Information display method, device, storage medium and program product

Abstract

The embodiments of the present application provide an information display method, device, storage medium and program product. In the information display method, the human-computer dialogue operation and the search operation on the product information page can be linked, and search conditions and dialogue messages with associated relationships can be generated. According to the search conditions and dialogue messages with associated relationships, the search results and reply messages of associated products can be obtained. On the product information page, the reply messages and product search results with associated relationships are displayed on the same screen for users to compare and view. For users, they can use search services and shopping guide dialogue services without jumping to different pages, which can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information display method, device, storage medium and program product. Background Art

[0002] With the development of artificial intelligence technology, artificial intelligence (AI) technology has gradually become a key force in promoting innovation in various industries. In the field of e-commerce, AI technology can provide users with AI shopping guide assistants. AI shopping guide assistants can provide users with more intelligent and personalized shopping guide dialogue services by talking to users. However, the existing AI shopping guide assistants cannot effectively guide users' shopping behavior. Therefore, a new solution needs to be proposed. Summary of the invention

[0003] Multiple aspects of the present application provide an information display method, device, storage medium and program product for effectively guiding the user's shopping behavior based on an AI shopping guide assistant.

[0004] An embodiment of the present application provides an information display method, including: displaying a product information page, the product information page including a dialog window and a product information display area; responding to a search operation in the product information page, obtaining a first search condition corresponding to the search operation; displaying a first dialog message associated with the first search condition in the dialog window, and obtaining a first reply message corresponding to the first dialog message and product search results matched according to the first search condition; displaying the first reply message in the dialog window; and displaying the product search results matched according to the first search condition in the product information display area.

[0005] An embodiment of the present application also provides an information display method, including: displaying a product information page, the product information page including a dialog window and a product information display area; responding to a dialog input operation in the dialog window, obtaining an input dialog message; displaying the dialog message in the dialog window, and obtaining a reply message corresponding to the dialog message and a product search result matched according to a search condition associated with the dialog message; displaying the reply message in the dialog window; and displaying the product search result matched according to the search condition in the product information display area.

[0006] An embodiment of the present application also provides an information display method, including: receiving a first search condition sent by a client according to a search operation in a product information page and a first dialogue message associated with the first search condition, and displaying the first dialogue message in a dialogue window in the product information page; calling a target AI agent to generate a first reply message according to the first dialogue message; and calling a search engine to obtain product search results that match the first search condition; returning the first reply message and the product search results that match the first search condition to the client, so that the client displays the first reply message in the dialogue window, and displays the product search results that match the first search condition in the product information display area in the product information page.

[0007] An embodiment of the present application also provides an electronic device, comprising: a memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to: execute the steps in the method provided in the embodiment of the present application.

[0008] The embodiment of the present application also provides a computer-readable storage medium storing a computer program, which can implement the steps in the method provided in the embodiment of the present application when the computer program is executed by a processor.

[0009] The embodiment of the present application also provides a computer program product, including: a computer program / instructions, which, when executed by a processor, can implement the steps in the method provided in the embodiment of the present application.

[0010] In an embodiment of the present application, the human-computer dialogue operation and the search operation on the product information page can be linked to generate associated search conditions and dialogue messages. According to the associated search conditions and dialogue messages, associated product search results and reply messages can be obtained. On the product information page, the associated reply messages and product search results are displayed on the same screen for users to check and view. For users, there is no need to jump to different pages to use search services and shopping guide dialogue services. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services on the same screen with the product search results can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0012] Figure 1 is a structural diagram of an information display system provided by an exemplary embodiment of the present application;

[0013] Figure 2 is a schematic diagram of a product information page provided by an exemplary embodiment of the present application;

[0014] Figure 3 is a structural schematic diagram of an information display system provided by another exemplary embodiment of the present application;

[0015] Figure 4 It is a flowchart of an information display method provided by an exemplary embodiment of the present application when it is executed on a terminal device side;

[0016] Figure 5 is a flowchart of an information display method provided by another exemplary embodiment of the present application when it is executed on a terminal device side;

[0017] Figure 6 It is a flowchart of an information display method provided by an exemplary embodiment of the present application when it is executed on the server side;

[0018] Figure 7 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0020] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two, but does not exclude the inclusion of at least one.

[0021] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0022] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a product or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the product or system including the element.

[0023] In the field of e-commerce, AI shopping guide assistants can be provided to users based on AI technology. The AI ​​shopping guide assistant can provide users with more intelligent and personalized shopping guide dialogue services by communicating with users. In one implementation scheme of the AI ​​shopping guide assistant, the product search service provided by the AI ​​shopping guide assistant and the e-commerce platform are scattered on different pages or hierarchical menus. The AI ​​shopping guide assistant cannot provide shopping guide dialogue services based on the user's search behavior for products, and the search service cannot improve the search service based on the shopping guide dialogue service provided by the AI ​​shopping guide assistant. In another implementation scheme of the AI ​​shopping guide assistant, the AI ​​shopping guide assistant is mainly used to integrate and distribute product information on different e-commerce platforms, and does not provide product purchase services. Therefore, when users need to purchase products based on the product information provided by the AI ​​shopping guide assistant, they need to jump to a third-party e-commerce platform. The above-mentioned implementation scheme of the AI ​​shopping guide assistant cannot effectively guide the user's shopping behavior.

[0024] In view of the above technical problems, a solution is provided in some embodiments of the present application. The technical solutions provided by the embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0025] Figure 1 is a structural diagram of an information display system provided by an exemplary embodiment of the present application. Figure 1 As shown, the information display system 10 may include: a client 11 and a server 12 .

[0026] Among them, the client 11 can be implemented as a Web client, a desktop client or a mobile client, which is not limited in this embodiment. The client 11 can run on a terminal device, which can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc. on the user side. The terminal device can include a display screen for displaying the product information page corresponding to the client 11, and performing human-computer interaction with the user through the display screen. Among them, the server 12 can run on a server, which can be a conventional physical server, or can be a cloud server, such as an elastic computing instance on the cloud, a virtual machine, etc., which is not limited in this embodiment.

[0027] In the information display system 10, the client 11 is used to display a product information page, which includes a dialog window and a product information display area. The product information page is a page provided by the client 11 for displaying products of interest to the user. The product information page can provide the user with an operation entry for inputting keywords, selecting categories or other filtering conditions, so as to find products of interest to the user. The product information page may include a search control, a product information display area, and a dialog window. The product search control may include a search box, an instant search suggestion card, a search button, filter items, sorting options, etc. The product information display area is used to display product search results. The product search results may be displayed in the form of a list or a grid, and each product entry may include basic information such as product pictures, names, and prices. The filter items may include price range options, brand options, color / size options, etc. The sorting options may include sales sorting options, rating sorting options, new product sorting options, discount sorting options, etc.

