Interactive content display method and electronic equipment

Abstract

The embodiment of the invention discloses an interactive content display method and electronic equipment. The method comprises the following steps: displaying a live broadcast interface of a target live broadcast room to a viewer user; interactive content generated by an artificial intelligence AI generative model is displayed in a live broadcast interface, and the interactive content is generated by the following steps: obtaining user evaluation content in historical transaction data related to a target commodity currently explained by the target live broadcast room, and performing natural language understanding and rewriting processing on the user evaluation content by the AI generative model to generate interactive content suitable for a live broadcast room style. According to the embodiment of the invention, the residence time of the viewer newly entering the live broadcast room in the live broadcast room can be prolonged.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an interactive content display method and an electronic device. Background Art

[0002] Many commodity information service systems can provide a live broadcast room function. The so-called live broadcast room is an important part of online live broadcasting. It refers to the virtual space where the anchor broadcasts live. The audience can enter this space to watch the live content and interact with the anchor in real time. The live broadcast room can provide a variety of functions, such as barrage chat, gift giving, paid viewing, etc., to enhance the audience's sense of participation and interactive experience.

[0003] For a live broadcast room, the number of online viewers and the length of time viewers stay are very important indicators. Generally speaking, if the number of online viewers is large and the length of time viewers stay is long enough, it will be beneficial to bring higher indicators such as product click-through rate and transaction conversion rate. In the prior art, traffic can be obtained by placing live broadcast room links on some channels and other methods to increase the number of online viewers in the live broadcast room. However, the actual situation may be that after users enter the live broadcast room by clicking on links and other methods, they quickly exit the live broadcast room. Therefore, this method is often difficult to improve indicators such as the length of stay. The length of stay is an important factor that affects indicators such as click-through rate and transaction conversion rate. Therefore, how to increase the length of time users stay in the live broadcast room to further improve indicators such as click-through rate and transaction conversion rate has become a technical problem that needs to be solved by technicians in this field. Summary of the invention

[0004] The present application provides an interactive content display method and an electronic device, which are conducive to extending the stay time of viewers who have just entered the live broadcast room in the live broadcast room.

[0005] This application provides the following solutions:

[0006] An interactive content display method, the method is applied to a client of a commodity live broadcast service, the method comprising:

[0007] Display the live broadcast interface of the target live broadcast room to the viewing users;

[0008] The interactive content generated by the artificial intelligence (AI) generative model is displayed in the live broadcast interface, wherein the interactive content is generated in the following manner: user evaluation content in historical transaction data related to the target product currently being explained in the target live broadcast room is obtained, and the AI ​​generative model performs natural language understanding and rewrites the user evaluation content to generate interactive content suitable for the style of the live broadcast room.

[0009] There are multiple interactive contents associated with the same target product;

[0010] The interactive content generated by the AI ​​generative model is displayed in the live broadcast interface, including:

[0011] At preset time intervals, multiple interactive contents associated with the target product are displayed in a carousel until the next product is introduced.

[0012] The interactive content is also associated with user account information, where the user account is an account registered by a real user in the current product information service system and authorized to publish the interactive content generated by the AI ​​generative model to the product information service system;

[0013] When displaying the interactive content generated by the AI ​​generative model in the live broadcast interface, it also includes:

[0014] The interactive content and the corresponding user account information are displayed to simulate the interactive content posted by the user while watching the live broadcast.

[0015] Among them, the interactive content is generated by an AI generative model by acquiring user evaluation content related to multiple products in the product list on the server side of the product live broadcast service after the live broadcast in the target live broadcast room is started and the list of products to be explained is determined. The generated interactive content is cached on the server side; after the server side determines the target product currently being explained, the corresponding interactive content is taken out from the cache, and a user account is selected. By calling the service interface for publishing interactive content provided by the product live broadcast service, the process of publishing the target interactive content through the selected user account is simulated, so that the client can display the target interactive content corresponding to the target product in the interactive area of ​​the live broadcast interface of the target live broadcast room.

