐方法及装置 |
| US11275747B2 (en) * | 2015-03-12 | 2022-03-15 | Yahoo Assets Llc | System and method for improved server performance for a deep feature based coarse-to-fine fast search |
| US9940575B2 (en) * | 2015-06-04 | 2018-04-10 | Yahoo Holdings, Inc. | Image searching |
| CN106331778B (zh) * | 2015-07-06 | 2020-08-14 | 腾讯科技（深圳）有限公司 | 视频推荐方法和装置 |
| US9728229B2 (en) * | 2015-09-24 | 2017-08-08 | International Business Machines Corporation | Searching video content to fit a script |
| US9762943B2 (en) * | 2015-11-16 | 2017-09-12 | Telefonaktiebolaget Lm Ericsson | Techniques for generating and providing personalized dynamic live content feeds |
| US10616199B2 (en) * | 2015-12-01 | 2020-04-07 | Integem, Inc. | Methods and systems for personalized, interactive and intelligent searches |
| US10482146B2 (en) * | 2016-05-10 | 2019-11-19 | Massachusetts Institute Of Technology | Systems and methods for automatic customization of content filtering |
| US9836977B1 (en) * | 2016-06-07 | 2017-12-05 | Delphi Technologies, Inc. | Automated vehicle steering control system with lane position bias |
| US10803111B2 (en) * | 2017-11-27 | 2020-10-13 | Facebook, Inc. | Live video recommendation by an online system |
| US20210144418A1 (en) * | 2018-08-10 | 2021-05-13 | Microsoft Technology Licensing, Llc | Providing video recommendation |
| CN109246483B (zh) * | 2018-09-30 | 2021-06-15 | 武汉斗鱼网络科技有限公司 | 一种直播间推荐方法、装置、设备及存储介质 |
| CN111263229B (zh) * | 2018-11-30 | 2023-06-16 | 南京超聚通信科技有限公司 | 一种视频分发方法、装置及电子设备 |
| EP3690674A1 (en) * | 2019-02-01 | 2020-08-05 | Moodagent A/S | Method for recommending video content |
| EP3921783A1 (en) * | 2019-03-26 | 2021-12-15 | Huawei Technologies Co., Ltd. | Apparatus and method for hyperparameter optimization of a machine learning model in a federated learning system |
| US11500927B2 (en) * | 2019-10-03 | 2022-11-15 | Adobe Inc. | Adaptive search results for multimedia search queries |
| CN110830812B (zh) * | 2019-10-31 | 2021-11-30 | 广州市网星信息技术有限公司 | 相似主播分类模型训练方法、主播推荐方法及相关装置 |
| CN113761271A (zh) * | 2020-06-03 | 2021-12-07 | 青岛海高设计制造有限公司 | 用于视频推荐的方法及装置、带显示屏的冰箱 |
| CN112000820A (zh) * | 2020-08-10 | 2020-11-27 | 海信电子科技(武汉)有限公司 | 一种媒资推荐方法及显示设备 |
| KR20220141854A (ko) * | 2020-09-16 | 2022-10-20 | 구글 엘엘씨 | 디지털 비디오 분석 |
| CN112188295B (zh) * | 2020-09-29 | 2022-07-05 | 有半岛(北京)信息科技有限公司 | 一种视频推荐方法及装置 |
| US11727051B2 (en) * | 2020-11-19 | 2023-08-15 | Adobe Inc. | Personalized image recommendations for areas of interest |
| CN115278326A (zh) * | 2021-04-29 | 2022-11-01 | 腾讯科技（深圳）有限公司 | 视频展示方法、装置、计算机可读介质及电子设备 |
| JP7217902B1 (ja) * | 2022-02-22 | 2023-02-06 | １７Ｌｉｖｅ株式会社 | ストリーミングデータをレコメンドするためのシステム、方法、及びコンピュータ可読媒体 |
-
2021
- 2021-03-30 EP EP21933672.4A patent/EP4161085A4/en active Pending
- 2021-03-30 WO PCT/CN2021/084114 patent/WO2022204991A1/zh active Application Filing
- 2021-03-30 CN CN202180000653.8A patent/CN115486089B/zh active Active
- 2021-03-30 US US17/780,700 patent/US20240163515A1/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120173502A1 (en) * | 2010-11-09 | 2012-07-05 | Harsha Prem Kumar | System and method for displaying, enabling exploration and discovery, recommending, and playing back media files based on user preferences |
