Content generation method and device

Abstract

The embodiment of the invention provides a content generation method and related equipment / products, and belongs to the technical field of live broadcast. The content generation method comprises the steps that interaction data of a target object for a target live broadcast room is acquired, the interaction data comprises multiple pieces of interaction content, and each piece of interaction content is associated with a corresponding live broadcast segment; determining an interaction label of the target object based on the plurality of interaction contents; based on the interaction label of the target object, target interaction content is determined from the multiple pieces of interaction content, and the target interaction content is matched with the interaction label; and generating live broadcast review content for being pushed to the target object based on the target interaction content and the corresponding live broadcast segment. According to the technical scheme provided by the embodiment of the invention, the interaction data of the audience in the live broadcast process is analyzed, and the intelligent label technology is combined, so that the personalized review content can be generated for the audience, and the audience can review the interaction with the anchor, thereby improving the platform return visit rate and the audience stickiness.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of live broadcast technology, and in particular to a content generation method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In current online live streaming, only a simple notification to end the broadcast or a recommendation for another host is displayed after the broadcast ends. This immediately disconnects the viewer from the live content, leaving them with a lack of subsequent review and feedback. However, existing live review mechanisms simply provide viewers with a full replay of the entire show, failing to personalize it for audience interaction. This results in unengaging review content and fails to improve platform return rates and audience engagement.

[0003] It should be noted that the above content is not necessarily prior art, nor is it intended to limit the scope of patent protection of this application. Summary of the Invention

[0004] The embodiments of the present application provide a content generation method, apparatus, computer device, computer-readable storage medium, and computer program product to solve or alleviate one or more technical problems raised above.

[0005] One aspect of an embodiment of the present application provides a content generation method for a server, the method comprising: Obtaining interaction data of a target object with respect to a target live broadcast room, wherein the interaction data includes a plurality of interaction contents, and each interaction content is associated with a corresponding live broadcast segment; Determining an interaction tag for the target object based on the multiple interactive contents; Determining target interactive content from the plurality of interactive contents based on the interactive tag of the target object, the target interactive content matching the interactive tag; Based on the target interactive content and the corresponding live broadcast segment, live broadcast review content is generated for being pushed to the target object.

[0006] Optionally, the interactive content includes the interactive time; correspondingly, the live broadcast segment corresponding to the interactive content is determined by the following operations: Determining the interaction time according to the interaction content; Based on the interactive content and the interactive time, a corresponding live segment is determined from the live stream of the target live room; wherein the corresponding live segment includes: the response of the host of the target live room to the interactive content; and / or a live event associated with the interactive content.

[0007] Optionally, one interactive content corresponds to one interactive operation, the interactive operation includes multiple interactive types, and each interactive content corresponds to one interactive type; correspondingly, determining the interactive tag of the target object based on the multiple interactive contents includes: Determining the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type based on the multiple interactive contents; Determine the interaction label of the target object based on the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type.

[0008] Optionally, the interactive tag includes a plurality of tags, each of which is configured with a corresponding priority; correspondingly, based on the target interactive content and the corresponding live broadcast segment, generating live broadcast review content for pushing to the target object includes: Determining a candidate review template from a plurality of pre-configured review templates according to the interaction tag; wherein the candidate review template matches the plurality of tags; Determining a target review template from the candidate review templates according to the priorities corresponding to the multiple tags; wherein the target review template matches a target tag, and the target tag is a tag with a higher priority than the remaining tags among the multiple tags; According to the target review template, the target interactive content and the corresponding live broadcast segment, live broadcast review content for being pushed to the target object is generated.

[0009] Optionally, based on the target interactive content and the corresponding live broadcast segment, generating live broadcast review content for pushing to the target object includes: Acquiring preference information of the target object; wherein the preference information includes the editing mode preferred by the target object; Determining a target review template from a plurality of pre-configured review templates based on the preference information and interaction tags of the target object; wherein each review template is associated with a preset interaction tag and editing mode; According to the target review template, the target interactive content and the corresponding live broadcast segment, live broadcast review content for being pushed to the target object is generated.

[0010] Optionally, the content generation method further includes: Acquire historical operation data of the target object, where the historical operation data is used to indicate an operation mode of the target object; Determining a target push time according to an operation mode of the target object; Within the target push time, the live broadcast review content is pushed to the target object.

[0011] Optionally, pushing the live broadcast review content to the target object includes: Acquire push configuration information of the target object, the push configuration information including the push channel selected by the target object; When the push configuration information is obtained, the live broadcast review content is pushed to the target object through the push channel selected by the target object; In the case where the push configuration information is not obtained, a target push channel is determined from a plurality of preset push channels according to the operation mode of the target object, and the live broadcast review content is pushed to the target object through the target push channel.

[0012] Another aspect of an embodiment of the present application provides a content generation device for a server, the device comprising: An acquisition module is used to acquire interaction data of a target object with respect to a target live broadcast room, wherein the interaction data includes a plurality of interaction contents, and each interaction content is associated with a corresponding live broadcast segment; A first determining module, configured to determine an interactive tag of the target object based on the plurality of interactive contents; a second determining module, configured to determine target interactive content from the plurality of interactive contents based on the interactive tag of the target object, wherein the target interactive content matches the interactive tag; A generation module is used to generate live review content for pushing to the target object based on the target interactive content and the corresponding live segment.

[0013] Another aspect of an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein: the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0014] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0015] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the above-mentioned method when executed by a processor.

[0016] The above technical solution adopted in the embodiments of the present application may have the following advantages: The interactive data of the audience in the live broadcast room is obtained, wherein the interactive data includes multiple interactive contents, and each interactive content is associated with a corresponding live broadcast segment. Based on the multiple interactive contents, the interactive tags of the audience are determined, and the target interactive content that matches the interactive tags is screened out from the multiple interactive contents. Based on the target interactive content and the corresponding live broadcast segment, live broadcast review content is generated and pushed to the audience. It can be seen that the embodiment of the present application can generate personalized review content for the audience by analyzing the interactive data of the audience during the live broadcast process and combining it with smart tag technology, so that the audience can review the interaction between the audience and the anchor, thereby improving the live broadcast experience, platform return rate and audience stickiness. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings illustrate exemplary embodiments and constitute a part of the specification. Together with the description of the specification, they serve to explain exemplary implementation of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals designate similar, but not necessarily identical, elements.

[0018] Figure 1 The following schematically shows an operating environment diagram of the content generation method according to the first embodiment of the present application; Figure 2 The following schematically shows a flow chart of a content generation method according to the first embodiment of the present application; Figure 3 The flowchart of determining the live broadcast segment corresponding to the interactive content according to the first embodiment of the present application is schematically shown; Figure 4 Schematically shows Figure 2 Flowchart of sub-steps of step S202; Figure 5 Schematically shows Figure 2 Flowchart of sub-steps of step S206; Figure 6 Schematically shows Figure 2 Flowchart of sub-steps of step S206; Figure 7 Schematically shows a newly added flow chart of the content generation method according to the first embodiment of the present application; Figure 8 Schematically shows Figure 7 Flowchart of sub-steps of step S704; Figure 9 A block diagram schematically shows a content generation device according to the second embodiment of the present application; and Figure 10 The following schematically shows a hardware architecture diagram of a computer device according to the third embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this application more clear, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] It should be noted that the descriptions of "first", "second", etc. in the embodiments of the present application are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0021] In the description of this application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed. They are only used to facilitate the description of this application and to distinguish each step. Therefore, they cannot be understood as limitations on this application.

[0022] First, an explanation of the terms used in this application is provided: APP (Application): application.

[0023] Secondly, to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the following describes the relevant technologies: In current online live broadcasts, only a simple shutdown prompt or recommendation of other anchors is displayed after the live broadcast ends, resulting in the connection between the audience and the live content being immediately severed when the live broadcast ends, and there is a lack of subsequent review and feedback.

[0024] However, the applicant has learned that the relevant live review mechanism directly provides viewers with a full replay of the entire show, which has the following drawbacks: (1) The review content is relatively general and lacks the ability to be personalized and adapted to the audience, making it difficult to truly attract the audience.

[0025] (2) The review content does not take into account the audience’s interactive operations during the live broadcast, lacks feedback on the audience’s interactive operations, and cannot enhance the audience’s sense of participation.

[0026] (3) After the live broadcast ends, the connection between the audience and the live broadcast content is immediately cut off, and there is a lack of effective connection, which makes it impossible to continue to improve the audience's sense of participation and activity after the live broadcast ends, thereby affecting the platform's return visit rate and audience stickiness.

[0027] To this end, the embodiment of the present application provides a technical solution for content generation. In this technical solution: (1) by analyzing the audience's interactive operations, personalized review content is generated, allowing the audience to re-experience the interaction with the anchor, improving their sense of participation and live interactive experience. (2) by intelligently pushing the audience's personalized review content, the audience is encouraged to visit the live broadcast platform again after the live broadcast, thereby improving the platform's return rate and audience stickiness. (3) through intelligent tag technology, review content that meets each viewer's interactive preferences is generated, allowing the audience to feel the personalized care of the platform, thereby enhancing audience stickiness. (4) based on the audience's operation mode, the audience's active time is determined, so as to select the best push time, and personalized review content is pushed through multiple channels to improve the audience's click-through rate and participation. See below for details.

[0028] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0029] like Figure 1 As shown, the operating environment diagram includes: service platform (server) 2, host terminals (4A, 4B, ..., 4M), and viewer terminals (6A, 6B, ..., 6N). In the live broadcast scenario, the host terminals (4A, 4B, ..., 4M) log in to service platform 2, which then pushes live broadcast data to viewer terminals (6A, 6B, ..., 6N) in real time.