[0028] In some optional embodiments, the client 11 may include a search component and a shopping assistant component. The search component is used to provide display logic for interface elements such as the search window and the product information display area, as well as processing logic related to the search service. The shopping assistant component is used to provide display logic for the dialogue window and processing logic related to the AI ​​dialogue. The search component may share data related to the search conditions with the shopping assistant component, and the shopping assistant component may share dialogue data with the search component to achieve linkage between the search service and the shopping guide dialogue service. Optionally, the shopping assistant component may be embedded in the client 11, or integrated in the client 11, which is not limited in this embodiment.

[0029] The client 11 is used to: respond to the search operation in the product information page, obtain the first search condition corresponding to the search operation, display the first dialogue message associated with the first search condition in the dialogue window, and obtain the first reply message corresponding to the first dialogue message and the product search results matched according to the first search condition from the server 12. Figure 1 This shows a way to implement a product information page, such as Figure 1 As shown, when the user enters "computer" as a search condition in the search box of the product information page and triggers the search operation, the client 11 can display "computer" as a dialogue message in the dialogue window of the product information page.

[0030] Among them, the search operation initiated on the product information page can be an operation in which the user enters a search keyword in the search box on the product information page and triggers the search button, or it can be an operation in which the user selects a search suggestion in the instant search suggestion card on the product information page, or it can be an operation in which the user selects a filter item on the product information page, or it can be a search operation for a search keyword initiated by the user through the voice interface on the product information page, and this embodiment includes but is not limited to this. Of course, in some other optional embodiments, the search operation initiated on the product information page can be implemented as a system operation other than a user operation, for example, a search operation triggered by a system timer event, etc., which is not limited in this embodiment.

[0031] Optionally, the first search condition corresponding to the search operation may include at least one of a search keyword input through a search box or a voice interface, a search suggestion selected in an instant search suggestion card, and a filtering condition corresponding to a selected filtering item, and this embodiment does not impose any restrictions thereto. When the client 11 displays the first dialog message associated with the first search condition in the dialog window, the first search condition may be directly displayed as the first dialog message, or the first search condition may be rewritten and the rewritten first search condition may be displayed as the first dialog message, and this embodiment does not impose any restrictions thereto. "First" is used here to limit the search condition, which is only used to facilitate the distinction from other search conditions described subsequently, and does not limit the number of search conditions.

[0032] Optionally, when obtaining the first reply message corresponding to the first conversation message, the client 11 may use a local or remote conversation engine to generate the first reply message corresponding to the first conversation message, or may send the first conversation message to the server 12, and the server 12 may use the conversation engine to generate the first reply message corresponding to the first conversation message. This embodiment does not impose any restrictions on this.

[0033] Optionally, when obtaining product search results matched according to the first search condition, the client 11 may use a local or remote search engine to match the products according to the first search condition, or the client 11 may send the first search condition to the server 12, and the server 12 may use a search engine to match the products according to the first search condition to obtain product search results. This embodiment does not impose any restrictions on this.

[0034] The server 12 is mainly used to: receive the first search condition sent by the client 11 and the first dialogue message associated with the first search condition; call the target AI agent, generate a first reply message according to the first dialogue message, and call the search engine to obtain the product search results matching the first search condition; return the first reply message and the product search results matching the first search condition to the client 11. Among them, the AI ​​agent (Artificial Intelligence Agent) is an abstract entity that can obtain external input information, process information, make decisions and take actions. The abstract entity can be a software program, an algorithm module or any other form of computer object. The AI ​​agent can learn from data through machine learning algorithms and continuously optimize its own performance. When called, the AI ​​agent can obtain the information input by the caller and perform operations such as data analysis, pattern recognition, and natural language processing based on the input information. When performing the above operations on the input information, the AI ​​agent autonomously uses various algorithms and models (such as machine learning models, deep learning models, reinforcement learning models, etc.), etc., and can independently complete the task without human intervention. In this embodiment, the AI ​​agent may provide an open API (Application Programming Interface) for the client 11 or the server 12 to call.

[0035] In some embodiments, Figure 1 As shown, the server 12 may include a dialogue engine 13 and a search engine 14. The dialogue engine 13 may be connected to one or more AI agents, and may use one or more AI agents to provide the client with natural language processing capabilities, commodity recognition capabilities, knowledge query capabilities, and reply generation capabilities. The search engine 14 is used to perform commodity search operations according to the search conditions provided by the client 11. The dialogue engine 13 and the search engine 14 may run on the same server, or may run on different servers, which is not limited in this embodiment.

[0036] In this embodiment, the target AI agent called by the server 12 when processing the first dialogue message can be any one of one or more AI agents connected to the server 12. Any AI agent is created to generate shopping guide information adapted to the dialogue message as a reply message according to the dialogue message sent by the client 11. Optionally, the shopping guide information may include at least one of: product recommendation information, price comparison information, event promotion information, shopping suggestion information, product details information and user evaluation information. Among them, the above-mentioned shopping guide information may include one or more recommended search keywords for users to re-initiate search according to the shopping guide information.

[0037] The client 11 is used to receive the first reply message corresponding to the first conversation message and the product search results matched according to the first search condition returned by the server 12, and display the first reply message in the conversation window, and display the product search results matched according to the first search condition in the product information display area. Figure 1 As shown, the client 11 can display the reply message returned by the server 12 according to the dialogue message "computer" in the dialogue window of the product information page, and the reply message can be: "Do you want a desktop or a laptop?" The client 11 can display the search results of computer products matched according to the search condition "computer" in the product information display area of ​​the product information page.

[0038] In this implementation, since the first reply message is the shopping guide information generated by the target AI agent and adapted to the first dialog message, and the shopping guide information is associated with the search criteria in the first dialog message, the shopping guide information in the first reply message is also associated with the product search results matched according to the search criteria, and thus, the first reply message can assist the user in selecting the product search results. Figure 1 For example, the reply message displayed in the dialog window can use a rhetorical question to guide the user to select the computer type, thereby assisting the user to select different types of computer products displayed in the product information display area.

[0039] Based on this implementation, the client 11 can trigger a dialogue with the shopping assistant component according to the search operation on the product information page, and determine the content of the dialogue to be actively asked according to the search conditions, thereby realizing the linkage between the shopping guide dialogue service and the product search service. On the product information page of the client 11, the first reply message with an associated relationship and the product search results are displayed on the same screen for users to check and compare. For users, there is no need to jump to different pages to use the search service and the shopping guide dialogue service. Users do not need to remember or record certain information, but can directly analyze and judge intuitively based on the shopping guide information and search results, reducing the time and energy spent by users switching between different information. In addition, displaying the shopping guide information and search results on the same screen can facilitate users to quickly capture key information, thereby promoting user decision-making and improving the conversion rate of shopping behavior.