| CN106658086A (zh) * | 2016-09-22 | 2017-05-10 | 广州华多网络科技有限公司 | 一种直播间切换方法及装置 |
| CN109379608A (zh) * | 2018-09-13 | 2019-02-22 | 武汉斗鱼网络科技有限公司 | 一种直播间的推荐方法以及相关设备 |
| CN109388693A (zh) * | 2018-09-13 | 2019-02-26 | 武汉斗鱼网络科技有限公司 | 一种确定分区意图的方法以及相关设备 |
| CN110267067A (zh) * | 2019-06-28 | 2019-09-20 | 广州酷狗计算机科技有限公司 | 直播间推荐的方法、装置、设备及存储介质 |
| CN111163076A (zh) * | 2019-12-25 | 2020-05-15 | 广州华多网络科技有限公司 | 网络直播的开播消息推送方法及相关设备 |
| CN111866528A (zh) * | 2020-04-30 | 2020-10-30 | 火币（广州）区块链科技有限公司 | 一种直播节目推送方法和可读存储介质 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP4161085A4 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115988238A (zh) * | 2022-12-19 | 2023-04-18 | 北京奇艺世纪科技有限公司 | 视频信息的显示方法、装置、系统、电子设备及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115486089A (zh) | 2022-12-16 |
| EP4161085A4 (en) | 2023-11-01 |
| CN115486089B (zh) | 2024-10-15 |
| EP4161085A1 (en) | 2023-04-05 |
| US20240163515A1 (en) | 2024-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12079226B2 (en) | Approximate template matching for natural language queries | |
| US11797625B2 (en) | Displaying information related to spoken dialogue in content playing on a device | |
| US9838759B2 (en) | Displaying information related to content playing on a device | |
| JP5981024B2 (ja) | ソーシャルネットワーキングを介してテレビ番組およびビデオ番組を共有すること | |
| JP2018185841A (ja) | メディアアセットに関するコンテクスト上関係する情報を表示するための方法およびシステム | |
| US8583725B2 (en) | Social context for inter-media objects | |
| US10139917B1 (en) | Gesture-initiated actions in videoconferences | |
| CN111279709B (zh) | 提供视频推荐 | |
| US20150012840A1 (en) | Identification and Sharing of Selections within Streaming Content | |
| US20130227086A1 (en) | Systems and methods for data processing in conjunction with media presentations | |
| US9871606B1 (en) | Identification of concurrently broadcast time-based media | |
| US9946769B2 (en) | Displaying information related to spoken dialogue in content playing on a device | |
| Berg | Independent podcasts on the Apple Podcast platform in the streaming era | |
| WO2022204991A1 (zh) | 实时音视频推荐方法、装置、设备以及计算机存储介质 | |
| TW201403501A (zh) | 虛擬社群建立系統及方法 | |
| CN112073757B (zh) | 情绪波动指数获取方法、显示方法及多媒体内容制作方法 | |
| WO2015051996A1 (en) | Association of a social message with a related multimedia flow | |
| JP5800391B2 (ja) | 放送プログラム選別方法、装置およびシステム | |
| EP3742364B1 (en) | Displaying information related to content playing on a device | |
| TWI538491B (zh) | 電視服務系統與提供影音服務的方法 | |
| KR20200079741A (ko) | 개인화 서비스를 제공하는 단말, 방법 및 컴퓨터 프로그램 | |
| US12126878B2 (en) | Displaying information related to content playing on a device | |
| CA3187486A1 (en) | Methods and apparatuses for preventing spoilers in autocompleted search queries | |
| CN116781949A (zh) | 一种口才演讲直播的推荐方法、系统、设备及存储介质 | |
| CN115757870A (zh) | 一种信息确定、信息提供方法、装置及电子设备 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WWE | Wipo information: entry into national phase |
Ref document number: 17780700 Country of ref document: US |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21933672 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2021933672 Country of ref document: EP Effective date: 20221228 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |