Data processing method, apparatus, device, and medium

Abstract

The embodiment of the application provides a data processing method, device and equipment and medium, the method comprises the following steps: in the theme information page corresponding to the first concerned theme, the interaction control of the intelligent body object is displayed; in response to the trigger operation for the interaction control, the dialogue page of the intelligent body object is displayed, the dialogue page comprises a first display area, and the first display area is used for displaying first live information associated with the first concerned theme; in response to the information viewing operation for the first display area, live service data is output in the virtual service space indicated by the first live information. The embodiment of the application can improve the efficiency of obtaining live information.

Description

Technical Field

[0001] This application relates to the field of computer network technology, and in particular to a data processing method, apparatus, device, and medium. Background Technology

[0002] In an era of rapid digital information development, news applications are exhibiting unprecedented diversity. Live streaming, as a highly attractive and real-time form of information dissemination, has gained widespread popularity.

[0003] Current news apps can feature live streaming channels where various types of live streams can be categorized, such as entertainment, news, education, and e-commerce. Users wanting to watch live streams within these apps must navigate to the live streaming channel and manually sift through a large number of streams to find those that match their interests. However, this process is cumbersome, and the sheer volume of live streams makes it difficult for users to quickly and accurately identify their preferred content, resulting in low efficiency in accessing live streaming information. Summary of the Invention

[0004] This application provides a data processing method, apparatus, device, and medium that can improve the efficiency of acquiring live broadcast information.

[0005] One embodiment of this application provides a data processing method, including:

[0006] On the topic information page corresponding to the first topic of interest, the interactive controls for the intelligent agent object are displayed;

[0007] In response to a trigger operation on an interactive control, a dialogue page of the intelligent agent object is displayed, which includes a first display area for displaying first live information associated with a first topic of interest;

[0008] In response to an information viewing operation targeting the first display area, output live streaming business data in the virtual service space indicated by the first live streaming information.

[0009] One embodiment of this application provides a data processing apparatus, including:

[0010] The first display module is used to display the interactive controls of the intelligent agent object on the topic information page corresponding to the first topic of interest;

[0011] The second display module is used to respond to the trigger operation of the interactive control and display the dialogue page of the intelligent agent object. The dialogue page includes a first display area, which is used to display the first live broadcast information associated with the first topic of interest.

[0012] The playback module is used to respond to information viewing operations in the first display area and output live broadcast business data in the virtual service space indicated by the first live broadcast information.

[0013] The first display module is also used to perform the following steps:

[0014] In response to the launch operation of the news application, the news application's information feed display page is displayed. The information feed display page includes a follow topic area, which displays M follow topics, where M is a positive integer.

[0015] In response to the first selection operation for the area of ​​interest, the topic selected by the first selection operation is designated as the first topic of interest, and the topic information page corresponding to the first topic of interest is displayed.

[0016] The first selection operation includes swiping and clicking.

[0017] When the first display module responds to a first selection operation on a region of interest and designates the selected region as the first topic of interest, it specifically performs the following steps:

[0018] In response to a swipe gesture targeting the area of ​​followed topics, update the displayed followed topics in the area of ​​followed topics based on the swipe speed indicated by the gesture.

[0019] In response to a click operation on a topic within the topic area, the topic identified by the click operation is designated as the first topic of interest.

[0020] Specifically, when the first display module displays the interactive controls of the intelligent agent object on the topic information page corresponding to the first topic of interest, it is used to perform the following steps:

[0021] On the topic information page corresponding to the first topic of interest, a list of event information related to the first topic of interest is displayed;

[0022] Get the first feedback data for each event in the event information list, and determine the second feedback data for the first topic of concern based on the first feedback data for each event.

[0023] Obtain the traffic data and topic type of the first topic of interest, and determine the first popularity parameter value of the first topic of interest based on the second feedback data, traffic data, and topic type.

[0024] If the first popularity parameter value is greater than the parameter threshold, the interactive controls of the intelligent agent object will be displayed on the topic information page.

[0025] Specifically, when the first display module determines the first popularity parameter value of the first topic of interest based on the second feedback data, traffic data, and topic type, it performs the following steps:

[0026] Obtain the topic popularity reference table, and based on the topic popularity reference table, map the second feedback data to feedback parameter values, map the traffic data to traffic parameter values, and map the topic type to type parameter values;

[0027] The first popularity parameter value of the first topic of interest is obtained by summing the feedback parameter value, the traffic parameter value, and the type parameter value.

[0028] The chat page also includes a second display area:

[0029] The data processing device also includes:

[0030] The information query module is used to generate a topic summary text for the first topic of concern based on the event information list corresponding to the first topic of concern, and to determine the event information list and topic summary text as the first information information for the first topic of concern.

[0031] This information query module is also used to obtain the first live broadcast information related to the first topic of interest, display the first live broadcast information in the first display area, and display the first news information in the second display area.

[0032] Specifically, when the information query module generates a topic summary text for the first topic of interest based on the event information list corresponding to the first topic of interest, it performs the following steps:

[0033] Obtain the list of event information corresponding to the first topic of interest, concatenate the text content of each event information in the event information list to obtain the initial text data of the first topic of interest, remove invalid characters from the initial text data to obtain candidate text data;

[0034] The candidate text data is converted into a text embedding representation, and features are extracted from the text embedding representation to obtain the text semantic feature sequence of the candidate text data.

[0035] The text semantic feature sequence is decoded to obtain the character probability distribution of each text semantic feature in the text semantic feature sequence, and the topic summary text of the first topic of interest is generated based on the character probability distribution.

[0036] When the information query module retrieves the first live broadcast information related to the first topic of interest, it specifically performs the following steps:

[0037] Obtain a candidate live stream data set, retrieve candidate live stream data a from the candidate live stream data set, perform semantic analysis on candidate live stream data a and each event information in the event information list, and obtain the correlation between candidate live stream data a and each event information;

[0038] If there is an event in the event information list whose correlation with candidate live data a is greater than the correlation threshold, then candidate live data a is identified as the first live information associated with the first topic of interest.

[0039] The first live stream information includes K live stream data points, where K is an integer greater than 1;

[0040] The data processing device also includes:

[0041] The live preview module is used to display broadcast prompts and expand controls in the first display area. The broadcast prompts include the amount of live data associated with the first topic of interest.

[0042] The live preview module is also used to respond to the trigger operation of the expand control and display the live preview screen corresponding to each of the K live data in the first display area according to the arrangement order of the K live data.

[0043] Specifically, when the playback module responds to information viewing operations in the first display area and outputs live streaming service data in the virtual service space indicated by the first live streaming information, it performs the following steps:

[0044] In response to an information viewing operation targeting the first display area, the live data determined by the information viewing operation is identified as the target live data.

[0045] Determine the business application to which the virtual service space indicated by the target live data belongs, and output the live business data in the virtual service space of the business application.

[0046] Specifically, when the playback module determines the business application to which the virtual service space indicated by the target live data belongs, and outputs the live service data in the virtual service space of the business application, it performs the following steps:

[0047] Based on the target live streaming data, determine the business application to which the virtual service space corresponding to the target live streaming data belongs;

[0048] If the business application is the information application to which the intelligent agent object belongs, then access the virtual service space in the information application and output the live business data in the virtual service space.

[0049] If the business application is not the information application to which the intelligent agent object belongs, then jump from the information application to the business application, access the virtual service space in the business application, and output the live business data in the virtual service space.

[0050] The data processing device also includes:

[0051] The live streaming sorting module is used to obtain the live streaming indicator information indicated by each of the K live streaming data points, and determine the second popularity parameter value corresponding to each live streaming data point based on the live streaming indicator information indicated by each live streaming data point.

[0052] The live streaming sorting module is also used to sort the second popularity parameter value corresponding to each live streaming data in descending order to determine the sorting order of K live streaming data. The sorting order is used to determine the display position of K live streaming data in the first display area.

[0053] The dialogue page also includes interactive input boxes;

[0054] The data processing device also includes:

[0055] The live update module is used to respond to input operations in the interactive input box. In the second display area of ​​the dialog page, it displays the input content determined by the input operation, as well as the second information associated with the input content.

[0056] The live stream update module is also used to update the first live stream information to a second live stream information associated with the input content in the first display area of ​​the chat page.

[0057] The data processing device also includes:

[0058] The semantic analysis module is used to obtain the input content in the interactive input box, perform semantic analysis on the input content, and obtain the semantic features of the input content.

[0059] The semantic analysis module is also used to determine a second topic of interest that matches the semantic features of the content in the information application to which the intelligent agent object belongs, and to obtain second information information of the second topic of interest. The second information information is used to display in the second display area of ​​the dialogue page.

[0060] The semantic analysis module is also used to perform semantic analysis on each candidate live stream data in the candidate live stream data set for the second topic of interest, and to determine the second live stream information associated with the second topic of interest.

[0061] The interactive controls include an interactive overlay, which is displayed independently on the topic information page and includes a term area.

[0062] The data processing device also includes:

[0063] The term carousel module is used to rotate N event terms related to the most relevant topic in the term area of ​​the interactive overlay, where N is a positive integer.

[0064] The second display module responds to the trigger operation of the interactive control and displays the dialogue page of the intelligent agent object. When the first display area and the first information of the first topic of interest are displayed on the dialogue page, it is specifically used to perform the following steps:

[0065] In response to a trigger operation targeting a term area, the event term displayed in the term area is identified as the target term, and the dialogue page of the intelligent agent object is displayed. The dialogue page includes a first display area and a second display area.

[0066] The first live broadcast information associated with the target term is displayed in the first display area, and the first news information of the target term is displayed in the second display area.

[0067] One aspect of this application provides a computer device, including a memory and a processor. The memory is connected to the processor, the memory is used to store a computer program, and the processor is used to call the computer program so that the computer device executes the method provided in one aspect of this application.

[0068] One aspect of this application provides a computer-readable storage medium storing a computer program adapted to be loaded and executed by a processor, so that a computer device having a processor performs the method provided in one aspect of this application.

[0069] According to one aspect of this application, a computer program product is provided, which may include a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and executes the computer program, causing the computer device to perform the method provided in the above aspect.

[0070] In this embodiment, an interactive control for an intelligent agent object can be displayed on the topic information page corresponding to the first topic of interest. Triggering this interactive control displays a dialogue page for the intelligent agent object. This dialogue page may include a first display area, which can be used to display first live stream information associated with the first topic of interest. By triggering the first live stream information in the first display area, users can quickly enter the virtual service space indicated by the first live stream information to view live stream data. By associating event information of the topic of interest with the current live stream information, live stream information of interest to the user can be quickly obtained, improving the efficiency of obtaining live stream information. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a schematic diagram of a network architecture provided in an embodiment of this application;

[0073] Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Figure 1 ;

[0074] Figure 3 This is a schematic diagram of a topic information page provided in an embodiment of this application;

[0075] Figure 4a This is a schematic diagram of the interface of an interactive control for an intelligent agent object provided in an embodiment of this application. Figure 1 ;

[0076] Figure 4b This is a schematic diagram of the interface of an interactive control for an intelligent agent object provided in an embodiment of this application. Figure 2 ;

[0077] Figure 5 This application provides an embodiment of a dialog page for a smart agent object. Figure 1 ;

[0078] Figure 6 This is a schematic diagram of a dialog page for an intelligent agent object provided in an embodiment of this application. Figure 2 ;

[0079] Figure 7 This is a schematic diagram of an interface for updating the topic of interest in a dialog page of an intelligent agent object, provided in an embodiment of this application.

[0080] Figure 8 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Figure 2 ;

[0081] Figure 9 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0082] Figure 10 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0083] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0084] Please see Figure 1 , Figure 1 This is a schematic diagram of a network architecture provided in an embodiment of this application; the network architecture may include a server 10d and a terminal cluster, and the terminal cluster may include one or more terminal devices, without limiting the number of terminal devices included in the terminal cluster. Figure 1 As shown, the terminal cluster may specifically include terminal device 10a, terminal device 10b, and terminal device 10c, etc.; all terminal devices in the terminal cluster (for example, may include terminal device 10a, terminal device 10b, and terminal device 10c, etc.) can be connected to server 10d via the network so that each terminal device can interact with server 10d through the network connection.

[0085] in, Figure 1 The terminal devices in the terminal cluster shown may include, but are not limited to: smartphones, tablets, laptops, PDAs, desktop computers, wearable devices (such as smartwatches, smart bracelets, etc.), smart voice interaction devices, smart home appliances (such as smart TVs, etc.), in-vehicle devices, aircraft, and other electronic devices. This application does not limit the type of terminal device.

[0086] Figure 1 The server 10d shown can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. This application does not limit the type of server.

[0087] In the embodiments of this application, Figure 1Each terminal device in the terminal cluster shown can run a news application, which is a software application whose main function is to provide various news information. This news application can be a news portal application, a search engine application, a content generation application, an audio-visual information application, a news organization application, etc.; this application does not limit the type of news application. The application can be a browser, an app (application), or a lightweight application (such as a mini-program). When the news application runs on each terminal device, each terminal device can install the news application's client and... Figure 1 Data interaction occurs between the servers 10d shown, and at this time, server 10d can be the backend server of the information application.

[0088] Please see Figure 2 , Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Figure 1 Understandably, this data processing method can be executed by a computer device, which can be a terminal device, such as... Figure 1 Any terminal device in the terminal cluster shown can be a server, such as... Figure 1 The server 10d shown is not limited in this application; for ease of understanding, the following description uses the example of a computer device as a terminal device. Figure 2 As shown, the data processing method may include the following steps S101 to S103:

[0089] Step S101: Display the interactive controls of the intelligent agent object on the topic information page corresponding to the first topic of interest.

[0090] The "first focus topic" can refer to a news feature focusing on current hot topics and events. It can also refer to a specific topic or event selected from a large amount of information that has high attention, significant influence, and broad relevance. The focus topic in this embodiment can also be called a "hot topic selection feature." The "topic information page" can refer to a page designed for a specific topic or event within an information application. This page can be used to display a series of information related to the first focus topic. Information can refer to timely and informative messages, data, and materials disseminated through various channels. This information can include news on politics, economy, society, and technology; industry information on finance, healthcare, education, and real estate; and lifestyle information on food, travel, fashion, and home furnishings. Alternatively, the information can include at least one of the following: text data, video data, image data, audio data, and live streaming data.

[0091] An intelligent agent object can refer to an intelligent entity capable of perceiving its environment, making decisions based on the perceived information, and executing actions to achieve a goal. An intelligent agent object can be a software program, a robot, or other system with intelligent functions. An interactive control can refer to a channel or interface provided in an information application for objects to interact with the intelligent agent object; through this interactive control, related services of the intelligent agent object can be initiated, such as displaying a dialogue page between the object and the intelligent agent object. This interactive control can be at least one of the following forms: shortcut icon, voice wake-up control, interactive overlay, card area, text view, etc. This application does not limit the type of interactive control.

[0092] Specifically, when an object wants to view information in a news application, it can launch the news application installed on its computer device. The computer device can respond to the launch operation of the news application, and the information flow display page of the news application can be displayed on the terminal screen of the computer device. The information flow display page can include a topic area, which can be used to display M topics of interest, where M is a positive integer.

[0093] The information feed display page refers to a page layout in a news application that displays information content in a stream format; this information feed display page can be the homepage after launching the news application. On this information feed display page, various types of news information can be arranged sequentially according to certain rules and orders, forming a continuous information flow to facilitate browsing and access to content of interest. The "Focus Topics Area" can refer to a view area within the information feed display page used to display M topics of interest.

[0094] The M topics of interest can refer to different topics or events selected from a large amount of information. These M topics of interest can be displayed in a list format, either horizontally or vertically within the topic of interest area. This application does not limit the presentation method of the M topics of interest. The M topics of interest can be randomly sorted within the topic of interest area, or sorted in descending order based on metrics such as number of views, clicks, and comments. This application does not limit the sorting method of the M topics of interest.

[0095] In response to the first selection operation on the area of ​​interest, the topic selected by the first selection operation is designated as the first topic of interest, and the topic information page corresponding to the first topic of interest is displayed. The first topic of interest can be any one of the M topics of interest displayed in the area of ​​interest. An object can select any of the M topics of interest displayed in the area of ​​interest to view information about that topic, and enter the topic information page of that topic. The topic of interest selected by the object can be called the first topic of interest.

[0096] In one or more embodiments, when the size of the "Following Topics" area in the information flow display page is limited and cannot display M following topics to an object at once, a sliding control can be set in the following topics area. This sliding control allows viewing the M following topics in the following topics area. In this case, the aforementioned first selection operation can include a sliding operation and a clicking operation. The computer device can respond to a sliding operation on the following topics area, updating the following topics displayed in the following topics area according to the sliding speed indicated by the sliding operation; furthermore, it can respond to a clicking operation on a following topic in the following topics area, determining the following topic identified by the clicking operation as the first following topic, and displaying the topic information page for the first following topic.

[0097] In one or more embodiments, a list of event information corresponding to the first topic of interest can be displayed on the topic information page corresponding to the first topic of interest. The event information list is a collection that organizes and lists event information (e.g., news articles) associated with the first topic of interest. The event information list may include one or more event information items, which can refer to information materials with a specific event as their core content. First feedback data for each event information item in the event information list can be obtained, and second feedback data for the first topic of interest can be determined based on the first feedback data for each event information item. Traffic data and topic type of the first topic of interest can be obtained, and a first popularity parameter value for the first topic of interest can be determined based on the second feedback data, traffic data, and topic type. If the first popularity parameter value is greater than a parameter threshold, the interactive control of the intelligent agent object is displayed on the topic information page; if the first popularity parameter value is less than or equal to the parameter threshold, the interactive control of the intelligent agent object does not need to be displayed on the topic information page.

[0098] The first feedback data can refer to data generated within a certain period after the release of event information, without relying on the direct reactions of the target audience to the event information. The first feedback data can determine the target audience's level of attention, points of interest, and initial attitude towards the event information. This first feedback data may include at least one of the following: number of reads, likes, comments, shares, searches, and dwell time. This application does not limit the type of first feedback data.

[0099] The second feedback data for the first topic of concern can be obtained by summing the first feedback data of all events in the event information list. Alternatively, the second feedback data for the first topic of concern can be obtained by summing the first feedback data of all events in the event information list and then averaging the sums. Optionally, when the first feedback data includes multiple data points, the second feedback data can be the result of summing each data point independently in the first feedback data of all events in the event information list, or the result of averaging the sums.

[0100] Traffic data refers to the traffic of the topic information page corresponding to the first topic of interest, including page views and page dwell time. Topic type refers to the type of the first topic of interest, such as, but not limited to, political events, widely influential public events, technological events, entertainment events, medical events, and educational events. The first popularity parameter value represents the current popularity of the first topic of interest. The first popularity parameter value can be any value greater than or equal to 0; the higher the first popularity parameter value, the higher the popularity of the first topic of interest. The parameter threshold can be any value set according to the specific needs of the actual application scenario. This parameter threshold can serve as the basis for whether to display the interactive controls of the intelligent agent object on the topic information page. For topics of interest with a first popularity parameter value greater than the parameter threshold, the corresponding topic information page can display the interactive controls of the intelligent agent object; for topics of interest with a first popularity parameter value less than or equal to the parameter threshold, the corresponding topic information page does not need to display the interactive controls of the intelligent agent object.

[0101] Optionally, interactive controls for the intelligent agent object can be displayed on the topic information page for each topic of interest. Alternatively, other metrics (such as the importance of the topic of interest, the scope of dissemination of the topic of interest, etc.) can be used to determine whether to display interactive controls for the intelligent agent object on the topic information page. This application does not limit this.

[0102] In one or more embodiments, the calculation method for the first popularity parameter value may include, but is not limited to: a topic popularity reference table may be pre-defined, which may include parameter values ​​corresponding to different numerical ranges of feedback data, parameter values ​​corresponding to different numerical ranges of traffic data, and parameter values ​​corresponding to different topic types, etc. Optionally, when the feedback data includes multiple data items, the topic popularity reference table may include parameter values ​​corresponding to different numerical ranges of each data item.

[0103] For example, taking feedback data including readership as an example, readership can be divided into multiple numerical ranges in ascending order, such as [0, a1], (a1, a2], (a2, a3], (a1, a4], (a4, +∞), etc., where a1, a2, a3, and a4 can be increasing positive integers. Different numerical ranges can be set with different parameter values, and the parameter values ​​corresponding to the multiple numerical ranges of readership can also be increasing values. The method for setting parameter values ​​for different numerical ranges of traffic data can be found in the parameter value setting method for feedback data mentioned above, and will not be repeated here; the larger the value of the traffic data, the larger its corresponding parameter value. Different topic types have different levels of importance. For example, public events with widespread impact (such as natural phenomena that damage the human living environment) are more important than current affairs events, and current affairs events are more important than entertainment events, etc. Different levels of importance can be set with different parameter values, and the same level of importance can be set with the same parameter value; the higher the importance of a topic type, the larger the parameter value corresponding to that topic type.

[0104] Based on the topic popularity reference table, the second feedback data can be mapped to feedback parameter values, the traffic data of the first topic of interest can be mapped to traffic parameter values, and the topic type of the first topic of interest can be mapped to type parameter values. Summing these feedback parameter values, traffic parameter values, and type parameter values ​​yields the first popularity parameter value for the first topic of interest. In other words, by looking up the feedback parameter value corresponding to the second feedback data, the traffic parameter value corresponding to the traffic data, and the type parameter value corresponding to the topic type in the topic popularity reference table, and then summing these values, the first popularity parameter value for the first topic of interest can be obtained.

[0105] It is understood that the method of calculating the first popularity parameter value of the first topic of interest based on a pre-set topic popularity reference table is merely an illustrative example of an embodiment of this application. This application does not limit the calculation method of the first popularity parameter value; for example, a formula for calculating the popularity parameter value can be designed, and the first popularity parameter value of the first topic of interest can be calculated according to this formula.

[0106] Please see Figure 3 , Figure 3 This is a schematic diagram of the interface of a topic information page provided in an embodiment of this application. Figure 3The terminal device 20a shown is a computer device used by object A. When object A launches the news application installed on the terminal device 20a, the terminal device 20a can respond to the launch operation of the news application and display the news application's information flow display page 20c. The information flow display page 20c may include a search box 20b, a tab bar 20r, a topic of interest area 20d, controls 20e, 20f, 20g, and 20h. Object A can enter query information in the search box 20b to invoke a search engine and search for news information of interest within the news application.

[0107] The tab bar (20r) can include multiple tabs, each corresponding to a different tab channel page. A tab channel page, in a news application, can be a page displaying a collection of content with the same tab or category. Various information can be categorized using specific tabs, allowing for the design of tab channel pages corresponding to different tabs. For example... Figure 3 As shown, the tab bar 20r can include a "Top News" tab, tab 1, tab 2, tab 3, tab 4, etc. The tab bar 20r can also include an "Expand" control; by triggering this "Expand" control, all tabs in the tab bar 20r can be viewed. The content displayed on the information flow display page 20c can be the content displayed on the tab channel page corresponding to the "Top News" tab in the tab bar 20r.

[0108] The "Follow Topics" area 20d can display M followed topics. These M topics are selected from a large amount of information, focusing on trending topics. They are displayed horizontally within the "Follow Topics" area 20d, ordered from highest to lowest based on the first popularity parameter value. For example, when M is 5... Figure 3 The topic 1 shown can be the topic with the highest first popularity parameter value among the 5 topics. Object A can trigger any position in the topic area 20d and slide horizontally within that topic area 20d, updating the currently displayed topics in that topic area 20d. Preview information for the 5 topics can be viewed within this topic area 20d. The preview information for a topic may include the topic itself and any accompanying image; or it may include the title of any trending event related to the topic and any corresponding accompanying image, etc., and this application does not limit this to any specific type of topic.

[0109] Optionally, the M followed topics can be displayed vertically in the followed topic area 20d in descending order of their first popularity parameter value, with the followed topic having the highest first popularity parameter value displayed first in the followed topic area 20d. Object A can trigger a vertical scroll within the followed topic area 20d from any position, and can view preview information of 5 followed topics within that area.

[0110] like Figure 3 As shown, triggering the "News" control 20e displays the information flow page 20c, which shows various news information in a stream format. Triggering the "Video" control 20f displays video news information from the news application. Triggering the "Following" control 20g displays the accounts followed by object A in the news application and the news information they have published. Triggering the "My" control 20h displays basic information about object A, such as object A's account, nickname, and configuration information in the news application; this application does not limit this information.

[0111] Optionally, in addition to displaying the aforementioned information, the information flow display page 20c may also display other news information, such as news information 1, news information 2, news information 3, and news information 4, which are pinned to the top. Pinning to the top refers to the operation of displaying some news information at the top of the information display area of ​​the information flow display page 20c. This information display area can refer to the area used to display the news information in the information flow display page 20c, and may include the topic area 20d. The information flow display page 20c may also display other news information according to a pre-set information layout, such as news information 1. News information 1 may be a news report combining text and images, or it may be video news, etc. This application does not limit this.

[0112] like Figure 3As shown, when object A selects topic 1 in the topic area 20d and clicks on the display area of ​​topic 1, topic 1 can be called the first topic of interest. The display can switch from the information flow page 20c of the news application to the topic information page 20i corresponding to topic 1. This topic information page 20i can display the event information list 20j corresponding to topic 1, and the interactive control 20k of the intelligent agent object. The interactive control 20k can be a text view, displaying topic 1. The event information list 20j can include event information related to topic 1, such as news reports. Object A can click on event information in the event information list 20j to view details of each event. Object A can trigger operations on the interactive control 20k of the intelligent agent object, such as clicking the interactive control 20k to enter a dialogue page between object A and the intelligent agent object. The presentation of this dialogue page will be described later.

[0113] It is understandable that, in addition to the interactive control 20k displaying the event information list 20j, the topic information page 20i can also display the event timeline of the topic 1. This event timeline can refer to the development process of all event information related to the topic 1, organized and listed in chronological order. Optionally, the topic information page 20i can display partial introductory information about the topic 1. When object A performs an expand operation on the topic 1, the complete introductory information about the topic 1 can be displayed on the topic information page 20i. Alternatively, the complete introductory information about the topic 1 can be displayed directly on the topic information page 20i.

[0114] Optionally, the topic information page 20i may also include different types of feedback controls, such as a comment posting control 20m, a comment viewing control 20n, a favorites control 20p, and a share control 20q. Object A can trigger the comment posting control 20m to input the comment content they want to post on the topic they are interested in, thus commenting on the topic 1. This comment content can be understood as object A's insights or opinions on the topic 1. When object A triggers the comment viewing control 20n, they can view the comments from various objects on the topic 1 on the topic information page 20i, and the comment viewing control 20n can display the number of comments on the topic 1. Figure 3As shown, the total number of comments for the followed topic 1 is 234. When object A triggers the collection control 20p, the followed topic 1 can be added to object A's collection. The collection can refer to a storage space used to store all information that object A is interested in, so that object A can quickly view these collected information later. Optionally, the collection control 20p can display the number of collections for the followed topic 1. When object A triggers the share control 20q, the link of the followed topic 1 can be shared to other objects or other platforms. Other objects can refer to objects other than object A, and other platforms can refer to applications other than the current news application. Optionally, the share control 20q can display the number of shares for the followed topic 1, that is, the total number of times the followed topic 1 has been shared.

[0115] Understandable Figure 3 The interactive control 20k shown is only one presentation method in this embodiment. This embodiment does not limit the presentation method of interactive controls for intelligent agent objects in information applications. For example, please refer to... Figure 4a and Figure 4b , Figure 4a This is a schematic diagram of the interface of an interactive control for an intelligent agent object provided in an embodiment of this application. Figure 1 Assuming Figure 4a The terminal device 30a shown is the terminal device used by object A. When object A selects and clicks on the "Followed Topic 1" in the information flow display page of the information application, the topic information page 30b corresponding to "Followed Topic 1" can be displayed. The topic information page 30b can display the interactive controls of the intelligent agent object. These interactive controls can be... Figure 4a As shown in area 30c, this area 30c can be presented in the form of cards. Here, "card" can refer to a design format that groups information, functions, or content together, presenting it as an independent rectangular element with clear boundaries and a sense of visual hierarchy.

[0116] In this area 30c, multiple event terms associated with the topic of interest 1 can be displayed, such as event term 1, event term 2, event term 3, and event term 4. Each event term can be the title of an article related to the topic of interest 1, or it can be a keyword of the event information related to the topic of interest 1, etc. This application does not limit this. When object A clicks on any event term in this area 30c, it can enter the dialogue page of the intelligent agent object in the information application.

[0117] Figure 4b This is a schematic diagram of the interface of an interactive control for an intelligent agent object provided in an embodiment of this application. Figure 2 Assuming Figure 4bThe terminal device 30a shown is the terminal device used by object A. When object A selects and clicks on the "Followed Topic 1" in the information flow display page of the information application, the topic information page 30b corresponding to "Followed Topic 1" can be displayed. The topic information page 30b can display the interactive controls of the intelligent agent object. These interactive controls can be... Figure 4b As shown in the interactive overlay 30d, this interactive overlay 30d can be a subpage displayed independently on the topic information page 30b. This interactive overlay 30d can include a term display area, in which multiple event terms related to the topic 1 can be rotated.

[0118] Understandably, the display duration of each event term in the interactive overlay 30d can be preset, such as 1 second; that is, the display duration of each event term can be used to determine the carousel frequency of the event terms in the interactive overlay 30d. When the display duration of event term 1 in the interactive overlay 30d reaches 1 second, event term 1 in the interactive overlay 30d can be updated to event term 2. When object A clicks on the currently displayed event term 2 in the interactive overlay 30d, it can enter the dialogue page of the intelligent agent object in the information application.

[0119] Step S102: In response to the trigger operation of the interactive control, display the dialogue page of the intelligent agent object. The dialogue page includes a first display area, which is used to display the first live broadcast information associated with the first topic of interest.

[0120] The dialogue page, also known as the intelligent agent dialogue page, is the interface through which objects using the information application (which can be called business objects) interact with intelligent agent objects. It is typically presented as a webpage or application interface. This dialogue page provides a visual space that allows objects to input text or voice to converse with intelligent agent objects. The first live broadcast information can refer to real-time playback information disseminated via live streaming. This first live broadcast information can be currently broadcast video or audio data; this application does not limit its scope.