[0016] The user evaluation content used when generating the interactive content includes: the user evaluation content corresponding to other products that are the same product as the target product but from different suppliers or with different specifications.

[0017] An interactive content processing method, the method is applied to a service end of a commodity live broadcast service, the method comprising:

[0018] Determine a list of products to be explained that are associated with the target live broadcast room, and obtain user evaluation content in historical transaction data related to multiple products in the product list;

[0019] By calling the AI ​​generative model to perform natural language understanding and rewriting processing on the user evaluation content, interactive content suitable for the style of the live broadcast room is generated for the multiple products respectively, and the interactive content is cached on the server;

[0020] After determining the target product currently being explained in the target live broadcast room, the target interactive content corresponding to the target product is retrieved from the cache, and a user account is selected. By calling the service interface for publishing interactive content provided by the live broadcast service, the process of publishing the target interactive content through the selected user account is simulated, so that the client can display the target interactive content corresponding to the target product in the live broadcast interface of the target live broadcast room.

[0021] Among them, it also includes:

[0022] Preliminarily determining whether multiple commodities in the commodity library are of the same type, classifying multiple commodities of the same type into the same commodity group, and aggregating the user evaluation contents respectively corresponding to the multiple commodities in the same commodity group as the user evaluation contents shared by the commodities in the same commodity group;

[0023] When it is necessary to obtain the user evaluation content corresponding to a certain product, the product group to which the product belongs is determined, and the user evaluation content aggregated by the product group is obtained, so as to generate the interactive content for the product based on the aggregated user evaluation content.

[0024] Before determining the commodity group to which the commodity belongs, the method further includes:

[0025] If the product is a newly released product, or the richness of the associated user evaluation content does not meet the preset conditions, the step of determining the product group to which the product belongs is triggered to generate interactive content for the user through the user evaluation content aggregated by the product group to which the product belongs.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described above.

[0027] An electronic device, comprising:

[0028] one or more processors; and

[0029] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the aforementioned methods.

[0030] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions implement the steps of any of the aforementioned methods when executed by a processor in an electronic device.

[0031] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0032] Through the embodiment of the present application, in the process of explaining the product in the live broadcast room, the interactive content generated by the AI ​​generative model can be displayed in the live broadcast interface, including barrage or comment content, among which the specific interactive content can be generated based on the user evaluation content in the historical transaction data related to the target product currently explained in the target live broadcast room. In the generation process, the user evaluation content is understood and rewritten by the AI ​​generative model to generate interactive content suitable for the style of the live broadcast room. In this way, the interactive activity of the live broadcast room can be improved through the interactive content generated by AI. In addition, since the generated interactive content is related to the product currently explained and is based on the user evaluation content, it is generated by the AI ​​model after rewriting according to the style of the live broadcast room, and can be mainly displayed in the live broadcast interface in the form of text, etc. Therefore, compared with the pictures, voices, etc. during the host's explanation, it has a higher information density, which is more conducive to extending the stay time of viewers who have just entered the live broadcast room in the live broadcast room.

[0033] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0036] Figure 2 is a flow chart of the first method provided in an embodiment of the present application;

[0037] Figure 3 is a flow chart of the second method provided in an embodiment of the present application;

[0038] Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0040] First of all, it should be noted that the inventor of the present application discovered in the process of realizing the present application that the live broadcast room usually transmits specific information such as the selling points of the product to the audience users through the audio form of the oral explanation by the anchor. However, this form of audio information of oral explanation has the problem of low information density compared with the text and other contents directly displayed on the screen. The audience needs to listen patiently for a while before they can know what the anchor is talking about, what are the selling points of the current product, etc. Of course, the live broadcast interface usually also provides an interactive area for users. Users can enter their own comments or ask questions to the anchor during the live broadcast, etc. This interactive content is usually directly displayed in the interactive area of ​​the live broadcast interface in the form of text. Compared with the audio content of the oral explanation, it has a higher information density. Therefore, the existence of this interactive content is conducive to extending the user's retention time. In other words, if the interactive content in the interactive area is rich enough, after the audience enters the live broadcast room, they may obtain richer information from the interactive content more intuitively, thereby possibly extending the retention time. However, some live broadcast rooms may have relatively few people online at the same time, and few people may post comments and interact with the anchor, that is, the user's active participation in the interaction is also relatively low. For such live broadcast rooms, it is common for viewers to leave soon after entering the room, which makes it impossible to guarantee the transaction conversion rate of the live broadcast room.

[0041] In view of the above situation, in the embodiment of the present application, a method of generating interactive content for the products explained in the live broadcast room through an AI (Artificial Intelligence) generative model is provided to improve the interactive activity of the live broadcast room, so that when there are relatively few people online in the live broadcast room at the same time, or the user's spontaneous interaction is not active enough, the interactive content generated by this AI can be used as a supplement to improve the information density in the live broadcast interface, which is conducive to extending the user's stay time in the live broadcast room. Among them, the so-called AI generative model refers to a deep learning model containing a large number of parameters. This model is large in scale and can store and process a large amount of information. It has strong natural language text understanding, logical thinking ability and content generation ability, so as to achieve higher performance in various tasks. The embodiment of the present application can make use of the advantages of the AI ​​generative model in the above aspects to generate interactive content in the live broadcast room through the AI ​​generative model as a supplement to the interactive content, so as to achieve the purpose of extending the user's stay time in the live broadcast room.

[0042] From the perspective of system architecture, Figure 1As shown, the embodiments of the present application may involve the client and server of the commodity live broadcast service, wherein the commodity live broadcast service may be associated with the commodity information service system, for example, it may be a commodity live broadcast service provided in the commodity information service system. In this way, the user evaluation content generated in the commodity information service system may be used as the basis for AI to generate interactive content in the live broadcast room, so as to ensure the correlation between the generated interactive content and the specific live commodities in the live broadcast room. Regarding the client, in the live broadcast scenario, it may include the client on the anchor side, and it may also include the client on the audience side. The client on the anchor side may specifically be the central console interface on the anchor side, etc., while the client on the audience side may display the live broadcast interface and play specific live broadcast content. Specifically, AI generation of interactive content may be performed on the server side, and the client on the audience side may display the interactive content generated by AI in the interactive area of ​​the live broadcast interface. Among them, in order to ensure the smoothness of the interactive content display, at the beginning of the live broadcast in the live broadcast room, the client on the anchor side can submit the list of products to be explained to the server, and then the server will generate AI interactive content for each product in the list. Then, the generated interactive content can be saved in the cache on the server side. When explaining a specific product, the interactive content corresponding to the product can be read from the cache, and then the interactive content can be published by calling the service interface for publishing interactive content, and then the interactive content can be displayed in the interactive area of ​​the live broadcast interface on the client side.

[0043] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0044] Embodiment 1

[0045] First, this embodiment 1 provides an interactive content display method, which can be applied to the client of the commodity live broadcast service. Figure 2 , the method may specifically include:

[0046] S201: Display the live broadcast interface of the target live broadcast room to the viewer user.

[0047] The client in the embodiment of the present application may refer to a client for viewer users. When the viewer user enters the live broadcast room by clicking on a live broadcast room link, the live broadcast interface of the live broadcast room can be displayed, which includes the picture and voice content of the host user explaining a certain product. It can also include an interactive area. Users can input interactive content through the input controls of the interactive area while watching the live broadcast, including commenting on the product or the host, or asking questions to the host, etc.

[0048] S202: Displaying interactive content generated by an artificial intelligence (AI) generative model in a live broadcast interface, wherein the interactive content is generated in the following manner: obtaining user evaluation content from historical transaction data related to a target product currently being explained in the target live broadcast room, and using the AI ​​generative model to perform natural language understanding and rewrite processing on the user evaluation content to generate interactive content suitable for the style of the live broadcast room.

[0049] In the embodiment of the present application, in order to enrich the interactive content in the live broadcast interface, it can be supplemented by AI generation. Specifically, the user evaluation content in the historical transaction data related to the target product currently explained in the target live broadcast room can be obtained, and the AI ​​generative model can perform natural language understanding and rewrite processing on the user evaluation content to generate interactive content suitable for the style of the live broadcast room.

[0050] Among them, the specific interactive content can be displayed in an interactive area fixed at a position such as the lower left corner of the live broadcast interface. Of course, this interactive area usually scrolls and displays multiple interactive contents in chronological order, and the capacity of the area is limited. With the release of new interactive content, the old interactive content may scroll out of the interactive area. Alternatively, the interactive content can also be displayed in the form of barrages, which can appear in the live broadcast interface in the form of floating, flashing, staying, or even more actions from right to left. The content that appears in the form of this barrage will not be restricted by the position of the above-mentioned interactive area and is more likely to be noticed by users. Of course, if all of them appear in this barrage form, more effective information may be submerged. Therefore, in actual applications, some more important or more user-concerned interactive content can be displayed in the form of this barrage, and other content can be displayed through the above-mentioned fixed-position interactive area, and so on.

[0051] Since the live broadcast room in the embodiment of the present application is mainly a live broadcast room related to the explanation of the product, the interactive content generated by AI can also be related to the specific explained product. Specifically, since the products explained in the live broadcast room are usually also products released on the platform (that is, the system that provides product information services), sales data will be generated during the sales process of such products on the platform and saved in the platform database, which will include the evaluation content published by users on the products. Since this evaluation content is also input by the user and has a certain interactive nature, the interactive content of the live broadcast room can be generated based on this evaluation content.

[0052] That is to say, in the embodiment of the present application, interactive content suitable for the style of the live broadcast room can be generated by AI generation based on the user evaluation content generated during the platform sales process of the product currently being explained in the live broadcast room. Then, this AI-generated interactive content can be displayed in the interactive area of ​​the live broadcast interface as a supplement to the interactive content in the live broadcast room to enhance the interactive activity of the live broadcast room and provide users who have just entered the live broadcast room with higher density and more intuitive information, thereby helping to extend the user's stay time in the live broadcast room.

[0053] Among them, since the AI ​​generative model may take a certain amount of time to generate interactive content, in order to adapt to the use of live broadcast scenarios, the server can generate interactive content in advance through AI and save it in the server's cache. Specifically, when the host starts the live broadcast, they usually first configure the list of products to be explained in this live broadcast, that is, which products will be explained in a live broadcast can be determined at the beginning of the live broadcast. Therefore, the client on the host side can submit the list of products to be explained to the server, and the server can obtain the user evaluation content generated by each product in the list in the product information service system, and perform natural language understanding and rewriting of the user evaluation content through the AI ​​model to generate interactive content suitable for the style of the live broadcast room, that is, it can simulate the tone and style of the user's comments during the live broadcast to generate specific interactive content. After generating interactive content for each product in the list, the interactive content can be added to the cache on the server side. In this way, when the anchor user clicks "Start explaining" a product through the anchor-side client interface, the client can notify the server of the event that the product starts to be explained. The server can then learn about the product currently being explained, and then retrieve the interactive content corresponding to the product from the cache. It can also simulate the operation of a user account publishing the interactive content to the live broadcast room by calling relevant service interfaces, so that the interactive content can be pushed to the client on the audience side and displayed in the interactive area of ​​the live broadcast interface.

[0054] The historical evaluation content of a specific target product may be the user evaluation content obtained by the product itself, or, in some scenarios, the same product may have a product ID that has changed due to a change in supplier, etc., which may result in the new product ID not generating user evaluations during the sales process, or generating only a small amount of user evaluation content, etc. In this case, when AI generates interactive content in the live broadcast room, the generated interactive content may not be rich enough or have high homogeneity due to insufficient input information.

[0055] For example, the above situation often occurs in the live broadcast of fresh products. Fresh products are usually supplied by suppliers in the platform's own stores. Assume that for a certain variety of sweet potatoes, it was originally supplied by supplier A, and the corresponding product ID is 0001. The product has been on the platform for a period of time and has accumulated many user reviews; but for some reason, the supplier of this variety of sweet potatoes has been changed to B, which means that although it is still the same variety of sweet potatoes, the quality and other aspects are similar, but because the supplier has changed, the product ID may become 0002, and the new product ID may not have obtained enough user reviews. At this time, if the user evaluation content obtained by the new product ID itself is directly used for AI generation of interactive content, the quality of the generated interactive content may be low, and there may even be a situation where no user evaluation content is available.

[0056] In response to this situation, the embodiment of the present application also provides an implementation scheme for identifying the same product and aggregating user evaluation content. That is to say, the same product can be identified in advance in units of product ID. If it is identified that some product IDs actually correspond to the same product, but correspond to different suppliers or different parameter specifications, then the user evaluation content of these products can be mutually referenced or borrowed. Therefore, such products can be classified into the same product group, and then the user evaluation content obtained by each of the multiple products in the same product group can be aggregated as the user evaluation content corresponding to the product group. The aggregated user evaluation content corresponding to the same product group can be shared by multiple products in the product group. In this way, if it is necessary to generate interactive content for a product to be explained in the live broadcast room, it is possible to first determine which product group the product belongs to, and then, based on the user evaluation content aggregated from the product group, AI generation of interactive content in the live broadcast room can be performed for the product.

[0057] For example, suppose that product 0001 and product 0002 are identified as the same product, where product 0001 has obtained 1,000 user evaluation contents, while product 0002 has only obtained 5 user evaluation contents because it is newly released on the shelves. Then, product 0001 and product 0002 form a product group, and the 1,000 user evaluation contents corresponding to product 0001 and the 5 user evaluation contents corresponding to product 0002 are aggregated to obtain the user evaluation contents of the product group. In the process of aggregation, some deduplication or removal of invalid evaluation content can also be performed. The above aggregated information can be saved in the database. Since the platform may continuously release new products and continuously generate new user evaluation content, the aggregation results of the product group and its corresponding user evaluation content can also be updated according to a certain period. Afterwards, if a live broadcast room starts live broadcast, and product 0002 is in the list of products to be explained in the live broadcast room, the product group to which product 0002 belongs can be determined first, and the user evaluation content aggregation results corresponding to the product group can be obtained from the database. Then, this user evaluation content aggregation result can be used to perform AI generation of live broadcast room interactive content for product 0002.

[0058] Among them, the specific AI generative model can be an AI model of the "text-generating text" type, that is, it can generate new text based on the input text. Specifically in the embodiment of the present application, the input text can be the user evaluation content obtained in the sales process associated with the specific product, and the generated text can be the interactive content in the process of explaining the product in the live broadcast room, and this interactive content mainly exists in the form of text. In the specific implementation, in order to make the interactive content generated by AI have the style of the live broadcast room, some interactive content samples of the live broadcast room can also be provided in the input text, or the AI ​​generative model can be fine-tuned with some interactive content samples in advance, and then the interactive content can be generated, and so on.

[0059] In specific implementation, there can be multiple AI-generated interactive contents associated with the same target product, and these interactive contents can be displayed in a carousel in the interactive area. Of course, if the frequency of such AI-generated interactive contents appears too high, it may also cause user disgust, so it is also possible to display multiple interactive contents associated with the target product in a carousel at preset time intervals until the next product is introduced.

[0060] In addition, in order to make the displayed interactive content more like the interactive content actually input by the audience user, the specific interactive content can also be associated with the user account information, that is, the user account information can be displayed first, and then the specific interactive content can be displayed, so that it looks like the interactive content input by the user account. Among them, the specific user account used can be an account registered by a real user in the current commodity information service system, and authorized to the current commodity information service system to publish the interactive content generated by the AI ​​generative model. For example, it can be an account registered by some operators in the commodity information service system, and authorized to use the system, and so on. In this case, the process of such a user account publishing the corresponding interactive content can be simulated by calling the relevant service interface of the system.

