Interaction resource generation method and device, equipment and computer readable storage medium

Abstract

The invention discloses an interaction resource generation method, apparatus and device, and a computer readable storage medium, and belongs to the field of digital technology. The method comprises the steps of obtaining at least one piece of interaction intention information of at least one first user, wherein attributes of the interaction intention information comprise one or more of types and user levels; according to the at least one piece of interaction intention information, a first interaction resource is adjusted, the first interaction resource is the content watched by the first user, the first interaction resource comprises a sub-interaction resource corresponding to the at least one sub-title, and the type of the first interaction resource comprises one or more of a text, an audio, a picture and a video. The first interaction resource is adjusted in real time according to the interaction intention information, and the adjustment efficiency of the first interaction resource is high, so that the first interaction resource is more adaptive to the interaction process, the interaction capability in the interaction scene is improved, and the experience feeling of interaction based on the first interaction resource is improved.

Description

Technical Field

[0001] The present application relates to the field of digital technology, and in particular to a method, device, equipment and computer-readable storage medium for generating interactive resources. Background Art

[0002] With the continuous development of digital technology, interactive behaviors between different objects are becoming more and more common. Taking virtual live broadcast as an example, the objects with interactive behaviors include the virtual anchor who is broadcasting live and the audience watching the live broadcast. The virtual anchor interacts with the audience during the live broadcast and needs to rely on interactive resources to perform actions. Therefore, a method for generating interactive resources is needed. Summary of the invention

[0003] The present application provides a method, apparatus, device and computer-readable storage medium for generating interactive resources to obtain interactive resources for interaction. The technical solution is as follows:

[0004] In a first aspect, a method for generating interactive resources is provided, the method comprising: obtaining at least one interactive intention information of at least one first user, the attributes of the interactive intention information comprising one or more of type and user level, the type of the interactive intention information comprising one or more of text message, reward, like, dislike, share, follow, and unfollow; adjusting a first interactive resource according to the at least one interactive intention information, the first interactive resource being content viewed by the first user, the first interactive resource comprising a sub-interactive resource corresponding to at least one subtitle, the type of the first interactive resource comprising one or more of text, audio, picture, and video.

[0005] The first interactive resource is adjusted in real time according to the interactive intention information generated during the interactive process, thereby improving the real-time performance of the first interactive resource. The adjustment efficiency of the first interactive resource is high, so that the first interactive resource is more adapted to the interactive process, thereby improving the interactive capability in the interactive scenario and the experience of interacting based on the first interactive resource.

[0006] In a possible implementation, the method further includes: receiving an interactive resource adjustment strategy, the interactive resource adjustment strategy including one or more of a priority, a weight, or a threshold corresponding to an attribute of interactive intent information; adjusting the first interactive resource according to at least one interactive intent information includes: adjusting the first interactive resource according to at least one interactive intent information and the interactive resource adjustment strategy. The type of information included in the interactive resource adjustment strategy is not limited, and may be at least one of a priority, a weight, or a threshold, and has high versatility. Regardless of the type of information included in the interactive resource adjustment strategy, the first interactive resource can be adjusted according to the interactive intent information and the interactive resource adjustment strategy, and the flexibility of adjusting the first interactive resource is high.

[0007] In a possible implementation, adjusting the first interactive resource includes: skipping the sub-interaction resources corresponding to the subtitle currently displayed and the n subtitles to be displayed in the first interactive resource, where n is an integer greater than or equal to 0; and displaying the sub-interaction resources corresponding to the n+1 subtitles after the currently displayed subtitle. The sub-interaction resources corresponding to the subtitles that the first user does not want to view can be skipped according to the interactive intention information, thereby achieving flexible display of the first interactive resource and ensuring the viewing experience of the first user.

[0008] In a possible implementation, the first interactive resource is generated based on the second interactive resource. Before obtaining at least one interactive intention information of at least one first user, the method further includes: obtaining reference intention information input by the second user, the reference intention information is used to indicate the theme of the second interactive resource; obtaining at least one subtitle and the text content corresponding to each of the at least one subtitle according to the reference intention information, the subtitle is used to indicate the theme of part of the content in the theme of the second interactive resource; and displaying the second interactive resource, the second interactive resource including at least one subtitle and the text content corresponding to each subtitle. The subtitle is determined by the reference intention information, and the text content corresponding to the subtitle is automatically obtained, thereby generating the second interactive resource required for use in the interactive process. The process of generating the second interactive resource has low manual participation, low generation cost, and high generation efficiency.

[0009] In a possible implementation, the method further includes: obtaining a subtitle configuration request input by a second user, the subtitle configuration request is used to delete a first subtitle in at least one subtitle, or to add a second subtitle; the subtitle configuration request is used to add a second subtitle, the subtitle configuration request also includes a subtitle text of the second subtitle, and the method further includes: obtaining text content corresponding to the second subtitle. The adjustment of the subtitle can be to delete the first subtitle or to add the second subtitle, and the adjustment methods are diverse and highly versatile. In addition, for adding the second subtitle, the text content corresponding to the second subtitle is obtained, and the text content included in the second interactive resource is added to make the text content of the second interactive resource more comprehensive and accurate.

[0010] In a possible implementation, the method further includes: obtaining a media resource corresponding to each of at least one subtitle, the type of the media resource includes one or more of an image, an audio, and a video, and the source of the media resource is one or more of a knowledge base, the Internet, and an artificial intelligence (AI) model generation; and displaying a first interactive resource, the first interactive resource being generated based on a second interactive resource corresponding to each of at least one subtitle and a corresponding media resource. The method of obtaining the media resources required to be used in the process of generating the first interactive resource is not limited, and can be obtained through any method such as a knowledge base, the Internet, and an AI model, which is highly flexible.

[0011] In a possible implementation, the method further includes: receiving a media resource input by a second user; and storing the media resource in a knowledge base. Storing the received media resource in the knowledge base enriches the media resources included in the knowledge base, and the media resources corresponding to each sub-title obtained by searching based on the richer knowledge base are more accurate.

[0012] In a second aspect, a device for generating interactive resources is provided, which includes: an acquisition module for acquiring at least one interactive intention information of at least one first user, the attributes of the interactive intention information include one or more of type and user level, and the type of the interactive intention information includes one or more of text message, reward, like, dislike, share, follow, and unfollow; an adjustment module for adjusting a first interactive resource according to at least one interactive intention information, the first interactive resource being content viewed by the first user, the first interactive resource including a sub-interactive resource corresponding to at least one subtitle, and the type of the first interactive resource including one or more of text, audio, picture, and video.

[0013] In one possible implementation, the device also includes: a receiving module for receiving an interaction resource adjustment strategy, the interaction resource adjustment strategy including one or more of a priority, a weight or a threshold corresponding to the attributes of the interaction intent information; an adjustment module for adjusting the first interaction resource according to at least one interaction intent information and the interaction resource adjustment strategy.

[0014] In a possible implementation, the adjustment module is used to skip the sub-interaction resources corresponding to the currently displayed subtitle and n subtitles to be displayed in the first interaction resource, where n is an integer greater than or equal to 0; and display the sub-interaction resources corresponding to the n+1 subtitle after the currently displayed subtitle.

[0015] In a possible implementation, a first interactive resource is generated based on a second interactive resource, and an acquisition module is further used to acquire reference intent information input by a second user, where the reference intent information is used to indicate a subject of the second interactive resource; at least one subtitle and text content corresponding to each of at least one subtitle are acquired based on the reference intent information, where the subtitle is used to indicate a subject of part of the subject of the second interactive resource; the device also includes: a display module, used to display the second interactive resource, where the second interactive resource includes at least one subtitle and text content corresponding to each subtitle.

[0016] In a possible implementation, the acquisition module is further used to obtain a subtitle configuration request input by a second user, the subtitle configuration request is used to delete a first subtitle in at least one subtitle, or to add a second subtitle; the subtitle configuration request is used to add a second subtitle, the subtitle configuration request also includes a subtitle text of the second subtitle, and the acquisition module is further used to obtain text content corresponding to the second subtitle.

[0017] In one possible implementation, the acquisition module is also used to acquire media resources corresponding to each subtitle in at least one subtitle, where the types of media resources include one or more of images, audio, and video, and the sources of the media resources are one or more of a knowledge base, the Internet, and artificial intelligence (AI) model generation; the display module is also used to display a first interactive resource, which is generated based on a second interactive resource and a corresponding media resource corresponding to each subtitle in at least one subtitle.

[0018] In a possible implementation, the acquisition module is further configured to receive a media resource input by a second user; and store the media resource in a knowledge base.

[0019] In a third aspect, a computing device cluster is provided, the computing device cluster comprising at least one computing device, each computing device comprising a processor and a memory; the processor of at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes any one of the interactive resource generation methods of the first aspect above.

[0020] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes any one of the interactive resource generation methods in the first aspect.

[0021] In a fifth aspect, a computer program (product) comprising instructions is provided. When the instructions are executed by a computing device cluster, the computing device cluster executes any one of the methods for generating interactive resources of the first aspect.

[0022] In a sixth aspect, a communication device is provided, the device comprising: a transceiver, a memory, and a processor. The transceiver, the memory, and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory to control the transceiver to receive signals and control the transceiver to send signals, and when the processor executes the instructions stored in the memory, the processor executes the method in the first aspect or any possible implementation of the first aspect.

[0023] Optionally, the number of the processors is one or more, and the number of the memories is one or more.

[0024] Optionally, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

[0025] In the specific implementation process, the memory can be a non-transitory memory, such as a read-only memory (ROM), which can be integrated with the processor on the same chip or can be set on different chips. This application does not limit the type of memory and the setting method of the memory and the processor.

[0026] In a seventh aspect, a chip is provided, comprising a processor for calling and executing instructions stored in a memory from the memory, so that a communication device equipped with the chip executes the methods in the above aspects.

[0027] In an eighth aspect, another chip is provided, comprising: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the methods in the above aspects.

[0028] It should be understood that the beneficial effects achieved by the technical solutions of the second to eighth aspects of the present application and the corresponding possible implementation methods can be referred to the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of an implementation environment provided for an embodiment of the present application;

[0030] Figure 2 A flowchart of a method for generating interactive resources provided in an embodiment of the present application;

[0031] Figure 3 A schematic diagram of a process for obtaining a resource set provided in an embodiment of the present application;

[0032] Figure 4 A schematic diagram of a process for adjusting a first interaction resource provided in an embodiment of the present application;

[0033] Figure 5 A schematic diagram of an interaction process provided in an embodiment of the present application;

[0034] Figure 6 A schematic diagram of the structure of a device for generating interactive resources provided in an embodiment of the present application;

[0035] Figure 7 A schematic diagram of the structure of a computing device provided in an embodiment of the present application;

[0036] Figure 8 A connection diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The terms used in the implementation method of this application are only used to explain the specific embodiments of this application, and are not intended to limit this application. In order to make the purpose, technical solution and advantages of this application clearer, the implementation method of this application will be further described in detail below with reference to the accompanying drawings.

[0038] With the development of digital technology, more and more interactive scenarios begin to realize the interaction between different objects through interactive resources. Taking the interactive scenario of live broadcast interaction as an example, the different objects for interaction are the anchor who is broadcasting live and the audience watching the live broadcast. The interactive resources can be the video of the anchor's performance played during the live broadcast, the audience watching the played video, and adjusting the played video according to the audience's feedback to realize the interaction between the anchor and the audience. Therefore, a method for generating interactive resources is needed.

[0039] In the related art, the interactive resources displayed are manually adjusted according to the audience's feedback to achieve dynamic generation of interactive resources. However, the method of relying on manual adjustment will result in high acquisition costs of interactive resources and low adjustment efficiency. When the number of audience interaction intentions exceeds the reaction threshold, it will lead to the inability to adjust the interactive resources according to the interaction intentions in time, and the real-time performance of the interactive resources will be reduced. The experience of interaction based on low real-time interactive resources is poor. Among them, the reaction threshold is an indication set according to experience to indicate the number of manual reaction capabilities.

[0040] The embodiment of the present application provides a method for generating interactive resources, which is used to dynamically generate and adjust the interactive resources used in the interactive process. Figure 1 , which shows a schematic diagram of the implementation environment of the interactive resource generation method provided in the embodiment of the present application. The implementation environment is a computing device cluster 10, and the computing device cluster 10 includes at least one orchestration device. The orchestration devices can communicate with each other via a wired or wireless network. Optionally, the interactive resource generation method can be independently executed by an orchestration device, or can be interactively executed by multiple orchestration devices included in the computing device cluster 10. The embodiment of the present application does not limit the number of orchestration devices included in the computing device cluster 10. Figure 1 Only two orchestration devices are used as examples for illustration.

[0041] Exemplarily, the orchestration device included in the computing device cluster 10 can be any network device with data processing function, and the orchestration device can be a server, such as a central server, an edge server, or a local server in a local data center. The server can be a physical server or a cloud server that provides a cloud computing server. In some embodiments, the orchestration device included in the computing device cluster 10 can also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0042] The flowchart of the method for generating interactive resources provided in the embodiment of the present application is as follows: Figure 2 As shown, including S201-S202.

[0043] S201, obtaining at least one interaction intention information of at least one first user, where attributes of the interaction intention information include one or more of type and user level, and types of the interaction intention information include one or more of text message, reward, like, dislike, share, follow, and unfollow.

[0044] Exemplarily, the first user refers to a user who watches a live broadcast. The embodiment of the present application does not limit the number of first users, which may be one or more. In one possible case, the live broadcast watched by the first user is realized by displaying a first interactive resource. Therefore, the arrangement device needs to obtain the first interactive resource first. Among them, the type of the first interactive resource may be one or more of text, audio, picture, and video. Regardless of the type of the first interactive resource, the process of obtaining the first interactive resource is similar.

[0045] In a possible implementation, the first interactive resource is generated based on the second interactive resource, and the layout device needs to obtain the second interactive resource before obtaining the first interactive resource. Optionally, the process of the layout device obtaining the second interactive resource includes: obtaining reference intent information input by the second user, the reference intent information is used to indicate the theme of the second interactive resource; according to the reference intent information, obtaining at least one subtitle and the text content corresponding to each of the at least one subtitle, the subtitle is used to indicate the theme of part of the content in the theme of the second interactive resource; displaying the second interactive resource, the second interactive resource includes at least one subtitle and the text content corresponding to each subtitle.

[0046] Exemplarily, the reference intent information indicates the subject of the second interactive resource, and the subject refers to the information that needs to be delivered to the first user during the interaction through the second interactive resource. For example, if the live interactive scenario is selling products through live broadcast, and the second user is the audience watching the live broadcast, the information that needs to be delivered to the first user during the live broadcast through the second interactive resource is the information of the products to be sold. Therefore, the subject of the second interactive resource is the information of the products to be sold.

[0047] In a possible implementation, the arrangement device may receive reference intent information input by the second user. Exemplarily, the arrangement device provides an information input control, and the second user inputs the reference intent information according to the information input control. The second user may be a person who supervises and manages the live broadcast, and the second user may determine the reference intent information according to the business arrangement. For example, the business arrangement requires a live broadcast to introduce product A, and the second object thereby determines the reference intent information as introducing product A, and inputs the determined reference intent information into the arrangement device through the information input control.

[0048] Optionally, the orchestration device can also determine reference intent information based on historical interaction data. The generation time of the historical interaction data is before the moment of generating the second interaction resource, and the interaction data generated by the first user in the process of watching the historical live broadcast is the historical interaction data. The orchestration device can determine the reference intent information based on the historical interaction data. Continuing with the live broadcast interaction as an example, the anchor asks about the needs of the next live broadcast at the end of the previous live broadcast, "What do you want to see when we meet next time?" The first user watching the live broadcast replies through the barrage, "I want to see the anchor sing." The orchestration device collects the live broadcast data of the previous live broadcast as historical interaction data, parses the text information in the historical interaction data, and obtains the reference intent information.

[0049] The arrangement device may choose to receive the reference intent information input by the second user, or may choose to determine the reference intent information based on historical interaction data, or may use the above two methods to determine the reference intent information. For example, the arrangement device determines that the reference intent information of the second interactive resource is to introduce product A and perform singing based on the introduction of product A input by the second user and the performance of singing determined by historical interaction data. That is, the embodiment of the present application does not limit the number of reference intent information used in the process of generating the second interactive resource, which can be any number. The reference intent information can be a topic as exemplified above, or it can be a sentence, which is not limited in the embodiment of the present application. Since the process of generating a second interactive resource based on multiple reference intent information is similar to the process of generating a second interactive resource based on one reference intent information, the method of generating a second interactive resource will be introduced below by taking the process of generating a second interactive resource based on one reference intent information as an example.

[0050] Exemplarily, the layout device determines at least one subtitle corresponding to the reference intent information based on the reference intent information. The subtitle is used to indicate the theme of part of the content in the theme of the second interactive resource. The theme of the second interactive resource indicates the information that needs to be transmitted, and the transmitted information can be summarized into at least one subtitle based on the content characteristics of each paragraph. Optionally, the layout device can search according to the reference intent information to determine at least one subtitle corresponding to the reference intent information. Taking the reference intent information as an introduction to product A as an example, the layout device searches according to product A to obtain the product's function, appearance design, material quality, and usage experience. Therefore, the subtitles corresponding to the reference intent information are function introduction, appearance design introduction, material quality introduction, and usage experience introduction.

[0051] In one possible case, the editing device will also refer to the interactive features corresponding to the second interactive resource in the process of determining at least one subtitle corresponding to the reference intent information. The interactive features are, for example, personality features of a third user and at least one of the interactive scenarios of the second interactive resource. Among them, the third user refers to a user who performs live broadcast, and the third user may be a virtual object created by technical means such as modeling, motion capture, and artificial intelligence (AI). A virtual object is, for example, a digital human with human or human-like appearance features and behavior patterns, that is, the method for generating interactive resources provided in the embodiment of the present application can be used in live interactive scenarios such as digital human live broadcast, digital human performance, or digital human intelligent interaction. In addition, the virtual object may also be a virtual cartoon character with the appearance features of a cartoon image.

[0052] The editing device can obtain the interactive features provided by the second user, and determine the subtitle according to the interactive features. Continuing to take the interactive scenario of live broadcast as an example, since live broadcast is a playback method that can interact with the audience, the editing device determines the subtitles needed for interaction, such as welfare delivery and barrage question answering. In addition, based on the personality characteristics of the third user, some information transmission needs will also arise. Taking the personality characteristics of the third object as cheerful, extroverted and fond of talent shows as an example, the editing device can set the subtitle to talent show according to the personality characteristics of the third object. Based on the reference intent information and performance characteristics, at least one subtitle is generated in a targeted manner to clarify the content characteristics of each part of the content that needs to be displayed during the live broadcast.

[0053] Exemplarily, after determining at least one subtitle, the layout device can directly obtain the text content corresponding to each subtitle, or adjust the subtitle to obtain the text content corresponding to the adjusted subtitle. For example, the layout device obtains a subtitle configuration request input by the second user, and the subtitle configuration request is used to delete the first subtitle in at least one subtitle, or add a second subtitle. Optionally, the layout device displays at least one subtitle to the second user, and the second user adjusts the displayed subtitle to obtain the adjusted subtitle. The adjustment can be to add a subtitle, and the added subtitle can be called the second subtitle in some cases. The adjustment can also be to delete a subtitle, and the deleted subtitle can be called the first subtitle in some cases. For example, the second user believes that an overall introduction of the product is needed before introducing the product, which can facilitate the audience's understanding. The second user inputs the overall introduction as the second subtitle to be added according to the information input control provided by the layout device. The layout device obtains the subtitle configuration request according to the operation of the second user, and adds the second subtitle to at least one subtitle according to the subtitle configuration request to obtain the adjusted subtitle.

[0054] Regardless of whether at least one subtitle is adjusted, the layout device can obtain text content corresponding to each subtitle in at least one subtitle. The text content corresponding to the subtitle refers to the text said by the third user in the process of introducing the subtitle, such as an introduction. The layout device can obtain the text content corresponding to each subtitle through search, or generate the text content corresponding to each subtitle according to the content characteristics of each subtitle. For example, based on natural language processing technology, by simulating the processing and understanding of human language, the corresponding text content is generated according to the subtitle.

[0055] After the editing device determines at least one subtitle and the text content corresponding to each subtitle by performing the above operations, it obtains a second interactive resource including each subtitle and the text content of the subtitle. After that, the editing device can generate a first interactive resource based on the second interactive resource. Exemplarily, the process of the editing device generating a first interactive resource based on the second interactive resource includes: obtaining a media resource corresponding to each subtitle in at least one subtitle, the type of the media resource includes one or more of an image, audio, and video, and the source of the media resource is one or more of a knowledge base, the Internet, and an artificial intelligence (AI) model generation; generating a first interactive resource based on the second interactive resource corresponding to each subtitle in at least one subtitle and the corresponding media resource.

[0056] The embodiments of the present application do not limit the media resources corresponding to the subtitle. In addition to the images, audio, and video shown in the above embodiments, they may also include artistic words, stickers, backgrounds, etc. Among them, the video refers to the video displayed during the third user's introduction of the subtitle, and the music is the music played during the third user's introduction of the subtitle, such as the background music played when the third user reads the text content corresponding to the subtitle. The artistic words are text that has been artistically processed and can be used to highlight the text that needs to be emphasized during the display of the subtitle. Taking live broadcast as an example, the artistic words are the subtitle names displayed on the live video being played. Stickers are data for optimizing the first interactive resource by the third user in the process of displaying the subtitle. Taking the first interactive resource as a video as an example, the stickers can be special-effect stickers for optimizing the portrait of the third user in the video. The background is the spatial background where the third user is located during the display of the subtitle, and the picture is the picture used by the third user in the process of introducing the subtitle.

[0057] In one possible case, the editing device needs to determine the type of media resources corresponding to each subtitle, and then obtain the media resources corresponding to each subtitle according to the type of media resources corresponding to each subtitle. For a clearer description, the type of media resources is referred to as media type below. Optionally, the editing device can determine all the multiple media types involved as the media types corresponding to each subtitle, thereby ensuring the comprehensive collection of media resources, or determine the media type corresponding to each subtitle according to the selection of the second user, or randomly select a media type from multiple media types and use the selected media type as the media type to be used. The embodiment of the present application does not limit the method for determining the media type corresponding to each subtitle. Moreover, the media types corresponding to different subtitles can be the same or different.

[0058] After determining the media type corresponding to each subtitle, the editing device obtains the media resource corresponding to the subtitle according to the media type. The acquisition method is, for example, to search according to the subtitle and the media type to obtain the media resource. Exemplarily, the editing device searches in a knowledge base or the Internet through a search engine. The knowledge base can be an open source knowledge base or a knowledge base created by a second user. For example, the second user inputs multiple media resources, and the editing device receives the media resources input by the second user; and stores the media resources in the knowledge base. The editing device thereby obtains a knowledge base including multiple media resources. The knowledge base is, for example, a video website, a photo library, and the like. In addition, in addition to obtaining media resources through search, the editing device can also generate media resources. For example, media resources are generated according to subtitles and media types through an AI model, and the AI ​​model is, for example, a generative artificial intelligence (artificial intelligence generated content, AIGC) model.