[0121] Specifically, the object using the information application can be called the business object of the information page. When the business object performs a trigger operation on the interactive control of the intelligent agent object displayed on the topic information page, the computer device can respond to the trigger operation for the interactive control and display the dialogue page of the intelligent agent object. The dialogue page may include a first display area and a second display area. Based on the event information list corresponding to the first topic of interest, a topic summary text of the first topic of interest is generated, and the event information list and topic summary text are determined as the first information information of the first topic of interest. The first live broadcast information associated with the first topic of interest is obtained, and the first live broadcast information is displayed in the first display area and the first information information is displayed in the second display area.

[0122] The first information can refer to information that organizes, summarizes, analyzes, and reports events, phenomena, trends, etc., that have occurred over a period of time. The events involved in the first information are not currently being broadcast live. The first information can include at least one of the following: text-based information, image-based information, audio-based information, video-based information, graphic-text information, image + audio information, and text + video information; this application does not limit this. The first display area can be used to display first live information related to the current first topic of interest, such as live data associated with that first topic of interest. Here, live data can be understood as real-time playback data. The second display area can be used to display the first information related to that first topic of interest, such as a list of event information and a topic summary text. This first information can refer to information published after a series of operations such as collection, organization, and editing of events or issues that have occurred, such as published news reports or commentary articles on a specific event; this application does not limit this. This second display area, also known as the dialogue display area between the business object and the intelligent agent object, can be used to display the dialogue details between them. This could include questions from the business object and answers from the intelligent agent object. Here, the question can be understood as the topic of interest, and the answer as primary information related to that topic. The topic summary text can refer to a summary description generated using natural language processing technology for the primary topic of interest. The first display area can be displayed at the top of the dialogue page. This application does not limit the display position or presentation method of the first and second display areas on the dialogue page.

[0123] In one or more embodiments, the process of generating topic summary text may include, but is not limited to: obtaining a list of event information corresponding to a first topic of interest; concatenating the text content of each event information in the event information list to obtain initial text data of the first topic of interest; removing invalid characters from the initial text data to obtain candidate text data; converting the candidate text data into a text embedding representation; extracting features from the text embedding representation to obtain a text semantic feature sequence of the candidate text data; decoding the text semantic feature sequence to obtain the character probability distribution of each text semantic feature in the text semantic feature sequence; and generating topic summary text of the first topic of interest based on the character probability distribution.

[0124] The text content of the event information may include the title, body, and other text of the event information. The initial text data may refer to the result of concatenating the text content of each event information in the event information list sequentially. Optionally, the initial text data may refer to the original text of the event information with the highest popularity parameter value (e.g., the third popularity parameter value) in the event information list. Invalid characters may refer to special characters, whitespace characters, repeated characters, semantically meaningless characters, garbled characters, invisible characters, etc. in the initial text data. This application does not limit the type of invalid characters.

[0125] Text embedding representation can refer to converting candidate text data into a text representation in a low-dimensional vector space. A text semantic feature sequence can refer to a sequence of text semantic features, where each text semantic feature can be a semantic feature of a sentence, a paragraph, or a word in the candidate text data. Text semantic features can be used to describe the contextual semantics in the candidate text data. A character probability distribution can refer to the probability value predicted based on the previous word in the candidate text data, indicating that a word belongs to any word in the vocabulary. The character corresponding to the highest probability value in the character probability distribution can be used as the predicted next word. A vocabulary can refer to a set of all commonly used characters or words in the field, similar to a "dictionary".

[0126] In one or more embodiments, the first live broadcast information is described as live broadcast data as an example. The steps to obtain the first live broadcast information associated with the first topic of interest may include, but are not limited to: obtaining a candidate live broadcast data set; obtaining candidate live broadcast data a from the candidate live broadcast data set; performing semantic analysis on candidate live broadcast data a and each event information in the event information list to obtain the correlation degree between candidate live broadcast data a and each event information; if there is an event information in the event information list whose correlation degree with candidate live broadcast data a is greater than the correlation degree threshold, then candidate live broadcast data a is determined as the first live broadcast information associated with the first topic of interest.

[0127] Understandably, for each candidate live stream in the candidate live stream dataset, the correlation between each candidate live stream and the primary focus topic can be calculated using the above method. Then, based on the correlation, live streams related to the primary focus topic can be filtered from the candidate live stream dataset. Candidate live streams with a correlation greater than the correlation threshold can be used as primary live stream information and recommended to business users on the chat page; candidate live streams with a correlation less than or equal to the correlation threshold can be filtered and do not need to be recommended to business users.

[0128] The candidate live streaming data set can refer to the collection of all currently live streaming data in a news application; or it can refer to the collection of all currently live streaming data across multiple business platforms (e.g., including the current news application, as well as news media platforms, live streaming platforms, short video platforms, etc.). The correlation between the candidate live streaming data and the primary topic of interest can be calculated through semantic analysis, the implementation of which will be described later. The correlation can be a quantitative representation used to measure the relevance between the candidate live streaming data and the primary topic of interest. The correlation threshold can be a pre-set fixed value, which can be flexibly set according to the specific needs of the actual application scenario.

[0129] Step S103: In response to the information viewing operation for the first display area, output live broadcast business data in the virtual service space indicated by the first live broadcast information.

[0130] The virtual service space can refer to a digital space generated based on network technology, where business users can have an immersive and interactive experience. For example, a virtual service space could be a live streaming room, a virtual environment created based on network technology where the host can provide various services, and viewers can access the live stream via the network to watch and interact with the host. Live streaming business data can refer to real-time data generated within the virtual service space, such as the host's audio and video data within the live stream, chat data between viewers and the host, and viewer feedback data for the current live stream, such as the number of likes.

[0131] For ease of understanding, this application describes the first live broadcast information as live broadcast data as an example. Live broadcast data may include live broadcast title, live broadcast time, live broadcast content summary, live broadcast category, live broadcast link, live broadcast room ID (identifier), etc. This application does not limit the information in the live broadcast data.

[0132] Specifically, when a business object performs an information viewing operation on the first display area of ​​the dialog page, this information viewing operation can be a click operation on the first display area. The computer device can respond to the information viewing operation on the first display area, determine the live data determined by the information viewing operation as the target live data, determine the business application to which the virtual service space indicated by the target live data belongs, and output the live business data in the virtual service space of the business application.

[0133] Understandably, when the first live stream information includes a single live stream data item associated with the first topic of interest, the business user can click anywhere in the first display area to directly enter the live stream room indicated by that single live stream data item. This single live stream data item can be called the target live stream data item. When the first live stream information includes multiple live stream data items associated with the first topic of interest, the business user can select one live stream data item of interest from the multiple live stream data items and click to enter the live stream room indicated by the selected live stream data item. The live stream data item selected by the business user from the multiple live stream data items can be called the target live stream data item.

[0134] The live streaming data displayed in the first display area can be live streaming data from the current news application, or it can be any business application with live streaming functionality other than the current news application; this application does not limit this. After determining the target live streaming data in the first display area, the business application to which the virtual service space corresponding to the target live streaming data belongs can be determined based on the target live streaming data, such as the live streaming link or the live streaming room ID. If the business application is the news application to which the intelligent agent object belongs, then the virtual service space in the current news application is accessed, and the live streaming business data is output in the virtual service space. If the business application is not the news application to which the intelligent agent object belongs, then the business application installed on the computer device is launched, and the user is redirected from the current news application to the business application, accesses the virtual service space in the business application, and outputs the live streaming business data in the virtual service space.

[0135] Live streaming business data can refer to the data generated by each live stream. This live streaming business data can include live video data and live interaction data during the live stream. The live interaction data can include chat data, number of likes, number of comments, number of shares, number of followers, etc. This application does not limit this.

[0136] Please see Figure 5 , Figure 5 This application provides an embodiment of a dialog page for a smart agent object. Figure 1 ; Figure 5 The terminal device 40a shown is an electronic device used by object A. The current interface displayed on the terminal device 40a is a dialogue page 40b between object A and an intelligent agent object in the information application. The dialogue page 40b may include an area 40c, a first display area 40d, a second display area 40f, an interactive input box 40g, etc. Object A can update the topic of the current dialogue through the interactive input box 40g, and thus update the live data in the first display area 40d.

[0137] Area 40c can be used to display the text content of the first topic of interest, and the first display area 40d can be used to display live stream data associated with the first topic of interest. When there is only one live stream associated with the first topic of interest, it means that there is only one live stream associated with that topic. In this case, the live stream data of that live stream can be displayed in the first display area 40d, such as the live stream title, live stream content summary, etc. Figure 5 As shown, when the primary focus topic is "high-temperature thunderstorms," ​​it can be displayed in area 40c; the first display area 40d can display "Live Broadcast: Causes of High-Temperature Thunderstorms." The second display area 40f can display the topic summary text 40e and the latest news information (e.g., News 11, News 12, etc.) of the primary focus topic. Optionally, the dialogue page 40b can also display multiple recommended terms, such as Recommended Terms 1, Recommended Terms 2, etc., which can be questions that object A might be interested in. When object A performs a trigger operation (such as a click operation) on any of the multiple recommended terms, the recommended term triggered by object A can be used as its updated topic, such as the secondary focus topic.

[0138] When object A performs a trigger operation on the first display area 40d in the chat page, terminal device 40a can respond to the trigger operation (i.e., information viewing operation) on the first display area 40d, enter the live room indicated by the live data displayed in the first display area 40d, and display the live page 40h of the live room on terminal device 40a. The live page 40h can output live business data, which may include: live screen 40i, communication information in chat area 40j, etc. The chat area 40j can display the latest messages from the audience in the live room; optionally, the chat area 40j may also include an input box 40k and a control 40m. Among them, object A, as the audience in the live room, can post messages in chat area 40j through the input box 40k; and can reward the host in the live room through the control 40m, such as liking or sending gifts to the host in the live room.

[0139] In one or more embodiments, it is assumed that the first live broadcast information includes K live broadcast data points, where K is an integer greater than 1. Live broadcast indicator information indicated by each of the K live broadcast data points can be obtained. Based on the live broadcast indicator information indicated by each live broadcast data point, a second popularity parameter value corresponding to each live broadcast data point is determined. The second popularity parameter values ​​corresponding to each live broadcast data point are sorted in descending order to determine the arrangement order of the K live broadcast data points. This arrangement order is used to determine the display position of the K live broadcast data points in the first display area.

[0140] In one or more embodiments, a broadcast prompt message and an expansion control can be displayed in a first display area. The broadcast prompt message includes the number of live data associated with a first topic of interest. In response to a trigger operation on the expansion control, live preview screens corresponding to the K live data are displayed in the first display area according to the order of the K live data.

[0141] The live streaming metrics information refers to a series of quantitative indicators used to measure the effectiveness and performance of a live stream. These metrics may include, but are not limited to, at least one of the following: number of viewers, viewing duration, number of likes, number of comments, and number of shares. The secondary popularity parameter value represents the popularity of the current live stream content. This value can be any value greater than or equal to 0; a higher value indicates greater popularity. K live stream data points can be used to generate a live stream list in descending order of their secondary popularity parameter values. This list can be displayed in the first display area.

[0142] Optionally, the first display area of ​​the chat page can display an expand control. By default, the live stream list can be hidden in the first display area of ​​the chat page. When object A performs an expand operation (such as a click) on the expand control in the first display area, the live stream list can be displayed in the first display area, and each live stream in the list can be presented as a live preview. When object A performs a trigger operation on the expand control in the first display area again, the live stream list can be hidden in the first display area.

[0143] Please see Figure 6 , Figure 6 This is a schematic diagram of a dialog page for an intelligent agent object provided in an embodiment of this application. Figure 2 . Figure 6 The terminal device 40a shown is an electronic device used by object A. The current interface displayed on the terminal device 40a is a dialogue page 40b between object A and an intelligent agent object in the information application. The dialogue page 40b may include an area 40c, a first display area 40d, a second display area 40f, an interactive input box 40g, etc. Among them, the area 40c can be used to display the text content of the first topic of interest; the second display area 40f can display the topic summary text 40e of the first topic of interest and the latest information (e.g., information 11, information 12, etc.).

[0144] The first display area 40d can be used to display live data associated with the first topic of interest. When there are multiple live data associated with the first topic of interest, it means that there are multiple live streams associated with the first topic of interest. For ease of understanding, the following description will take a value of 4 for K as an example.

[0145] like Figure 6 As shown, when the primary focus is "high-temperature thunderstorms," ​​a broadcast notification message for K live streams associated with "high-temperature thunderstorms" can be displayed in the first display area 40d, such as "4 live streams are in progress." When object A expands the first display area 40d, its display size in the dialog page 40b can be increased, and a live stream list can be displayed in the first display area 40d. This live stream list can include four live streams associated with the primary focus, which can be labeled as Live 1, Live 2, Live 3, and Live 4, respectively. In the live stream list contained in the first display area 40d, a thumbnail of each live stream can be displayed, or the live stream footage of each live stream can be played silently, or the live stream title of each live stream can be displayed, or the live stream content of the first live stream (e.g., Live 1) can be played silently, while the remaining live streams (e.g., Live 2, Live 3, and Live 4) can display thumbnails. This application does not limit this.

[0146] When object A triggers a live stream (Live 1) in the live stream list displayed in the first display area 40d, terminal device 40a can respond to the trigger operation (i.e., information viewing operation) for the first live stream in the live stream list, enter the live stream room of Live 1, and display the live stream page 40h of the live stream room corresponding to Live 1 in terminal device 40a. The live stream page 40h can output live stream business data, which may include: live stream screen 40i, communication information in chat area 40j, etc. The chat area 40j can display the latest messages from the audience in the live stream room; optionally, the chat area 40j may also include an input box 40k and a control 40m. Object A, as a audience member in the live stream room, can post messages in chat area 40j through the input box 40k; and can reward the host in the live stream room through the control 40m, such as liking the host.

[0147] In one or more embodiments, the dialog page also includes an interactive input box, such as... Figure 5 The interactive input box 40k shown can be responded to by a computer device. In the second display area of ​​the dialog page, the input content determined by the input operation and the second information associated with the input content are displayed. In the first display area of ​​the dialog page, the first live information is updated to the second live information associated with the input content.

[0148] The input content of the business object in the interactive input box can be called the second topic of interest. Then, the content displayed in the first display area of ​​the dialog page can be updated to display the second live broadcast information associated with the second topic of interest, based on the first live broadcast information associated with the first topic of interest. For a description of the second live broadcast information, please refer to the description of the first live broadcast information, which will not be repeated here.

[0149] Specifically, the system can acquire the input content from the interactive input box, perform semantic analysis on the input content to obtain the semantic features of the input content; in the information application to which the intelligent agent object belongs, determine the second topic of interest that matches the semantic features of the content, acquire the second information information of the second topic of interest, and display the second information information in the second display area of ​​the dialogue page; and perform semantic analysis on the second topic of interest and each candidate live broadcast data in the candidate live broadcast data set to determine the second live broadcast information associated with the second topic of interest.

[0150] Please see Figure 7 , Figure 7 This is a schematic diagram of an interface for updating the topic of interest in a dialog page of an intelligent agent object, provided in an embodiment of this application. Figure 7 The terminal device 50a shown is an electronic device used by object A. The current interface displayed on the terminal device 50a is a dialogue page 50b between object A and an intelligent agent object in an information application. This dialogue page 50b may include an area 50c, a first display area 50d, a second display area 50f, and an interactive input box 50g. Area 50c may display the current primary topic of interest, such as "high-temperature thunderstorms." The first display area 50d may display live data associated with the primary topic of interest, such as "4 live streams are in progress." The second display area 50f may display a summary text 50e of the primary topic of interest and the latest information about that primary topic of interest (e.g., information 11, information 12, etc.).

[0151] like Figure 7As shown, when object A triggers an operation on the interactive input box 50g, entering text content (such as "Following Topic 2," which can be called the second followed topic) into the interactive input box 50g, and sending "Following Topic 2" to the second display area 50f in the form of message 50n, the first display area 50d can display the following prompt message "Searching for related live streams...", and the dialog page 50b can display the prompt message "Searching for information...". After finding live stream data associated with followed topic 2, the live stream data associated with followed topic 2 can be displayed in the first display area 50d. When the number of live streams associated with followed topic 2 is 2, "2 related live streams are in progress" can be displayed. The second display area 50f can update the displayed content, such as displaying message 50n and the latest information on followed topic 2.

[0152] When object A expands the first display area 50d, its size on the chat page 50b increases, displaying a list of live streams corresponding to the followed topic 2. This list can include two live streams associated with the followed topic 2, designated as Live 5 and Live 6. When object A views Live 5 (e.g., clicks) on it, it enters the live stream room and displays the live stream page 50h on the terminal device 50a. The live stream page 50h displays the live stream screen 50i, chat information in the chat area 50j, etc. The chat area 50j displays the latest messages from viewers; optionally, it may also include an input box 50k and a control 50m. Object A, as a viewer, can post messages in the chat area 50j using the input box 50k and reward the host using the control 50m, such as giving a "like."

[0153] In one or more embodiments, the interactive control includes an interactive overlay, which is displayed independently on the topic information page. The interactive overlay includes a term area. In the term area of ​​the interactive overlay, N event terms related to the first topic of interest can be displayed in a carousel, where N is a positive integer, such as... Figure 4b The interactive overlay 30d is shown. When a business object performs a trigger operation on the interactive overlay 30d, the computer device can respond to the trigger operation targeting the term area, determine the event term displayed in the term area as the target term, and display the dialogue page of the intelligent agent object. The dialogue page includes a first display area and a second display area; the first display area displays the first live information associated with the target term, and the second display area displays the first news information of the target term.

[0154] In this embodiment, an interactive control for an intelligent agent object can be displayed on the topic information page corresponding to the first topic of interest. Triggering this interactive control displays the intelligent agent object's dialogue page, which shows a first display area and first information about the first topic of interest. The first display area can be used to display first live information associated with the first topic of interest. Triggering the first live information in the first display area allows quick access to the virtual service space indicated by the first live information to watch live business data. By associating the event information of the topic of interest with the current live information, live information of interest to the user can be quickly obtained, improving the efficiency and accuracy of obtaining live information. When the dialogue topic between the business object and the intelligent agent object changes, the second live information associated with the updated topic (second topic of interest) can be quickly determined by recognizing the business object's intent, avoiding the omission of real-time information in the information application and improving the real-time performance of the information application.

[0155] Please see Figure 8 , Figure 8 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Figure 2 Understandably, this data processing method can be executed by a computer device, which can be a terminal device, such as... Figure 1 Any terminal device in the terminal cluster shown can be a server, such as... Figure 1 The server 10d shown is not limited in this application; for ease of understanding, the following description uses a computer device as an example of a server. Figure 8 As shown, this may include the following steps S201 to S213:

[0156] Step S201: Obtain candidate live streaming data from one or more business platforms.

[0157] Step S202: Organize and store data such as live stream title, content description, live stream time, and live stream category into the data warehouse.

[0158] Specifically, computer devices can pull currently running live streaming data from multiple business platforms and add this pulled live streaming data as candidate live streaming data to the data warehouse (which can be called the candidate live streaming data set).

[0159] The term "one or more business platforms" can refer to business platforms that support live streaming services, such as news applications, media platforms, live streaming platforms, and social platforms. This application does not limit the type of one or more business platforms. Candidate live streaming data may include, but is not limited to, at least one of the following: live stream title, live stream content description, live stream time, live stream category, live stream link, and live stream room ID. The data warehouse can be a subject-oriented, integrated, and relatively stable collection of data that can reflect historical changes and support management decisions.

[0160] Step S203: Input the large language model for deep semantic analysis.

[0161] Step S204: Use a large language model to determine the correlation between candidate live streaming data and topics of interest.

[0162] Specifically, a large language model can be used to perform semantic analysis on each candidate live stream in the candidate live stream dataset, comparing it with the topic of interest (e.g., the first topic of interest or the second topic of interest). This identifies live streams associated with the current topic of interest. If the number of selected live streams is K, where K is an integer greater than 1, then the live stream metrics information for each selected live stream can be obtained. Based on the live stream metrics information for each live stream, a second popularity parameter value is calculated for each selected live stream. The K live streams are then sorted according to their second popularity parameter values ​​from largest to smallest, and the sorted K live streams are displayed in the first display area of ​​the agent object's dialogue page.

[0163] The large language model can include, but is not limited to: GPT4 (Generative Pre-trained Transformer 4, a fourth-generation generative pre-trained large language model based on the Transformer structure), Qwen1.5-32B-Chat (an open-source large language model), llama3-70B (a general-purpose large language model), Skywork-13B (an open-source large language model), or any other large language model. For example, the correlation between each candidate live stream data in the candidate live stream dataset and the primary topic of interest can be obtained by asking questions to the large language model; the question format can be set according to the specific application scenario, or it can be adjusted in real time according to the specific content of the candidate live stream data and the primary topic of interest. This application does not limit the form of the question statement.

[0164] In one feasible implementation, each candidate live stream data in the candidate live stream dataset can be input into a language big model. Through the embedding layer in the language big model, each candidate live stream data is converted into a live stream data embedding representation. Through the encoding component in the language big model, the live stream data embedding representation is encoded to obtain the live stream data encoding features corresponding to the candidate live stream data. Through the fully connected layer in the language big model, the live stream data encoding features are transformed to generate the live stream feature representation corresponding to each candidate live stream data.

[0165] Specifically, the candidate live stream data can be segmented into multiple unit characters (where a unit character can be a single character or word in the candidate live stream data). Each unit character is then transformed into a vector representation, yielding its corresponding word vector representation. For example, one-hot encoding can be used to represent each unit character as a word vector, resulting in a vector containing only one 1 and all others being 0. The dictionary (also known as a bag-of-words) can include a series of general unit characters. Based on the position of each general unit character in the dictionary, its corresponding one-hot encoding can be obtained. The word vector representations (such as one-hot encodings) corresponding to each unit character in the candidate live stream data are concatenated to obtain the text vector representation of the candidate live stream data. This text vector representation is then transformed using the embedding layer in the language model to obtain the embedded representation of the live stream data. In this language model, the embedding layer can be a word vector model, which may include, but is not limited to: word2vec (a word vector model that obtains the vectorized representation of a word through its context), glove (a word vector model that utilizes a co-occurrence matrix), ELMo (Embeddings from Language Models), BERT (Bidirectional Encoder Representations from Transformers), Latent Semantic Analysis (LSA), and Latent Dirichlet Allocation (LDA). The embodiments of this application do not limit the word vector model used.

[0166] By using the encoding component in the large language model, feature extraction is performed on the embedded representation of live data to obtain the encoded features of live data. Specifically, the encoding component in the large language model can be used to convert the input embedded representation of live data into a fixed-length context vector, which can be called the encoded features of live data. This encoding component can be any one, or a combination or variation of any two or more network structures, such as transformer (a deep learning model employing an attention mechanism), residual network, recurrent neural network (RNN), convolutional neural network (CNN), and gated network. This application does not limit the structure of the encoding component in the large language model. Furthermore, the encoded features of live data can be transformed using the fully connected layer in the large language model to generate the live data feature representations corresponding to candidate live data.

[0167] It should be understood that the text content of each event in the event information list of each topic of interest can be concatenated to obtain the initial text data of the first topic of interest. Invalid characters in the initial text data are removed to obtain candidate text data. This candidate text data is then input into a language model, which outputs text feature representations of the candidate text data. The method for generating these text feature representations can be found in the method for generating feature representations of live data, and will not be elaborated upon here. Invalid characters can include punctuation marks, repeated characters, garbled characters, and semantically meaningless characters; this application does not limit the type of invalid characters.

[0168] After obtaining the live data feature representation of each candidate live stream in the candidate live stream dataset and the text feature representation of the primary topic of interest through a large language model, the correlation between each candidate live stream and the topic of interest can be calculated based on the live data feature representation and the text feature representation. The correlation can be calculated using similarity calculation methods, including but not limited to: cosine similarity, Pearson correlation coefficient, edit distance, etc.

[0169] Step S205: Is it related to the topic of interest?

[0170] Step S206: Discard candidate live data.

[0171] Specifically, the relevance of each candidate live stream data point to the topic of interest can be used to determine whether the candidate live stream data is relevant to the topic of interest. For example, if the relevance between the candidate live stream data and the topic of interest is greater than a relevance threshold, the candidate live stream data can be identified as relevant to the topic of interest, and step S207 can be continued. If the relevance between the candidate live stream data and the topic of interest is less than or equal to the relevance threshold, the candidate live stream data can be discarded.

[0172] Step S207: Calculate the second popularity reference value based on indicators such as the number of live stream viewers, the number of likes, and the number of comments.

[0173] Specifically, by sequentially calculating the correlation between each candidate live stream in the candidate live stream dataset and the topic of interest, live streams related to the topic of interest can be filtered out from the candidate live stream dataset. Live stream metrics information for each filtered live stream can be obtained, such as the number of viewers, likes, and comments, and a second popularity reference value can be calculated for each filtered live stream. The calculation method for the second popularity reference value is the same as that for the first popularity reference value, and will not be repeated here.

[0174] Step S208: Sort the selected live stream data according to the second popularity reference value.

[0175] Step S209: Display the top-ranked live stream data in the chat page as a hover bar.

[0176] Specifically, the selected live stream data can be sorted according to the second popularity reference value to generate a live stream list. This list can include all live stream data selected from the candidate live stream data set; or it can include a portion of the live stream data selected from the candidate live stream data set, such as the top 5 live streams with the highest second popularity reference values; or it can include all live stream data selected from the candidate live stream data set whose second popularity parameter value is greater than the parameter threshold, etc. This application does not limit this. The live stream list can be displayed in the first display area of ​​the dialog page, which can be displayed as a hover bar. The hover bar can be an interface element that is displayed in the dialog page when the contact point between the business object and the terminal screen is located in the first display area. If the business object releases the terminal screen, the hover bar can be hidden in the dialog page.

[0177] Step S210: Are there multiple live stream data?

[0178] Specifically, if only one live stream is selected from the candidate live stream data set, then step S212 can be executed. If multiple live streams are selected from the candidate live stream data set, then step S211 can be executed.

[0179] Step S211: Display the first display area, showing multiple live data in card format.

[0180] Specifically, if there are multiple live stream data points, a first display area can be shown on the chat page, where the live stream list can be displayed in the form of cards. This live stream list can include multiple live stream data points.

[0181] Step S212: Directly display the hover bar for a single live data point.

[0182] Specifically, if only one live stream data is selected, a first display area can be shown on the chat page, where a hover bar for that single live stream data can be displayed.

[0183] Step S213: Click on the card or hover bar to enter the live stream room to watch.

[0184] Specifically, users can click on the card in the first display area (in the case of multiple live streams) or directly click on the hover bar (in the case of one live stream) to enter the selected live stream room for viewing.

[0185] It is understood that semantic understanding models from natural language processing, such as the BERT model based on the Transformer architecture, or other network structures, can be used; this application does not limit this. The semantic understanding model can be pre-trained using large amounts of text data and can perform deep semantic analysis on the text content input by various objects (e.g., the input content in the interactive input box of an agent's dialogue page). For example, the input text can be preprocessed with word segmentation and part-of-speech tagging, where part-of-speech refers to grammatical classification, used to represent the role of each word in a sentence. The preprocessed text input is then fed into the semantic understanding model, which outputs semantic understanding results, such as the final text feature representation. These results can include features extracted from the input content, such as keywords, topic classifications, and the sentiment of the business object.

[0186] After obtaining the semantic understanding results of the input content, the interest information of the business object can be determined. Based on this interest information, a second live broadcast related to the input content can be filtered from the candidate live broadcast dataset and pushed to the first display area of ​​the chat page for display. Upon receiving the second live broadcast information, the front end of the news application can update the first live broadcast information in the first display area to show the second live broadcast information, achieving rapid updates of live broadcast information and improving the satisfaction of live broadcast information recommendations.

[0187] In this embodiment, an interactive control for an intelligent agent object can be displayed on the topic information page corresponding to the first topic of interest. Triggering this interactive control displays the intelligent agent object's dialogue page, which shows a first display area and first information about the first topic of interest. The first display area can be used to display first live information associated with the first topic of interest. Triggering the first live information in the first display area allows quick access to the virtual service space indicated by the first live information to watch live business data. By associating the event information of the topic of interest with the current live information, live information of interest to the user can be quickly obtained, improving the efficiency and accuracy of obtaining live information. When the dialogue topic between the business object and the intelligent agent object changes, the second live information associated with the updated topic (second topic of interest) can be quickly determined by recognizing the business object's intent, avoiding the omission of real-time information in the information application and improving the real-time performance of the information application.

[0188] It is understood that in the specific implementation of this application, information such as user account, nickname, configuration information, and follow information in the information application may be involved. When the above embodiments of this application are applied to specific products or technologies, permission or consent from relevant institutions or departments, or the user himself or himself or himself or her or his or her ...

[0189] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application. Figure 9 As shown, the data processing device 1 may include: a first display module 101, a second display module 102, and a playback module 103;

[0190] The first display module 101 is used to display the interactive controls of the intelligent agent object in the topic information page corresponding to the first topic of interest;

[0191] The second display module 102 is used to respond to the trigger operation of the interactive control and display the dialogue page of the intelligent agent object. The dialogue page includes a first display area, which is used to display the first live broadcast information associated with the first topic of interest.

[0192] The playback module 103 is used to respond to information viewing operations for the first display area and output live broadcast business data in the virtual service space indicated by the first live broadcast information.

[0193] In one or more embodiments, the first display module 101 is further configured to perform the following steps:

[0194] In response to the launch operation of the news application, the news application's information feed display page is displayed. The information feed display page includes a follow topic area, which displays M follow topics, where M is a positive integer.

[0195] In response to the first selection operation for the area of ​​interest, the topic selected by the first selection operation is designated as the first topic of interest, and the topic information page corresponding to the first topic of interest is displayed.

[0196] In one or more embodiments, the first selection operation includes a swipe operation and a click operation;

[0197] When the first display module 101 responds to a first selection operation for a region of interest and determines the topic of interest determined by the first selection operation as the first topic of interest, it specifically performs the following steps:

[0198] In response to a swipe gesture targeting the area of ​​followed topics, update the displayed followed topics in the area of ​​followed topics based on the swipe speed indicated by the gesture.

[0199] In response to a click operation on a topic within the topic area, the topic identified by the click operation is designated as the first topic of interest.

[0200] In one or more embodiments, when the first display module 101 displays the interactive controls of the intelligent agent object on the topic information page corresponding to the first topic of interest, it is specifically used to perform the following steps:

[0201] On the topic information page corresponding to the first topic of interest, a list of event information related to the first topic of interest is displayed;

[0202] Get the first feedback data for each event in the event information list, and determine the second feedback data for the first topic of concern based on the first feedback data for each event.

[0203] Obtain the traffic data and topic type of the first topic of interest, and determine the first popularity parameter value of the first topic of interest based on the second feedback data, traffic data, and topic type.

[0204] If the first popularity parameter value is greater than the parameter threshold, the interactive controls of the intelligent agent object will be displayed on the topic information page.

[0205] In one or more embodiments, when the first display module 101 determines the first popularity parameter value of the first topic of interest based on the second feedback data, traffic data, and topic type, it specifically performs the following steps:

[0206] Obtain the topic popularity reference table, and based on the topic popularity reference table, map the second feedback data to feedback parameter values, map the traffic data to traffic parameter values, and map the topic type to type parameter values;

[0207] The first popularity parameter value of the first topic of interest is obtained by summing the feedback parameter value, the traffic parameter value, and the type parameter value.

[0208] In one or more embodiments, the data processing apparatus 1 may further include:

[0209] The information query module 104 is used to generate a topic summary text for the first topic of concern based on the event information list corresponding to the first topic of concern, and to determine the event information list and the topic summary text as the first information information of the first topic of concern.

[0210] The information query module 104 is also used to obtain the first live broadcast information associated with the first topic of interest, display the first live broadcast information in the first display area, and display the first news information in the second display area.

[0211] In one or more embodiments, when the information query module 104 generates a topic summary text for the first topic of interest based on the event information list corresponding to the first topic of interest, it specifically performs the following steps:

[0212] Obtain the list of event information corresponding to the first topic of interest, concatenate the text content of each event information in the event information list to obtain the initial text data of the first topic of interest, remove invalid characters from the initial text data to obtain candidate text data;

[0213] The candidate text data is converted into a text embedding representation, and features are extracted from the text embedding representation to obtain the text semantic feature sequence of the candidate text data.

[0214] The text semantic feature sequence is decoded to obtain the character probability distribution of each text semantic feature in the text semantic feature sequence, and the topic summary text of the first topic of interest is generated based on the character probability distribution.

[0215] In one or more embodiments, when the information query module 104 obtains the first live broadcast information associated with the first topic of interest, it specifically performs the following steps:

[0216] Obtain a candidate live stream data set, retrieve candidate live stream data a from the candidate live stream data set, perform semantic analysis on candidate live stream data a and each event information in the event information list, and obtain the correlation between candidate live stream data a and each event information;

[0217] If there is an event in the event information list whose correlation with candidate live data a is greater than the correlation threshold, then candidate live data a is identified as the first live information associated with the first topic of interest.

[0218] In one or more embodiments, the first live broadcast information includes K live broadcast data, where K is an integer greater than 1;

[0219] The data processing device 1 also includes: a live preview module 105;

[0220] The live preview module 105 is used to display broadcast prompt information and expansion controls in the first display area. The broadcast prompt information includes the amount of live data associated with the first topic of interest.

[0221] The live preview module 105 is also used to respond to the trigger operation of the expand control and display the live preview screen corresponding to each of the K live data in the first display area according to the arrangement order of the K live data.

[0222] In one or more embodiments, when the playback module 103 responds to an information viewing operation for the first display area and outputs live streaming service data in the virtual service space indicated by the first live streaming information, it specifically performs the following steps:

[0223] In response to an information viewing operation targeting the first display area, the live data determined by the information viewing operation is identified as the target live data.

[0224] Determine the business application to which the virtual service space indicated by the target live data belongs, and output the live business data in the virtual service space of the business application.

[0225] In one or more embodiments, when the playback module 103 determines the business application to which the virtual service space indicated by the target live data belongs, and outputs the live service data in the virtual service space of the business application, it specifically performs the following steps:

[0226] Based on the target live streaming data, determine the business application to which the virtual service space corresponding to the target live streaming data belongs;

[0227] If the business application is the information application to which the intelligent agent object belongs, then access the virtual service space in the information application and output the live business data in the virtual service space.

[0228] If the business application is not the information application to which the intelligent agent object belongs, then jump from the information application to the business application, access the virtual service space in the business application, and output the live business data in the virtual service space.

[0229] In one or more embodiments, the data processing device 1 further includes: a live streaming sorting module 106;

[0230] The live streaming sorting module 106 is used to obtain the live streaming indicator information indicated by each of the K live streaming data, and determine the second popularity parameter value corresponding to each live streaming data based on the live streaming indicator information indicated by each live streaming data.

[0231] The live streaming sorting module 106 is also used to sort the second popularity parameter value corresponding to each live streaming data in descending order to determine the sorting order of K live streaming data. The sorting order is used to determine the display position of K live streaming data in the first display area.

[0232] In one or more embodiments, the dialog page also includes an interactive input box;

[0233] The data processing device also includes: a live update module 107;

[0234] The live update module 107 is used to respond to input operations on the interactive input box and to display the input content determined by the input operation and the second information associated with the input content in the second display area of ​​the dialog page.

[0235] The live stream update module 107 is also used to update the first live stream information to a second live stream information associated with the input content in the first display area of ​​the dialogue page.

[0236] In one or more embodiments, the data processing apparatus further includes: a semantic analysis module 108;

[0237] The semantic analysis module 108 is used to obtain the input content in the interactive input box, perform semantic analysis on the input content, and obtain the semantic features of the input content.

[0238] The semantic analysis module 108 is also used to determine a second topic of interest that matches the semantic features of the content in the information application to which the intelligent agent object belongs, and to obtain second information information of the second topic of interest. The second information information is used to display in the second display area of ​​the dialogue page.

[0239] The semantic analysis module 108 is also used to perform semantic analysis on each candidate live stream data in the candidate live stream data set for the second topic of interest, and to determine the second live stream information associated with the second topic of interest.

[0240] In one or more embodiments, the interactive control includes an interactive overlay, which is displayed independently on the topic information page, and the interactive overlay includes a term area;

[0241] The data processing device 1 also includes: a term carousel module 109;

[0242] The term carousel module 109 is used to carousel N event terms of the first topic of interest in the term area of ​​the interactive overlay, where N is a positive integer.

[0243] In one or more embodiments, when the second display module 102 responds to a trigger operation on the interactive control and displays the dialogue page of the smart agent object, it is specifically used to perform the following steps:

[0244] In response to a trigger operation targeting a term area, the event term displayed in the term area is identified as the target term, and the dialogue page of the intelligent agent object is displayed. The dialogue page includes a first display area and a second display area.

[0245] The first live broadcast information associated with the target term is displayed in the first display area, and the first news information of the target term is displayed in the second display area.

[0246] According to one embodiment of this application, the foregoing Figure 2 The data processing method shown can be related to the steps involved by Figure 9 The data processing apparatus 1 shown is executed by each module. For example, Figure 2 The step S101 shown can be performed by Figure 9 The first display module 101 shown is used to perform this function. Figure 2 The step S102 shown can be performed by Figure 9 The second display module shown is used to execute this. Figure 2 The step S103 shown can be performed by Figure 9 The playback module 103 shown is used to perform the above.

[0247] According to one embodiment of this application, Figure 9The modules in the data processing device 1 shown can be individually or entirely combined into one or more modules, or some of the modules can be further divided into at least two functionally smaller units to achieve the same operation without affecting the technical effects of the embodiments of this application. The above modules are based on logical function division. In practical applications, the function of one module can also be implemented by at least two units, or the function of at least two modules can be implemented by one module. In other embodiments of this application, the data processing device 1 may also include other modules or units. In practical applications, these functions can also be implemented with the assistance of other modules, and can be implemented collaboratively by at least two modules.

[0248] In this embodiment, an interactive control for an intelligent agent object can be displayed on the topic information page corresponding to the first topic of interest. Triggering this interactive control displays a dialogue page for the intelligent agent object. This dialogue page may include a first display area, which can be used to display first live information associated with the first topic of interest. Triggering the first live information in the first display area allows quick access to the virtual service space indicated by the first live information to watch live business data. By associating event information of the topic of interest with the current live information, live information of interest to the user can be quickly obtained, improving the efficiency and accuracy of obtaining live information. When the dialogue topic between the business object and the intelligent agent object changes, the intent of the business object can be identified to quickly determine the second live information associated with the updated topic (second topic of interest), avoiding the omission of real-time information in the information application and improving the real-time performance of the information application.

[0249] Please see Figure 10 , Figure 10 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 10 As shown, the computer device 1000 can be a terminal device, for example, the one described above. Figure 1 The terminal device 10a in the corresponding embodiment can also be a server, for example, as described above. Figure 1The server 10d in the corresponding embodiment will not be limited here. For ease of understanding, this application takes a computer device as an example as the terminal device. The computer device 1000 may include: a processor 1001, a network interface 1004, and a memory 1005. In addition, the computer device 1000 may also include: a user interface 1003, and at least one communication bus 1002. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The memory 1005 may also optionally be at least one storage device located remotely from the aforementioned processor 1001. Figure 10 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a device control application.

[0250] The network interface 1004 in the computer device 1000 can also provide network communication functions, and the optional user interface 1003 can also include a display screen and a keyboard. Figure 10 In the computer device 1000 shown, the network interface 1004 provides network communication functionality; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to achieve:

[0251] On the topic information page corresponding to the first topic of interest, the interactive controls for the intelligent agent object are displayed;

[0252] In response to a trigger operation on an interactive control, a dialogue page of the intelligent agent object is displayed, which includes a first display area for displaying first live information associated with a first topic of interest;

[0253] In response to an information viewing operation targeting the first display area, output live streaming business data in the virtual service space indicated by the first live streaming information.

[0254] It should be understood that the computer device 1000 described in the embodiments of this application can perform the foregoing... Figure 2 , Figure 8 The description of the data processing method in any of the embodiments can also be performed as described above. Figure 9The description of the data processing device 1 in the corresponding embodiments will not be repeated here. Furthermore, the beneficial effects of using the same method will also not be repeated here.

[0255] Furthermore, it should be noted that this application embodiment also provides a computer-readable storage medium, which stores a computer program executed by the aforementioned data processing device 1. The computer program includes computer instructions, and when the processor executes the computer instructions, it can execute the aforementioned... Figure 2 , Figure 8 The description of the data processing method in any of the embodiments is redundant and will not be repeated here. Similarly, the beneficial effects of using the same method will not be repeated here either. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. For technical details not disclosed in the embodiments of the computer-readable storage medium involved in this application, please refer to the description of the method embodiments of this application. As an example, program instructions can be deployed and executed on a single computer device, or on multiple computer devices located in one location, or on multiple computer devices distributed across multiple locations and interconnected via a communication network. Multiple computer devices distributed across multiple locations and interconnected via a communication network can constitute a blockchain system.

[0256] Furthermore, it should be noted that this application also provides a computer program product, which may include a computer program that can be stored in a computer-readable storage medium. The processor of a computer device reads the computer program from the computer-readable storage medium, and the processor can execute the computer program, causing the computer device to perform the aforementioned... Figure 2 , Figure 8 The description of the data processing method in any of the embodiments is redundant and will not be repeated here. Similarly, the beneficial effects of using the same method will not be repeated here either. For technical details not disclosed in the computer program products or computer program embodiments related to this application, please refer to the description of the method embodiments of this application.

[0257] The terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish different media content, not to describe a specific order. Furthermore, the term "comprising," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other step units inherent to these processes, methods, apparatuses, products, or devices.

[0258] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0259] The methods and related apparatuses provided in this application are described with reference to the method flowcharts and / or structural diagrams provided in this application. Specifically, each block of the method flowchart and / or structural diagram, as well as combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to create a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, generate instructions for implementing the process. Figure 1 A schematic diagram of one or more processes and / or structures. Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 A schematic diagram of one or more processes and / or structures. Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 A process or multiple processes and / or structures illustrate the steps of the functions specified in one or more boxes.

[0260] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0261] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A data processing method, characterized in that, include: On the topic information page corresponding to the first topic of interest, the interactive controls for the intelligent agent object are displayed; In response to a trigger operation on the interactive control, a dialogue page of the intelligent agent object is displayed. The dialogue page includes a first display area, which is used to display first live broadcast information associated with the first topic of interest. In response to an information viewing operation targeting the first display area, live streaming service data is output in the virtual service space indicated by the first live streaming information.

2. The method according to claim 1, characterized in that, The method further includes: In response to the launch operation of the information application, the information flow display page of the information application is displayed. The information flow display page includes a follow topic area, which is used to display M follow topics, where M is a positive integer. In response to the first selection operation for the area of ​​interest, the topic of interest determined by the first selection operation is identified as the first topic of interest, and the topic information page corresponding to the first topic of interest is displayed.

3. The method according to claim 2, characterized in that, The first selection operation includes a swipe operation and a click operation; The response to the first selection operation of the topic of interest region, defining the topic of interest determined by the first selection operation as the first topic of interest, includes: In response to the swipe operation on the area of ​​interest, update the displayed interest topics in the area of ​​interest according to the swipe speed indicated by the swipe operation; In response to a click operation on a topic within the topic area of ​​interest, the topic of interest determined by the click operation is identified as the first topic of interest.

4. The method according to claim 1, characterized in that, The interactive controls for displaying the intelligent agent object are shown on the topic information page corresponding to the first topic of interest, including: On the topic information page corresponding to the first topic of interest, a list of event information corresponding to the first topic of interest is displayed; Obtain the first feedback data for each event in the event information list, and determine the second feedback data for the first topic of interest based on the first feedback data for each event. Obtain the traffic data and topic type of the first topic of interest, and determine the first popularity parameter value of the first topic of interest based on the second feedback data, the traffic data, and the topic type. If the first popularity parameter value is greater than the parameter threshold, then the interactive control of the intelligent agent object is displayed on the topic information page.

5. The method according to claim 4, characterized in that, The step of determining the first popularity parameter value of the first topic of interest based on the second feedback data, the traffic data, and the topic type includes: Obtain a topic popularity reference table, and based on the topic popularity reference table, map the second feedback data to feedback parameter values, map the traffic data to traffic parameter values, and map the topic type to type parameter values; The first popularity parameter value of the first topic of interest is obtained by summing the feedback parameter value, the traffic parameter value, and the type parameter value.

6. The method according to claim 1, characterized in that, The dialog page also includes a second display area; The method further includes: Based on the event information list corresponding to the first topic of interest, generate a topic summary text for the first topic of interest, and determine the event information list and the topic summary text as the first information information of the first topic of interest. Obtain first live stream information associated with the first topic of interest, display the first live stream information in the first display area, and display the first news information in the second display area.

7. The method according to claim 6, characterized in that, The step of generating a topic summary text for the first topic of interest based on the event information list corresponding to the first topic of interest includes: Obtain the event information list corresponding to the first topic of interest, concatenate the text content of each event information in the event information list to obtain the initial text data of the first topic of interest, remove invalid characters from the initial text data to obtain candidate text data; The candidate text data is converted into a text embedding representation, and features are extracted from the text embedding representation to obtain a text semantic feature sequence of the candidate text data; The text semantic feature sequence is decoded to obtain the character probability distribution of each text semantic feature in the text semantic feature sequence, and the topic summary text of the first topic of interest is generated based on the character probability distribution.

8. The method according to claim 6, characterized in that, The step of obtaining the first live broadcast information associated with the first topic of interest includes: Obtain a candidate live streaming data set, obtain candidate live streaming data a from the candidate live streaming data set, perform semantic analysis on the candidate live streaming data a and each event information in the event information list, and obtain the correlation degree between the candidate live streaming data a and each event information; If there is an event in the event information list whose correlation with the candidate live data a is greater than the correlation threshold, then the candidate live data a is determined as the first live information associated with the first topic of interest.

9. The method according to claim 1, characterized in that, The first live broadcast information includes K live broadcast data points, where K is an integer greater than 1; The method further includes: The broadcast prompt information and expansion control are displayed in the first display area. The broadcast prompt information includes the number of live data related to the first topic of interest. In response to a trigger operation on the expand control, the live preview screens corresponding to the K live data are displayed in the first display area according to the arrangement order of the K live data.

10. The method according to claim 9, characterized in that, The response to the information viewing operation in the first display area outputs live streaming service data in the virtual service space indicated by the first live streaming information, including: In response to an information viewing operation targeting the first display area, the live data determined by the information viewing operation is identified as the target live data. Determine the business application to which the virtual service space indicated by the target live data belongs, and output the live service data in the virtual service space of the business application.

11. The method according to claim 10, characterized in that, The step of determining the business application to which the virtual service space indicated by the target live data belongs, and outputting live service data in the virtual service space of the business application, includes: Based on the target live streaming data, determine the business application to which the virtual service space corresponding to the target live streaming data belongs; If the business application is the information application to which the intelligent agent object belongs, then access the virtual service space in the information application and output the live broadcast business data in the virtual service space; If the business application is not the information application to which the intelligent agent object belongs, then the user is redirected from the information application to the business application, accesses the virtual service space in the business application, and outputs live business data in the virtual service space.

12. The method according to claim 9, characterized in that, The method further includes: Obtain the live streaming indicator information indicated by each of the K live streaming data, and determine the second popularity parameter value corresponding to each live streaming data based on the live streaming indicator information indicated by each live streaming data. The second popularity parameter value corresponding to each live data is sorted in descending order to determine the arrangement order of the K live data. The arrangement order is used to determine the display position of the K live data in the first display area.

13. The method according to claim 1, characterized in that, The dialog page also includes interactive input boxes; The method further includes: In response to an input operation on the interactive input box, the input content determined by the input operation and the second information associated with the input content are displayed in the second display area of ​​the dialog page; In the first display area of ​​the dialog page, the first live broadcast information is updated and displayed as the second live broadcast information associated with the input content.

14. The method according to claim 13, characterized in that, The method further includes: Obtain the input content in the interactive input box, perform semantic analysis on the input content, and obtain the content semantic features of the input content; In the information application to which the intelligent agent object belongs, a second topic of interest that matches the semantic features of the content is determined, and second information information of the second topic of interest is obtained. The second information information is used to display in the second display area of ​​the dialogue page. Semantic analysis is performed on each candidate live stream data in the second topic of interest and the candidate live stream data set to determine the second live stream information associated with the second topic of interest.

15. The method according to claim 1, characterized in that, The interactive control includes an interactive overlay, which is displayed independently on the topic information page, and the interactive overlay includes a term area. The method further includes: In the term area of ​​the interactive overlay, N event terms of the first topic of interest are rotated, where N is a positive integer.

16. The method according to claim 15, characterized in that, The response to the triggering operation of the interactive control displays the dialogue page of the intelligent agent object, including: In response to a trigger operation targeting the term area, the event term displayed in the term area is identified as the target term, and the dialogue page of the intelligent agent object is displayed, the dialogue page including the first display area and the second display area; The first live broadcast information associated with the target term is displayed in the first display area, and the first news information of the target term is displayed in the second display area.

17. A data processing apparatus, characterized in that, include: The first display module is used to display the interactive controls of the intelligent agent object on the topic information page corresponding to the first topic of interest; The second display module is used to respond to the trigger operation of the interactive control and display the dialogue page of the intelligent agent object. The dialogue page includes a first display area, which is used to display the first live broadcast information associated with the first topic of interest. The playback module is used to respond to information viewing operations for the first display area and output live streaming service data in the virtual service space indicated by the first live streaming information.

18. A computer device, characterized in that, Including memory and processor; The memory is connected to the processor, the memory is used to store computer programs, and the processor is used to invoke the computer programs so that the computer device performs the method according to any one of claims 1 to 16.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded and executed by a processor to cause a computer device having the processor to perform the method of any one of claims 1 to 16.

20. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 16.

Images