[0040] In some optional embodiments, the first reply message returned by the server 12 may include at least one recommended search keyword, and the at least one recommended search keyword is used to guide the user to search and provide shopping suggestions. Optionally, when the client 11 displays the first reply message in the dialog window, at least one recommended search keyword in the first reply message is highlighted. Optionally, when highlighting any recommended search term, the highlighted state of the recommended search term may be displayed, the font size of the recommended search term may be enlarged, the underline corresponding to the recommended search term may be displayed, etc. This embodiment includes but is not limited to this. For example, in Figure 1 In the illustrated product information page, the reply information displayed in the dialog window includes multiple recommended search keywords such as "desktop" and "laptop computer". The client 11 can highlight the recommended search keywords by underlining the multiple recommended search keywords. Accordingly, the client 11 can respond to the selection operation of the target search keyword in the at least one recommended search keyword, obtain the product search results matched according to the target search keyword, and display the product search results matched according to the target search keyword in the product information display area.

[0041] Optionally, at least one recommended search keyword in the first reply message may be identified by the server 12 from the first reply message. For example, in some embodiments, after the server 12 obtains the first reply message returned by the target AI agent, it may perform keyword matching or entity recognition on the first reply message to obtain keywords containing product description information as recommended search keywords. Among them, keyword matching is used to identify specific keywords or phrases in the first reply message, such as "material", "size", "color", "features", etc. Entity recognition is used to use named entity recognition technology to identify entity information such as product name, brand name, specifications, etc. in the first reply message. After the server 12 identifies at least one recommended search keyword from the first reply message, it may add a tag to the at least one recommended search keyword, and the tag is used to enable the client 11 to render the at least one recommended search keyword as a prominent display effect. For any recommended search keyword with a tag, the client 11 may add a monitoring event for the recommended search keyword, and the monitoring event is used to capture the click operation on the search keyword, and in response to the click operation, perform a predefined operation of sending a search request to the server 12 according to the search keyword.

[0042] In some optional embodiments, when obtaining the product search results matched according to the target search keyword, the client 11 may call a local or remote search engine to perform a product matching operation according to the target search keyword to obtain a product matching result.

[0043] In some other optional embodiments, when the client 11 obtains the product search results matched according to the target search keyword, it may send a search request according to the target search keyword to the server 12. If the server 12 receives the search request sent by the client 11 according to the target search keyword, it may match the products in the product database according to the target search keyword, and return the product search results matched according to the target search keyword to the client 11. The client 11 may display the product search results matched by the server according to the target search keyword in the product information display area of ​​the product information page.

[0044] Continue with Figure 1 Taking the product information page shown in FIG. 1 as an example, the client 11 can monitor the user's selection operation of multiple recommended search keywords such as "desktop" or "laptop". Figure 2 As shown, if a selection operation of the recommended search keyword "laptop computer" is detected, the client 11 can send a search request to the server 12 according to the recommended search keyword "laptop computer", and the server 12 can return product search results related to "laptop computer". Figure 2 As shown, the client 11 can display the product search results related to "laptop computer" in the product information display area.

[0045] Based on this implementation method, the shopping guide information returned by the shopping assistant component is linked with the search service, so that the shopping guide information can be applied to the user's shopping screening process, which is conducive to improving the conversion rate of shopping behavior.

[0046] It is worth noting that, since at least one recommended search keyword in the first reply message has a certain association with the first search condition, when the server 12 performs a search operation based on the target search keyword in the at least one recommended search keyword, the target search keyword can be associated with the first search condition to ensure a certain degree of continuity between multiple search operations. Optionally, when the server 12 associates the target search keyword with the first search condition, it can identify intent modifiers related to the target search keyword in the first reply message, such as intent modifiers such as "yes, no, want to buy, want, don't want to buy, more inclined to, can also". The server 12 can obtain the logical relationship between the target search keyword and the first search condition based on the intent modifier, and combine the target search keyword and the first search condition based on the logical relationship to obtain the adjusted target search keyword. The server 12 can match commodities in the commodity database based on the adjusted target search keyword, and return the commodity search results matched according to the adjusted target search keyword.

[0047] Continue with Figure 2For example, suppose the first reply message displayed by the client 11 is: "Do you use it for daily office use or for gaming and entertainment?" The first reply message is used to guide the user to choose a laptop computer according to the usage scenario. When the trigger operation of the keyword "daily office use" is detected, the client 11 can use the keyword "daily office use" as the target search keyword, and send a search request to the server 12 based on the target search keyword. After receiving the search request, the server 12 can identify the intent modifier related to the target search keyword as "yes" from the first reply message, and can determine that there is a logical relationship of "and" between the two search keywords "laptop computer" and "daily office use". Furthermore, the server 12 can use: "laptop computer and daily office use" as the adjusted target search keyword, and match the goods in the commodity database according to the adjusted target search keyword to obtain the commodity search results.

[0048] The above-mentioned embodiment provides an implementation method in which the client 11 can trigger a dialogue with the shopping assistant component based on a search operation on the product information page. In some exemplary embodiments, the client 11 can trigger a search operation on the product information page based on a dialogue operation with the shopping assistant component. Specific exemplary descriptions are given below.

[0049] In some exemplary embodiments, the client 11 may respond to the dialogue input operation in the dialogue window and obtain the input second dialogue message. Optionally, the dialogue input operation in the dialogue window may be an input operation initiated through an input control (e.g., a text input control or a voice input control) in the dialogue window, or may be an input operation initiated through a picture / document upload control in the dialogue window, or may be a selection operation of any recommended search keyword in the reply message displayed in the dialogue window, which is not limited in this embodiment. Accordingly, the second dialogue message may be a text message, a voice message, a picture message, etc., which is not limited in this embodiment.

[0050] After obtaining the second conversation message, the client 11 may display the second conversation message in the conversation window, and obtain a second reply message corresponding to the second conversation message and a product search result matched by a second search condition associated with the second conversation message.

[0051] Optionally, when obtaining a second reply message corresponding to the second conversation message, the client 11 may utilize a local or remote conversation engine to obtain the second reply message corresponding to the second conversation message, or the client 11 may send the second conversation message to the server 12, and the server 12 may utilize the conversation engine to generate a second reply message corresponding to the second conversation message.

[0052] Optionally, when obtaining product search results that match the second search condition associated with the second conversation message, the client 11 may use a local or remote search engine to match products according to the second search condition associated with the second conversation message to obtain product search results; or, the client 11 may send the second search condition associated with the second conversation message to the server 12, and the server 12 may call the search engine to match products according to the second search condition associated with the second conversation message to obtain product search results.

[0053] In some optional embodiments, when sending the second search condition associated with the second dialogue message to the server 12, the client 11 may directly send the second dialogue message as the second search condition to the server 12. In some other optional embodiments, the client 11 may extract information based on the second dialogue message and / or the context dialogue message of the second dialogue message to obtain the second search condition, and send the extracted second search condition to the server 12. The context dialogue message of the second dialogue message refers to a message in a multi-round dialogue between the user and the shopping assistant component, and the context dialogue message may include a dialogue message provided by the user in the multi-round dialogue and a reply message returned by the server 12.

[0054] Optionally, when extracting information based on the second dialogue message and / or the context dialogue message of the second dialogue message, the client 11 may use an entity recognition method and / or a keyword matching method to identify at least one product description information from the second dialogue message and / or the context message, and determine the search keyword based on the at least one product description information. Optionally, the search keyword may be one or more. If there are multiple, the client 11 may identify the intent modifiers of each of the multiple search keywords from the second dialogue message and / or the context message, and determine the logical relationship between the multiple search keywords based on the identified intent modifiers. Optionally, the client 11 may perform semantic recognition on the second dialogue message and / or the context message to obtain keywords containing filtering semantics, such as keywords such as filtering, price range, brand name, home use, and place of shipment, to obtain filtering conditions. Optionally, the client 11 may perform semantic recognition on the second dialogue message and / or the context message to obtain keywords containing sorting semantics, such as keywords such as cost-effectiveness, good reviews, new models, and high sales, as sorting conditions. The client 11 may execute at least one of the above-mentioned information extraction methods to obtain at least one of the search keywords, the screening conditions and the sorting conditions as the second search condition.

[0055] Accordingly, the server 12 may receive the second dialogue message and the second search condition associated with the second dialogue message, call the target AI agent, generate a second reply message according to the second dialogue message, and call the search engine to obtain the product search results matching the second search condition. The server 12 may return the second reply message and the product search results matching the second search condition to the client 11.

[0056] Furthermore, the client 11 can display the second reply message corresponding to the second dialogue message generated by the server calling the target AI agent in the dialogue window, and display the product search results matched by the server according to the second search condition in the product information display area. Based on this implementation, based on the interaction between the client 11 and the server 12, the search operation on the product information page can be triggered according to the dialogue operation in the dialogue window, so that the shopping guide dialogue service and the product search service provided by the product information page can be linked, which is conducive to improving the contribution of the shopping guide dialogue service to the product purchase link and improving the conversion rate of shopping behavior.

[0057] In some optional embodiments, any of the one or more AI agents connected to the server 12 may call a language model to provide question-answering services, and the language models called by different AI agents may be different. In some embodiments, the language model called by any AI agent may be a large language model. Among them, a large language model is a natural language processing (NLP) model that has been trained on a large scale. The large language model is usually built based on deep learning technology and trained on a large-scale training data set, so that it can show strong performance when processing natural language tasks. The number of parameters of the large language model is greater than the set threshold, which is usually on the order of millions or billions.

[0058] In addition to the large language model, any AI agent can access the knowledge base and retrieve knowledge from the knowledge base based on the conversation message. The AI ​​agent can provide the retrieved knowledge that matches the conversation message to the large language model, so that the large language model can generate a reply message that matches the conversation message based on the input knowledge. Different AI agents can access different knowledge bases. The knowledge base may include, but is not limited to: at least one of: product specification knowledge, product usage knowledge, market sales trend data, social media comment data, and seasonal / festival promotion knowledge.

[0059] In some embodiments, Figure 3 The architecture of the information display system provided in the embodiment of the present application is further illustrated, such as Figure 3As shown, the one or more AI agents accessed by the server 12 may include: a native AI agent provided by the server 12, an AI agent provided by a third-party information service provider, and at least one of the AI ​​agents created by the user on the capability exposure platform provided by the server 12, and this embodiment includes but is not limited to this. Among them, the native AI agent provided by the server 12 refers to an AI agent customized and developed to provide conversation capabilities to the shopping assistant component, and the AI ​​agent is deployed as a part of the server 12. The third-party information service provider may be other e-commerce platforms, shopping information sharing or social media platforms, etc. The server 12 can be connected to the AI ​​agent provided by the third-party information service provider through an API or other integration methods.

[0060] In this embodiment, the capability opening platform provided by the server 12 is a platform that allows third-party developers to access and use the functions, data and services provided by the platform to develop new products and services. In this embodiment, the third-party developer can be a merchant, a consumer, or a shopping expert, etc., and this embodiment does not limit this. The capability opening platform can provide the main link for creating an AI agent, such as Figure 3 As shown, the main link may include operations such as creating an AI agent for dialogue, setting the role of the AI ​​agent, building a knowledge base, creating skills (such as dialogue message rewriting skills), associating tools (such as image search tools), and associating large language models. After a third-party developer creates and publishes an AI agent, the capability open platform may verify the AI ​​agent, such as function verification, load verification, and compatibility verification. If the AI ​​agent passes the verification, the capability open platform may register the AI ​​agent with the server 12 so that the server 12 can access the AI ​​agent.

[0061] Accordingly, when the server 12 calls the target AI agent and generates the first reply message according to the first dialogue message, it can call the target AI agent and provide the first dialogue message to the target language model so that the target language model generates the first reply message. Optionally, the target AI agent can also search the knowledge base according to the first dialogue message to obtain the target knowledge matching the first dialogue message, and provide the target knowledge and the first dialogue message to the target language model so that the target language model generates the first reply message corresponding to the first dialogue message according to the target knowledge.

[0062] In this embodiment, the target language model refers to the language model bound to the target AI agent, and the target language model is a deep learning model trained on a product information dataset. Among them, the product information dataset may include: at least one of basic product information (such as product description information, product classification information, etc.), product sales information (such as price, discount, etc.), and purchase guidance data (such as product matching, combination, size selection, etc.). Furthermore, the target language model can return a reply message related to the product information according to the search condition associated with the first dialogue message. Optionally, the first reply message includes at least one of the following: at least one recommended search keyword associated with the search keyword in the first dialogue message, information about similar products associated with the picture in the first dialogue message (such as the name of the product, the link to the product, etc.), a recommended question associated with the user question in the first dialogue message, and a rhetorical question associated with the user question in the first dialogue message.

[0063] When the server 12 is connected to one or more AI agents, the client 11 may provide the user with an operation entry for personalized selection of AI agents. Optionally, the dialog window displayed by the client 11 may include: an AI agent switching control. The client 11 may respond to a triggering operation on the AI ​​agent switching control and display at least one AI agent identifier.

[0064] Optionally, the at least one AI agent identifier displayed by the client 11 may be determined by the server 12. The client 11 may send an AI agent switching request to the server 12 in response to the triggering operation of the AI ​​agent switching control. After receiving the AI ​​agent switching request, the server 12 may determine at least one AI agent identifier based on the historical search data in the product information page and / or the contextual dialogue data in the dialogue window, and return the at least one AI agent representation to the client 11. In some scenarios, when different AI agents have different knowledge bases or different AI agents are associated with different language models, different AI agents have different shopping guide dialogue service capabilities for different categories of goods. For example, some AI agents are good at providing shopping guide dialogue services for electronic products, while other AI agents are good at providing shopping guide dialogue services for clothing products. Based on this, the server 12 may identify the category to which the product that the user intends to purchase belongs based on the historical search data in the product information page and / or the contextual dialogue data in the dialogue window, determine at least one AI agent that is more suitable for the identified category, and return the identifier of the at least one AI agent to the client 11. The AI ​​agent identifier may be the name or ID of the AI ​​agent.

[0065] When displaying the at least one AI agent identifier returned by the server 12, the client 11 may obtain the selected AI agent identifier according to the selection operation of the at least one AI agent identifier. The client 11 may send the selected AI agent identifier to the server 12, and the selected AI agent identifier is used to determine the target AI agent. After receiving the AI ​​agent identifier sent by the client, the server 12 may determine the AI ​​agent corresponding to the AI ​​agent identifier from at least one preset AI agent as the target AI agent. Furthermore, when receiving the first dialogue message, the server 12 may call the target AI agent and generate a first reply message according to the first dialogue message, which will not be described further.

[0066] In some optional embodiments, any AI agent may include multiple roles, and different roles are used to adapt to the shopping guide needs in different scenarios. After determining to select the AI ​​agent identifier, the client 11 may display multiple roles corresponding to the AI ​​agent identifier for the user to select the preferred dialogue role, which will not be repeated. Based on this implementation, a personalized selection service of an AI agent can be provided to the user, and then different shopping guide-related knowledge can be provided to the user through different AI agents. For the user, different AI agents can be switched in different demand scenarios based on personal preferences. For example, when the user has the need to buy clothes, an AI agent with rich knowledge of clothes and good at handling clothing shopping guide problems can be selected. When the user has the need to buy electronic products, an AI agent with rich knowledge of electronic products can be selected to meet the shopping guide needs in various scenarios.

[0067] In addition to the information display system provided in the aforementioned embodiment, the embodiment of the present application also provides an information display method. The following will introduce different implementation methods of the information display method in conjunction with the accompanying drawings.

[0068] Figure 4 is a flow chart of an information display method provided by an exemplary embodiment of the present application when it is executed on a terminal device side, such as Figure 4 As shown, the method mainly includes the following steps:

[0069] Step 401: Display a product information page, which includes a dialog window and a product information display area.

[0070] Step 402: respond to a search operation in the product information page and obtain a first search condition corresponding to the search operation.

[0071] Step 403: Display a first dialog message associated with the first search condition in the dialog window, and obtain a first reply message corresponding to the first dialog message and a product search result matched according to the first search condition.

[0072] Step 404: Display the first reply message in the dialog window; and display the product search results matched according to the first search condition in the product information display area.

[0073] Optionally, when obtaining a first reply message corresponding to a first conversation message, the terminal device may utilize a local or remote conversation engine to generate a first reply message corresponding to the first conversation message, or may send the first conversation message to a server, which may utilize a conversation engine to generate a first reply message corresponding to the first conversation message. This embodiment does not impose any restrictions on this.

[0074] Optionally, when obtaining product search results matched according to the first search condition, the terminal device may use a local or remote search engine to match the products according to the first search condition, or the terminal device may send the first search condition to the server, and the server uses a search engine to match the products according to the first search condition to obtain product search results. This embodiment does not impose any restrictions on this.

[0075] In some exemplary embodiments, the method further includes: when displaying the first reply message in the dialog window, highlighting at least one recommended search keyword in the first reply message; in response to a selection operation of a target search keyword in the at least one recommended search keyword, obtaining a product search result matched according to the target search keyword; and displaying the product search result matched according to the target search keyword in the product information display area. Optionally, when obtaining the product search result matched according to the target search keyword, the terminal device may use a local or remote search engine to match the product according to the target search keyword, or the terminal device may send the target search keyword to the server, and the server uses a search engine to match the product according to the target search keyword to obtain the product search result, which is not limited in this embodiment.

[0076] In some exemplary embodiments, the method also includes: responding to a conversation input operation in the conversation window, obtaining an input second conversation message; displaying the second conversation message in the conversation window, and obtaining a second reply message corresponding to the second conversation message and a product search result matched according to a second search condition associated with the second conversation message; displaying the second reply message in the conversation window; and displaying the product search result matched according to the second search condition in the product information display area.

[0077] In some exemplary embodiments, a method for obtaining product search results that match the second search keyword associated with the second conversation message may include: performing semantic recognition on the second conversation message to obtain the second search condition, the second search condition including: at least one of the search keyword, the filtering condition, and the sorting condition; sending the second search condition to the server; and obtaining the product search results that match the second search condition returned by the server.

[0078] In some exemplary embodiments, the first reply message is generated by the server calling the target AI agent, and the dialog window includes: an AI agent switching control; in the dialog window, before displaying the first reply message, the method also includes: in response to a trigger operation on the AI ​​agent switching control, displaying at least one AI agent identifier; according to a selection operation on the at least one AI agent identifier, obtaining a selected AI agent identifier; sending the selected AI agent identifier to the server, so that the server determines the target AI agent based on the selected AI agent identifier.

[0079] In some exemplary embodiments, a method of displaying at least one AI agent identifier in response to a trigger operation on the AI ​​agent switching control may include: sending an AI agent switching request to the server in response to a trigger operation on the AI ​​agent switching control; and displaying the at least one AI agent identifier returned by the server based on the AI ​​agent switching request, wherein the at least one AI agent identifier is determined by the server based on historical search data in the product information page and / or contextual conversation data in the conversation window.

[0080] In this embodiment, the search operation on the product information page can trigger a human-computer dialogue operation, and the dialogue message provided by the human-computer dialogue operation is associated according to the search conditions corresponding to the search operation, thereby realizing the linkage between the search operation and the human-computer dialogue operation. According to the associated search conditions and dialogue messages, the associated product search results and reply messages can be obtained. On the product information page, the associated reply messages and product search results are displayed on the same screen for users to check. For users, there is no need to jump to different pages to use the search service and the shopping guide dialogue service. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services on the same screen with the product search results can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior.