[0059] After obtaining the media resources corresponding to each subtitle, the layout device can, for example, Figure 3 As shown, after calling the subtitle generation unit and the resource search and generation unit included in the resource generation module, and generating the second interactive resource and the media resource according to the reference intent information, the resource set including the media resource and the second interactive resource is displayed to the second user, and the second user reviews or adjusts the displayed resource set for user review. Optionally, since the second interactive resource includes each subtitle and the text content corresponding to each subtitle, and the media resource is the media resource corresponding to each subtitle, the resource set can be understood as a set including the text content and media resources corresponding to each subtitle. Among them, the adjustment of the resource set is, for example, adding the text content or media resources included in the resource set, or deleting the media resources or text content included in the resource set. After completing the user review, the editing device can generate the first interactive resource based on the resource set reviewed by the second user.

[0060] In some cases, the resource collection can be referred to as a script or a script tree. The script is used to guide live interaction, and the guidance method is, for example, to generate a first interactive resource for live display based on the script, and the first interactive resource is, for example, a video of a digital human performance. In the case where the host of the live broadcast is a real user, the guidance method can also be to display the script to the real user so that the real user can perform according to the script. In the scenario where the resource collection is called a script tree, the subtitles included in the resource collection can be understood as the leaf nodes included in the script tree, the text content corresponding to the subtitles can be understood as the words contained in the leaf nodes, and the media resources corresponding to the subtitles can be understood as the materials corresponding to the leaf nodes.

[0061] Regardless of whether it is a resource collection, a script, or a script tree, the editing device can generate a first interactive resource based on the media resources and text content corresponding to each subtitle. Exemplarily, the editing device can select a subtitle to be displayed from at least one subtitle to generate a first interactive resource based on the second interactive resource and media resource corresponding to the subtitle to be displayed. For example, the editing device can select a subtitle to be displayed from multiple subtitles based on a reference threshold, and the reference threshold can be an arbitrary value set based on experience. The editing device can also determine the subtitle to be displayed based on the selection of the second user. In one possible case, the editing device can select the media type of the media resource required to display each subtitle from the media resources corresponding to each subtitle in the process of generating the first interactive resource based on the media resources and the second interactive resources corresponding to the subtitle, and generate the sub-interactive resource corresponding to each subtitle based on the selected media type, so as to obtain a first interactive resource including the sub-interactive resources corresponding to multiple subtitles.

[0062] Optionally, the layout device performs semantic analysis on the text content of each subtitle, and determines the media type to be used based on the semantic analysis results. Taking the reference intent information as introducing the watch and the subtitle as the appearance design as an example, the layout device performs semantic analysis on the text content corresponding to the appearance design to determine that the appearance design requires displaying the shape, pattern, color, etc. of the watch. The layout device thus determines that the media types to be used are pictures / backgrounds and artistic words. Among them, pictures are used to display the shape and pattern of the watch, etc., and artistic words are used to emphasize the design features of the watch.

[0063] Exemplarily, in addition to selecting the media type of any subtitle through semantic analysis, the layout device can also use other methods. For example, receive the media type of the subtitle input by the second user. Regardless of the method used to complete the selection of the media type, the layout device can generate a sub-interaction resource corresponding to the subtitle according to the selected media type. Continuing with the example of introducing the appearance design of a watch, the layout device selects a high-definition photo of a watch as the background or as a picture displayed by a third user, and adds some artistic words to the photo of the watch to highlight the design features of the watch. Afterwards, the introduction words and the watch photo as text content are integrated with the artistic words to generate an introductory video or graphic content introducing the appearance design of the watch. The generation process of the sub-interaction resources corresponding to other subtitles is similar.

[0064] In one possible implementation, different subtitles have a display order, and the display order can be determined according to the language logic order. Taking the reference intent information as an introduction to a product, the subtitles that need to be displayed include function introduction, appearance design introduction, material quality introduction, user experience introduction, welfare delivery, and barrage question answering as an example. The editing device determines the display order of multiple subtitles as appearance design introduction, function introduction, welfare delivery, material quality introduction, user experience introduction, and barrage question answering according to the language logic order. The sub-interaction resources corresponding to each subtitle are arranged in sequence according to the execution order of the subtitles.

[0065] In addition, after the arrangement device arranges the sub-interaction resources corresponding to each sub-title in sequence, it is also necessary to perform transition processing on each sub-title to achieve the connection of the sub-interaction resources corresponding to different sub-titles, thereby obtaining a first interaction resource including multiple sub-interaction resources. Exemplarily, the transition processing process includes: determining two sub-titles that need transition processing, the two sub-titles are adjacent sub-titles in the display order; generating transition data according to the text content corresponding to the two sub-titles, the transition data is used to connect the text content corresponding to the two sub-titles; generating transition resources according to the transition data, the transition resources are used to connect the sub-interaction resources corresponding to the two sub-titles.

[0066] Taking the subtitles that need transition processing as function introduction and appearance design introduction as an example, when the third user introduces the product function and then starts to introduce the appearance design, it is necessary to consider the rationality of the transition between the sub-interaction resources corresponding to the subtitles to avoid too fast transition, which will reduce the viewing experience of the first user. Therefore, it is necessary to perform transition processing on the subtitles, and the editing device generates transition data based on the text content corresponding to the two subtitles, "After understanding the appearance of product No. 52, I believe everyone will be more curious about the functions of this product. Please wait patiently. The host will introduce them to you one by one." Media resources are generated based on the transition data. The media resource can be a video of a third user reading the transition data. By performing transition processing on each subtitle, the continuity between the sub-interaction resources corresponding to each subtitle is guaranteed, thereby ensuring that the content of the entire first interaction resource is smooth and natural.

[0067] After acquiring the first interactive resource, the arrangement device may display the first interactive resource to realize the interaction between the third user and the first user. In the process of displaying the first interactive resource for interaction, the arrangement device may also obtain the interactive intention information to adjust the displayed first interactive resource according to the interactive intention information. Optionally, the interactive intention information is, for example, the interactive intention information of at least one first user. The interactive intention information of the first user may be the intention information generated by the first user in the process of viewing the first interactive resource. For example Figure 4 As shown, the arrangement device starts the interactive performance by displaying the first interactive resource. The first user performs some user behaviors while watching the interactive performance, and the user behaviors generate the interactive intention information of the first user.

[0068] In a possible implementation, the interactive intent information obtained by the orchestration device also has attributes, and the attributes include one or more of type or user level. The types of intent information include text messages, rewards, on-demand, clicks, sharing, and attention. Among them, the type of interactive intent information refers to the way in which the interactive intent information is generated. The user level in the attributes of the interactive intent information refers to the user level of the first user who generates the interactive intent information. The user level of the first user indicates the importance of the first user. The user level can be determined based on the historical interaction of the first user. For example, the higher the historical rewards accumulated by the first user and the more historical barrage releases, the higher the user level of the first user.

[0069] Optionally, the process of the arrangement device obtaining the interaction intention information of the first user includes: obtaining the interaction environment data of the first interaction resource, the interaction environment data including the interaction intention information of the first user; extracting at least one interaction intention information from the interaction environment data. Continuing with the live interaction as an example, the interaction environment data is, for example, the background data of the live broadcast room playing the first interaction resource. The arrangement device can be as follows Figure 4As shown, the background data of the live broadcast room is pulled by the interactive environment perception unit in the environment perception module as the interactive environment data. In one possible case, the interactive environment data includes the interactive intention information of the first user. For example, the background data of the live broadcast room as the interactive environment data includes the text message of the first user sending the bullet screen, the gift record generated by the reward, the transaction data generated by placing an order, and the fan attention record generated by following or unfollowing.

[0070] The embodiments of the present application do not limit the manner in which the orchestration device obtains the interaction intention information from the interaction environment data. The orchestration device may obtain the interaction conditions, and extract the interaction intention information from the interaction environment data through the interaction conditions. The interaction conditions may be obtained based on experience and implementation environment settings, and the implementation environment may be, for example, an interaction scenario. For example, the interaction conditions corresponding to the live broadcast room are set based on experience as one or more of text messages, rewards, likes, dislikes, shares, follows, and unfollows. After the orchestration device obtains the interaction conditions, it determines whether the information included in the interaction environment data hits the interaction conditions. When the information in the interaction environment data hits any interaction condition, it determines that the information is interaction intention information that requires interaction feedback from a third user. When the information in the interaction environment data does not hit the interaction condition, it determines that the information does not require interaction feedback from a third user. The above operations are also Figure 4 The environment perception module includes operations performed by the interactive condition unit.