[0061] In summary, through the embodiments of the present application, in the process of explaining the product in the live broadcast room, the interactive content generated by the AI ​​generative model can be displayed in the interactive area, including barrage or comment content, etc., wherein the specific interactive content can be generated based on the user evaluation content in the historical transaction data related to the target product currently explained in the target live broadcast room. During the generation process, the AI ​​generative model performs natural language understanding and rewrite processing on the user evaluation content to generate interactive content suitable for the style of the live broadcast room. In this way, the interactive activity of the live broadcast room can be improved through the interactive content generated by AI. In addition, since the generated interactive content is related to the product currently explained and is based on the user evaluation content, it is generated by the AI ​​model after rewriting according to the style of the live broadcast room, and can be mainly displayed in the live broadcast interface in the form of text, etc., therefore, compared with the picture, voice, etc. during the host's explanation, it has a higher information density, which is more conducive to extending the stay time of viewers who have just entered the live broadcast room in the live broadcast room.

[0062] Embodiment 2

[0063] This second embodiment corresponds to the first embodiment, and provides an interactive content processing method from the perspective of the server. The method is applied to the server of the commodity live broadcast service, see Figure 3 , the method may include:

[0064] S301: Determine a list of products to be explained that are associated with the target live broadcast room, and obtain user evaluation content in historical transaction data related to multiple products in the product list;

[0065] S302: Performing natural language understanding and rewriting processing on the user evaluation content by calling an AI generative model, generating interactive content suitable for the style of the live broadcast room for the multiple products, and caching the interactive content on the server;

[0066] S303: After determining the target product currently being explained in the target live broadcast room, the target interactive content corresponding to the target product is retrieved from the cache, and a user account is selected. By calling the service interface for publishing interactive content provided by the live broadcast service, the process of publishing the target interactive content through the selected user account is simulated, so that the client can display the target interactive content corresponding to the target product in the live broadcast interface of the target live broadcast room.

[0067] In specific implementation, multiple products in the product library can be judged as the same type of products in advance, and multiple products belonging to the same type of products can be divided into the same product group, and the user evaluation contents corresponding to multiple products in the same product group can be aggregated as the user evaluation contents shared by all products in the same product group; in this way, when it is necessary to obtain the user evaluation contents corresponding to a certain product, the product group to which the product belongs can be determined first, and the user evaluation contents aggregated from the product group can be obtained, so as to generate the interactive content for the product based on the aggregated user evaluation contents.

[0068] Alternatively, in an optional manner, before determining the product group to which the product belongs, it is also possible to determine whether the product currently being explained is a newly released product, or whether the richness of the associated user evaluation content does not meet the preset conditions. If so, the step of determining the product group to which the product belongs is triggered again, so as to generate interactive content for the user through the user evaluation content aggregated by the product group to which the product belongs. Otherwise, if the user evaluation content associated with the product currently being explained is rich enough, the user evaluation content associated with the product itself can be directly used to generate interactive content.

[0069] For the parts not described in detail in the second embodiment, please refer to the description of the first embodiment and other parts of this specification, which will not be repeated here.

[0070] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0071] Corresponding to the first embodiment, the embodiment of the present application further provides an interactive content display device, which is applied to a client of a commodity live broadcast service, including:

[0072] A live broadcast interface display unit, used to display the live broadcast interface of the target live broadcast room to the viewer user;

[0073] An interactive content display unit is used to display interactive content generated by an artificial intelligence (AI) generative model in a live broadcast interface, wherein the interactive content is generated in the following manner: user evaluation content in historical transaction data related to a target product currently being explained in the target live broadcast room is obtained, and the AI ​​generative model performs natural language understanding and rewriting processing on the user evaluation content to generate interactive content suitable for the style of the live broadcast room.

[0074] There are multiple interactive contents associated with the same target product;

[0075] The interactive content display unit can be specifically used for:

[0076] At preset time intervals, multiple interactive contents associated with the target product are displayed in a carousel until the next product is introduced.

[0077] The interactive content is also associated with user account information, where the user account is an account registered by a real user in the current product information service system and authorized to publish the interactive content generated by the AI ​​generative model to the product information service system;

[0078] The interactive content display unit can also be used for:

[0079] The interactive content and the corresponding user account information are displayed to simulate the interactive content posted by the user while watching the live broadcast.

[0080] Specifically, the interactive content is generated by an AI generative model by acquiring user evaluation content related to multiple products in the product list on the server side of the product live broadcast service after the live broadcast in the target live broadcast room is started and the list of products to be explained is determined. The generated interactive content is cached on the server side; after the server side determines the target product currently being explained, the corresponding interactive content is taken out from the cache, and a user account is selected. By calling the service interface for publishing interactive content provided by the product live broadcast service, the process of publishing the target interactive content through the selected user account is simulated, so that the client can display the target interactive content corresponding to the target product in the interactive area of ​​the live broadcast interface of the target live broadcast room.

[0081] The user evaluation content used when generating the interactive content includes: the user evaluation content corresponding to other products that are the same product as the target product but from different suppliers or with different specifications.

[0082] Corresponding to the second embodiment, the embodiment of the present application further provides an interactive content processing device, which is applied to the server end of the commodity live broadcast service, and the device may include:

[0083] A commodity and evaluation content acquisition unit, used to determine a list of commodities to be explained that is associated with a target live broadcast room, and to acquire user evaluation content in historical transaction data respectively related to a plurality of commodities in the commodity list;

[0084] An interactive content generation unit, configured to perform natural language understanding and rewrite processing on the user evaluation content by calling an AI generative model, generate interactive content suitable for the style of the live broadcast room for the multiple commodities, and cache the interactive content on the server side;

[0085] The interactive content publishing unit is used to determine the target product currently being explained in the target live broadcast room, retrieve the target interactive content corresponding to the target product from the cache, select a user account, and simulate the process of publishing the target interactive content through the selected user account by calling the service interface for publishing interactive content provided by the live broadcast service, so that the client can display the target interactive content corresponding to the target product in the live broadcast interface of the target live broadcast room.

[0086] Specifically, the device may further include:

[0087] A same-item product evaluation content aggregation unit is used to pre-judge multiple products in the product library as the same product, classify multiple products belonging to the same product into the same product group, and aggregate the user evaluation contents corresponding to the multiple products in the same product group as the user evaluation contents shared by all products in the same product group;

[0088] When it is necessary to obtain the user evaluation content corresponding to a certain product, the product and evaluation content acquisition unit can be specifically used to: determine the product group to which the product belongs, and obtain the user evaluation content aggregated by the product group, so as to generate the interactive content for the product based on the aggregated user evaluation content.

[0089] In addition, before determining the commodity group to which the commodity belongs, it can also be used to:

[0090] If the product is a newly released product, or the richness of the associated user evaluation content does not meet the preset conditions, the step of determining the product group to which the product belongs is triggered to generate interactive content for the user through the user evaluation content aggregated by the product group to which the product belongs.

[0091] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0092] And an electronic device, comprising:

[0093] one or more processors; and

[0094] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0095] A computer program product includes a computer program / computer executable instructions, which, when executed by a processor in an electronic device, implement the steps of the method described in the aforementioned method embodiment.

[0096] in, Figure 4 The architecture of an electronic device is exemplarily shown. For example, device 400 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, an aircraft, etc.

[0097] Reference Figure 4 , device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0098] The processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the method provided by the technical solution of the present disclosure. In addition, the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.

[0099] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0100] The power supply component 406 provides power to the various components of the device 400. The power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 400.

[0101] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0102] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the device 400 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0103] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0104] The sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, and the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and the temperature change of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0105] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, or a mobile communication network such as 2G, 3G, 4G / LTE, 5G, etc. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0106] In an exemplary embodiment, the device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0107] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, and the above instructions can be executed by a processor 420 of a device 400 to complete the method provided by the technical solution of the present disclosure. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0108] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0109] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0110] The above is a detailed introduction to the present application. The principles and implementation methods of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. An interactive content display method, characterized in that: The method is applied to a client of a commodity live broadcast service, and the method comprises: Display the live broadcast interface of the target live broadcast room to the viewing users; The interactive content generated by the artificial intelligence (AI) generative model is displayed in the live broadcast interface, wherein the interactive content is generated in the following manner: user evaluation content in historical transaction data related to the target product currently being explained in the target live broadcast room is obtained, and the AI ​​generative model performs natural language understanding and rewrites the user evaluation content to generate interactive content suitable for the style of the live broadcast room.

2. The method according to claim 1, characterized in that There are multiple interactive contents associated with the same target product; The interactive content generated by the AI ​​generative model is displayed in the live broadcast interface, including: At preset time intervals, multiple interactive contents associated with the target product are displayed in a carousel until the next product is introduced.

3. The method according to claim 1, characterized in that The interactive content is also associated with user account information, where the user account is an account registered by a real user in the current product information service system and authorized to publish the interactive content generated by the AI ​​generative model to the product information service system; When displaying the interactive content generated by the AI ​​generative model in the live broadcast interface, it also includes: The interactive content and the corresponding user account information are displayed to simulate the interactive content posted by the user while watching the live broadcast.

4. The method according to any one of claims 1 to 3, characterized in that: The interactive content is generated by an AI generative model by acquiring user evaluation content related to multiple products in the product list on the server side of the product live broadcast service after the live broadcast in the target live broadcast room is started and the list of products to be explained is determined. The generated interactive content is cached on the server side; after the target product currently being explained is determined on the server side, the corresponding interactive content is taken out from the cache, and a user account is selected. By calling the service interface for publishing interactive content provided by the product live broadcast service, the process of publishing the target interactive content through the selected user account is simulated, so that the client can display the target interactive content corresponding to the target product in the interactive area of ​​the live broadcast interface of the target live broadcast room.

5. The method according to any one of claims 1 to 3, characterized in that: The user evaluation content used when generating the interactive content includes: the user evaluation content corresponding to other products that are the same product as the target product but from different suppliers or with different specifications.

6. An interactive content processing method, characterized in that: The method is applied to the server of a commodity live broadcast service, and the method comprises: Determine a list of products to be explained that are associated with the target live broadcast room, and obtain user evaluation content in historical transaction data related to multiple products in the product list; By calling the AI ​​generative model to perform natural language understanding and rewriting processing on the user evaluation content, interactive content suitable for the style of the live broadcast room is generated for the multiple products respectively, and the interactive content is cached on the server; After determining the target product currently being explained in the target live broadcast room, the target interactive content corresponding to the target product is retrieved from the cache, and a user account is selected. By calling the service interface for publishing interactive content provided by the live broadcast service, the process of publishing the target interactive content through the selected user account is simulated, so that the client can display the target interactive content corresponding to the target product in the live broadcast interface of the target live broadcast room.

7. The method according to claim 6, characterized in that Also includes: Preliminarily determining whether multiple commodities in the commodity library are of the same type, classifying multiple commodities of the same type into the same commodity group, and aggregating the user evaluation contents respectively corresponding to the multiple commodities in the same commodity group as the user evaluation contents shared by the commodities in the same commodity group; When it is necessary to obtain the user evaluation content corresponding to a certain product, the product group to which the product belongs is determined, and the user evaluation content aggregated by the product group is obtained, so as to generate the interactive content for the product based on the aggregated user evaluation content.

8. The method according to claim 7, characterized in that Before determining the commodity group to which the commodity belongs, the method further includes: If the product is a newly released product, or the richness of the associated user evaluation content does not meet the preset conditions, the step of determining the product group to which the product belongs is triggered to generate interactive content for the user through the user evaluation content aggregated by the product group to which the product belongs.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

10. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method according to any one of claims 1 to 8.

11. A computer program product comprising a computer program / computer executable instructions, characterized in that: When the computer program / computer executable instructions are executed by a processor in an electronic device, the steps of the method according to any one of claims 1 to 8 are implemented.

Images