CN114095749B - Recommendation and live interface display method, computer storage medium and program product - Google Patents
Recommendation and live interface display method, computer storage medium and program product Download PDFInfo
- Publication number
- CN114095749B CN114095749B CN202210057911.2A CN202210057911A CN114095749B CN 114095749 B CN114095749 B CN 114095749B CN 202210057911 A CN202210057911 A CN 202210057911A CN 114095749 B CN114095749 B CN 114095749B
- Authority
- CN
- China
- Prior art keywords
- live broadcast
- content
- live
- audience
- materials
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
-
- 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
-
- 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
- H04N21/454—Content or additional data filtering, e.g. blocking advertisements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
-
- 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
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
-
- 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
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Abstract
The embodiment of the application provides a real-time personalized information recommendation method suitable for a live broadcast room, a live broadcast interface display method, a computer storage medium and a program product. The real-time personalized information recommendation method suitable for the live broadcast room comprises the following steps: acquiring real-time explanation contents of a main broadcast of a live broadcast room in a preset time period, wherein the explanation contents comprise voice, characters or images; analyzing the intention of the explanation content to obtain a live broadcast intention corresponding to a preset time period; obtaining a plurality of candidate recommended materials matched with the live broadcast intention from a live broadcast content library pre-stored with a plurality of live broadcast materials; acquiring user preference information of a plurality of audience users in a live broadcast room in a preset time period; aiming at each audience user, respectively selecting matched recommended materials from a plurality of candidate recommended materials according to corresponding user preference information; and respectively displaying the matched recommended materials in a preset area of a display interface of the live broadcast room aiming at each audience user.
Description
Technical Field
The embodiment of the application relates to the technical field of live broadcast, in particular to a real-time personalized information recommendation method suitable for a live broadcast room, a live broadcast interface display method, a computer storage medium and a program product.
Background
With the rise of live broadcast applications, more and more transactions are performed by means of live broadcast, such as information promotion or commodity selling by means of live broadcast. In the current live broadcast, the relationship between the anchor of the live broadcast room and the audience users is 1 to N, that is, the same anchor can only explain the same content to different audience users in the same time period.
However, the viewer user's appeal may not be the same for the same time slot into the live room. For example, in an e-commerce scenario, some audience users want to know the material and material of a commodity, some audience users want to know the functional efficacy of the commodity, some audience users want to know the preferential activity of the commodity, and the like, for the commodity to be sold. However, in the existing live broadcast scheme, regardless of the appeal of the audience users, the same content explanation or explanation is carried out on the audience users by the anchor broadcast, and the scheme only can help the audience users to know the commodities, but cannot solve the problem that the appeal of different audience users is different. Similar problems exist in other live scenes.
Disclosure of Invention
In view of the above, embodiments of the present application provide a proposed solution to at least partially solve the above problems.
According to a first aspect of the embodiments of the present application, a method for recommending personalized information in real time in a live broadcast room is provided, including: acquiring real-time explanation contents of a main broadcast of a live broadcast room in a preset time period, wherein the explanation contents comprise voice, characters or images; analyzing the intention of the explanation content to obtain a live broadcast intention corresponding to the preset time period; obtaining a plurality of candidate recommended materials matched with the live broadcast intention from a live broadcast content library pre-stored with a plurality of live broadcast materials; acquiring user preference information of a plurality of audience users in the live broadcast room in the preset time period; aiming at each audience user, respectively selecting matched recommended materials from the candidate recommended materials according to corresponding user preference information; and respectively displaying the matched recommended materials in a preset area of a display interface of the live broadcast room aiming at each audience user.
According to a second aspect of the embodiments of the present application, a live interface display method is provided, including: after detecting that a plurality of audience users enter a live broadcasting room, displaying a live broadcasting interface to the plurality of audience users; displaying information of current explanation content of a main broadcast of the live broadcast room in a first area of the live broadcast interface, and displaying different recommendation information aiming at different audience users in a second area of the live broadcast interface; the information of the explained content and the recommended information are different content information meeting preset content similarity.
According to a third aspect of embodiments of the present application, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method as described above.
According to a fourth aspect of embodiments of the present application, there is provided a computer program product comprising computer instructions for instructing a computing device to perform operations corresponding to the method as described above.
According to the recommendation scheme provided by the embodiment of the application, the real-time explanation content of the anchor in the live broadcast room in the preset time period is obtained and analyzed, the intention of the explanation content is obtained and corresponds to the live broadcast intention in the preset time period, so that the live broadcast intention in the preset time period can be obtained according to the live broadcast intention in the preset time period, a plurality of candidate recommendation materials matched with the live broadcast intention are obtained from a live broadcast content library pre-stored with a plurality of live broadcast materials, the plurality of candidate recommendation materials are correlated with the live broadcast intention of the anchor in the preset time period, and the subsequent acquisition is carried out in the preset time period, the user preference information of a plurality of audience users in the live broadcast room is obtained and is directed to each of the audience users, and the matched recommendation materials are selected and displayed according to the corresponding user preference information. Because the recommended material is selected from the candidate recommended materials, the recommended material is related to the live broadcast intention in the preset time period, and different recommended materials are recommended for different audience users based on the recommended material and in combination with user preference information of different audience users, and because the recommended material comprehensively considers the factors of two aspects of the content being explained by the main broadcast and the preference of the user, the recommended material displayed in the live broadcast of different audience users can effectively meet the personalized appeal of the user, and the audience users can be helped to better know the content explained by the main broadcast; and the recommended material can be complemented with the main broadcasting explanation content, so that the information known by audience users is more comprehensive.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a schematic diagram of a live broadcast system to which an embodiment of the present application is applied;
fig. 2A is a flowchart illustrating steps of a real-time personalized information recommendation method applied to a live broadcast room according to an embodiment of the present application;
FIG. 2B is a diagram illustrating an example of a scenario in the embodiment shown in FIG. 2A;
fig. 3A is a flowchart illustrating steps of a real-time personalized information recommendation method applied to a live broadcast room according to an embodiment of the present application;
FIG. 3B is a diagram illustrating an example of a scenario in the embodiment shown in FIG. 3A;
fig. 4A is a flowchart illustrating steps of a real-time personalized information recommendation method applied to a live broadcast room according to an embodiment of the present application;
FIG. 4B is a schematic illustration of an interface in the embodiment of FIG. 4A;
FIG. 4C is a schematic view of another interface in the embodiment of FIG. 4A;
FIG. 5 is a flowchart illustrating steps of a method for displaying a live interface according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application shall fall within the scope of the protection of the embodiments in the present application.
The following further describes specific implementations of embodiments of the present application with reference to the drawings of the embodiments of the present application.
Example one
Fig. 1 illustrates an exemplary system to which the method for recommending personalized information in real time in a live broadcast room according to the embodiment of the present application is applied. As shown in fig. 1, the system 100 may include a server 102, a communication network 104, and/or one or more user devices 106, illustrated in fig. 1 as a plurality of user devices.
In some embodiments, the communication network 104 may be any suitable combination of one or more wired and/or wireless networks. For example, the communication network 104 can include any one or more of the following: the network may include, but is not limited to, the internet, an intranet, a Wide Area Network (WAN), a Local Area Network (LAN), a wireless network, a Digital Subscriber Line (DSL) network, a frame relay network, an Asynchronous Transfer Mode (ATM) network, a Virtual Private Network (VPN), and/or any other suitable communication network. The user device 106 can be connected to the communication network 104 by one or more communication links (e.g., communication link 112), and the communication network 104 can be linked to the server 102 via one or more communication links (e.g., communication link 114). The communication link may be any communication link suitable for communicating data between the user device 106 and the server 102, such as a network link, a dial-up link, a wireless link, a hardwired link, any other suitable communication link, or any suitable combination of such links.
Although server 102 is illustrated as one device, in some embodiments, any suitable number of devices may be used to perform the functions performed by server 102. For example, in some embodiments, multiple devices may be used to implement the functions performed by the server 102. Alternatively, the functionality of the server 102 may be implemented using a cloud service.
Based on the system, the embodiment of the application provides a real-time personalized information recommendation method suitable for a live broadcast room, and the following description is given by a plurality of embodiments.
Example two
Referring to fig. 2A, a schematic flow diagram of a method for recommending personalized information in real time in a live broadcast room provided in the embodiment of the present application is shown, and as shown in the figure, the method includes:
s201, acquiring real-time explanation content of a main broadcast of a live broadcast room in a preset time period, wherein the explanation content comprises voice, characters or images.
In this embodiment, the anchor may be a live anchor or a virtual anchor, which is not limited in this embodiment.
The content of the main broadcast during the preset time period may be the real-time content of the main broadcast during a preset short time period before and/or after the current time point. The preset time period may be determined according to a broadcast segment of the anchor, for example, according to a time when the anchor broadcasts a current object (for example, a current commodity, a current news, and the like), or the preset time period may also be a preset fixed time period, and the like, which is not limited in this embodiment.
The lecture content of the main broadcast may include, but is not limited to, various content broadcast forms such as news broadcast, event broadcast, program broadcast, commodity broadcast, and the like, and may specifically adopt a form of a part or all of voice, text, images, and the like.
For convenience of subsequent processing, if the content of the explanation is Speech, the Speech may be converted into words by an ASR (Automatic Speech Recognition) technique, and then the subsequent processing is performed.
And S202, analyzing the intention of the explanation content to obtain the live intention corresponding to the preset time period.
In this embodiment, the specific interpretation content may be analyzed by means of intent analysis, such as: and performing intention analysis through key information included in the explanation content, performing intention analysis on the explanation content through a trained machine learning model, and the like.
Through intention analysis of the explanation content, live intention corresponding to real-time explanation content in a preset time period can be obtained, on the basis, recommended content and anchor explanation content can be supplemented with each other when recommendation is carried out subsequently by combining user preference information, and the recommended content can better serve audience users by referring to the content being explained by the anchor in the recommendation process. Illustratively, the live intent may be, for example: a point of sale of the goods that the viewer-user is expected to know, a news story that the viewer-user is expected to know, science popularization knowledge, and the like.
S203, obtaining a plurality of candidate recommended materials matched with the live broadcast intention from a live broadcast content library pre-stored with a plurality of live broadcast materials.
Live broadcast materials in the live broadcast content library are pre-stored materials, and when candidate recommended materials matched with the live broadcast intention are obtained, the live broadcast materials can be realized by technical personnel in the field in a flexible mode according to actual requirements, such as label matching, semantic matching and the like, and the embodiment does not limit the materials.
By obtaining a plurality of candidate recommended materials matched with the live broadcast intention, the relevance of the materials recommended to the user and the real-time explanation content is ensured.
And S204, acquiring user preference information of a plurality of audience users in the live broadcast room in the preset time period.
It should be noted that step S204 may be executed in parallel with steps S201 to S203, or may be executed before or after steps S201 to S203 or at any time during the execution, which is not limited in this embodiment.
The user preference information may be obtained from a history of the user, preference settings of the user, user information, and the like. The user preference information may characterize the user's preferences for determining material that meets the user's preferences from among a plurality of candidate recommended material.
S205, aiming at each audience user, respectively selecting matched recommended materials from the candidate recommended materials according to the corresponding user preference information.
If the user preference information of different audience users is different, the selected recommended materials are also different for different audience users. When the recommended material is selected from the candidate recommended materials according to the corresponding preference information, a machine learning model with matching degree according to the user preference information and the live broadcast material output after training can be adopted, but the method is not limited to the form, and other modes such as label matching and semantic matching are also applicable.
As described above, the recommended material determined by combining the live intention corresponding to the lecture content of the anchor and the user preference information can make the recommended content and the content of the lecture of the anchor complement each other, and make the recommended content better serve audience users by referring to the content being lectured by the anchor when recommending.
And S206, aiming at each audience user, respectively displaying the matched recommended materials in a preset area of a display interface of the live broadcast room.
After selecting the matched recommended material from the candidate recommended materials for each audience user, the recommended material matched with the audience user can be displayed in a preset area of a live broadcast room watched by the audience user. The recommended materials displayed to different audience users are different, so that the individual requirements of the audience users are effectively met.
Referring to fig. 2B, a schematic view of a scenario of an embodiment of the present application is shown.
As shown in the figure, according to the current explanation content in the preset time period of the live broadcast room, the live broadcast intention corresponding to the preset time period can be obtained. For example, the intention recognition is performed based on the current explanation content within one minute, and the live intention within one minute can be obtained as the introduction of the article X.
According to the live broadcast intention, candidate recommended materials matched with the live broadcast intention can be obtained from a live broadcast content library in which various live broadcast materials are prestored, for example, multiple candidate recommended materials matched with the commodity characteristics of the commodity X can be obtained, and the candidate recommended materials can be respectively the material of the commodity X, the using method of the commodity X, and the like.
When a plurality of audience users exist in the live broadcast room, user preference information corresponding to the audience users can be obtained, corresponding recommended materials are selected for the audience users from the candidate recommended materials according to the user preference information, and the matched materials are displayed on a display interface of the live broadcast room of the audience users.
For example, based on the candidate recommended material corresponding to the commodity X, the recommended material selected by combining the preference information of the audience user a is related to the material of the commodity X; the recommended material selected by combining the preference information of the audience user B is related to the using method of the commodity X; the recommended material selected according to the preference information of the viewer user C is related to the preference information of the commodity X. Referring to fig. 2B, the recommended materials matched with each other may be displayed in the preset areas of the display interfaces in the live rooms of the audience users a, B, and C, respectively.
According to the technical scheme, the real-time explanation content of the anchor broadcast in the live broadcast room in the preset time period is obtained and is subjected to intention analysis, the corresponding live broadcast intention in the preset time period is obtained, so that the live broadcast intention in the preset time period can be obtained, a plurality of candidate recommended materials matched with the live broadcast intention can be obtained from a live broadcast content library pre-stored with a plurality of live broadcast materials, and the relevance is realized between the candidate recommended materials and the live broadcast intention of the anchor broadcast in the preset time period. And subsequently acquiring user preference information of a plurality of audience users in the live broadcast room in the preset time period, and respectively selecting and displaying matched recommended materials from the candidate recommended materials according to the corresponding user preference information for each audience user. Because the recommended material is selected from the candidate recommended materials, the recommended material is related to the live broadcast intention in the preset time period, and different recommended materials are recommended for different audience users based on the fact that the recommended material is combined with the user preference information of different audience users. Because the recommended material comprehensively considers the factors of the content being explained by the main broadcast and the preference of the user, the recommended material displayed by the live broadcast rooms of different audience users can effectively meet the personalized appeal of the user and help the audience users to better know the content explained by the main broadcast; and the recommended material can be complemented with the main broadcasting explanation content, so that the information known by audience users is more comprehensive.
EXAMPLE III
Referring to fig. 3A, a schematic flow chart of a method for recommending personalized information in real time in a live broadcast room according to an embodiment of the present application is shown, and as shown in the drawing, the method includes:
s301, acquiring real-time explanation content of a main broadcast in a live broadcast room in a preset time period.
The specific implementation manner of this step can refer to the above embodiments, and is not described herein again.
S302, intention analysis of a first granularity is carried out on the explanation content, and a first intention analysis result is obtained.
And S303, performing intention analysis of a second granularity on the explanation content based on the first intention analysis result to obtain a second intention analysis result.
S304, determining the live broadcast intention corresponding to the preset time period according to the second intention analysis result.
Wherein the first granularity has a lower analysis accuracy than the second granularity.
In this embodiment, by combining the intent analysis of the first granularity and the intent analysis of the second granularity, and the analysis precision of the first granularity is lower than that of the second granularity, the intent analysis of the coarse and fine levels is realized, and the accuracy of the obtained live broadcast intent can be improved. For example, for the case where the content of the explanation is text or text converted from speech, the first granularity of intent analysis may be paragraph or sentence based granularity analysis and the second granularity of intent analysis may be word based granularity analysis. For the case where the instructional content is an image, the first granularity of intent analysis can be an analysis of the image content and the second granularity of intent analysis can be an analysis of key information in the image content. In one possible approach, the intent analysis for textual content may employ a text input based machine learning model, and the analysis for images may employ an image input based machine learning model. However, the present invention is not limited to this, and the text and the image may be analyzed simultaneously using a machine learning model based on multi-modal data input. In the embodiment of the present application, the specific implementation forms of various machine learning models and the training and processing processes thereof can be implemented by referring to the related technologies, and only corresponding functions need to be provided, which is not limited in the embodiment of the present application.
It should be noted that, in other implementations of the embodiments of the present application, one of the above-mentioned intent analysis of the first granularity and the intent analysis of the second granularity may be performed to obtain the live intent, which is also within the scope of the present application.
Optionally, in this embodiment, step S303 includes: analyzing the intention of the content type of the explanation content to obtain the live content type; correspondingly, step S304 includes: and performing keyword analysis on the explanation content based on the type of the live content to obtain live content keywords.
The corresponding live key points of different live content types are different, so the corresponding keywords may also be different. On the contrary, different keywords can further enhance the type of the live content to a certain extent. In this embodiment, the live content type is obtained through intention analysis, and then keyword analysis is performed based on the live content type, so that accuracy of the obtained live content keywords can be improved, and accuracy of the live intention of the preset time period determined according to the live content keywords can be improved.
For example, the type of the live content obtained through the intention analysis may be a commodity introduction, a science popularization explanation, or a news report, and then the keyword analysis based on the type of the live content may obtain that the live content keyword may correspond to a moisturizing or cost performance ratio (corresponding to the commodity introduction), a water safety notice (corresponding to the science popularization explanation), a swimming game prize winning result (corresponding to the news report), and the like.
In this embodiment, the live content keyword obtained through the intention analysis with the second granularity may be directly used as the live intention of the preset time period, or the live intention of the preset time period may be determined by determining a tag corresponding to the obtained live content keyword based on the obtained live content keyword, and so on.
Optionally, in this embodiment of the application, the performing keyword analysis on the explanation content based on the type of the live content to obtain the keywords of the live content includes: and performing keyword analysis on the explanation content according to the preset corresponding relation between the type of the live broadcast content and a preset keyword set to obtain the keywords of the live broadcast content. Different live content types can correspond to different live content keywords, for example, if the live content type is live telecast, the obtained live content keywords can be live content keywords of commodities sold by an e-commerce; if the type of the live content is a sports event, the obtained keywords of the live content can be related to the champion of the event, the time of the event and the like.
In one possible approach, step S303 may include: determining a knowledge graph or nodes in a knowledge graph corresponding to the first intent analysis result; performing intention analysis of a second granularity on the explanation content according to the node information in the knowledge graph; or performing intention analysis of a second granularity on the explanation content according to the information of the lower node of the node in the knowledge graph.
In one implementation manner, different intention analysis results may correspond to different knowledge maps, for example, the first intention analysis result is taken as an example of a commodity introduction and a science popularization explanation, the commodity introduction corresponds to a commodity knowledge map, and the science popularization explanation corresponds to a science popularization knowledge map. Then, in this way, after the first intention analysis result is obtained, the corresponding knowledge graph can be determined, and the intention analysis of the second granularity is performed based on the node information in the knowledge graph. In another implementation, there may be a large, comprehensive knowledge-graph, which includes graph nodes corresponding to commodity introductions, and the nodes further include a plurality of child nodes, i.e., subordinate nodes; the knowledge graph also comprises graph nodes corresponding to science popularization explanation, and a plurality of lower nodes are also arranged below the nodes. In this way, after the first intention analysis result is obtained, the node in the knowledge graph corresponding to the first intention analysis result may be determined, information of the node and its lower nodes may be obtained, and intention analysis of the explanation content at the second granularity may be performed based on the information. By positioning the knowledge graph or the knowledge graph node corresponding to the first intention analysis result, intention analysis of the second granularity can be realized based on the existing knowledge content in the knowledge graph, and the accuracy of the intention analysis of the second granularity is greatly improved.
In another possible manner, the performing intent analysis on the explanation content at a second granularity based on the first intent analysis result includes: inputting the first intention analysis result and the explanation content into a machine learning model trained in advance, and performing intention analysis of a second granularity on the explanation content through the machine learning model.
In this embodiment, the machine learning model may be any model capable of performing intent analysis, such as a classification model, and this embodiment is not limited thereto. The machine learning model is obtained through training of a large amount of sample data, richer information can be obtained, accurate analysis can be carried out based on the obtained information, and the analysis result is more objective and accurate.
S305, obtaining a plurality of candidate recommended materials matched with the live broadcast intention from a live broadcast content library pre-stored with a plurality of live broadcast materials.
The live content library may be pre-stored with a variety of live materials, such as audio materials, video materials, text materials, image materials, etc., or a certain material may be a combination of some or all of text, image, audio, or video. When candidate recommended material matching the live intent is obtained from the live content library, the obtained plurality of candidate recommended material may also include at least one of the following types: audio material, video material, text material, image material.
When the live content library comprises various live materials, different live materials can be obtained in different modes, and the live materials can be obtained in at least one of the following modes: acquiring historical live broadcast content materials of the live broadcast room, acquiring live broadcast content materials pushed by a live broadcast platform where the live broadcast room is located, and acquiring webpage materials related to current live broadcast content; and storing the obtained live broadcast material into a live broadcast content library. Therefore, the richness and comprehensiveness of the live broadcast materials can be guaranteed.
The method comprises the steps of obtaining historical live broadcast content materials of a live broadcast room, specifically obtaining historical live broadcast videos, historical live broadcast voices or images used for introduction in the historical live broadcast of the live broadcast room as live broadcast materials. The method comprises the steps of obtaining live broadcast content materials pushed by a live broadcast platform where a live broadcast room is located, and specifically, the live broadcast content materials pushed by other live broadcast rooms through the live broadcast platform, live broadcast activities pushed by the live broadcast platform, live broadcast platform pushed hot content and the like. The method comprises the steps of obtaining webpage materials related to current live content, specifically webpage materials such as a selling webpage, an official website and an encyclopedia website corresponding to the current live content.
S306, acquiring user preference information of a plurality of audience users in the live broadcast room in the preset time period.
It should be noted that step S306 may be executed in parallel with steps S301 to S305, or may be executed before or after or at any time during steps S301 to S305, which is not limited in this embodiment.
Optionally, in any embodiment of the present application, the user preference information of the viewer user is determined according to at least one of the following information: attribute information of the audience users, historical browsing behavior information of the audience users, and real-time live broadcast room behavior information of the audience users. By this information, the preferences of the viewer user can be efficiently characterized.
The attribute information of the audience user may represent basic characteristics of the audience user, for example, the attribute information may represent the gender, age, occupation, membership, and the like of the audience user; the historical browsing behavior information of the audience user can represent the behavior characteristics of the audience user in the live broadcasting process, for example, the historical browsing behavior information of the audience user in the current live broadcasting room or other live broadcasting rooms (such as commodity browsing behavior, news browsing behavior, content program browsing behavior, and the like), or the historical browsing behavior information of the audience user in a website or platform related to the live broadcasting platform; the audience user's real-time live room behavior information may be the audience user's real-time live room behavior information in the current live room, including but not limited to: interactive behavior, browsing behavior, commenting behavior, clicking behavior, etc. .
S307, aiming at each audience user, respectively selecting matched recommended materials from the candidate recommended materials according to the corresponding user preference information.
In this embodiment, when the candidate recommended material includes multiple types (for example, includes any two or all of text, voice, image, and video), step S307 may include: aiming at various live broadcast material types corresponding to a plurality of candidate recommended materials, determining a machine learning model which is matched with each material type and is used for screening the live broadcast materials; for each viewer user, recommending live broadcast materials for each candidate in each live broadcast material type, and taking the live broadcast materials and the acquired user preference information of the viewer user as input data; inputting the input data into a machine learning model matched with the material type; and selecting live broadcast candidate recommended materials matched with the user preference information from the candidate recommended live broadcast materials as recommended materials based on the matching degree according to the matching degree of the candidate recommended live broadcast materials output by the machine learning model and the user preference information of the audience users.
Specifically, the candidate recommended materials may be divided into multiple groups according to the types of the candidate recommended materials, each group corresponds to one type of candidate recommended materials, and each group may include one or more candidate recommended materials; and then, determining a machine learning model corresponding to each group of candidate recommended materials, inputting the group of candidate recommended materials and user preference information of the audience user into the machine learning model corresponding to the candidate recommended materials as input data, and outputting the matching degree of the candidate recommended materials and the user preference information of the audience user through the machine learning model. Optionally, multiple machine learning models may be integrated into one ranking model, and an output layer of the ranking model may rank according to matching degrees of multiple candidate recommended materials with the audience users and output the recommended materials.
After the matching degree of the candidate recommended materials and the user preference information is determined, the candidate recommended materials with higher matching degree with the audience users can be selected from the candidate recommended materials; the number of the selected candidate recommended materials may be one or more (two or more), which is not limited in this embodiment.
In addition, the audience user may perform an interactive operation on the displayed recommended material, so optionally, the recommendation method in the embodiment of the present application may further include: receiving the interactive operation of the audience user on the displayed recommended material; adjusting the user preference information according to the interaction operation; and according to the adjusted user preference information, re-selecting matched recommended materials from the candidate recommended materials. Therefore, according to the recommendation scheme provided by the embodiment of the application, the user preference information of the audience users can be adjusted in time according to the interaction operation of the audience users for the recommended materials, and then the recommended materials recommended to the audience users are adjusted, so that the recommended materials displayed to the audience users in the live broadcast room can meet the new preference and requirements of the audience users in time.
For example, in this embodiment, the interaction operation of the audience user for the recommended material may be classified into a positive operation or a negative operation, the positive operation may be, for example, the audience user triggers the recommended material to view, and the like, and the negative operation may be, for example, the audience user switches or closes the recommended material, and the like. Exemplarily, if a forward operation of the viewer user is received, the preference degree corresponding to the recommendation element currently shown to the viewer user may be increased; if negative operation of the audience user is received, the preference degree of the recommendation elements currently displayed to the audience user can be reduced.
And S308, aiming at each audience user, respectively displaying the matched recommended materials in a preset area of a display interface of the live broadcast room.
Because the recommended materials corresponding to different audience users are different, the recommended materials matched with the different audience users can be respectively displayed in the preset area of the display interface of the live broadcast room. The preset area can be flexibly set by a person skilled in the art according to actual requirements, such as being disposed in an edge area of a live broadcast interface, or being displayed on the preset area through a floating layer or a pop-up window, and the like
Referring to fig. 3B, a scene schematic diagram provided in the embodiment of the present application is shown, and as shown in fig. 3B, the scene schematic diagram includes:
after the explanation content of the anchor is obtained within the preset time period, the intention analysis of the content type of the explanation content can be performed, and the live broadcast content type corresponding to the anchor is determined, which can be, for example, a commodity introduction, a news broadcast, a science popularization explanation, or the like, as shown in fig. 3B.
And then, performing keyword analysis based on the type of the live content and the explanation content to obtain a live content keyword, which may be water retention and moisture supplement (corresponding to commodity introduction), chinese cash capture (corresponding to news report), or winter olympic conference (corresponding to science popularization explanation), referring to fig. 3B.
After the live broadcast content keywords are obtained, a plurality of candidate recommended materials matched with the live broadcast intentions can be obtained from a live broadcast content library pre-stored with a plurality of live broadcast materials according to the live broadcast content keywords. Illustratively, as shown in fig. 3B, 100 candidate recommended materials may be obtained.
In addition, personalized features of the audience users (i.e., user preference information) can be obtained according to user preference information of a plurality of audience users currently existing in the live broadcast room. Referring to fig. 3B, the personalized features of the audience users may be determined according to attribute information of the audience users, historical browsing behavior information of the audience users, real-time live broadcast room behavior information of the audience users, and the like.
After the individual personalized features of the multiple audience users are determined, the candidate recommended materials and the personalized features of the audience users can be input into the sorting model, the multiple candidate recommended materials are sorted according to the personalized features through the sorting model, the recommended materials displayed to the multiple audience users are determined from the candidate recommended materials according to the sorting result, the personalized features of different audience users are different, and the determined recommended materials are different.
The real-time personalized information recommendation method applicable to the live broadcast room of the embodiment may be executed by any suitable electronic device with data processing capability, including but not limited to: server, mobile terminal (such as mobile phone, PAD, etc.), PC, etc.
The scheme provided by the embodiment of the application is that the real-time explanation content of the anchor broadcast in the live broadcast room in the preset time period is obtained and is right, the intention analysis is carried out on the explanation content, the correspondence is obtained, the live broadcast intention in the preset time period is obtained, so that the live broadcast intention in the preset time period can be based on the live broadcast intention of the preset time period, a plurality of candidate recommendation materials matched with the live broadcast intention are obtained from a live broadcast content library pre-stored with various live broadcast materials, the relevance is realized between the candidate recommendation materials and the live broadcast intention of the anchor broadcast in the preset time period, the follow-up acquisition is carried out in the preset time period, the user preference information of a plurality of audience users in the live broadcast room is obtained, and each audience user preference information is respectively selected according to the corresponding user preference information to select the matched recommendation materials in the candidate recommendation materials and display. Because the recommended material is selected from the candidate recommended materials, the recommended material is related to the live broadcast intention in the preset time period, and different recommended materials are recommended for different audience users based on the recommended material and in combination with user preference information of different audience users, and because the recommended material comprehensively considers the factors of two aspects of the content being explained by the main broadcast and the preference of the user, the recommended material displayed in the live broadcast of different audience users can effectively meet the personalized appeal of the user, and the audience users can be helped to better know the content explained by the main broadcast; and the recommended material can be complemented with the main broadcasting explanation content, so that the information known by audience users is more comprehensive.
Example four
Referring to fig. 4A, a schematic flow chart of a real-time personalized information recommendation method applicable to a live broadcast room provided in the embodiment of the present application is shown. In this embodiment, the recommendation method in the embodiment of the present application is described with emphasis on presentation of recommended materials, as shown in fig. 4A, the recommendation method includes:
s401, acquiring real-time explanation content of a main broadcast in a live broadcast room in a preset time period.
S402, analyzing the intention of the explanation content to obtain the live broadcast intention corresponding to the preset time period.
And S403, obtaining a plurality of candidate recommended materials matched with the live broadcast intention from a live broadcast content library pre-stored with a plurality of live broadcast materials.
S404, acquiring user preference information of a plurality of audience users in the live broadcast room in the preset time period.
S405, aiming at each audience user, respectively selecting matched recommended materials from the candidate recommended materials according to corresponding user preference information.
In the embodiment of the present application, the specific implementation manner of steps S401 to S405 may refer to the description of the relevant parts in the above embodiment, and is not described herein again.
S406, aiming at each audience user, displaying the information of the current explanation content of the main broadcast in a first area of a display interface of the live broadcast room, and displaying matched recommended materials in a second area of the display interface.
Referring to fig. 4B, a schematic view of a live interface in the embodiment of the present application is shown, as shown in the figure, a main is displayed in the middle of the interface, a first area is arranged on the upper portion of the interface and used for displaying the content being explained by the main, and a second area is arranged on the lower portion of the interface and used for displaying the recommended material. In the live broadcast interfaces corresponding to different audience users, the recommended materials displayed in the second area are different.
Optionally, in this embodiment of the application, if the recommended material includes a plurality of recommended materials, the displaying the matched recommended material in the second area of the display interface includes: and displaying a plurality of the recommended materials in turn in a second area of the display interface according to a preset time interval.
For example, referring to fig. 4C, the left and right sides of the second area show a plurality of recommended materials for presentation, and arrows in the interface are used for presenting the presentation order of the recommended materials. The display sequence of the recommended materials can be determined according to the matching degree of the recommended materials and audience users, the display sequence with high matching degree is in front, and the displayed recommended materials can be updated according to the preset time interval after the display sequence with low matching degree is in back. The specific setting of the time interval is determined by those skilled in the art according to actual needs, and is not limited in the embodiment of the present application.
In addition, as shown in fig. 4C, text content and goods and the like may also be displayed in the interface, and the text content may be comments input by the viewer user or prompt information of a live broadcast; the upper right corner of the interface can also show an offer entrance with an offer activity. Therefore, in an optional mode, the display interface may further include an interaction area (such as a comment area, a preferential entry area, a prompt information viewing area, and the like) for the audience user to perform interaction input in a live broadcast process; based on this, the recommendation method according to the embodiment of the present application further includes: and aiming at each audience user, acquiring the interactive input operation of the audience user in the interactive area, and updating the user preference information of the audience user according to the interactive input operation. Therefore, the recommendation materials which meet the requirements of the audience users better can be provided for the audience users on the basis of more accurate user preference information.
For example, as shown in the figure, the interaction area may be a third area below the second area, the third area may include a trigger option, and the trigger option may specifically be an image (an image corresponding to the article 1, the article 2, the article 3, and the article 4) corresponding to the real-time explanation content of the anchor user, so that the interaction input operation of the audience user in the interaction area may trigger a trigger operation of a certain trigger option for the audience user.
According to the scheme provided by the embodiment, the recommended materials are displayed in the second area of the live interface, the user preference information of the audience can be updated according to the interactive input operation of the user aiming at the interactive area, and the displayed recommended materials are further updated, so that the recommended materials can better accord with the preference of the audience user.
EXAMPLE five
Referring to fig. 5, a flow diagram of a live interface display method provided in the embodiment of the present application is shown, and as shown in the drawing, the method includes:
s501, after detecting that a plurality of audience users enter a live broadcast room, displaying live broadcast interfaces for the plurality of audience users.
In this embodiment, a plurality of viewers may enter the live broadcast room at the same time or at different times, which is not limited in this embodiment.
S502, displaying information of the current explanation content of the main broadcasting of the live broadcasting room in a first area of the live broadcasting interface, and displaying different recommendation information aiming at different audience users in a second area of the live broadcasting interface.
The information of the explanation content and the recommendation information are different content information meeting the preset content similarity, so that the explanation content information is complementary with the recommendation information, the audience user can better know the related content of the anchor explanation through a live interface, the recommendation information is complementary with the anchor explanation content, and the information known by the audience user is more comprehensive.
The live interface displayed to the viewer user may be as shown in fig. 4B and 4C, which are not described herein again.
In this embodiment, the displayed explanation content information may be explanation content information corresponding to real-time explanation content in a preset time period in the above embodiment; the recommendation information may be the recommended material determined by the above-described embodiment.
Optionally, in this embodiment of the application, the recommendation information is determined according to an intention analysis result of the current explanation content and the user preference information of the audience user. Specifically, with reference to the above embodiment, the intention analysis may be performed on the current explanation content to obtain a live broadcast intention, and a plurality of candidate recommended materials matched with the live broadcast intention may be obtained from a live broadcast content library in which a plurality of live broadcast materials are prestored according to the live broadcast intention; and determining recommended materials serving as recommendation information from the candidate recommended materials based on the user preference information. For a specific implementation method, reference may be made to the foregoing embodiments, which are not described in detail herein.
Optionally, in this embodiment, the intention analysis result includes: a live content type and/or a live content keyword; the user preference information is determined by at least one of: attribute information of the audience users, historical browsing behavior information of the audience users, and real-time live broadcast room behavior information of the audience users.
Optionally, in this embodiment, the method further includes: displaying an interactive area for the audience user to perform interactive input in a live broadcast process in the live broadcast interface; and acquiring the interactive input operation of the audience user in the interactive area, sending the information of the interactive input operation to a server so that the server processes the interactive input operation, and updating the user preference information of the audience user according to the interactive input operation.
In this embodiment, the description of the relevant steps is relatively simple, and the specific implementation of each step may refer to the description of the relevant parts in the foregoing embodiments.
Through the embodiment, the problem that in a traditional live broadcast mode, the relationship between the anchor and the audience users in a live broadcast room is 1 to N, and the anchor cannot meet the requirements of all the audience users at the same time can be effectively avoided. Through the scheme of the embodiment, different recommendation information can be provided for different users according to the preference of the users, and the users can be helped to better know the related content of the main broadcasting explanation. In addition, when recommending information, the user preference is combined, and the content explained by the main broadcast is combined, so that the recommended information can be complemented with the explained content of the main broadcast, and the information known by audience users is more comprehensive.
Example six
Referring to fig. 6, a schematic structural diagram of an electronic device according to a sixth embodiment of the present application is shown, and the specific embodiment of the present application does not limit a specific implementation of the electronic device.