[0071] Through the interactive conditions, the arrangement device extracts the bullet screen data, gift records, transaction data and fan attention records from the background data to obtain multiple interactive intention information. Among them, a second object can correspond to one interactive intention information or multiple interactive intention information, which is not limited in the embodiment of the present application. Figure 4 In the figure, a solid arrow indicates that the processing is performed by a module included in the orchestration device, and a dotted arrow indicates that the processing is performed by a user, such as the first user or the second user.

[0072] Optionally, the interaction intention information may also be the intention information generated by the second user. For example, during the live broadcast based on the first interaction resource, the second user finds that the introduction of product B in the first interaction resource needs to be canceled because the cooperation time of product B has ended. The interaction intention information is to cancel the introduction of product B. In this case, the orchestration device may receive the interaction intention information input by the second user to obtain the interaction intention information. For example, the second user inputs the interaction intention information through the information input control provided by the orchestration device, and the orchestration device thereby obtains the interaction intention information generated during the interaction process.

[0073] S202, adjusting a first interactive resource according to at least one interactive intention information, where the first interactive resource is content viewed by a first user, the first interactive resource includes a sub-interactive resource corresponding to at least one subtitle, and the type of the first interactive resource includes one or more of text, audio, picture, and video.

[0074] Regardless of the method by which the arrangement device acquires the interactive intent information, the arrangement device can adjust the first interactive resource according to the multiple interactive intents after acquiring the multiple interactive intent information. Because there may be interactive intent information that requires interaction among the multiple interactive intent information, such as the barrage question that the first user needs the third user to answer, or the first user needs the third user to thank his reward. And there may also be interactive intent information that does not require interaction among the multiple interactive intent information acquired by the arrangement device. For example, in order to improve his user level during the process of watching the first interactive resource, the first user will send meaningless water posts, such as emoticons and numbers, through the barrage. For such meaningless water posts, the third user does not need to interact and feedback. Or, the number of interactive intent information that the third user can interact and feedback is limited. For example, in order to control the length of the live broadcast, the host only has ten minutes to interact with the audience after introducing the product, or the host can only answer ten barrage questions.

[0075] Therefore, the orchestration device needs to select interactive intent information for interactive feedback from multiple interactive intent information. Exemplarily, the orchestration device receives an interactive resource adjustment strategy, which includes one or more of the priority, weight, or threshold corresponding to the attributes of the interactive intent information, and then can select the interactive intent information that requires interactive feedback according to the interactive resource adjustment strategy, thereby adjusting the first interactive resource according to at least one interactive intent information and the interactive resource adjustment strategy.

[0076] Next, the process of selecting interactive intent information that requires interactive feedback according to the interactive resource adjustment strategy is introduced according to weight, threshold and priority respectively. The embodiment of the present application does not limit the process of determining the weight of interactive intent information. The orchestration device can cluster each interactive intent information according to the interaction requested by each interactive intent information to obtain multiple intent sets, and any intent set includes at least one interactive intent information; obtain at least one of the first weight, the second weight and the third weight of any intent set, and determine the weight of any intent set according to at least one of the first weight, the second weight and the third weight. The first weight is determined according to the number of interactive intent information included in any intention set, the second weight is determined according to the user level of the first user corresponding to any intention set, and the third weight is determined according to the conditional weight of the interactive condition hit by any interactive set.

[0077] In one possible case, there are multiple interactions with the same interaction intent information request, for example, the same first user posts the same question multiple times in the bullet screen in order to attract the attention of the third user. Or, the questions asked by different first users in the bullet screen have different intent information requests. Figure 1 For example, the first user A asks: What size should I wear if I am XXX in height and XX in weight? The first user B asks: I am curious about the size information. The interaction requests of the interaction intention information of the first user A and the interaction intention information of the first user B are both to provide feedback on the product size chart.

[0078] For the interactive intent information requesting the same interaction, the third user only needs to provide interactive feedback once. Therefore, the orchestration device can cluster multiple interactive intent information according to the interactions requested by each interactive intent information to obtain multiple intent sets, and the interactions required for the interactive intent information included in any intent set are consistent. The clustering process is, for example, when the interactions requested by multiple interactive intent information are the same, dividing the multiple interactive intent information into one intent set. For example, in the above embodiment, the interactive intent information of the first user A and the interactive intent information of the first user B belong to one intent set. After obtaining at least one intent set through clustering, the orchestration device can determine the interaction weight of any intent set.

[0079] Optionally, the orchestration device may determine the first weight according to the number of interactive intent information included in any intent set. In one possible case, the number of interactive intent information and the first weight are positively correlated. The more interactive intent information included in any intent set, the more interested the first user is in the interaction requested by the interactive intent information, and the more the third user needs to interact. The orchestration device may determine the number of interactive intent information included in any intent set as the first weight, or may process the number to obtain the first weight. The processing, for example, is to analyze the number using the analytic hierarchy process (AHP) to obtain the first weight.

[0080] In one possible case, the first user corresponding to any intent set will also affect the weight of any intent set. Among them, the first user corresponding to any intent set refers to the interactive intent information generated by the first user as the interactive intent information included in any intent set. Exemplarily, the user level and the second weight are positively correlated. The orchestration device can determine the second weight of each intent set according to the user level and the second weight determination strategy included in the interactive resource adjustment strategy. The process of determining the second weight according to the user level is similar to the process of determining the first weight according to the quantity. For detailed description, please refer to the above embodiment, which will not be repeated here.

[0081] Optionally, the interactive conditions hit by any intent set will also affect the weight of any intent set. Each interactive condition also has a conditional weight, and the conditional weight of the interactive condition indicates the importance of the interactive condition. The conditional weight of each interactive condition can be determined according to the interactive resource adjustment strategy. Taking the interactive conditions including rewards and text information as an example, the interactive resource adjustment strategy indicates that the importance of text information is higher than the importance of rewards, then the conditional weight of text information is higher than the conditional weight of rewards. The orchestration device can determine the third weight according to the conditional weight based on the interactive conditions hit by the interactive intent information included in any intent set. When the conditional weights hit by each interactive intent information included in any intent set are the same, the conditional weight of the hit can be determined as the third weight. When the conditional weights hit by each interactive intent information included in any intent set are different, the third weight can be calculated based on multiple conditional weights.

[0082] After obtaining at least one of the first weight, the second weight, and the third weight, the orchestration device may determine the weight of the intent set according to at least one of the first weight, the second weight, and the third weight. Optionally, the orchestration device may determine the first weight as the weight of the intent set, or the second weight as the weight of the intent set, or the third weight as the weight of the intent set, or may determine the weight of any intent set through weighted calculation based on any two or three of the first weight, the second weight, and the third weight.

[0083] After obtaining the weights of each intent set, the orchestration device can determine at least one intent set that needs to interact based on the weights of each intent set. Exemplarily, the orchestration device can select at least one intent set that needs to interact based on the weights of the intent sets. For example, a weight threshold is set based on experience, and for any intent set, if the weight of any intent set is greater than the weight threshold, then any intent set needs to interact. Alternatively, a quantity threshold is set based on experience, and multiple intent sets are arranged in sequence according to the weights of the intent sets, and the intent sets whose arrangement order is not lower than the quantity threshold are determined as intent sets that need to interact. After selecting the intent set that needs to interact, the interactive intent information corresponding to the intent set can be determined as the interactive intent information for adjusting the first interactive resource.

[0084] The above is the interactive intention information for adjusting the first interactive resource selected according to the weight. In a possible case, the arrangement device can also determine the interactive intention information for adjusting the first interactive resource according to the information volume and threshold of each interactive intention information. The information volume refers to the amount of interactive intention information. For example, the first user's interest in each subtitle is determined according to the information volume and threshold of the interactive intention information corresponding to each subtitle. Among them, the interactive intention information corresponding to the subtitle means that the interactive intention information is generated by the first user in the process of displaying the sub-interactive resource corresponding to the subtitle. When the information volume of the interactive intention information is lower than the first threshold, it is determined that the first user has a low interest in the subtitle, and the interactive intention information for adjusting the first interactive resource is determined to skip the subtitle. When the information volume of the interactive intention information is higher than the second threshold, it is determined that the second user has a high interest in the subtitle, and the interactive intention information for adjusting the first interactive resource is determined to enrich the sub-interactive resource corresponding to the subtitle. Among them, the first threshold and the second threshold are numerical values ​​of any size set based on experience.

[0085] Optionally, the orchestration device may also obtain the priorities corresponding to the attributes of each interactive intent information, and select the interactive intent information used to adjust the first interactive resource according to the priorities corresponding to the attributes of each interactive intent information. Exemplarily, the orchestration device extracts the priorities corresponding to the attributes of each interactive intent information from the received interactive resource adjustment strategy, arranges each interactive intent information in sequence according to the priorities corresponding to the attributes of each interactive intent information, and determines the interactive intent information whose arrangement order is not lower than the quantity threshold as the interactive intent information used to adjust the first interactive resource. Among them, the priorities corresponding to the attributes of the interactive intent information are, for example, that the priority of text messages is higher than that of sharing, and the priority of clicks is higher than that of text messages.

[0086] Regardless of the method by which the editing device determines the interactive intent information for adjusting the first interactive resource, the first interactive resource can be adjusted according to the determined interactive intent information. In one possible case, the adjustment process includes: adjusting the subtitle corresponding to the first interactive resource according to the interactive intent information to obtain an adjusted subtitle; and obtaining the adjusted first interactive resource according to the sub-interactive resource corresponding to the adjusted subtitle.

[0087] Among them, adjusting the subtitle may be adding a new subtitle. For example, for the interaction of the interaction intention information request to provide feedback on the size chart of product A, the layout device adds a subtitle named "Size Introduction of Product A". Figure 5In the live broadcast process shown in the figure, in the subtitles included in the introduction of product A, subtitle 1.4: Introduction to the size of product A is added. Adjusting the interactive theme can also be to reduce the original subtitles. For example, in response to the interaction request of the interactive intention information, the editing device deletes the currently displayed subtitle and the subtitle to be displayed corresponding to the name of introducing product A included in the first interactive resource. Figure 5 As shown, the subtitle currently displayed is the function introduction of product A, and the layout device deletes the function introduction of product A and the subtitles including the introduction of product A after the function introduction of product A. After completing the adjustment of the subtitle, the layout device can determine the sub-interaction resource corresponding to the adjusted subtitle. Figure 5 The dashed box in the box indicates the subtitle currently displayed.

[0088] For the added new subtitle, the layout device obtains the sub-interaction resource corresponding to the new subtitle. Taking the added subtitle as the second subtitle as an example, the layout device obtains the text content corresponding to the second subtitle, obtains the media resource corresponding to the second subtitle, and obtains the incremental resource corresponding to the second subtitle. After that, the layout device can Figure 4 As shown, the incremental resource generated by calling the resource generation module is sent to the resource arrangement module, and the sub-interaction resource corresponding to the incremental resource is generated by the intelligent arrangement unit. The process of generating the incremental resource and generating the sub-interaction resource corresponding to the second subtitle according to the incremental resource is similar to the process of generating the sub-interaction resource included in the first interaction resource in S201, and the relevant description can be referred to, which will not be repeated here.

[0089] The above is the process of adjusting the sub-interaction resource corresponding to the sub-title after requesting to add a sub-title. For a request to delete a sub-title, the editing device can skip the sub-interaction resource corresponding to the currently displayed sub-title and the n sub-titles to be displayed in the first interaction resource, where n is an integer greater than or equal to 0; and display the sub-interaction resource corresponding to the n+1 sub-title after the currently displayed sub-title. The currently displayed sub-title and the n sub-titles to be displayed are determined according to the interaction intent information. Figure 5 For example, if the interaction requested by the interaction intent information is to stop introducing product A, the n sub-titles to be displayed are product A's appearance design, material quality, and user experience. The layout device skips displaying Figure 5 Introducing multiple sub-interaction resources corresponding to product A, and then starting to display the sub-interaction resources corresponding to the n+1th subtitle after the currently displayed subtitle, that is, Figure 5 Sub-interaction resources corresponding to the overall introduction of product B.

[0090] The problem of discontinuity of the sub-interaction resources corresponding to the sub-titles may occur due to the adjustment of the first interaction resource. For example, the sub-interaction resources corresponding to the newly added sub-titles are discontinuous with the sub-interaction resources corresponding to the original sub-titles, or after skipping the sub-interaction resources corresponding to the original sub-titles, the sub-interaction resources corresponding to the currently displayed content and the sub-interaction resources corresponding to the n+1th sub-title to be displayed are discontinuous.

[0091] Therefore, the layout device needs to perform transition processing on the adjusted first interactive resource, for example, for the adjusted subtitle, generate transition data corresponding to the subtitle, or rewrite the text data of the sub-interactive resource corresponding to the adjusted subtitle, so as to ensure that the sub-interactive resource corresponding to the adjusted subtitle is smooth and natural. Figure 4 The interactive rearrangement unit in the resource arrangement module is called to perform transition processing on the adjusted first interactive resource. Since the continuity between the sub-interactive resources corresponding to the multiple sub-titles needs to be considered during the transition processing, it is necessary to Figure 4 As shown, the full amount of resources, that is, the adjusted first interactive resources as a whole, are obtained to rearrange the interactions according to the adjusted first interactive resources as a whole, so as to ensure that the entire first interactive resource flow is natural. Optionally, the resource generation module can directly send the full amount of resources to the resource arrangement module, or Figure 4 As shown, the second user first reviews all resources, and then sends all resources reviewed by the user to the resource scheduling module.

[0092] Regardless of the method used to obtain the full amount of resources, the resource orchestration module can perform transition processing on the full amount of resources. The process of transition processing is similar to the process of transition processing in the process of generating the first interactive resource in S201. Please refer to the relevant description and will not be repeated here. By adjusting the first interactive resource, the orchestration device can adjust the first interactive resource according to the interactive intent information generated during each interaction process, thereby achieving different interactive processes.

[0093] In summary, the method for generating interactive resources provided by the embodiment of the present application adjusts the first interactive resource in real time according to the interactive intention information generated during the interaction process, so that the first interactive resource is more adapted to the interactive process, and the adjustment efficiency of the first interactive resource is high, so that the first interactive resource is more adapted to the interactive process, the interactive ability in the interactive scene is improved, and the experience of the interaction based on the first interactive resource is improved. At least one subtitle is determined by referring to the intention information, and then the text content and media resources required to be used are automatically obtained according to the subtitle, so as to generate the first interactive resource required to be used in the interactive process. The process of generating the first interactive resource has low manual participation, low cost and high efficiency. In the process of acquiring media resources, the layout device can automatically search and generate, reducing the search cost and manual effort of the second user in the process of generating the first interactive resource, reducing the difficulty of resource generation, and improving the resource production efficiency and the quality of the generated first interactive resource. Since the subtitle corresponds to multiple media resources, the third user who interacts according to the first interactive resource can show rich interactive capabilities, such as gestures, expressions, etc., which improves the interactive experience of the first interactive resource.

[0094] The above describes the method for generating interactive resources according to the embodiment of the present application. Corresponding to the above method, the embodiment of the present application also provides a device for generating interactive resources. Figure 6 Schematic diagram of a device for generating interactive resources provided by an embodiment of the present application. Figure 6 As shown in the following multiple modules, the Figure 6 The interactive resource generation device shown can perform the above Figure 2 It should be understood that the device may include more additional modules than the modules shown or omit some of the modules shown, and the embodiments of the present application are not limited to this. Figure 6 As shown, the device is used for live broadcast interaction, and the device includes:

[0095] An acquisition module 601 is used to acquire at least one interaction intention information of at least one first user, where the attributes of the interaction intention information include one or more of type and user level, and the type of the interaction intention information includes one or more of text message, reward, like, dislike, share, follow, and unfollow;

[0096] Adjustment module 602 is used to adjust the first interaction resource according to at least one interaction intention information, where the first interaction resource is the content viewed by the first user, the first interaction resource includes a sub-interaction resource corresponding to at least one subtitle, and the type of the first interaction resource includes one or more of text, audio, picture, and video.

[0097] In one possible implementation, the device also includes: a receiving module for receiving an interaction resource adjustment strategy, the interaction resource adjustment strategy including one or more of a priority, a weight or a threshold corresponding to the attributes of the interaction intent information; an adjustment module 602 for adjusting the first interaction resource according to at least one interaction intent information and the interaction resource adjustment strategy.

[0098] In a possible implementation, the adjustment module 602 is used to skip the sub-interaction resources corresponding to the currently displayed subtitle and n subtitles to be displayed in the first interaction resource, where n is an integer greater than or equal to 0; and display the sub-interaction resources corresponding to the n+1 subtitle after the currently displayed subtitle.

[0099] In one possible implementation, the first interactive resource is generated based on the second interactive resource, and the acquisition module 601 is also used to obtain reference intent information input by the second user, and the reference intent information is used to indicate the subject of the second interactive resource; according to the reference intent information, at least one subtitle and the text content corresponding to each subtitle in at least one subtitle are obtained, and the subtitle is used to indicate the subject of part of the content in the subject of the second interactive resource; the device also includes: a display module, which is used to display the second interactive resource, and the second interactive resource includes at least one subtitle and the text content corresponding to each subtitle.

[0100] In a possible implementation, the acquisition module 601 is further used to obtain a subtitle configuration request input by a second user, the subtitle configuration request is used to delete a first subtitle in at least one subtitle, or to add a second subtitle; the subtitle configuration request is used to add a second subtitle, the subtitle configuration request also includes a subtitle text of the second subtitle, and the acquisition module 601 is further used to obtain text content corresponding to the second subtitle.

[0101] In one possible implementation, the acquisition module 601 is also used to acquire media resources corresponding to each subtitle in at least one subtitle, where the types of media resources include one or more of images, audio, and video, and the sources of the media resources are one or more of a knowledge base, the Internet, and artificial intelligence AI model generation; the display module is also used to display a first interactive resource, which is generated based on a second interactive resource and a corresponding media resource corresponding to each subtitle in at least one subtitle.

[0102] In a possible implementation, the acquisition module 601 is further configured to receive a media resource input by a second user; and store the media resource in a knowledge base.

[0103] The above-mentioned device adjusts the first interactive resource in real time according to the interactive intention information generated during the interactive process, thereby improving the real-time performance of the first interactive resource. The adjustment efficiency of the first interactive resource is high, so that the first interactive resource is more adaptable to the interactive process, and the interactive ability in the interactive scenario and the experience of interaction based on the first interactive resource are enhanced.

[0104] Wherein, both the acquisition module 601 and the adjustment module 602 can be implemented by software or by hardware. Exemplarily, the implementation of the acquisition module 601 is described below by taking the acquisition module 601 as an example. Similarly, the implementation of the adjustment module 602 can refer to the implementation of the acquisition module 601.

[0105] As an example of a software functional unit, the acquisition module 601 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the acquisition module 601 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including a data center or multiple data centers with close geographical locations. Among them, usually a region may include multiple AZs.

[0106] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0107] As an example of a hardware functional unit, the acquisition module 601 may include at least one computing device, such as a server, etc. Alternatively, the acquisition module 601 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0108] The multiple computing devices included in the acquisition module 601 can be distributed in the same region or in different regions. The multiple computing devices included in the acquisition module 601 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the acquisition module 601 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0109] It should be noted that, in other embodiments, the acquisition module 601 can be used to execute any step in the method for generating interactive resources, and the adjustment module 602 can be used to execute any step in the method for generating interactive resources. The steps that the acquisition module 601 and the adjustment module 602 are responsible for implementing can be specified as needed. The full functions of the interactive resource generation device are realized by respectively implementing different steps in the method for generating interactive resources through the acquisition module 601 and the adjustment module 602.

[0110] The present application also provides a computing device 700. Figure 7 As shown, computing device 700 includes: bus 702, processor 704, memory 706 and communication interface 708. Processor 704, memory 706 and communication interface 708 communicate through bus 702. Computing device 700 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in computing device 700.

[0111] The bus 702 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 The bus 702 may include a path for transmitting information between various components of the computing device 700 (eg, the memory 706, the processor 704, and the communication interface 708).

[0112] The processor 704 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0113] The memory 706 may include a volatile memory, such as a random access memory (RAM). The processor 704 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0114] The memory 706 stores executable program codes, and the processor 704 executes the executable program codes to respectively implement the functions of the acquisition module and the adjustment module, thereby implementing the interactive resource generation method. That is, the memory 706 stores instructions for executing the interactive resource generation method.

[0115] The communication interface 708 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 700 and other devices or communication networks.

[0116] The embodiment of the present application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0117] Optionally, the structure of at least one computing device included in the computing device cluster can be found in Figure 7 The computing device 700 shown. The memory 706 in one or more computing devices 700 in the computing device cluster may store the same instructions for executing the method for generating interactive resources.

[0118] In some possible implementations, the memory 706 of one or more computing devices 700 in the computing device cluster may also store partial instructions for executing the method for generating interactive resources. In other words, the combination of one or more computing devices 700 may jointly execute instructions for executing the method for generating interactive resources.

[0119] It should be noted that the memory 706 in different computing devices 700 in the computing device cluster can store different instructions, which are respectively used to execute part of the functions of the interactive resource generation device. That is, the instructions stored in the memory 706 in different computing devices 700 can implement the functions of one or more modules in the acquisition module and the adjustment module.

[0120] In some possible implementations, one or more computing devices in the computing device cluster may be connected via a network, which may be a wide area network or a local area network. Figure 8 A possible implementation is shown. Figure 8 As shown, two computing devices 800A and 800B are connected via a network. Specifically, the network is connected via a communication interface in each computing device. In this type of possible implementation, computing devices 800A and 800B include a bus 802, a processor 804, a memory 806, and a communication interface 808. The memory 806 in the computing device 800A stores instructions for executing the functions of the acquisition module. At the same time, the memory 806 in the computing device 800B stores instructions for executing the functions of the adjustment module.

[0121] Figure 8 The connection method between the computing device clusters shown may be based on the consideration that the method for generating interactive resources provided in the present application needs to obtain interactive intent information based on the display of the first interactive resource, so it is considered that the functions implemented by the adjustment module are handed over to the computing device 800B for execution.

[0122] It should be understood that Figure 8The functions of the computing device 800A shown in FIG. 8 may also be completed by multiple computing devices 800. Similarly, the functions of the computing device 800B may also be completed by multiple computing devices 800.

[0123] The embodiment of the present application also provides a communication device, which includes: a transceiver, a memory, and a processor. The transceiver, the memory, and the processor communicate with each other through an internal connection path, the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to control the transceiver to receive signals and control the transceiver to send signals, and when the processor executes the instructions stored in the memory, the processor executes the method for generating interactive resources.

[0124] It should be understood that the above processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0125] Further, in an optional embodiment, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. The memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0126] The memory may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM) and direct memory bus random access memory (DR RAM).

[0127] The embodiment of the present application also provides a computer program (product) containing instructions. The computer program (product) may be software or a program (product) containing instructions that can be run on a computing device or stored in any available medium. When the computer program (product) is run on at least one computing device, the at least one computing device executes the method for generating interactive resources.

[0128] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute a method for generating interactive resources.

[0129] An embodiment of the present application also provides a chip, including a processor, for calling and executing instructions stored in a memory from the memory, so that a communication device equipped with the chip executes any of the above-described methods for generating interactive resources.

[0130] An embodiment of the present application also provides another chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute any of the interactive resource generation methods described above.

[0131] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in this application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk), etc.

[0132] In order to clearly illustrate the interchangeability of hardware and software, the steps and components of each embodiment have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person of ordinary skill in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0133] The computer program code for realizing the method for the embodiment of the present application can be written in one or more programming languages. These computer program codes can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable rule-finding device, so that the program code, when executed by a computer or other programmable rule-finding device, causes the function / operation specified in the flow chart and / or block diagram to be implemented. The program code can be executed completely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer or completely on a remote computer or server.

[0134] In the context of the embodiments of the present application, computer program codes or related data may be carried by any appropriate carrier to enable a device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, etc. Examples of signals may include electrical, optical, radio, acoustic or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, or it can be an electrical, mechanical or other form of connection.

[0137] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0138] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0139] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the interactive intent information involved in this application is obtained with full authorization.

[0140] In this application, the terms "first", "second", etc. are used to distinguish between identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is the quantity and execution order limited. It should also be understood that although the following description uses the terms first, second, etc. to describe various elements, these elements should not be limited by the terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the various described examples, a first link may be referred to as a second link, and similarly, a second link may be referred to as a first link.

[0141] It should also be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0142] The term "at least one" in this application means one or more, and the term "multiple" in this application means two or more, for example, multiple second messages means two or more second messages. The terms "system" and "network" are often used interchangeably herein.

[0143] It should be understood that the terms used in the description of the various examples herein are only for describing specific examples and are not intended to be limiting. As used in the description of the various examples and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0144] It should also be understood that the term “comprise” (also known as “includes,” “including,” “comprises” and / or “comprising”) when used in this specification specifies the presence of stated features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0145] It should also be understood that, depending on the context, the phrase “if it is determined that…” or “if [stated condition or event] is detected” may be interpreted to mean “upon determining that…” or “in response to determining that…” or “upon detecting [stated condition or event]” or “in response to detecting [stated condition or event]”.

[0146] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0147] It should also be understood that the references to "one embodiment", "an embodiment", or "a possible implementation" throughout the specification mean that specific features, structures, or characteristics related to the embodiment or implementation are included in at least one embodiment of the present application. Therefore, the references to "in one embodiment" or "in an embodiment", or "a possible implementation" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating interactive resources, characterized in that: The method comprises: Acquire at least one interaction intention information of at least one first user, where the attributes of the interaction intention information include one or more of type and user level, and the type of the interaction intention information includes one or more of text message, reward, like, dislike, share, follow, and unfollow; According to the at least one interactive intention information, a first interactive resource is adjusted, where the first interactive resource is content viewed by a first user, the first interactive resource includes a sub-interactive resource corresponding to at least one subtitle, and the type of the first interactive resource includes one or more of text, audio, picture, and video.

2. The method according to claim 1, characterized in that The method further comprises: receiving an interaction resource adjustment strategy, wherein the interaction resource adjustment strategy includes one or more of a priority, a weight, or a threshold corresponding to an attribute of the interaction intention information; The adjusting the first interaction resource according to the at least one interaction intention information includes: The first interaction resource is adjusted according to the at least one interaction intention information and the interaction resource adjustment strategy.

3. The method according to claim 1 or 2, characterized in that: The adjusting the first interaction resource includes: Skipping the sub-interaction resources corresponding to the sub-title currently displayed and n sub-titles to be displayed in the first interaction resource, where n is an integer greater than or equal to 0; The sub-interaction resource corresponding to the n+1 sub-title after the currently displayed sub-title is displayed.

4. The method according to any one of claims 1 to 3, characterized in that: The first interaction resource is generated based on the second interaction resource. Before acquiring at least one interaction intention information of at least one first user, the method further includes: Acquire reference intention information input by a second user, where the reference intention information is used to indicate a subject of the second interactive resource; Acquire, according to the reference intent information, the at least one subtitle and text content corresponding to each of the at least one subtitle, wherein the subtitle is used to indicate a topic of a portion of the content in the topic of the second interactive resource; The second interactive resource is displayed, where the second interactive resource includes the at least one subtitle and text content corresponding to each subtitle.

5. The method according to claim 4, characterized in that The method further comprises: Acquire a subtitle configuration request input by the second user, where the subtitle configuration request is used to delete a first subtitle in the at least one subtitle, or to add a second subtitle; The subtitle configuration request is used to add the second subtitle, the subtitle configuration request also includes a subtitle text of the second subtitle, and the method further includes: Get the text content corresponding to the second subtitle.

6. The method according to claim 4 or 5, characterized in that: The method further comprises: Acquire a media resource corresponding to each subtitle in the at least one subtitle, where the type of the media resource includes one or more of an image, an audio, and a video, and the source of the media resource is one or more of a knowledge base, the Internet, and an artificial intelligence (AI) model generation; The first interactive resource is displayed, where the first interactive resource is generated based on the second interactive resource corresponding to each subtitle in the at least one subtitle and the corresponding media resource.

7. The method according to claim 6, characterized in that The method further comprises: receiving a media resource input by the second user; The media resource is stored in the knowledge base.

8. A device for generating interactive resources, characterized in that: The device comprises: an acquisition module, configured to acquire at least one interaction intention information of at least one first user, wherein the attributes of the interaction intention information include one or more of a type and a user level, and the type of the interaction intention information includes one or more of a text message, a reward, a like, a dislike, a share, a follow, and a cancel; An adjustment module is used to adjust a first interaction resource according to the at least one interaction intention information, wherein the first interaction resource is content viewed by a first user, the first interaction resource includes a sub-interaction resource corresponding to at least one subtitle, and the type of the first interaction resource includes one or more of text, audio, picture, and video.

9. The device according to claim 8, characterized in that The device also includes: a receiving module for receiving an interaction resource adjustment strategy, wherein the interaction resource adjustment strategy includes one or more of a priority, a weight or a threshold corresponding to the attributes of the interaction intent information; and an adjustment module for adjusting the first interaction resource according to the at least one interaction intent information and the interaction resource adjustment strategy.

10. The device according to claim 8 or 9, characterized in that The adjustment module is used to skip the sub-interaction resources corresponding to the currently displayed subtitle and n subtitles to be displayed in the first interaction resource, where n is an integer greater than or equal to 0; and display the sub-interaction resources corresponding to the n+1 subtitle after the currently displayed subtitle.

11. The device according to any one of claims 8 to 10, characterized in that: The first interactive resource is generated based on the second interactive resource, and the acquisition module is further used to acquire reference intent information input by a second user, where the reference intent information is used to indicate a subject of the second interactive resource; and according to the reference intent information, acquire the at least one subtitle and text content corresponding to each of the at least one subtitle, where the subtitle is used to indicate a subject of a portion of the subject of the second interactive resource; The device further includes: a display module, configured to display the second interactive resource, wherein the second interactive resource includes the at least one subtitle and text content corresponding to each subtitle.

12. The device according to claim 11, characterized in that The acquisition module is further used to acquire a subtitle configuration request input by the second user, the subtitle configuration request is used to delete the first subtitle in the at least one subtitle, or to add a second subtitle; the subtitle configuration request is used to add the second subtitle, the subtitle configuration request also includes a subtitle text of the second subtitle, and the acquisition module is further used to acquire text content corresponding to the second subtitle.

13. The device according to claim 11 or 12, characterized in that The acquisition module is further used to acquire media resources corresponding to each of the at least one subtitle, the types of the media resources include one or more of images, audio, and video, and the sources of the media resources are one or more of a knowledge base, the Internet, and artificial intelligence (AI) model generation; the display module is further used to display the first interactive resource, which is generated based on the second interactive resource corresponding to each of the at least one subtitle and the corresponding media resource.

14. The device according to claim 13, characterized in that The acquisition module is further used to receive the media resources input by the second user; and store the media resources in the knowledge base.

15. A computing device cluster, characterized in that: The computing device cluster includes at least one computing device, each computing device including a processor and a memory; The processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method for generating interactive resources as described in any one of claims 1-7.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method for generating interactive resources according to any one of claims 1 to 7.

Images