[0081] Figure 5is a flowchart of an information display method provided by another exemplary embodiment of the present application when it is executed on a terminal device side, such as Figure 5 As shown, the method mainly includes the following steps:

[0082] Step 501: Display a product information page, which includes a dialog window and a product information display area.

[0083] Step 502: Respond to the dialog input operation in the dialog window and obtain the input dialog message.

[0084] Step 503: Display the conversation message in the conversation window, and obtain a reply message corresponding to the conversation message and a product search result matched according to the search condition associated with the conversation message.

[0085] Step 504: Display the reply message in the dialog window; and display the product search results matched according to the search condition in the product information display area.

[0086] Optionally, when obtaining a reply message corresponding to a conversation message, the terminal device may use a local conversation engine to generate a reply message corresponding to the conversation message, or may send the conversation message to a server, which uses a conversation engine to generate a reply message corresponding to the conversation message. This embodiment does not impose any restrictions on this.

[0087] Optionally, when obtaining product search results matched according to the search conditions, the terminal device may use a local search engine to match products according to the search conditions, or the terminal device may send the search conditions to the server, and the server uses a search engine to match products according to the search conditions to obtain product search results. This embodiment does not impose any restrictions on this.

[0088] In this embodiment, the human-computer dialogue operation on the product information page can trigger a search operation, and the search conditions provided by the search operation are associated with the dialogue message corresponding to the human-computer dialogue operation, thereby realizing the linkage between the human-computer dialogue operation and the search operation. According to the search conditions and dialogue messages with associated relationships, the search results and reply messages of associated products are obtained. On the product information page, the reply messages and product search results with associated relationships are displayed on the same screen for users to check and compare. For users, search services and shopping guide dialogue services can be used without jumping to different pages. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services on the same screen with the product search results can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improving the conversion rate of shopping behavior.

[0089] Figure 6 FIG. 1 is a flow chart of an information display method provided by an exemplary embodiment of the present application when executed on a server side. Figure 6 As shown, the method mainly includes the following steps:

[0090] Step 601: Receive a first search condition and a first dialog message associated with the first search condition sent by a client according to a search operation in a product information page, and display the first dialog message in a dialog window in the product information page.

[0091] Step 602: call the target AI agent to generate a first reply message according to the first dialogue message; and call the search engine to obtain product search results that match the first search condition.

[0092] Step 603: Return the first reply message and the product search results matching the first search condition to the client, so that the client displays the first reply message in the dialog window and displays the product search results matching the first search condition in the product information display area of ​​the product information page.

[0093] In some exemplary embodiments, the method also includes: receiving a second dialogue message sent by the client and a second search condition associated with the second dialogue message, the second dialogue message being input through the dialogue window; calling the target AI agent to generate a second reply message based on the second dialogue message; and calling a search engine to obtain product search results that match the second search condition; returning the second reply message and the product search results that match the second search condition to the client, so that the client displays the second reply message in the dialogue window, and displays the product search results that match the second search condition in the product information display area.

[0094] In some exemplary embodiments, a method of calling a target AI agent to generate a first reply message based on the first dialogue message may include: calling the target AI agent, providing the first dialogue message to a target language model so that the target language model generates the first reply message, and the target language model is a deep learning model trained on a product information dataset.

[0095] In some exemplary embodiments, the first reply message includes at least one of the following: at least one recommended search keyword associated with the search keyword in the first conversation message, information about similar products associated with the picture in the first conversation message, a recommended question associated with the user question in the first conversation message, and a rhetorical question associated with the user question in the first conversation message.

[0096] In some exemplary embodiments, before calling the target AI agent and generating a first reply message based on the first dialogue message, the method also includes: receiving an AI agent switching request sent by the client; returning at least one AI agent identifier to the client, wherein the at least one AI agent identifier is determined based on historical search data in the product information page and / or context dialogue data in the dialogue window; receiving an AI agent identifier sent by the client, wherein the AI ​​agent identifier is selected by the client from at least one AI agent identifier; and determining an AI agent corresponding to the AI ​​agent identifier from at least one preset AI agent as the target AI agent.

[0097] In this implementation, the human-computer dialogue operation and the search operation on the product information page can be linked. The server can return the product search results and reply messages with associated relationships based on the associated search conditions and dialogue messages. On the product information page, the associated reply messages and product search results are displayed on the same screen for users to compare and view. For users, there is no need to jump to different pages to use the search service and the shopping guide dialogue service. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services on the same screen with the product search results can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior.

[0098] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 401 to 404 can be device A; for another example, the execution subject of steps 401 and 402 can be device A, and the execution subject of step 403 can be device B; and so on.

[0099] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel, and the sequence numbers of the operations, such as 401, 402, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0100] It should be noted that, in the case where the embodiments of the present application involve user interaction operations or trigger operations, the user interaction operations or trigger operations involved in the embodiments of the present application include but are not limited to: touch operation, gesture operation, voice operation, head movement operation, eye movement operation and other interactive operations in various ways; among which, touch operation includes but is not limited to: click operation, double-click operation, long press operation, slide operation, pinch operation or mouse hover operation, etc. Slide operation includes but is not limited to: straight line sliding, curve sliding, etc.

[0101] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data 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 the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0102] Figure 7 A schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application is shown. Figure 7 As shown, the electronic device includes: a memory 701 , a processor 702 and a communication component 703 .

[0103] The memory 701 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application program or method operating on the electronic device.

[0104] In some optional embodiments, Figure 7 The electronic device shown in the figure can be implemented as a terminal device, and the terminal device can also include a display component 704. The processor 702 is coupled to the memory 701, and is used to execute the computer program in the memory 701, so as to: control the display component 704 to display a product information page, the product information page including a dialog window and a product information display area; respond to a search operation in the product information page, and obtain a first search condition corresponding to the search operation; display a first dialog message associated with the first search condition in the dialog window, and obtain a first reply message corresponding to the first dialog message and a product search result matched according to the first search condition; display the first reply message in the dialog window; and display the product search result matched according to the first search condition in the product information display area.

[0105] In some exemplary embodiments, the processor 702 is also used to: control the display component 704 to highlight at least one recommended search keyword in the first reply message when displaying the first reply message in the dialog window; respond to a selection operation of a target search keyword in the at least one recommended search keyword, and obtain product search results matched according to the target search keyword; and display the product search results matched according to the target search keyword in the product information display area.

[0106] In some exemplary embodiments, the processor 702 is also used to: respond to a conversation input operation in the conversation window and obtain an input second conversation message; control the display component 704 to display the second conversation message in the conversation window, and obtain a second reply message corresponding to the second conversation message and a product search result matched according to a second search condition associated with the second conversation message; display the second reply message in the conversation window; and display the product search result matched according to the second search condition in the product information display area.

[0107] In some exemplary embodiments, when the processor 702 obtains the product search results matched by the second search keyword associated with the second conversation message, it is specifically used to: perform semantic recognition on the second conversation message to obtain the second search condition, where the second search condition includes: at least one of the search keyword, the filtering condition and the sorting condition; control the communication component 703 to send the second search condition to the server; and obtain the product search results matched by the second search condition returned by the server.

[0108] In some exemplary embodiments, the first reply message is generated by the server calling the target AI agent, and the dialog window includes: an AI agent switching control; before the processor 702 controls the display component 704 to display the first reply message in the dialog window, it is also used to: respond to a trigger operation on the AI ​​agent switching control, control the display component 704 to display at least one AI agent identifier; obtain a selected AI agent identifier based on a selection operation on the at least one AI agent identifier; control the communication component 703 to send the selected AI agent identifier to the server, so that the server determines the target AI agent based on the selected AI agent identifier.

[0109] In some exemplary embodiments, when the processor 702 controls the display component 704 to display at least one AI agent identifier in response to a trigger operation on the AI ​​agent switching control, it is specifically used to: control the communication component 703 to send an AI agent switching request to the server in response to a trigger operation on the AI ​​agent switching control; control the display component 704 to display the at least one AI agent identifier returned by the server according to the AI ​​agent switching request, wherein the at least one AI agent identifier is determined by the server according to historical search data in the product information page and / or contextual conversation data in the conversation window.

[0110] In this embodiment, the search operation on the product information page can trigger a human-computer dialogue operation, and the dialogue message provided by the human-computer dialogue operation is associated according to the search conditions corresponding to the search operation, thereby realizing the linkage between the search operation and the human-computer dialogue operation. According to the associated search conditions and dialogue messages, the associated product search results and reply messages can be obtained. On the product information page, the associated reply messages and product search results are displayed on the same screen for users to check. For users, there is no need to jump to different pages to use the search service and the shopping guide dialogue service. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services on the same screen with the product search results can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior.

[0111] In some other optional embodiments, when Figure 7 When the illustrated electronic device is implemented as a terminal device, the processor 702 is coupled to the memory 701 and is used to execute a computer program in the memory 701, so as to: control the display component 704 to display a product information page, which includes a dialog window and a product information display area; respond to a dialog input operation in the dialog window and obtain an input dialog message; display the dialog message in the dialog window, and obtain a reply message corresponding to the dialog message and a product search result matched according to the search condition associated with the dialog message; display the reply message in the dialog window; and display the product search result matched according to the search condition in the product information display area.

[0112] In this embodiment, the human-computer dialogue operation on the product information page can trigger a search operation, and the search conditions provided by the search operation are associated with the dialogue message corresponding to the human-computer dialogue operation, thereby realizing the linkage between the human-computer dialogue operation and the search operation. According to the search conditions and dialogue messages with associated relationships, the search results and reply messages of associated products can be obtained. On the product information page, the reply messages and product search results with associated relationships are displayed on the same screen for users to check and compare. For users, there is no need to jump to different pages to use the search service and the shopping guide dialogue service. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services and product search results on the same screen can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior.

[0113] In some further optional embodiments, Figure 7 The illustrated electronic device can be implemented as a server, and the processor 702 is coupled to the memory 701, and is used to execute the computer program in the memory 701, so as to: control the communication component 703 to receive the first search condition and the first dialogue message associated with the first search condition sent by the client according to the search operation in the product information page, and the first dialogue message is displayed in the dialogue window in the product information page; call the target AI agent to generate a first reply message according to the first dialogue message; and call the search engine to obtain the product search results that match the first search condition; return the first reply message and the product search results that match the first search condition to the client, so that the client displays the first reply message in the dialogue window, and displays the product search results that match the first search condition in the product information display area in the product information page.

[0114] In some exemplary embodiments, the processor 702 is also used to: control the communication component 703 to receive a second dialogue message sent by the client and a second search condition associated with the second dialogue message, wherein the second dialogue message is input through the dialogue window; call the target AI agent to generate a second reply message based on the second dialogue message; and call the search engine to obtain product search results that match the second search condition; return the second reply message and the product search results that match the second search condition to the client, so that the client displays the second reply message in the dialogue window, and displays the product search results that match the second search condition in the product information display area.

[0115] In some exemplary embodiments, when the processor 702 calls the target AI agent and generates a first reply message according to the first dialogue message, it is specifically used to: call the target AI agent and provide the first dialogue message to the target language model so that the target language model generates the first reply message, and the target language model is a deep learning model trained on a product information dataset.

[0116] In some exemplary embodiments, the first reply message includes at least one of the following: at least one recommended search keyword associated with the search keyword in the first conversation message, information about similar products associated with the picture in the first conversation message, a recommended question associated with the user question in the first conversation message, and a rhetorical question associated with the user question in the first conversation message.

[0117] In some exemplary embodiments, before calling the target AI agent and generating a first reply message according to the first dialogue message, the processor 702 is also used to: receive an AI agent switching request sent by the client; return at least one AI agent identifier to the client, wherein the at least one AI agent identifier is determined based on the historical search data in the product information page and / or the context dialogue data in the dialogue window; receive an AI agent identifier sent by the client, wherein the AI ​​agent identifier is selected by the client from at least one AI agent identifier; and determine, from at least one preset AI agent, an AI agent corresponding to the AI ​​agent identifier as the target AI agent.

[0118] In this embodiment, the human-computer dialogue operation and the search operation on the product information page can be linked, so that the associated search conditions and dialogue messages are sent to the server. The server can return the associated product search results and reply messages based on the associated search conditions and dialogue messages. On the product information page, the associated reply messages and product search results are displayed on the same screen for users to check. For users, there is no need to jump to different pages to use the search service and the shopping guide dialogue service. On the one hand, users do not need to remember or record certain information, which reduces the time and energy spent by users switching between different information. On the other hand, displaying the reply messages used to provide shopping guide services on the same screen with the product search results can facilitate users to quickly capture key information, thereby effectively guiding users to make shopping decisions and improve the conversion rate of shopping behavior.

[0119] Further, if Figure 7 As shown, the electronic device also includes: a power supply component 705 and an audio component 706 and other components. Figure 7 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 7 Components shown. Figure 7 Components in the dashed box are optional components, not mandatory components, and may depend on the product form of the electronic device. The electronic device of this embodiment may be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT device, or may be a server device such as a conventional server, a cloud server, or a server array. If the electronic device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, etc., it may include Figure 7 If the electronic device of this embodiment is implemented as a server device such as a conventional server, a cloud server or a server array, it may not include Figure 7 Components within the dashed box.

[0120] Among them, the memory 701 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 storage, flash memory, magnetic disk or optical disk.

[0121] The communication component 703 is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as Wi-Fi (wireless network communication technology), 2G (such as Global System for Mobile Communications (GSM)), 3G (such as Wideband Code Division Multiple Access (WCDMA), 4G (such as Long Term Evolution (LTE)), 4G+ (such as upgraded Long Term Evolution (LTE-Advanced, LTE-A)) or 5G (5th Generation Mobile Communication Technology), or a combination thereof. In an exemplary embodiment, the communication component 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 can be implemented based on Near Field Communication (NFC) technology, Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology and other technologies.

[0122] The power supply component 705 is used to provide power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing and distributing power to the device where the power supply component is located.

[0123] The display assembly includes a screen, which 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 a 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 a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0124] The audio component may be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located 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 may be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0125] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement each step that can be executed by an electronic device in the above method embodiment.

[0126] The embodiment of the present application also provides a computer program product, including: a computer program / instruction, which can implement the steps in the method provided in the embodiment of the present application when executed by a processor.

[0127] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM (Compact Disc Read-Only Memory, read-only optical disc read-only memory), optical storage, etc.) containing computer-usable program codes.

[0128] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interface, network interface and memory.

[0132] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0133] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, Parallel Random Access Machine (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, Digital Video Disc (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0134] It should also be noted that the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, product or device including the element.

[0135] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An information display method, characterized in that: include: Displaying a product information page, the product information page including a dialog window and a product information display area; In response to a search operation in the product information page, obtaining a first search condition corresponding to the search operation; Displaying a first dialog message associated with the first search condition in the dialog window, and acquiring a first reply message corresponding to the first dialog message and a product search result matched according to the first search condition; In the dialog window, the first reply message is displayed; and in the product information display area, the product search results matched according to the first search condition are displayed.

2. The method according to claim 1, characterized in that Also includes: When displaying the first reply message in the conversation window, highlighting at least one recommended search keyword in the first reply message; In response to a selection operation of a target search keyword among the at least one recommended search keyword, obtaining a product search result matched according to the target search keyword; In the product information display area, product search results matched according to the target search keyword are displayed.

3. The method according to claim 1, characterized in that Also includes: In response to a dialog input operation in the dialog window, obtaining an input second dialog message; Displaying the second conversation message in the conversation window, and acquiring a second reply message corresponding to the second conversation message and a product search result matched according to a second search condition associated with the second conversation message; In the dialog window, displaying the second reply message; and, In the product information display area, product search results matched according to the second search condition are displayed.

4. The method according to claim 3, characterized in that Obtaining product search results matched by the second search keyword associated with the second conversation message includes: Performing semantic recognition on the second conversation message to obtain the second search condition, where the second search condition includes: at least one of a search keyword, a screening condition, and a sorting condition; Sending the second search condition to the server; Obtain the product search results returned by the server that match the second search condition.

5. The method according to any one of claims 1 to 4, characterized in that: The first reply message is generated by the server calling the target AI agent, and the dialog window includes: an AI agent switching control; In the dialog window, before displaying the first reply message, the method further includes: In response to a triggering operation on the AI ​​agent switching control, displaying at least one AI agent identifier; According to the selection operation of the at least one AI agent identifier, obtaining a selected AI agent identifier; The selected AI agent identifier is sent to the server, so that the server determines the target AI agent based on the selected AI agent identifier.

6. The method according to claim 5, characterized in that In response to the triggering operation of the AI ​​agent switching control, at least one AI agent identifier is displayed, including: In response to the triggering operation of the AI ​​agent switching control, sending an AI agent switching request to the server; The at least one AI agent identifier returned by the server according to the AI ​​agent switching request is displayed, wherein the at least one AI agent identifier is determined by the server according to the historical search data in the product information page and / or the contextual dialogue data in the dialogue window.

7. An information display method, characterized in that: include: Displaying a product information page, the product information page including a dialog window and a product information display area; Responding to a dialog input operation in the dialog window, obtaining an input dialog message; Displaying the conversation message in the conversation window, and obtaining a reply message corresponding to the conversation message and a product search result matched according to a search condition associated with the conversation message; In the dialog window, displaying the reply message; as well as, In the product information display area, product search results matched according to the search condition are displayed.

8. An information display method, characterized in that: include: receiving a first search condition and a first dialog message associated with the first search condition sent by a client according to a search operation in a product information page, wherein the first dialog message is displayed in a dialog window in the product information page; Invoke a target AI agent to generate a first reply message according to the first dialogue message; and invoke a search engine to obtain product search results matching the first search condition; The first reply message and the product search results matching the first search condition are returned to the client, so that the client displays the first reply message in the dialog window and displays the product search results matching the first search condition in the product information display area of ​​the product information page.

9. The method according to claim 8, characterized in that Also includes: receiving a second dialog message sent by the client and a second search condition associated with the second dialog message, wherein the second dialog message is input through the dialog window; Invoke the target AI agent to generate a second reply message according to the second dialogue message; and invoke a search engine to obtain product search results matching the second search condition; The second reply message and the product search results matching the second search condition are returned to the client, so that the client displays the second reply message in the dialog window and displays the product search results matching the second search condition in the product information display area.

10. The method according to claim 8, characterized in that Calling the target AI agent to generate a first reply message according to the first dialogue message, including: The target AI agent is called, and the first dialogue message is provided to a target language model so that the target language model generates the first reply message, wherein the target language model is a deep learning model trained on a commodity information dataset.

11. The method according to claim 8, characterized in that The first reply message includes at least one of the following: at least one recommended search keyword associated with the search keyword in the first dialogue message, information about similar products associated with the picture in the first dialogue message, a recommended question associated with the user question in the first dialogue message, and a rhetorical question associated with the user question in the first dialogue message.

12. The method according to any one of claims 8 to 11, characterized in that: Before calling the target AI agent to generate a first reply message according to the first dialogue message, the method further includes: Receiving an AI agent switching request sent by the client; at least one AI agent identifier returned to the client, wherein the at least one AI agent identifier is determined based on historical search data in the product information page and / or contextual dialogue data in the dialogue window; Receiving an AI agent identifier sent by the client, where the AI ​​agent identifier is selected by the client from at least one AI agent identifier; From at least one preset AI agent, determine an AI agent corresponding to the AI ​​agent identifier as the target AI agent.

13. An electronic device, characterized in that: include: Memory and processor; The memory is used to store one or more computer instructions; The processor is configured to execute the one or more computer instructions to perform the steps of the method of any one of claims 1-7 or any one of claims 8-12.

14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the method described in any one of claims 1 to 7 or any one of claims 8 to 12 can be implemented.

15. A computer program product, characterized in that include: A computer program / instruction, which, when executed by a processor, can implement the steps of the method described in any one of claims 1 to 7 or any one of claims 8 to 12.

Images