As shown in fig. 6, the electronic device may include: a processor (processor) 602, a communication Interface 604, a memory 606, and a communication bus 608.
The processor 602, communication interface 604, and memory 606 communicate with one another via a communication bus 608.
A communication interface 604 for communicating with other electronic devices or servers.
The processor 602 is configured to execute the program 610, and may specifically execute the relevant steps in the above embodiment of the method for recommending real-time personalized information in a live broadcast room.
In particular, program 610 may include program code comprising computer operating instructions.
The processor 602 may be a CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application. The intelligent device comprises one or more processors which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
The memory 606 stores a program 610. Memory 606 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 610 may be specifically configured to enable the processor 602 to execute operations corresponding to the method described in any of the foregoing embodiments
The specific implementation of each step in the program 610 may refer to the corresponding description in the corresponding step and unit in the embodiment of the real-time personalized information recommendation method applicable to the live broadcast room or the display method of the live broadcast interface, and has a corresponding beneficial effect, which is not described herein again. It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.
The embodiment of the application also provides a computer program product, which comprises a computer instruction, and the computer instruction instructs a computing device to execute any one of the above methods for recommending the real-time personalized information in the live broadcast room or the operation corresponding to the display method of the live broadcast interface.
It should be noted that, according to implementation needs, each component/step described in the embodiment of the present application may be divided into more components/steps, and two or more components/steps or partial operations of the components/steps may also be combined into a new component/step to achieve the purpose of the embodiment of the present application.
The above-described methods according to embodiments of the present application may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, a RAM, a floppy disk, a hard disk, or a magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the methods described herein may be stored in such software processes on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware such as an ASIC or FPGA. It will be appreciated that a computer, processor, microprocessor controller, or programmable hardware includes memory components (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by a computer, processor, or hardware, implements the methods described herein. Further, when a general-purpose computer accesses code for implementing the methods illustrated herein, execution of the code transforms the general-purpose computer into a special-purpose computer for performing the methods illustrated herein.
Those of ordinary skill in the art will appreciate that the various illustrative elements and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.
The above embodiments are only used for illustrating the embodiments of the present application, and not for limiting the embodiments of the present application, and those skilled in the relevant art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application, so that all equivalent technical solutions also belong to the scope of the embodiments of the present application, and the scope of patent protection of the embodiments of the present application should be defined by the claims.
Claims (11)
1. A real-time personalized information recommendation method suitable for a live broadcast room comprises the following steps:
acquiring real-time explanation contents of a main broadcast of a live broadcast room in a preset time period, wherein the explanation contents comprise voice, characters or images;
analyzing the intention of the explanation content to obtain the live broadcast intention of the anchor corresponding to the preset time period, wherein the method comprises the following steps: performing intention analysis of content types on the explanation contents to obtain live broadcast content types; performing keyword analysis on the explanation content based on the live content type to obtain live content keywords;
obtaining a plurality of candidate recommended materials matched with the live intention of the anchor from a live content library prestored with a plurality of live materials;
acquiring different user preference information of a plurality of audience users in the live broadcast room in the preset time period;
aiming at each audience user, respectively selecting matched recommended materials from the candidate recommended materials according to corresponding user preference information;
and respectively displaying the matched recommended materials in a preset area of a display interface of the live broadcast room aiming at each audience user.
2. The method of claim 1, wherein the performing keyword analysis on the explanation content based on the live content type to obtain live content keywords comprises:
and performing keyword analysis on the explanation content according to the preset corresponding relation between the type of the live content and a preset keyword set to obtain the keywords of the live content.
3. The method of any of claims 1-2, wherein the plurality of candidate recommended materials includes at least one of the following types: audio material, video material, text material, image material, the method also includes:
acquiring live material by at least one of: acquiring historical live broadcast content materials of the live broadcast room, acquiring live broadcast content materials pushed by a live broadcast platform where the live broadcast room is located, and acquiring webpage materials related to current live broadcast content;
and storing the obtained live broadcast material into a live broadcast content library.
4. The method of any of claims 1-2, wherein the user preference information of the viewer user is determined based on at least one of: attribute information of the audience users, historical browsing behavior information of the audience users and real-time live broadcast room behavior information of the audience users.
5. The method according to any one of claims 1-2, wherein the method further comprises:
receiving the interactive operation of the audience user on the displayed recommended material;
adjusting the user preference information according to the interaction operation;
and selecting matched recommended materials from the candidate recommended materials again according to the adjusted user preference information.
6. The method as claimed in any one of claims 1-2, wherein said separately presenting, for each of said viewer users, the matched recommended material in a predetermined area of a presentation interface of said live broadcast room comprises:
and aiming at each audience user, displaying the information of the current explanation content of the main broadcast in a first area of a display interface of the live broadcast room, and displaying matched recommended materials in a second area of the display interface.
7. The method of claim 6, wherein,
if the recommended material includes a plurality of recommended materials, the displaying the matched recommended material in the second area of the display interface includes: displaying a plurality of recommended materials in turn in a second area of the display interface according to a preset time interval;
the display interface also comprises an interaction area for the audience user to perform interaction input in the live broadcasting process;
the method further comprises the following steps:
and aiming at each audience user, acquiring the interactive input operation of the audience user in the interactive area, and updating the user preference information of the audience user according to the interactive input operation.
8. A live interface display method comprises the following steps:
after detecting that a plurality of audience users enter a live broadcast room, displaying a live broadcast interface to the plurality of audience users;
displaying information of current explanation content of a main broadcast of the live broadcast room in a first area of the live broadcast interface, and displaying different recommendation information aiming at different audience users in a second area of the live broadcast interface;
the information of the explained content and the recommended information are different content information meeting preset content similarity;
wherein the recommendation information is determined according to an intention analysis result of the current lecture content of the anchor and the user preference information of the audience user; the intention analysis result of the currently explained content of the anchor is determined by the following means: performing intention analysis of content types on the current explanation content to obtain live broadcast content types; and performing keyword analysis on the current explanation content based on the live content type to obtain live content keywords.
9. The method of claim 8, wherein,
the user preference information is determined by at least one of: attribute information of the audience users, historical browsing behavior information of the audience users and real-time live broadcast room behavior information of the audience users.