[0030] Service platform 2 can provide search services and live broadcast services. It can be a single server, a server cluster or a cloud computing service center. The server can include business servers, video cloud servers, etc.

[0031] The host terminals (4A, 4B, ..., 4M) are used to generate live broadcast data in real time and stream the live broadcast data. The live broadcast data may include audio or video data. The host terminals can be electronic devices such as smartphones and tablets. Alternatively, the host terminals can be virtual computing instances within the service platform 2.

[0032] The viewer terminals (6A, 6B, ..., 6N) can be configured to receive live broadcast data from the host terminal in real time. The viewer terminals (6A, 6B, ..., 6N) can be any type of computing device, such as a smartphone, tablet, laptop, smart TV, or in-car terminal. The viewer terminals (6A, 6B, ..., 6N) can have a built-in browser or dedicated program to receive the live broadcast data and output content to the user. The content can include video, audio, commentary, text data, and / or the like.

[0033] The viewer terminal (6A, 6B, ..., 6N) may include a player. The player may output (e.g., display, present) content to a user. The content may include video, audio, comments, text data, and / or the like. The viewer terminal (6A, 6B, ..., 6N) may include an interface, which may include an input element (touch screen). For example, the input element may be configured to receive user commands, which may cause the viewer terminal (6A, 6B, ..., 6N) to perform various operations, such as sending a comment, entering a comment, sending a gift, giving a like, voting, etc.

[0034] The host terminals (4A, 4B, ..., 4M), the viewer terminals (6A, 6B, ..., 6N), and the service platform 2 may be connected via a network. The network may include various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, and / or proxy devices. The network may include physical links, such as coaxial cable links, twisted-pair cable links, optical fiber links, combinations thereof, and / or the like. The network may also include wireless links, such as cellular links, satellite links, Wi-Fi links, and / or the like.

[0035] It should be noted that Figure 1 The number of host terminals and audience terminals is only illustrative and is not intended to limit the scope of patent protection of this application. Depending on the actual situation, there can be any number of host terminals and audience terminals.

[0036] The following describes the technical solution of the present application through multiple embodiments, taking the service platform (server) 2 as the execution body. It should be noted that these embodiments can be implemented in many different forms and should not be construed as being limited to the embodiments described here.

[0037] Example 1 Figure 2 The flowchart of the content generation method according to the first embodiment of the present application is schematically shown.

[0038] like Figure 2 As shown, the content generation method is used for a server and may specifically include steps S200 to S206, wherein: Step S200: Obtain interaction data of a target object with respect to a target live broadcast room, wherein the interaction data includes a plurality of interaction contents, and each interaction content is associated with a corresponding live broadcast segment.

[0039] Step S202: Determine the interactive tag of the target object based on the multiple interactive contents.

[0040] Step S204 : determining target interactive content from the plurality of interactive contents based on the interactive tag of the target object, wherein the target interactive content matches the interactive tag.

[0041] Step S206: Based on the target interactive content and the corresponding live broadcast segment, generate live broadcast review content for pushing to the target object.

[0042] The content generation method provided in this embodiment obtains the audience's interactive data in the live broadcast room, wherein the interactive data includes multiple interactive contents, and each interactive content is associated with a corresponding live broadcast segment. Based on the multiple interactive contents, the audience's interactive tags are determined, and the target interactive content that matches the interactive tags is screened out from the multiple interactive contents. Based on the target interactive content and the corresponding live broadcast segment, live broadcast review content is generated and pushed to the audience. It can be seen that the embodiment of the present application can generate personalized review content for the audience by analyzing the audience's interactive data during the live broadcast process and combining it with smart tag technology, so that the audience can review the interaction between them and the anchor, thereby improving the live broadcast experience, platform return rate and audience stickiness.

[0043] The following combination Figure 2 , each step in steps S200~S206 and other optional steps are described in detail.

[0044] Step S200 , obtain the target object's interaction data for the target live broadcast room, the interaction data includes multiple interaction contents, and each interaction content is associated with a corresponding live broadcast segment.

[0045] The target audience can be viewers. Viewers can log in to the live streaming platform through a viewer terminal (such as 6A) and access any live streaming room (the target live streaming room) to watch the live content. During the live streaming, viewers can also participate in live interactions through the interface provided by the viewer terminal (such as a touch screen), such as liking, sending barrage comments, voting, and sending gifts. Each interactive action can generate interactive content, which can include a detailed record of the corresponding interactive action. For example, if the interactive action is "send a gift," the corresponding interactive content may include the gift type, gift amount, sending time, and number of gifts. Another example is if the interactive action is "vote," the corresponding interactive content may include the voting time and voting options. Each interactive action can also generate a corresponding live clip in the live streaming room. For example, if the interactive action is "send a barrage comment," the corresponding live clip may include the barrage comment display in the live streaming room, the host's response to the barrage comment, and the live events triggered by the barrage comment (such as special animations or voice prompts). In practical applications, the interactive content and the corresponding live clip can be associated and stored for quick access later. Of course, you can also assign an identifier to the corresponding live segment, and store the live segment identifier in association with the interactive content to further improve query efficiency.

[0046] It should be noted that the embodiments of the present application ensure that all interactive data is obtained in compliance with regulations and with the user's consent, is desensitized, and is protected using encryption technology during transmission and storage to ensure user privacy security.

[0047] In an optional embodiment, the interactive content may include interactive time, such as voting time, gift giving time, like time, and barrage sending time. Figure 3 As shown, the live broadcast segment corresponding to the interactive content can be determined by the following operations: Step S300: Determine the interaction time according to the interaction content.

[0048] Step S302: Based on the interactive content and the interactive time, a corresponding live segment is determined from the live stream of the target live broadcast room. The corresponding live segment includes: the host's response to the interactive content; and / or a live event associated with the interactive content.

[0049] For example, by parsing the interactive content, the interaction time can be obtained. Based on the interactive content and interaction time, corresponding live segments can be extracted from the live stream of the live broadcast room. These live segments may include the host's response to the interactive content and / or live events associated with the interactive content (such as displays, special animations, voice prompts, etc.). For example, when a viewer posts a comment during a live broadcast, the server can extract relevant live segments from the live stream based on the timestamp of the comment. These may include the host's response to the comment, such as reading or replying to the comment, or specific events associated with the comment, such as special animations, voice prompts, and comment displays. When a viewer sends a gift to the host, the server can mark the time of the gift and extract the live segment at that time (the gift display) as well as the host's reaction to the gift. When a viewer participates in a vote during a live broadcast, the server can retrieve the corresponding live segment based on the live events associated with the vote, such as the live segment where the voting results are announced.

[0050] In this embodiment, an algorithm for associating interactive content with live broadcast content is provided to dynamically extract exciting live broadcast segments related to interactive operations (such as barrage interaction, gift giving, voting, etc.), which can improve the accuracy and personalization of subsequently generated review content and effectively optimize the review experience.

[0051] Step S202 , based on the multiple interactive contents, determine the interactive tag of the target object.

[0052] For example, multiple interactive content pieces can be analyzed and, combined with intelligent tagging technology, the target objects can be categorized to obtain interaction tags that accurately describe their interaction characteristics (interaction preferences). For example, viewer A frequently interacts with the host and could be labeled "high-frequency interaction"; viewer B frequently interacts with the host and possesses a fan badge, and could be labeled "active fan" and "high-frequency interaction"; viewer C's gift to the host exceeds a preset amount and could be labeled "large gift giving"; viewer D's participation in voting and a vote hit rate exceeding a preset threshold could be labeled "accurate voting." Of course, interaction tags can include multiple tags. For example, viewer E frequently posts comments, gives a high total gift amount, interacts frequently, and has a high vote hit rate, and could be labeled "active fan," "large gift giving," "high-frequency commenting," and "accurate voting" simultaneously.

[0053] In this embodiment, by analyzing the interactive content of viewers during the live broadcast and labeling it, the interactive characteristics of the viewers can be accurately identified, and personalized review content that is more suitable for the viewers can be generated to enhance the viewer experience. An exemplary solution is provided below.

[0054] In an optional embodiment, the interactive operation includes multiple interactive types (such as: like, share, vote, etc.), and each interactive content corresponds to an interactive type. Figure 4 As shown, step S202 may include: Step S400: Determine the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type based on the multiple interactive contents.

[0055] Step S402: Determine the interaction tag of the target object based on the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type.

[0056] For example, based on multiple interactive content, statistics can be collected for each type of interaction: frequency (e.g., number of likes, shares, and gifts), quality (e.g., voting success rate, gift amount, and gift type), distribution (e.g., whether it is concentrated in a certain time period or evenly distributed throughout the live stream), and / or host response (e.g., whether the host directly responded to the interactive content and the content of the response). Based on the frequency, quality, distribution, and / or host response of each type of interaction, interaction tags (e.g., "active fan," "large gift," "best friend," etc.) can be determined for the target audience, thereby accurately describing the audience's interactive characteristics and optimizing the accuracy and personalization of review content.

[0057] In this embodiment, through statistical analysis of multiple interactive contents, interactive tags that meet the user's interactive characteristics can be generated, providing an effective and accurate decision-making basis for subsequent review content generation.

[0058] Step S204 , based on the interactive tag of the target object, determining target interactive content from the multiple interactive contents, the target interactive content matches the interactive tag.

[0059] For example, based on the viewer's interaction tags, matching interactive content can be selected from multiple interactive contents as target interactive content for generating review content. For example, if the viewer has a "gifting" tag, the server can focus on interactive content related to gifting; if the viewer has a "bullet comment interaction" tag, the server can select interactive content related to sending bullet comments; if the viewer has a "voting participation" tag, the server can select interactive content related to voting.

[0060] In this embodiment, matching interactive content is selected based on the audience's interactive tags to generate review content, which can improve personalization and the audience's live review experience.

[0061] Step S206 Based on the target interactive content and the corresponding live broadcast segment, a live broadcast review content is generated for pushing to the target object.

[0062] Exemplarily, based on the target interactive content and the corresponding live broadcast clips, personalized live broadcast review content can be generated for the target object. For example, in the case where the interactive tag is "high-frequency interaction", the target interactive content can be the detailed content of interactive operations such as gift giving and voting. Live broadcast review content can be generated based on the target interactive content and the corresponding live broadcast clips, which may include live broadcast clips, pictures (such as representative key frames), interaction introductions, etc. for each interaction with the anchor (such as: a total of n likes, m gifts, the most given gift is a rocket, and the anchor expressed p times of gratitude to you). The server can send the live broadcast review content to the audience terminal, and the audience terminal can display an exclusive review page based on the received live broadcast review content. The page can include the highlight interaction moments between the audience and the anchor, gift giving records, voting records, etc., and supports the display of multiple elements such as live broadcast clips, pictures, text (such as interaction introductions), thereby presenting a complete personalized review content.

[0063] In this embodiment, personalized review content is generated based on the target interactive content and the corresponding live broadcast segment, which can provide viewers with a customized review experience, enhance the audience's sense of participation and the platform's return visit rate.

[0064] In practical applications, personalized live review content can also be automatically generated for each viewer based on a preset template and / or editing algorithm. An exemplary solution is provided below.

[0065] In an optional embodiment, the interactive tag includes multiple tags, each of which can be configured with a corresponding priority. Figure 5As shown, step S206 may include: Step S500 : determining a candidate review template from a plurality of pre-configured review templates according to the interactive tag; wherein the candidate review template matches the plurality of tags.

[0066] Step S502 : determining a target review template from the candidate review templates according to the priorities corresponding to the multiple tags; wherein the target review template matches a target tag, which is a tag with a higher priority than the remaining tags among the multiple tags.

[0067] Step S504: Generate live review content for pushing to the target object based on the target review template, the target interactive content and the corresponding live segment.

[0068] For example, one or more tags can be assigned to a target audience based on the frequency, quality, distribution, and / or host response of each interaction type, and each tag can be assigned a corresponding priority. For example, if a viewer gives a large gift amount and sends a large number of barrage comments, the tags could be "gifting" and "barrage comments." However, if the gift amount is significantly higher than the average, "gifting" can be prioritized over "barrage comments." If the gift amount is close to the average and the number of barrage comments is significantly higher than the average, "barrage comments" can be prioritized over "gifting." If the interaction frequency, quality, distribution, and / or host response are similar, the same or similar priorities can be assigned. Multiple pre-configured review templates are available, where one review template corresponds to one interaction tag (a combination of tags). However, one interaction tag can have multiple corresponding review templates, and these corresponding review templates may differ in display style and style. Based on the interaction tags (e.g., "gifting" + "barrage comments"), matching candidate review templates can be identified, such as a "highlight template" that combines interaction and gifting. Based on the priorities of multiple tags, a target review template is determined from the candidate review templates. The target review template corresponds to the target tag, which can be one or more tags with higher priorities. For example, if "gifting" has a higher priority than "bullet comment," the candidate review template with the higher proportion of "gifting" can be selected as the target review template. Based on the target review template, the target interactive content, and the corresponding live broadcast clip, live broadcast review content can be generated for push to viewers.

[0069] In this embodiment, a more suitable review template is selected according to the priority of the tag, so that more personalized and targeted live review content can be generated for the audience, thereby improving the accuracy of the review content and the audience participation experience.

[0070] In an optional embodiment, if Figure 6As shown, step S206 may include: Step S600: Obtain preference information of the target object; wherein the preference information includes the editing mode preferred by the target object.

[0071] Step S602 : determining a target review template from a plurality of pre-configured review templates based on the preference information and interaction tag of the target object; wherein each review template is associated with a preset interaction tag and editing mode.

[0072] Step S604: Generate live review content for pushing to the target object based on the target review template, the target interactive content and the corresponding live segment.

[0073] For example, multiple review templates can be pre-configured, and each review template is associated with a preset interactive tag and editing mode. The review template is used to combine live broadcast segments corresponding to interactive tags (several tags). Editing modes can correspond to different editing algorithms, such as simple combined editing, transitions, filters, special effects editing, etc. In actual applications, the server can obtain the preference information of the target object, that is, which editing mode the audience likes. Based on the target object's preference information and interactive tags, the target review template can be quickly determined from multiple review templates. Based on the target review template, target interactive content and corresponding live broadcast segments, live broadcast review content can be generated for push to the audience.

[0074] In this embodiment, by selecting a matching review template based on the viewer's preference information and interactive tags, personalized live review content that better suits the viewer's preferences can be customized for the viewer, thereby improving the viewer experience and platform competitiveness.

[0075] The above embodiments exemplify how to generate personalized live review content for viewers. The following further exemplifies how to push the live review content to viewers.

[0076] In an optional embodiment, if Figure 7 As shown, the content generation method may further include: Step S700: Acquire historical operation data of the target object, where the historical operation data is used to indicate an operation mode of the target object.

[0077] Step S702: Determine a target push time according to the operation mode of the target object.

[0078] Step S704: Push the live broadcast review content to the target object within the target push time.

[0079] For example, historical operational data of viewers can be obtained, such as online time and browsing history. Based on this historical operational data, the target user's operational pattern, such as active hours and operational habits, can be determined. Based on the operational pattern, a target push time can be determined. Within the target push time, the live broadcast review content is pushed to the target user. For example, if the viewer is highly active after the live broadcast, the server can use the period after the live broadcast as the optimal push time to push the live broadcast review content to the viewer. If the viewer is accustomed to checking messages the next day, the push can be made early the next morning.

[0080] In this embodiment, by analyzing the viewer's operation mode to optimize the push time and automatically select the best push opportunity, the push effect and user click rate can be improved.

[0081] In an optional embodiment, if Figure 8 As shown, step S704 may include: Step S800: Acquire push configuration information of the target object, where the push configuration information includes a push channel selected by the target object.

[0082] Step S802: When the push configuration information is obtained, the live broadcast review content is pushed to the target object through the push channel selected by the target object.

[0083] Step S804: If the push configuration information is not obtained, a target push channel is determined from a plurality of preset push channels according to the operation mode of the target object, and the live broadcast review content is pushed to the target object through the target push channel.

[0084] For example, the target user's push configuration information can be obtained, including the target user's pre-defined push channels, such as personal updates, private messages, and live broadcast room messages. If the push configuration information is obtained, the live broadcast review content can be pushed to the target user via the push channel selected by the target user. If the push configuration information is not obtained, the target push channel can be determined from multiple push channels based on the target user's operating mode (determining the channel they are most likely to view based on their historical operating data), such as in-site notifications, app push, and the live broadcast end page. The live broadcast review content is pushed to the target user via the target push channel.

[0085] In this embodiment, personalized review content is pushed to users through multiple channels, pushing efficiency is optimized, the exposure of review content is increased, and click-through rate and interaction rate are improved.

[0086] In order to make this application easier to understand, two exemplary applications are provided below.

[0087] Application 1: During a livestream, viewer A frequently posts comments and sends multiple gifts. The server records viewer A's interaction data in real time. Based on the frequent comments, the server extracts the highlights of viewer A's comments during the livestream. Combined with the time period of gift-giving, the server generates a highlight recap video that includes both the comments and the gift-giving moments. The server pushes the generated recap video to viewer A's app, where they click to watch, enhancing their engagement.

[0088] Application 2: Viewer B participated in a voting interaction and expressed his or her opinion through commentary and gift-giving when the results were announced. Based on Viewer B's voting behavior and gift-giving history, the server extracted highlights from the voting results and generated a personalized recap page containing these highlights. This recap page was pushed to Viewer B via an in-site notification. Viewer B viewed the recap the next day, increasing audience engagement on the platform.

[0089] In this exemplary application: (1) Real-time data collection and analysis: By real-time monitoring and collecting the audience's interactive operations during the live broadcast (such as likes, bullet screens, gift giving, voting, etc.), these interactive data are labeled and processed to generate personalized review content later. (2) Behavior-content association algorithm and personalized review generation: Based on the association algorithm between interactive operations and live broadcast content, the wonderful live broadcast clips related to the interactive operations (such as bullet screen interactions, gift giving, voting, etc.) are dynamically extracted, and personalized review content is automatically generated based on the audience's preferences and interaction types. (3) Personalized review page generation and display: Based on the generated review content, a dedicated review page is generated for each viewer, including the audience's highlight interaction moments with the anchor, gift giving records, voting records, etc., and supports the display of multiple elements such as video clips, pictures, and interactive data. (4) Intelligent push strategy and multi-channel push: Based on the audience's operation mode (operation habits and active time), the best push time is automatically selected, and personalized review content is pushed to the audience through multiple channels (such as APP push, site notifications, etc.), thereby improving the return visit rate and audience participation.

[0090] Example 2 Figure 9 The block diagram of the content generation device according to the second embodiment of the present application is schematically shown. The device can be used in a server and is further divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can perform specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Figure 9 As shown, the apparatus 1000 may include: an acquisition module 1100, a first determination module 1200, a second determination module 1300, and a generation module 1400, wherein: An acquisition module 1100 is configured to acquire interaction data of a target object with respect to a target live broadcast room, wherein the interaction data includes a plurality of interaction contents, each of which is associated with a corresponding live broadcast segment; A first determining module 1200 is configured to determine an interactive tag of the target object based on the plurality of interactive contents; A second determining module 1300 is configured to determine a target interactive content from the plurality of interactive contents based on the interactive tag of the target object, wherein the target interactive content matches the interactive tag; The generation module 1400 is used to generate live review content for pushing to the target object based on the target interactive content and the corresponding live segment.

[0091] As an optional embodiment, the interactive content includes the interactive time; correspondingly, the live broadcast segment corresponding to the interactive content is determined by the following operations: Determining the interaction time according to the interaction content; Based on the interactive content and the interactive time, a corresponding live segment is determined from the live stream of the target live room; wherein the corresponding live segment includes: the response of the host of the target live room to the interactive content; and / or a live event associated with the interactive content.

[0092] As an optional embodiment, one interactive content corresponds to one interactive operation, the interactive operation includes multiple interaction types, and each interactive content corresponds to one interaction type; correspondingly, determining the interactive tag of the target object based on the multiple interactive contents includes: Determining the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type based on the multiple interactive contents; Determine the interaction label of the target object based on the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type.

[0093] As an optional embodiment, the interactive tag includes multiple tags, each tag is configured with a corresponding priority; correspondingly, based on the target interactive content and the corresponding live broadcast segment, generating live broadcast review content for pushing to the target object includes: Determining a candidate review template from a plurality of pre-configured review templates according to the interaction tag; wherein the candidate review template matches the plurality of tags; Determining a target review template from the candidate review templates according to the priorities corresponding to the multiple tags; wherein the target review template matches a target tag, and the target tag is a tag with a higher priority than the remaining tags among the multiple tags; According to the target review template, the target interactive content and the corresponding live broadcast segment, live broadcast review content for being pushed to the target object is generated.

[0094] As an optional embodiment, based on the target interactive content and the corresponding live broadcast segment, generating live broadcast review content for pushing to the target object includes: Acquiring preference information of the target object; wherein the preference information includes the editing mode preferred by the target object; Determining a target review template from a plurality of pre-configured review templates based on the preference information and interaction tags of the target object; wherein each review template is associated with a preset interaction tag and editing mode; According to the target review template, the target interactive content and the corresponding live broadcast segment, live broadcast review content for being pushed to the target object is generated.

[0095] As an optional embodiment, the content generating device 1000 is further configured to: Acquire historical operation data of the target object, where the historical operation data is used to indicate an operation mode of the target object; Determining a target push time according to an operation mode of the target object; Within the target push time, the live broadcast review content is pushed to the target object.

[0096] As an optional embodiment, pushing the live broadcast review content to the target object includes: Acquire push configuration information of the target object, the push configuration information including the push channel selected by the target object; When the push configuration information is obtained, the live broadcast review content is pushed to the target object through the push channel selected by the target object; In the case where the push configuration information is not obtained, a target push channel is determined from a plurality of preset push channels according to the operation mode of the target object, and the live broadcast review content is pushed to the target object through the target push channel.

[0097] Example 3 Figure 10The following schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing a content generation method according to the third embodiment of the present application. In some embodiments, the computer device 10000 may be a terminal device such as a smartphone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers). Figure 10 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other via a system bus. Memory 10010 includes at least one type of computer-readable storage medium, including flash memory, a hard disk, a multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, an optical disk, and the like. In some embodiments, memory 10010 may be an internal storage module of computer device 10000, such as a hard disk or memory of computer device 10000. In other embodiments, memory 10010 may also be an external storage device of computer device 10000, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, and the like equipped on computer device 10000. Of course, memory 10010 may also include both internal storage modules and external storage devices of computer device 10000. In this embodiment, the memory 10010 is generally used to store an operating system and various application software installed on the computer device 10000, such as program code of a content generation method, etc. In addition, the memory 10010 can also be used to temporarily store various data that has been output or is to be output.

[0098] In some embodiments, processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. Processor 10020 is typically used to control the overall operation of computer device 10000, such as performing control and processing related to data exchange or communication with computer device 10000. In this embodiment, processor 10020 is used to execute program code stored in memory 10010 or process data.

[0099] Network interface 10030 may include a wireless network interface or a wired network interface. Network interface 10030 is typically used to establish a communication link between computer device 10000 and other computer devices. For example, network interface 10030 is used to connect computer device 10000 to an external terminal via a network, establishing a data transmission channel and a communication link between computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile Communications (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth, or Wi-Fi.

[0100] It should be pointed out that Figure 10 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementing all of the shown components is not a requirement, and more or fewer components may alternatively be implemented.

[0101] In this embodiment, the content generation method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0102] Example 4 An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the content generation method in the embodiment are implemented.

[0103] In this embodiment, computer-readable storage media include flash memory, hard disks, multimedia cards, card-type memories (e.g., SD or DX memories), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disks, optical disks, and the like. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the computer device's hard disk or memory. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, and the like. Of course, the computer-readable storage medium may also include both the internal storage unit and external storage devices of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device, such as the program code of the content generation method described in the embodiment. Furthermore, the computer-readable storage medium may also be used to temporarily store various types of data that has been output or is about to be output.

[0104] Example 5 An embodiment of the present application further provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0105] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented using general-purpose computer devices. They can be concentrated on a single computer device or distributed on a network composed of multiple computer devices. Alternatively, they can be implemented using program codes executable by the computer device, so that they can be stored in a storage device and executed by the computer device. In some cases, the steps shown or described can be performed in a different order than herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0106] It should be noted that the above are only preferred embodiments of the present application and do not limit the scope of patent protection of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the scope of patent protection of the present application.

Claims

1. A content generation method, characterized in that: For a server, the method includes: Obtaining interaction data of a target object with respect to a target live broadcast room, wherein the interaction data includes a plurality of interaction contents, and each interaction content is associated with a corresponding live broadcast segment; Determining an interaction tag for the target object based on the multiple interactive contents; Determining target interactive content from the plurality of interactive contents based on the interactive tag of the target object, the target interactive content matching the interactive tag; Based on the target interactive content and the corresponding live broadcast segment, live broadcast review content is generated for being pushed to the target object.

2. The method according to claim 1, characterized in that The interactive content includes the interactive time. Correspondingly, the live segment corresponding to the interactive content is determined by the following operations: Determining the interaction time according to the interaction content; Based on the interactive content and the interactive time, a corresponding live segment is determined from the live stream of the target live room; wherein the corresponding live segment includes: the response of the host of the target live room to the interactive content; and / or a live event associated with the interactive content.

3. The method according to claim 1, characterized in that One interactive content corresponds to one interactive operation, and the interactive operation includes multiple interactive types, and each interactive content corresponds to one interactive type. Correspondingly, based on the multiple interactive contents, determining the interactive tag of the target object includes: Determining the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type based on the multiple interactive contents; Determine the interaction label of the target object based on the interaction frequency, interaction quality, interaction distribution and / or host response of each interaction type.

4. The method according to claim 1, wherein The interactive tag includes multiple tags, each of which is configured with a corresponding priority; Correspondingly, based on the target interactive content and the corresponding live broadcast segment, generating live broadcast review content for pushing to the target object includes: Determining a candidate review template from a plurality of pre-configured review templates according to the interaction tag; wherein the candidate review template matches the plurality of tags; Determining a target review template from the candidate review templates according to the priorities corresponding to the multiple tags; wherein the target review template matches a target tag, and the target tag is a tag with a higher priority than the remaining tags among the multiple tags; According to the target review template, the target interactive content and the corresponding live broadcast segment, live broadcast review content for being pushed to the target object is generated.

5. The method according to claim 1, wherein Based on the target interactive content and the corresponding live broadcast segment, generating live broadcast review content for pushing to the target object, including: Acquiring preference information of the target object; wherein the preference information includes the editing mode preferred by the target object; Determining a target review template from a plurality of pre-configured review templates based on the preference information and interaction tags of the target object; wherein each review template is associated with a preset interaction tag and editing mode; According to the target review template, the target interactive content and the corresponding live broadcast segment, live broadcast review content for being pushed to the target object is generated.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Acquire historical operation data of the target object, where the historical operation data is used to indicate an operation mode of the target object; Determining a target push time according to an operation mode of the target object; Within the target push time, the live broadcast review content is pushed to the target object.

7. The method according to claim 6, characterized in that Pushing the live review content to the target object includes: Acquire push configuration information of the target object, the push configuration information including the push channel selected by the target object; When the push configuration information is obtained, the live broadcast review content is pushed to the target object through the push channel selected by the target object; In the case where the push configuration information is not obtained, a target push channel is determined from a plurality of preset push channels according to the operation mode of the target object, and the live broadcast review content is pushed to the target object through the target push channel.

8. A content generating device, characterized in that: For a server, the device comprises: An acquisition module is used to acquire interaction data of a target object with respect to a target live broadcast room, wherein the interaction data includes a plurality of interaction contents, and each interaction content is associated with a corresponding live broadcast segment; A first determining module, configured to determine an interactive tag of the target object based on the plurality of interactive contents; a second determining module, configured to determine target interactive content from the plurality of interactive contents based on the interactive tag of the target object, wherein the target interactive content matches the interactive tag; A generation module is used to generate live review content for pushing to the target object based on the target interactive content and the corresponding live segment.

9. A computer device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 7 are implemented.

Images