10. The method according to any one of claims 8-9, wherein the method further comprises:
displaying an interactive area for the audience user to perform interactive input in a live broadcast process in the live broadcast interface;
and acquiring the interactive input operation of the audience user in the interactive area, and sending the information of the interactive input operation to a server so that the server processes the interactive input operation and updates the user preference information of the audience user according to the interactive input operation.
11. A computer storage medium having stored thereon a computer program which, when executed by a processor, carries out the method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210057911.2A CN114095749B (en) | 2022-01-19 | 2022-01-19 | Recommendation and live interface display method, computer storage medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210057911.2A CN114095749B (en) | 2022-01-19 | 2022-01-19 | Recommendation and live interface display method, computer storage medium and program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114095749A CN114095749A (en) | 2022-02-25 |
| CN114095749B true CN114095749B (en) | 2022-12-06 |
Family
ID=80308585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210057911.2A Active CN114095749B (en) | 2022-01-19 | 2022-01-19 | Recommendation and live interface display method, computer storage medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114095749B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114547475B (en) * | 2022-04-27 | 2022-07-26 | 中信建投证券股份有限公司 | Resource recommendation method, device and system |
| CN116108262A (en) * | 2022-11-16 | 2023-05-12 | 上海视九信息科技有限公司 | Live broadcast information recommendation method and device, electronic equipment and storage medium |
| CN115720279B (en) * | 2022-11-18 | 2023-09-15 | 杭州面朝信息科技有限公司 | Method and device for showing arbitrary special effects in live broadcast scene |
| CN117135379B (en) * | 2023-10-26 | 2023-12-22 | 武汉耳东信息科技有限公司 | Live broadcast platform data analysis management system based on big data |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4144001B2 (en) * | 2003-05-20 | 2008-09-03 | 日本電信電話株式会社 | MULTIMEDIA CONTENT DISTRIBUTION METHOD, DISTRIBUTION DEVICE, DISTRIBUTION PROGRAM, AND DISTRIBUTION PROGRAM STORAGE MEDIUM |
| CN105100840A (en) * | 2015-07-28 | 2015-11-25 | 上海聚力传媒技术有限公司 | Method and device for inter-cut of recommended media information |
| CN107844586B (en) * | 2017-11-16 | 2022-05-06 | 百度在线网络技术（北京）有限公司 | News recommendation method and device |
| CN110099283A (en) * | 2019-05-09 | 2019-08-06 | 广州虎牙信息科技有限公司 | Information-pushing method, device, equipment and storage medium |
| CN110636325B (en) * | 2019-10-25 | 2023-03-24 | 网易（杭州）网络有限公司 | Method and device for sharing push information on live broadcast platform and storage medium |
| CN110996110B (en) * | 2019-12-02 | 2022-02-18 | 深圳市云积分科技有限公司 | Commodity adjusting method and device in live broadcast process |
| CN111327930A (en) * | 2020-02-28 | 2020-06-23 | 北京达佳互联信息技术有限公司 | Method and device for acquiring target object, electronic equipment and storage medium |
| CN113536098A (en) * | 2020-04-15 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
| CN113781144A (en) * | 2020-11-06 | 2021-12-10 | 北京京东振世信息技术有限公司 | Live shopping order generation method and device, electronic equipment and computer medium |
| CN112348649B (en) * | 2020-12-07 | 2022-07-29 | 福州灵和晞科技有限公司 | Live broadcast category recommendation method |
| CN112637629B (en) * | 2020-12-25 | 2023-06-20 | 百度在线网络技术（北京）有限公司 | Live content recommendation method and device, electronic equipment and medium |
| CN113784156A (en) * | 2021-08-20 | 2021-12-10 | 广州繁星互娱信息科技有限公司 | Live broadcast method and device, electronic equipment and storage medium |
| CN113727136B (en) * | 2021-09-30 | 2023-06-13 | 广州方硅信息技术有限公司 | Live broadcast pushing method, system, device, equipment and storage medium |
-
2022
- 2022-01-19 CN CN202210057911.2A patent/CN114095749B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于语义和用户偏好的网络电视直播推荐方法;张翔等;《微电子学与计算机》;20161205(第12期);全文 * |
| 网络直播平台:内容与资本的较量;陈洁;《视听界》;20161230;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114095749A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114095749B (en) | Recommendation and live interface display method, computer storage medium and program product | |
| CN111143610B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| US9342584B2 (en) | Server apparatus, information terminal, and program | |
| US9020824B1 (en) | Using natural language processing to generate dynamic content | |
| CN111818370B (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| US20170169040A1 (en) | Method and electronic device for recommending video | |
| CN111274442B (en) | Method for determining video tag, server and storage medium | |
| CN113079417B (en) | Method, device and equipment for generating bullet screen and storage medium | |
| CN106201246A (en) | Page layout processing method and processing device | |
| CN114339285B (en) | Knowledge point processing method, video processing method, device and electronic equipment | |
| CN112230838A (en) | Article processing method, article processing device, article processing equipment and computer readable storage medium | |
| CN107454454A (en) | Method for information display and device | |
| CN111597446B (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
| CN108197336B (en) | Video searching method and device | |
| CN114430490A (en) | Live question and answer and interface display method and computer storage medium | |
| CN113742567A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN111046292A (en) | Live broadcast recommendation method and device, computer-readable storage medium and electronic device | |
| CN114707502A (en) | Virtual space processing method and device, electronic equipment and computer storage medium | |
| CN112073757B (en) | Emotion fluctuation index acquisition method, emotion fluctuation index display method and multimedia content production method | |
| CN111104583A (en) | Live broadcast room recommendation method, storage medium, electronic device and system | |
| CN110797013A (en) | Live broadcast entrance display method of voice live broadcast room, related equipment and storage medium | |
| CN110889034A (en) | Data analysis method and data analysis system | |
| CN112073738B (en) | Information processing method and device | |
| CN111885139B (en) | Content sharing method, device and system, mobile terminal and server | |
| CN113626638A (en) | Short video recommendation processing method and device, intelligent terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 554, 5 / F, building 3, 969 Wenyi West Road, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: Room 508, 5 / F, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: Alibaba (China) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |