Page display method and device, storage medium and program product

Abstract

The embodiment of the invention provides a page display method and device, a storage medium and a program product. In the embodiment of the invention, the interaction page of the AI intelligent customer service and the user is associated with the component library, the component library comprises the message component and the display components of different message types, rich interface information is displayed through different display components, and the user experience is improved. Specifically, under the condition that service demand description information input by a user is intelligently replied through an AI intelligent customer service, sub-messages and message types of the sub-messages are analyzed from service result information provided by the AI intelligent customer service, an adaptive display component is selected from a component library according to message type information, and the sub-messages are displayed according to the selected display component. According to the method, the sub-messages are embedded into the display components matched with the sub-messages, and the display components are displayed on the interactive page through the message component, so that the information display types are enriched, and the user experience is improved. Furthermore, corresponding service product information can be displayed through different display assemblies, and popularization can be carried out.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a page display method, device, storage medium and program product. Background Art

[0002] In the Internet industry, online customer service is increasingly being used, whereby the intelligent customer service provided by the intelligent customer service system can replace manual customer service to interact with users and solve their problems. For example, a user provides a problem message to the intelligent customer service system in the form of text, and the intelligent customer service system matches the answer message corresponding to the problem message from the database and returns the answer message to the user.

[0003] Currently, intelligent customer service and users can interact through text messages on the chat page. However, this cannot meet the user's needs to display more types of information. Summary of the invention

[0004] Multiple aspects of the present application provide a page display method, device, storage medium and program product for displaying various display components on an interactive page through message components to enrich information display types and enhance user experience.

[0005] The embodiment of the present application provides a page display method, which is applicable to a terminal device, wherein the terminal device runs a target application, and an AI intelligent customer service is deployed on a server device, and a communication connection is established between the server device and the terminal device; the method comprises: displaying a page link provided by the AI ​​intelligent customer service on a first page provided by the target application; in response to a trigger operation on the page link, displaying a second page corresponding to the page link, wherein the second page is associated with a component library, and the component library comprises a message component and a plurality of display components adapted to a plurality of message types; in response to an input operation on the second page, obtaining service demand description information; sending the service demand description information to the AI ​​intelligent customer service, so that the AI ​​intelligent customer service generates and returns service result information corresponding to the service demand description information based on an intent recognition model and an AI language model; receiving the service result information, parsing the service result information to obtain at least one sub-message and its message type included in the service result information; selecting at least one target display component adapted to the at least one sub-message from a plurality of display components according to the at least one sub-message and its information type; embedding the at least one sub-message into the at least one target display component adapted thereto, and using the message component to display the at least one target display component embedded in the at least one sub-message on a third page, wherein the third page is the same as or different from the second page.

[0006] An embodiment of the present application also provides an electronic device, including: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement each step in the page display method provided in the embodiment of the present application.

[0007] The embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements each step of the page display method provided in the embodiment of the present application.

[0008] The embodiment of the present application also provides a computer program product, including a computer program / instruction. When the computer program / instruction is executed by a processor, the processor implements the steps in the page display method provided in the embodiment of the present application.

[0009] In an embodiment of the present application, the interactive page between the AI ​​intelligent customer service and the user is associated with a component library, which includes a message component and display components of different message types. Different display components are used to display rich interface information to improve the user experience. Specifically, when the AI ​​intelligent customer service intelligently replies to the service demand description information input by the user, each sub-message and its message type are parsed from the service result information provided by the AI ​​intelligent customer service, and an adapted display component is selected from the component library according to the message type information, and each sub-message is embedded in a display component adapted thereto. Each display component is displayed on the interactive page through the message component to enrich the information display type and improve the user experience. Furthermore, the corresponding service product information can also be displayed and promoted through different display components. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] 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:

[0011] Figure 1 A flow chart of a page display method provided for an exemplary embodiment of the present application;

[0012] Figure 2a A schematic diagram of a third page provided for an exemplary embodiment of the present application;

[0013] Figure 2b An architectural diagram of a server and a terminal device provided for an exemplary embodiment of the present application;

[0014] Figure 2c A network communication diagram of a server and a terminal device provided for an exemplary embodiment of the present application;

[0015] Figure 3A flowchart of an information processing method provided for an exemplary embodiment of the present application;

[0016] Figure 4a An architectural diagram of information processing provided by an exemplary embodiment of the present application;

[0017] Figure 4b A flowchart of another information processing method provided by an exemplary embodiment of the present application;

[0018] Figure 5 A schematic diagram of the structure of a page display device provided for an exemplary embodiment of the present application;

[0019] Figure 6 A schematic structural diagram of an electronic device provided for an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] 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.

[0021] 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.

[0022] The various models involved in this application (including but not limited to language models or large models) are in compliance with relevant laws and standards.

[0023] At present, most of the interactive pages between intelligent customer service and users can only carry out regular typing chats, and cannot transmit and display complex information (such as pictures and rich text, etc.). Therefore, the information seen by users is severely limited, resulting in the inability to better promote service products and display more information. Furthermore, the interactive page does not support phone interactions, resulting in the inability to quickly retain customers and the inability to accurately locate user needs. In addition, except for users entering information themselves, it currently does not support proactively providing users with some topics to make users interested in service products, and intelligent customer service has not played its greatest role.

[0024] In an embodiment of the present application, the interactive page between the AI ​​intelligent customer service and the user is associated with a component library, which includes a message component and display components of different message types. Different display components are used to display rich interface information to improve the user experience. Specifically, when the AI ​​intelligent customer service intelligently replies to the service demand description information input by the user, each sub-message and its message type are parsed from the service result information provided by the AI ​​intelligent customer service, and an adapted display component is selected from the component library according to the message type information, and each sub-message is embedded in a display component adapted thereto. Each display component is displayed on the interactive page through the message component to enrich the information display type and improve the user experience. Furthermore, the corresponding service product information can also be displayed and promoted through different display components.

[0025] Furthermore, the display component includes a telephone component, so that users can contact service personnel by clicking on the telephone component, ask questions and express their needs, and accurately locate user needs. In addition, AI intelligent customer service can also quickly retain the user's telephone information through the telephone information to facilitate subsequent service for the user.

[0026] Furthermore, in addition to the information input by the user, the display component also includes a topic component, which can actively provide some topics for the user to enhance the user's interest in use. In the case of a service product, the user will be interested in the service product, making the AI ​​intelligent customer service play the greatest role.

[0027] A solution provided by an embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0028] Figure 1 A flow chart of a page display method provided for an exemplary embodiment of the present application, the method is applicable to a terminal device, the terminal device runs a target application, the AI ​​intelligent customer service is deployed on a server device, and a communication connection is established between the server device and the terminal device, such as Figure 1 As shown, the method includes:

[0029] 101. Display the page link provided by the AI ​​intelligent customer service on the first page provided by the target application;

[0030] 102. In response to a triggering operation on a page link, a second page corresponding to the page link is displayed, where the second page is associated with a component library, and the component library includes a message component and multiple display components adapted to multiple message types;

[0031] 103. In response to an input operation on the first page, obtain service requirement description information;

[0032] 104. Send the service requirement description information to the AI ​​intelligent customer service, so that the AI ​​intelligent customer service can generate and return the service result information corresponding to the service requirement description information based on the intent recognition model and the AI ​​language model;

[0033] 105. Receive service result information, and parse the service result information to obtain at least one sub-message and its message type included in the service result information;

[0034] 106. Selecting, according to the at least one sub-message and its information type, at least one target display component adapted to the at least one sub-message from a plurality of display components;

[0035] 107. Embed at least one sub-message into at least one target display component, and use the message component to display the at least one target display component embedded with the at least one sub-message on a third page, where the third page is the same as or different from the second page.

[0036] In this embodiment, a target application is running on the terminal device, and the target application may be any type of application. For example, the target application may include but is not limited to: social applications, shopping applications, life service applications, and online learning applications.

[0037] In this embodiment, a first page is provided on the target application, and the first page can be any page of the target application, for example, the first page can be a home page, a search page, or a chat page, etc., without limitation. Regardless of what page the first page is implemented as, a page link provided by the AI ​​intelligent customer service can be displayed on the first page, and the page link points to the page corresponding to the AI ​​intelligent customer service. For the sake of distinction and description, the page corresponding to the AI ​​intelligent customer service is referred to as the second page.

[0038] The implementation method of displaying the page link provided by the AI ​​intelligent customer service on the first page is not limited. For example, if the first page is a chat page between a user and other users, when other users send the page link provided by the AI ​​intelligent customer service to the user, the page link is displayed on the chat page. For another example, if the first page is a search page, the user enters the domain name information corresponding to the AI ​​intelligent customer service on the search page, and the search page returns the page link corresponding to the domain name information, so as to display the page link on the search page.

[0039] In this embodiment, when the page link is triggered, in response to the triggering operation on the page link, the second page corresponding to the page link is displayed. The second page is associated with a component library. The component library may be provided by the AI ​​intelligent customer service for the second page. Specifically, when the terminal device displays the second page, the server device corresponding to the AI ​​intelligent customer service may send the component library to the terminal device corresponding to the second page. Further, the component library may be sent to the terminal device in real time by the server device each time the second component is displayed, or the component library may be sent when the second page is displayed for the first time. Alternatively, when the second page is displayed, it is determined whether there is a component library associated with the second page locally in the terminal. If not, the server device corresponding to the AI ​​intelligent customer service is requested to send the component library.

[0040] It should be noted that the second page can also be opened through a small program, a web page, etc. The second page can be a Hypertext Markup Language Version 5 page (Hyper Text Markup Language, H5).

[0041] In this embodiment, the component library includes a message component and multiple display components adapted to multiple message types. Among them, the message component is used to display multiple display components on the page. The message component can carry one or more display components. In the case of multiple display components, multiple display components can be displayed in combination, or multiple display components can be displayed separately in the message component. The style of the message component can be a message box or bubble in the page, etc. The size of the message component is related to its content. If the size of one or more display components included in the message component is larger, the message component is also larger. Conversely, if the size of one or more display components included in the message component is smaller, the message component is also smaller. Among them, the message component can also display plain text information, which is generally the interactive content between AI intelligent customer service and users.

[0042] The display component is an interface element used to display data. The data displayed by display components of different message types are also different. Display components may include but are not limited to: rich text components (image-text-box), phone components (phone-box), picture components, video components, and card components (card-box). Figure 2a Some components are shown as examples, but are not limited to them. Figure 2a It also includes: identification information corresponding to the AI ​​intelligent customer service and a closing component, such as a trademark (LOGO), wherein the closing component is used to close the identification information and no longer display it.

[0043] Among them, the rich text component is a component for displaying formatted text information. It can also display pictures or web page content. The form is intuitive and does not require users to interpret word by word. For example, rich text usually refers to text that contains elements such as bold, italic, underline, font style, size, color, paragraph alignment, list, link, image, etc. The phone component is usually used to display phone numbers, and can also include phone-related functions, such as making calls, copying phone numbers, etc. The phone component can be a simple display component or a display component with interactive functions, such as dialing the number corresponding to the component by clicking on the phone component. The picture component is used to display picture information, and the video component is used to display video information. The card component can display user information (such as merchant information) and service product information, generally including detailed information of the merchant or product, which is displayed independently in the form of a card to highlight the core content.

[0044] In this embodiment, the user can enter service demand description information on the second page. The service demand description information is a detailed description and explanation of the service demand so that the target agent can clearly understand the nature, scope and requirements of the required service. The service demand description information can be the user's demand description information for the set information object (such as post, phone call), for example, "Why are there so few customers calling me" or "I want to modify the keywords of the post", etc. The service demand description information can also be the user's status description information, for example, "Are you there?", "I want to learn about promotion information", etc.

[0045] The terminal device can obtain the service requirement description information in response to the input operation on the second page, and send the service requirement description information to the AI ​​intelligent customer service, so that the AI ​​intelligent customer service can generate and return the service result information corresponding to the service requirement description information based on the intent recognition model and the AI ​​language model. Among them, the detailed introduction of the AI ​​intelligent customer service generating and returning the service result information corresponding to the service requirement description information based on the intent recognition model and the AI ​​language model can be found in the subsequent embodiments, which will not be repeated here.

[0046] In this embodiment, when the AI ​​intelligent customer service returns service result information, the second page can receive the service result information and parse the service result information to obtain at least one sub-message and its message type included in the service result information. Among them, the service result information may include one or more message types, and each message type corresponds to one or more sub-messages. For example, the service result information includes information of a message type, such as text information, picture information, video information, rich text information, or telephone information. For another example, the service result information includes three message types: rich text information, picture information, video information, and telephone information.

[0047] In this embodiment, according to at least one sub-message and its information type, at least one target display component adapted to the at least one sub-message is selected from multiple display components included in the component library. Among them, an adaptation target display component can be selected for each message type of sub-message. For example, a rich text sub-message is adapted to a rich text display component, a phone message is adapted to a phone component, a picture message is adapted to a picture component, a video message is adapted to a video component, etc. Among them, a display component can carry one or more sub-messages adapted to the message type.

[0048] In this embodiment, at least one sub-message is embedded in at least one target display component adapted thereto, and the at least one target display component embedded in the at least one sub-message is displayed on a third page using a message component. The third page is the same as or different from the second page, that is, the third page is the same page as the second page, or the third page can be a new page different from the second page.

[0049] In an embodiment of the present application, the interactive page between the AI ​​intelligent customer service and the user is associated with a component library, which includes a message component and display components of different message types. Different display components are used to display rich interface information to improve the user experience. Specifically, when the AI ​​intelligent customer service intelligently replies to the service demand description information input by the user, each sub-message and its message type are parsed from the service result information provided by the AI ​​intelligent customer service, and an adapted display component is selected from the component library according to the message type information, and each sub-message is embedded in a display component adapted thereto. Each display component is displayed on the interactive page through the message component to enrich the information display type and improve the user experience. Furthermore, the corresponding service product information can also be displayed and promoted through different display components.

[0050] In an optional embodiment, considering that the message component package or the display component corresponds to a component template, the component template can reflect the HTML structure and layout of the component. The component template includes: state information (state) and property information (props). For the convenience of distinction and description, the component template corresponding to the display component is called the first component template, and the template corresponding to the message component is called the second component template. Among them, the property information is used for data transfer between components, for example, data transfer between components. The state information is used to manage the state and changes of the component itself. For example, the state information is used to store the dynamic data of the component, such as the service demand description information entered by the user or the service result information returned by the AI ​​intelligent customer service.

[0051] Based on this, an implementation method of embedding at least one sub-message into at least one target display component may be to use any sub-message as the state information of the first component template of its adapted target display component for any sub-message, so as to embed any sub-message into its adapted target display component.

[0052] Optionally, the implementation method of using the message component to display at least one target display component embedded in at least one sub-message on the third page is not limited. For example, at least one first component template of at least one target display component is introduced into the second component template of the message component to realize the nested relationship between the message component and the at least one target display component. The attribute information of the second component template includes global visualization attribute information; according to the global visualization information, the local visualization information of at least one target display component in the message component is determined, and the local visualization information is added to the first component template corresponding to the target display component adapted thereto; for example, the local visualization information is used as the attribute information of the first component template corresponding to the target display component adapted thereto. Based on the nested relationship, the second component template and the at least one first component template, the message component and the at least one target display component are rendered to display the at least one target display component in the message component on the third page, so as to display at least one sub-message through the at least one target display component.

[0053] Among them, based on the nested relationship, at least one target component can be displayed in the message component according to the local visualization attribute information, and based on the status information in the first component template, the sub-message corresponding to the status information can be displayed in the target display component corresponding to the first component template.

[0054] Among them, the visual attributes include but are not limited to: theme, color scheme, font size, border style, etc. Global visual information refers to the visual information of the message component, and local visual information can be the visual information of each target display component. The visual information of different target display components can be the same or different. For example, the size information of different target display components may be different. Specifically, the size information of each target display component can be determined based on the size information of the message component and the number of target display components. For another example, in order to unify the style, the background color and border style of the message component and each target display component can be the same.

[0055] In an optional embodiment, the multiple display components further include an input-area component, and the input-area component is used to input new service requirement description information. The service requirement description information can be displayed on the third page through the message component.

[0056] Optionally, if it is detected that the third page has not received a new message within a set time, the topic component is displayed on the third page through dynamic effects to attract users to click. The set time can be 5 seconds, 3 minutes or 10 minutes, etc., and there is no limitation on this. For example, the dynamic effects can be some dynamic transition effects, such as rotation, scaling, translation, enlargement and reduction of the page, or slight shaking of the page. Further, in the case of displaying the topic component, random topic information can be actively displayed. The random topic information can be found in the following embodiments, which will not be repeated here. For example, the topic component can be a dice component (dice-area).

[0057] Optionally, when a topic component is included on the third page, in response to a trigger operation on the topic component, random topic information for the user is returned and displayed through the AI ​​intelligent customer service according to the user portrait corresponding to the user. Among them, the user portrait may include but is not limited to: user description information, service products purchased by the user, user resource information, user behavior, needs and preferences, etc. Random topic information may include but is not limited to: user resource shortage reminder information, service product expiration reminder information, renewal guidance information, and guidance posting information, etc. Of course, random topic information can also include: user preference information, jokes, etc.

[0058] Optionally, the method provided in the embodiment of the present application supports both active display of random topic information and display of random topic information in response to a trigger operation on a topic component. For detailed description, please refer to the aforementioned embodiment.

[0059] In an optional embodiment, the multiple display components also include a time component; in response to the message component being displayed on the third page, the current time is obtained through the time component, and the current time is passed to the message component through the time component, so that the message component uses the current time as its display time.

[0060] In an optional embodiment, the third page also includes a loading-box component; the information display method further includes: when the service requirement description information is provided to the AI ​​intelligent customer service and the service result information corresponding to the service requirement description information is not received, the loading-box component is displayed, and when the service result information is received, the loading-box component is canceled. Further, the reception time of the service result information can be displayed through a time component.

[0061] In an optional embodiment, in addition to displaying the service result information through the target display component, the service requirement description information can also be displayed through the message component and display component in the component library. The detailed implementation method is the same or similar to the method of displaying the service result information. For details, please refer to the aforementioned embodiment and will not be repeated here.

[0062] In this embodiment, when the user visits the second page for the first time, the AI ​​intelligent customer service can proactively greet the user and create a friendly welcome atmosphere. The AI ​​intelligent customer service can output and display a friendly greeting message through the terminal device, such as: "Hello! How can I help you?" to make the user feel comfortable and guide them to start interacting.

[0063] If the service requirement description information entered by the user is of the following categories, AI intelligent customer service can provide targeted service result information:

[0064] Question answering: When users input questions or ideas, AI intelligent customer service can analyze the user's input and provide relevant answers. AI intelligent customer service can classify users' questions according to their types (by scenario) and give appropriate answers.

[0065] Contact information: If the user asks about the contact information, the AI ​​customer service can display a phone component and a phone button, allowing the user to make a phone call directly by clicking the phone button.

[0066] Store information: If the user asks about store-related information, AI intelligent customer service can display detailed store information cards through card components, including store location, business hours, contact information, etc.

[0067] Unknown questions: If the AI ​​customer service cannot determine the service result information of the user's service demand description information, a selection box can be displayed to allow the user to select different scenarios or topics so that the AI ​​customer service can better understand the user's needs and continue to answer.

[0068] Among them, regarding the internal implementation of AI intelligent customer service, please refer to the subsequent embodiments and will not be repeated here.

[0069] In an optional embodiment, a connection is established between the server device and the terminal device via server-sent events (SSE). The server device may establish an SSE connection with at least one terminal device, such as Figure 2b As shown, the server device establishes an SSE connection with three terminal devices as an example. The server device includes a communication module (SSE Endpoint), AI intelligent customer service (backend logic) and its corresponding service tools (backend interface), and the terminal device includes various components, such as time component, message component, card component, rich text component, phone component, loading component, input box component and topic component.

[0070] The implementation method of receiving the service result information includes: when the server device sends the service result information to the terminal device through the SSE protocol, the terminal device monitors the service result information sent by the server device based on the SSE interface. The SSE interface can be an EventSource object, which is a client API introduced by HTML5 and is used to implement a real-time communication mechanism for the server to push data to the client. Figure 2c It is a network communication diagram between server and terminal devices.

[0071] Among them, SSE establishes a persistent connection until the client disconnects or the server closes the connection, with low latency. Compared with the polling mechanism, SSE can push data to the client faster and is easy to use: SSE is relatively simple to implement and easy to integrate into existing Web applications. Among them, when the SSE connection is established, there is no need for the terminal device to actively send messages to the server device. The server can also actively push information to the terminal device, and the number of pushed messages is not limited.

[0072] Since SSE is suitable for scenarios with frequent updates, low latency, and from server-side devices to mid-terminal devices. In addition, when there is an associated component library, there is no need to add any new components, and any back-end language and framework can be used without creating a new IP or a new port number. SSE can operate on the existing HTTP / HTTPS protocol, so it can run directly on existing server devices. Among them, HTTP (HyperText Transfer Protocol) is an application layer protocol used to transfer hypertext from a Web server to a client program such as a local browser.

[0073] In an optional embodiment, during the communication between the terminal device and the server, the third page will continuously obtain the latest information and display the content word by word by utilizing the feature of SSE that can receive messages one by one. Each character will be gradually displayed on the third page at a certain speed to ensure that the user can clearly read and understand the information. This display method can not only improve the user experience, but also increase the interactivity and fun of information display, and avoid visual fatigue caused by displaying large blocks of content at one time.

[0074] The page display method provided in the embodiment of the present application has the following advantages:

[0075] 1. Reduce development costs: Through component-based design: split the page elements in the third page into different components, achieving high reusability and adaptability. Each component has independent functions and is modular, easy to maintain and update, and can be reused in different scenarios, reducing development costs and having high flexibility and adaptability. In later development, you only need to use existing components to quickly build a UI page with real-time chat function (such as the second page or the third page), reducing the workload of repeated development and reducing development costs.

[0076] 2. Improve user experience: 1) Rich information display: In the chat content, core product information, such as merchant details, product introduction, etc., can be displayed in the form of cards, making important information more intuitive and prominent. 2) Convenient contact function: The phone component allows users to directly click to make a call and quickly get in touch with the company, simplifying the user's operation process and effectively acquiring and retaining customers. 3) Interaction guidance: The topic component provides a random topic generation function. When the user does not have a clear question, a random topic is generated by clicking the topic component to increase the fun of the interaction and maintain user participation.

[0077] 3. Reliability and real-time performance: 1) By utilizing the characteristics of SSE (such as long connection, low latency, lightweight, etc.), it is possible to ensure that the server pushes real-time updated information to the client. SSE is a lightweight server push technology that can maintain a persistent connection between the terminal and the server, achieve low-latency message push, and ensure the real-time and reliability of the message. 2) Instant response: After the user enters the service requirement description information, the AI ​​intelligent customer service can quickly analyze and provide the corresponding service result information, ensuring the continuity and timeliness of the conversation, and improving user satisfaction.

[0078] In summary, this application not only improves the development and maintenance efficiency of the AI ​​interaction system through the combination of componentized design and SSE technology, but also significantly improves the user experience and the real-time and reliability of data transmission, providing developers and users with an efficient, reliable and easy-to-use AI interaction solution.

[0079] In addition to providing the above-mentioned page display method, the embodiment of the present application also provides an information processing method, which is applicable to a server-side device, and the server-side device runs an artificial intelligence AI intelligent customer service, and the AI ​​intelligent customer service includes an intent recognition model and an AI language model, such as Figure 3 As shown, the method includes:

[0080] 301. Receive service demand description information sent by the terminal device, where the service demand description information is information that the user requests the AI ​​intelligent customer service to provide services for him;

[0081] 302. Add the service requirement description information to a first prompt word template including at least two scene information to obtain a first prompt word, where different scene information corresponds to different intents, and the first prompt word template also includes first task description information, which is used to describe the task that the intent recognition model needs to perform;

[0082] 303. Input the first prompt word into the intention recognition model, and identify the target scene information corresponding to the service requirement description information from the at least two scene information according to the first task description information;

[0083] 304. Add the service requirement description information to the second prompt word template corresponding to the target scenario information to obtain a second prompt word, wherein the second prompt word template includes second task description information, which is used to describe the task that the AI ​​language model needs to perform;

[0084] 305. Input the second prompt word into the AI ​​language model, and generate service result information corresponding to the service requirement description information under the target scenario information according to the second task description information;

[0085] 306. Return the service result information to the terminal device, so that the terminal device can display the service result information to the user.

[0086] In this embodiment, a life service platform is provided, which can be implemented through a mobile phone application (APP), a web page, or a mini program, without limitation. The life service platform is a link between merchants and service demanders. Service demanders can obtain the required services on the platform, and merchants can publish their own services on the life service platform. The service content includes but is not limited to: moving, cleaning, confinement nanny, maintenance, renting, used cars and other fields.

[0087] In this embodiment, the execution subject of the information processing method is a server device, and an artificial intelligence (AI) intelligent customer service, referred to as AI intelligent customer service, runs on the server device. AI intelligent customer service can provide exclusive services for users. Among them, the services provided by AI intelligent customer service are different depending on the user. For example, if the user is implemented as a merchant, AI intelligent customer service can provide merchants with posting services, post modification services, keyword modification services, recharge services, renewal services, and question-answering services for service demanders. If the user is implemented as a service demander, AI intelligent customer service can provide service demanders with merchant recommendation services, appointment services for merchants, question-answering services, and ordering services. Among them, no matter which user is implemented, AI intelligent customer service can provide users with some services, help users solve some problems, and save the working time of manual customer service or users.

[0088] In this embodiment, AI intelligent customer service pre-maintains at least two types of scenario information, including: modify keyword scenario, service mismatch scenario, adjust ranking scenario, switch promotion scenario, use coupon scenario, recharge scenario, information query scenario, etc. Among them, modify keyword scenario refers to the scenario of helping merchants add or delete associated words in posts; service mismatch scenario refers to the scenario where merchants describe the calls they received and their services do not match; adjust ranking scenario refers to the merchant describing that the ranking of their posts is too low and asking for help to improve their search ranking; switch promotion scenario refers to turning on or off promotion, where the ranking of posts turned on will be higher; use coupon scenario refers to the use of coupons to offset part of the amount during promotion, and the merchant will enter this scenario when requesting to use coupons; recharge scenario refers to the scenario where merchants describe the desire to recharge the promotion balance; information query scenario refers to checking whether the promotion is online, what coupons are available, whether the recharge is successful, why no call was received from the service demander, why the promotion balance is consumed too quickly, and why the promotion post was offline, etc.

[0089] In this embodiment, the user interacts with the AI ​​intelligent customer service through the terminal device. The user can actively send service demand description information to the AI ​​intelligent customer service on the chat page corresponding to the AI ​​intelligent customer service. Correspondingly, the AI ​​intelligent customer service deployed on the server device receives the service demand description information sent by the terminal device. The service demand description information is a detailed elaboration and explanation of the service demand so that the target intelligent agent can clearly understand the nature, scope and requirements of the required service. The service demand description information can be the user's demand description information for the set information object (such as a post, a phone call), for example, "Why are there so few customers calling me" or "I want to modify the keywords of the post", etc. The service demand description information can also be the user's status description information, for example, "Are you there?", "I want to know about the promotion information", etc. Among them, the chat page can be an application page, a mini program page, a web page or a page of a third-party application. The service demand description information is the information that the user requests the AI ​​intelligent customer service to provide services for it. For example, the service demand description information can be "Help me modify the keywords of the post", "Help me enable the promotion service", "The call I received does not match my service, help me find the reason", "Help me recharge some promotion balance", "Check what coupons I have", "Check why there is no call connection", "Check why the balance is consumed too quickly", etc.

[0090] exist Figure 4a In the description, the terminal device sends service requirement description information to the server device, and the server device generates service result information according to the service requirement module information. However, this is not limited to this. If the computing resources of the terminal device are sufficient, the information processing method can also be implemented on the terminal device.

[0091] In this embodiment, AI intelligent customer service includes an intent recognition model. The intent recognition model is used to perform intent recognition on the service demand description information input by the user. Different scenario information corresponds to different intents, that is, to identify which service scenario the service demand description information input by the user corresponds to. The intent recognition model can be a large language model (LLM). For example, the intent recognition model includes but is not limited to: a generative model (GPT) based on a transformer and a pre-trained model (BERT) based on a transformer.

[0092] In this embodiment, the intent recognition model corresponds to a first prompt word template, and the first prompt word template may include but is not limited to: role, task, background, and requirements. Among them, the role is the profession or identity played by the intent recognition model, what personality characteristics the profession has, or what special skills the identity has, for example, the role played by the intent recognition model is a classifier; the background refers to some contextual information required by the role to complete the task, so that the intent recognition model can better understand the task background and related details. For example, description information for each scene, historical interaction information of the user, description information of the merchant, etc. The task refers to the specific task or goal completed by the role, for example, identifying the scene information corresponding to the service demand description information input by the user from at least two scene information. For the convenience of description and distinction, the task information in the first prompt word template is called the first task description information, and the first task description information is used to describe the task that the intent recognition model needs to perform. Restrictions refer to the specific requirements or restrictions for the role to complete the task, for example, content requirements for output data and time limits for output data. Among them, content requirements may include but are not limited to: format requirements, output data type requirements, removal of sensitive information, removal of modal particles, etc.

[0093] In this embodiment, the service requirement description information is added to the first prompt word template to obtain the first prompt word. The first prompt word is input into the intention recognition model, and the target scene information corresponding to the service requirement description information is identified from at least two scene information according to the first task description information.

[0094] For example, if the service demand description information is "Please help add a few keywords to my post", the target scenario information may be the "Modify keywords" scenario; if the service demand description information is "The call I received was not for a babysitter", the target scenario information may be "Service mismatch"; if the service demand description information is "Why is my post ranked so low and there are so few calls", the target scenario information may be the "Query" scenario.

[0095] In this embodiment, the AI ​​intelligent customer service also includes: an AI language model, which can intelligently reply to the service demand description information input by the user to obtain service result information. The AI ​​language model can be a large language model (LLM), for example, the AI ​​language model includes but is not limited to: a generative model (GPT) based on a transformer (Transformer) and a pre-trained model (BERT) based on a transformer, etc.

[0096] In this embodiment, in order to improve the effect of the AI ​​language model for intelligent reply, so that the service result information output by the AI ​​language model matches the service demand description information, different second prompt word templates can be pre-set for different scenarios. For example, the modification keyword scenario corresponds to the second prompt word template A1, the adjustment ranking scenario corresponds to the second prompt word template A2, and the service mismatch scenario corresponds to the second prompt word template A3. The second prompt word template may include but is not limited to: roles, tasks, backgrounds and restrictions. Among them, the role of the second prompt word template corresponding to any scene information can be intelligent customer service, and the background information can include but is not limited to: description information of any scene information and historical interaction information of the user. The task can also be called the second task description information, and the second task description information is used to describe the task that the AI ​​language model needs to perform. For example, the second task description information can be the AI ​​language model in any scenario. Provide services to users for service demand description information. Restrictions refer to specific requirements or restrictions for the role to complete the task, such as content specifications for output data and time limits for output data. Among them, content specifications can include but are not limited to: outputting data in a set format (such as text), removing sensitive information, adding modal particles, etc.

[0097] In this embodiment, the service requirement description information can be added to the second prompt word template corresponding to the target scenario information to obtain the second prompt word, the second prompt word is input into the AI ​​language model, and the service result information corresponding to the service requirement description information under the target scenario information is generated according to the second task description information. The service result information is returned to the terminal device so that the terminal device can display the service result information to the user.

[0098] The following uses the example of a user being a merchant, the merchant providing a description of service requirements, and the AI ​​intelligent customer service responding with service result information to illustrate some scenarios.

[0099] (1) For example, in the recharge scenario, the process of interaction between the merchant and the AI ​​intelligent customer service is illustrated.

[0100] Merchant: “Are you there?”

[0101] AI Intelligent Customer Service: "Hello, Boss. How can I help you?"

[0102] Merchant: "I want to turn on promotion"

[0103] AI intelligent customer service: "Okay, can we open it for you as before?"

[0104] Merchant: "Yes, I will open both posts as before and then recharge."

[0105] AI Intelligent Customer Service: "OK, thank you for your feedback. What kind of recharge service do you need? We are currently promoting three recharge methods: coins, gold coins, and trading treasures. Please tell me which specific service you want to recharge and the recharge amount, and I will help you with it."

[0106] Merchant: "I'm driving now, I'll take a screenshot and send it to you later"

[0107] AI intelligent customer service: "OK, no problem, drive safely, and contact me when you have time. I wish you a safe journey."

[0108] (2) For another example, in the balance inquiry scenario, the process of interaction between the merchant and the AI ​​intelligent customer service is illustrated.

[0109] Merchant: “I’m running out of money in my account”

[0110] AI intelligent customer service: "Hello, the current balance of promotional coins in your account is 2870.0. If you need to recharge, you can do so by scanning the QR code. At the same time, we will have recharge promotions, so you can pay attention to them. If you need anything, please let me know and I will do my best to provide you with service."

[0111] (3) For another example, in the scenario of consulting about promotional activities, the process of interaction between merchants and AI intelligent customer service is illustrated.

[0112] Merchant: "Is there a detailed breakdown of how much money I recharge and how much I get back?"

[0113] AI intelligent customer service: "The recharge promotion you enjoy is, recharge 5000 and receive 5750; recharge 2000 and receive 2240."

[0114] (4) For another example, the process of modifying a keyword scenario and the interaction between a merchant and an AI intelligent customer service is illustrated.

[0115] Merchant: "Where can I find this keyword? Can I modify it myself?"

[0116] AI Intelligent Customer Service: "The keywords you mentioned are usually found in the title, description or tags of the post. If you can provide specific keywords, I can help you modify them. If you want to modify them yourself, you can tell me the keywords you want to modify, and then you can change them directly in the post. Could you please tell me what keywords need to be modified?"

[0117] Merchant: "Can I tell you which keywords you don't want?"

[0118] AI intelligent customer service: "Of course, please tell me which keywords do not need to appear in your post, and I will help you modify it."

[0119] Merchant: "Second-hand equipment recycling, steel recycling"

[0120] AI intelligent customer service: "OK, please wait, I will help you";

[0121] At this time, the AI ​​language model calls the keyword modification tool, inputs the merchant ID and the keywords to be deleted into the keyword modification tool, and the keyword modification tool deletes the keywords to be deleted from the merchant's post.

[0122] In an embodiment of the present application, services are provided to users based on AI intelligent customer service. The AI ​​intelligent customer service includes an intent recognition model and an AI language model. The intent recognition model is used to identify target scenario information corresponding to the service requirement description information input by the user, and different prompt word templates are set for different scenario information. The service requirement description information is added to the prompt word template corresponding to the target scenario information to generate prompt words. The prompt words are used to guide the AI ​​language model to perform intelligent replies, thereby improving the reply effect of the AI ​​intelligent customer service, so that the output service result information is adapted to the service requirement description information provided by the user.

[0123] Furthermore, a prompt word template is set for the intent recognition model, and different prompt word templates are set for different scenario information. There is no need to conduct model training for the intent recognition model and the AI ​​language model. When a scenario function update is required, the prompt word template corresponding to the scenario information can be updated, which greatly simplifies the update process of AI intelligent customer service.

[0124] Furthermore, the AI ​​language model can better understand the context of the conversation and generate more coherent responses; through sentiment analysis technology, the AI ​​language model can identify and respond to users' emotions to make communication more humane; the AI ​​language model can describe information based on different service needs and dynamically generate service effect information, rather than selecting from preset templates, making the generated service result information more diverse and reducing repetitiveness and template-based phenomena.

[0125] In an optional embodiment, the first prompt word template may include at least two levels, and the intent recognition model is called once for each level, or the intent recognition model may be divided into at least two layers, each layer corresponding to one level. Taking the first prompt word including two levels as an example, the intent recognition model is called once for each level. The first prompt word template includes: a sub-template of the first level and a sub-template of the second level, the sub-template of the first level includes multiple category information, and the sub-template of the second level includes at least two scene information. For example, there is a sub-template of the second level corresponding to each category information. In this way, the amount of information carried in each sub-template of the second level will not be too large, making the process of intent recognition more precise and improving the accuracy of intent recognition.

[0126] Among them, the category information is not limited. In one implementation, the category information can be viewed from the dimension of service products. Different service products correspond to different category information. Each service product corresponds to at least two scene information. The scene information corresponding to different service products may be the same or different. For example, service product B1 includes scene C1, scene C2 and scene C3, and service product B2 includes scene C2, scene C3 and scene C4. In another implementation, the category information can be classified from the dimension of problem information feedback by users. Each type of problem information is regarded as a category, and each type of problem information corresponds to at least two scene information. For example, the problem information reported by the user is phone-related, and phone-related is a category information. The scenarios included in phone-related may be: few calls, phone and service mismatch, no phone access, call back, etc.

[0127] The first task description information includes the first subtask description information and the second subtask description information. The first subtask description information is the subtask description information corresponding to the sub-template of the first level, which is used to describe the task that the intention recognition model needs to perform, that is, to identify the target category information from multiple category information. The second subtask description information is the subtask description information corresponding to the sub-template of the second level, that is, to identify the target scene information from at least two scene information under the target category information. The sub-template of the first level also includes information such as role, background, task and restriction, wherein the background information includes description information corresponding to multiple category information, the role can be a classifier, the task is the first subtask description information, and other detailed introductions can be referred to in the introduction to the first prompt word template. The sub-template of the second level includes: information such as role, background, task and restriction, the background information includes description information corresponding to any category information, and description information of at least two scene information corresponding to the category information, the role can be a classifier, and the task is the second subtask description information, and other detailed introductions can be referred to in the introduction to the first prompt word template.

[0128] The implementation method of adding the service requirement description information to the first prompt word template including at least two scene information to obtain the first prompt word is not limited. A specific implementation method is as follows: adding the service requirement description information to the first-level sub-template to obtain the third prompt word, the first-level sub-template also includes: first sub-task description information; inputting the third prompt word into the intent recognition model, identifying the target category information corresponding to the service requirement description information from multiple category information according to the first sub-task description information; adding the target category information to the second-level sub-template to generate the first prompt word, the first prompt word includes at least two scene information under the target category information.

[0129] Optionally, the implementation method of inputting the first prompt word into the intent recognition model and identifying the target scene information corresponding to the service requirement description information from at least two scene information according to the first task description information is also not limited. A specific implementation method is: inputting the first prompt word into the intent recognition model, and identifying the target scene information of the service requirement description information under the target category information from at least two scene information under the target category information according to the second subtask description information.

[0130] In an optional embodiment, at least two scene information include: at least one preset scene information and non-preset scene information. Wherein, the preset scene information refers to the preset scene information, and each preset scene information corresponds to a second prompt word template. The second prompt word template is pre-set with description information corresponding to the preset scene information. Specifically, the background information of the second prompt word template may include the description information of the preset scene information, and the second prompt word template may also include information such as roles, tasks and restrictions. For details, please refer to the above embodiment, which will not be repeated here. Wherein, the preset scene information may include but is not limited to: modifying keyword scenes, service mismatching scenes, adjusting ranking scenes, switch promotion scenes, using coupon scenes, recharging scenes, information query scenes, etc. Non-preset scenes are relative to preset scenes. If the service demand description information does not match any preset scene information, it is considered that the service demand description information corresponds to a non-preset scene, that is, a non-preset scene may be a scene not covered by various preset scene information, such as a chat scene. It should be noted that the non-preset scene information also corresponds to a second prompt word template, and the background information of the second prompt word template may include description information of the non-preset scene information. In addition, other information included in the second prompt word template can be found in the aforementioned embodiment and will not be repeated here.

[0131] The service requirement description information is added to the second prompt word template corresponding to the target scene information to generate the second prompt word. For example, it can be determined whether the target scene information belongs to the preset scene information. If the target scene information belongs to the target preset scene information, the service requirement description information is added to the second prompt word template corresponding to the target preset scene information to obtain the second prompt word, such as Figure 4b The target preset scene information may be any one of the preset scene information.

[0132] Optionally, if the target scenario information belongs to non-preset scenario information, the customer service information in the intelligent customer service database can be used as a reference to guide the AI ​​language model to make intelligent replies and improve the accuracy of intelligent replies. However, adding all the customer service information in the intelligent customer service database to the second prompt word template may make the data volume of the second prompt word template larger, reducing the efficiency of the AI ​​language model's intelligent reply. At the same time, adding all the customer service information to the second prompt word template is also a waste of resources. In response to the above problems, at least one customer service information can be selected from the intelligent customer service database, and a prompt word can be generated based on at least one customer service information and service demand description information. The prompt word is input into the AI ​​language model for intelligent reply, wherein at least one customer service information is used as a guide to improve the accuracy of the intelligent reply.

[0133] Furthermore, in the process of matching at least one piece of customer service information from the intelligent customer service database, since each piece of customer service information includes requirement information and behavior information, the service requirement description information can be converted into target requirement information, and at least one piece of customer service information can be matched from the intelligent customer service database based on the target requirement information. Compared with directly matching at least one piece of customer service information from the customer service database based on the service requirement description information, the matching accuracy can be improved, which is beneficial to the accuracy of subsequent intelligent replies.

[0134] Among them, the service requirement description information is usually a specific problem statement or inquiry content, and the requirement information indicates what principles you want the AI ​​intelligent customer service to follow, what standards you want to achieve, and what things you want to do.

[0135] Specifically, if the target scenario information belongs to non-preset scenario information, the service requirement description information is converted into target requirement information; at least one candidate requirement information that meets the set similarity condition with the target requirement information is selected from the intelligent customer service database, and the at least one candidate requirement information and its behavior information are used as at least one target customer service information; at least one target customer service information and the service requirement description information are added to the second prompt word template corresponding to the non-preset scenario information to obtain a second prompt word, such as Figure 4bAs shown. The intelligent customer service database includes multiple customer service information, each of which includes requirement information and behavior information. The similarity condition may be that the similarity is higher than a set threshold, and the set threshold may be 88%, 90% or 95%, etc. Similarity matching can be achieved through a similarity matching model, and the similarity matching model may include but is not limited to: a BERT model, a model based on Bag of Words (BoW), a model based on combining term frequency and inverse document frequency (TF-IDF), a model based on word embeddings, etc.

[0136] As shown in Table 1 below, requirement information and behavior information included in a plurality of customer service information are exemplarily displayed, but are not limited thereto.

[0137]

[0138] Further optionally, an implementation method for converting service demand description information into target requirement information includes: adding the service demand description information to a third prompt word template to obtain a fourth prompt word, the third prompt word template including third task description information, which is used to guide the conversion of the service demand description information into requirement information; inputting the fourth prompt word into an AI conversion model, and converting the service demand description information into target requirement information according to the third task description information.

[0139] The third prompt word template includes roles, background, tasks and restrictions. The role may be a converter, and the background information may be the content, length, style, format, details and emotion of the requirement information. The task may be the third task description information used to convert the service requirement description information into the requirement information, and the restriction may include but not be limited to: restrictions on the content, length, style, format, details and emotion of the requirement information.

[0140] Among them, the AI ​​conversion model can be a large language model (LLM). For example, the AI ​​conversion model includes but is not limited to: a generative model (GPT) based on a transformer (Transformer) and a pre-trained model (BERT) based on a transformer, etc.

[0141] In an optional embodiment, a specific implementation method of inputting a second prompt word into an AI language model and generating service result information corresponding to service requirement description information under target scenario information based on the second task description information includes: inputting the second prompt word into the AI ​​language model, generating service parameters for the service requirement description information based on the second task description information; based on the service parameters, calling a target service tool corresponding to the service parameters to generate service result information.

[0142] Among them, the server-side device pre-maintains multiple service tools, each of which can realize a back-end function. The service tools may include but are not limited to: a recharge QR code generation tool, a query keyword tool, a tool for querying the corresponding promotion information of the merchant, a keyword addition tool, an information query tool, etc. Among them, the service parameters vary depending on the service tool. For example, if the service tool is a recharge QR code generation tool, the service parameters may include: recharge method, recharge amount, recharge type, etc.; if the service tool is a query keyword tool, the service parameters may include: merchant ID, merchant post identification information, etc.; if the service tool is a keyword addition tool, the service parameters may include: identification information of the post to which keywords need to be added, keywords to be added, merchant ID information, etc.; if the service tool is a query tool, the service parameters may include information to be queried.

[0143] In an alternative embodiment, if Figure 4b As shown, in the case of generating the second prompt word, the second prompt word can be pre-processed, for example, to determine whether the second prompt word includes sensitive information. If the second prompt word includes sensitive information, the intelligent reply process of the AI ​​intelligent customer service is terminated. Furthermore, prompt information can be output externally, for example, "I don't understand what you are saying? Please re-enter". If the second prompt word does not include sensitive information, the second prompt word is input into the AI ​​language model, and the AI ​​language model generates service result information corresponding to the service requirement description information based on the second task description information. Furthermore, post-processing is performed on the service result information, for example, to determine whether the service result information contains sensitive information. If the service result information contains sensitive information, the sensitive information in the service result information is filtered out, and the service result information without sensitive information is returned to the terminal device for display by the terminal device.

[0144] In an optional embodiment, the prompt word template can also be optimized. For example, the first prompt word template and the second prompt word template are optimized. For example, the service demand description information input by the user and the service result information output by the AI ​​intelligent customer service form a historical chat record, and the candidate scene information can be extracted from the chat record information at set intervals or when the chat record information reaches a set amount of data; for multiple candidate scene information that does not belong to the preset scene information, the multiple candidate scene information is classified, and at least part of the new preset scene information is selected to expand the preset scene information. Further, the description information of the new preset scene information can be added to the first prompt word template, or a second prompt word template can be set for the new preset scene information.

[0145] Regarding the embodiments of the present application Figure 1The detailed implementation and beneficial effects of each step in the method have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0146] 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 101 to 103 can be device A; for another example, the execution subject of steps 101 and 102 can be device A, and the execution subject of step 103 can be device B; and so on.

[0147] 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 101, 102, 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.

[0148] Figure 5 A schematic diagram of the structure of a page display device provided for an exemplary embodiment of the present application, the device corresponds to a terminal device, the terminal device runs a target application, the AI ​​intelligent customer service is deployed on a server device, and a communication connection is established between the server device and the terminal device; Figure 5 As shown, the device comprises:

[0149] A display module 51 is used to display a page link provided by the AI ​​intelligent customer service on the first page provided by the target application;

[0150] A display module 51, for responding to a trigger operation on a page link, and displaying a second page corresponding to the page link, wherein the second page is associated with a component library, and the component library includes a message component and multiple display components adapted to multiple message types;

[0151] An acquisition module 52, configured to acquire service requirement description information in response to an input operation on the second page;

[0152] A sending module 53 is used to send the service requirement description information to the AI ​​intelligent customer service, so that the AI ​​intelligent customer service can generate and return the service result information corresponding to the service requirement description information based on the intent recognition model and the AI ​​language model;

[0153] The receiving module 54 is used to receive the service result information and parse the service result information to obtain at least one sub-message and its message type included in the service result information;

[0154] A selection module 55, configured to select at least one target display component adapted to the at least one sub-message from a plurality of display components according to the at least one sub-message and its information type;

[0155] The embedding module 56 is used to embed at least one sub-message into at least one target display component adapted thereto, and the display module 51 is used to display at least one target display component embedded with at least one sub-message on a third page using a message component, and the third page is the same as or different from the second page.

[0156] In an optional embodiment, the embedding module is specifically used to: for any sub-message, use any sub-message as the state information of the first component template of its adapted target presentation component, so as to embed any sub-message into its adapted target presentation component.

[0157] Optionally, the display module is specifically used to: introduce at least one first component template of at least one target display component into the second component template of the message component to realize a nested relationship between the message component and the at least one target display component, the second component template including global visualization information; determine the local visualization information of at least one target display component in the message component according to the global visualization information, and add the local visualization information to the first component template corresponding to the target display component adapted thereto; render the message component and at least one target display component based on the nested relationship, the second component template and at least one first component template, so as to display at least one target display component in the message component on a third page, so as to display at least one sub-message through at least one target display component.

[0158] In an optional embodiment, the multiple display components include at least: a rich text component, a phone component, a picture component, a video component, and a card component.

[0159] In an optional embodiment, the multiple display components also include an input box component, which is used to input new service requirement description information, wherein the service requirement description information is displayed on the third page through a text component; a display module, specifically used to: if it is detected that the third page has not received a new message within a set time, then display the topic component on the third page through a dynamic effect; and / or a return module, which is used to include a topic component on the third page, and in response to a trigger operation on the topic component, return random topic information for the user according to the user portrait through AI intelligent customer service, and display it through the display module.

[0160] In an optional embodiment, the multiple display components also include a time component; the device also includes a transmission module, which is used to obtain the current time through the time component in response to the message component being displayed on the third page, and transmit the current time to the message component through the time component, so that the message component uses the current time as its display time.

[0161] In an optional embodiment, the third page also includes a loading component; the device also includes: a providing module; a providing module, which is used to display the loading component when the service requirement description information is provided to the AI ​​intelligent customer service and the service result information corresponding to the service requirement description information is not received, and cancel the display of the loading component when the service result information is received.

[0162] In an optional embodiment, a connection is established between the server device and the terminal device via a server push event SSE; a receiving module is used for the terminal device to monitor the service result information sent by the server device based on the SSE interface when the server device sends the service result information to the terminal device via the SSE protocol.

[0163] Regarding the embodiments of the present application Figure 5 The detailed implementation and beneficial effects of each step in the illustrated device have been described in detail in the aforementioned embodiments and will not be elaborated on here.

[0164] Figure 6 A schematic diagram of the structure of an electronic device provided for an exemplary embodiment of the present application, the device corresponds to a terminal device, the terminal device runs a target application, the AI ​​intelligent customer service is deployed on a server device, and a communication connection is established between the server device and the terminal device; Figure 6 As shown, the device includes: a memory 64 and a processor 65.

[0165] The memory 64 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 or method used to operate on the electronic device.

[0166] The processor 65 is coupled to the memory 64 and is used to execute the computer program in the memory 64, so as to: display a page link provided by the AI ​​intelligent customer service on a first page provided by the target application; in response to a trigger operation on the page link, display a second page corresponding to the page link, wherein the second page is associated with a component library, and the component library includes a message component and multiple display components adapted to multiple message types; in response to an input operation on the second page, obtain service demand description information; send the service demand description information to the AI ​​intelligent customer service, so that the AI ​​intelligent customer service can generate and return service result information corresponding to the service demand description information based on the intent recognition model and the AI ​​language model; receive the service result information, parse the service result information to obtain at least one sub-message and its message type included in the service result information; select at least one target display component adapted to the at least one sub-message from multiple display components according to the at least one sub-message and its information type; embed the at least one sub-message into the at least one target display component adapted to it, and use the message component to display the at least one target display component embedded in the at least one sub-message on a third page, and the third page is the same as or different from the second page.

[0167] In an optional embodiment, when the processor 65 embeds at least one sub-message into at least one target display component, it is specifically used to: for any sub-message, use any sub-message as the state information of the first component template of its adapted target display component, so as to embed any sub-message into its adapted target display component.

[0168] Optionally, when the processor 65 uses the message component to display at least one target display component embedded in at least one sub-message on the third page, it is specifically used to: introduce at least one first component template of at least one target display component into the second component template of the message component to realize the nested relationship between the message component and the at least one target display component, the second component template including global visualization information; determine the local visualization information of at least one target display component in the message component according to the global visualization information, and add the local visualization information to the first component template corresponding to the target display component adapted thereto; based on the nested relationship, the second component template and the at least one first component template, render the message component and the at least one target display component to display the at least one target display component in the message component on the third page, so as to display at least one sub-message through the at least one target display component.

[0169] In an optional embodiment, the multiple display components include at least: a rich text component, a phone component, a picture component, a video component, and a card component.

[0170] In an optional embodiment, the multiple display components also include an input box component, which is used to input new service requirement description information, wherein the service requirement description information is displayed on the third page through a text component; the processor 65 is also used to: if it is detected that the third page has not received any new message within a set time, then display the topic component on the third page through a dynamic effect; and / or when the third page includes a topic component, in response to a trigger operation on the topic component, return random topic information for the user according to the user portrait through AI intelligent customer service, and display it.

[0171] In an optional embodiment, the multiple display components also include a time component; the processor 65 is also used to: in response to the message component being displayed on the third page, obtain the current time through the time component, pass the current time to the message component through the time component, so that the message component uses the current time as its display time.

[0172] In an optional embodiment, the third page also includes a loading component; the processor 65 is also used to: when the service requirement description information is provided to the AI ​​intelligent customer service and the service result information corresponding to the service requirement description information is not received, display the loading component, and when the service result information is received, cancel the display of the loading component.

[0173] In an optional embodiment, a connection is established between the server device and the terminal device via a server push event SSE; when the processor 65 receives the service result information, it is specifically used to: when the server device sends the service result information to the terminal device via the SSE protocol, the terminal device monitors the service result information sent by the server device based on the SSE interface.

[0174] Regarding the embodiments of the present application Figure 6 The detailed implementation and beneficial effects of each step in the illustrated device have been described in detail in the aforementioned embodiments and will not be elaborated on here.

[0175] Further, if Figure 6 As shown, the electronic device also includes: a communication component 66, a display 67, a power component 68, an audio component 69 and other components. Figure 6 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 6 In addition, Figure 6The components in the dashed box are optional components, not mandatory components, and the specific components depend on the product form of the electronic device. The electronic device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT (Internet of Things) device, or 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 can include Figure 6 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 6 Components within the dashed box.

[0176] The detailed implementation and beneficial effects of the electronic device provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0177] Accordingly, the embodiment of the present application further provides a computer-readable storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The steps in the method embodiment shown may be executed by an electronic device.

[0178] Accordingly, the embodiment of the present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, causes the processor to implement the above Figure 1 The steps in the method embodiment shown may be executed by an electronic device.

[0179] The above-mentioned memory 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.

[0180] The above-mentioned communication component 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 WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, 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 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology and other technologies.

[0181] The above-mentioned display includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from 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 boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0182] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly 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 assembly is located.

[0183] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (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 can 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.

[0184] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage, etc.) containing computer-usable program code.

[0185] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0186] 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 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0187] 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 The steps for the functions specified in one or more boxes.

[0188] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interface, network interface and memory.

[0189] 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. Memory is an example of a computer-readable medium.

[0190] 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, phase-change random access memory (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, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape 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.

[0191] 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 process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0192] The above are only embodiments of the present application and are 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 within the scope of the claims of the present application.

Claims

1. A page display method, characterized in that: Applicable to a terminal device, the terminal device runs a target application, artificial intelligence AI intelligent customer service is deployed on a server device, and a communication connection is established between the server device and the terminal device; the method includes: On the first page provided by the target application, display the page link provided by the AI ​​intelligent customer service; In response to a triggering operation on the page link, a second page corresponding to the page link is displayed, wherein the second page is associated with a component library, and the component library includes a message component and a plurality of display components adapted to a plurality of message types; In response to the input operation on the second page, obtaining service requirement description information; Send the service requirement description information to the AI ​​intelligent customer service, so that the AI ​​intelligent customer service can generate and return the service result information corresponding to the service requirement description information based on the intent recognition model and the AI ​​language model; Receiving the service result information, parsing the service result information to obtain at least one sub-message and its message type included in the service result information; According to the at least one sub-message and its information type, selecting at least one target presentation component adapted to the at least one sub-message from the multiple presentation components; The at least one sub-message is embedded in the at least one target display component adapted thereto, and the at least one target display component embedded with the at least one sub-message is displayed on a third page using the message component, and the third page is the same as or different from the second page.

2. The method according to claim 1, characterized in that Embedding the at least one sub-message into the at least one target presentation component includes: For any sub-message, the sub-message is used as the state information of the first component template of the adapted target presentation component, so as to embed the sub-message into the adapted target presentation component.

3. The method according to claim 2, characterized in that Using the message component to display the at least one target display component embedded with at least one sub-message on a third page includes: Introducing at least one first component template of the at least one target display component into a second component template of the message component to implement a nested relationship between the message component and the at least one target display component, wherein the second component template includes global visualization information; Determine local visualization information of each of the at least one target display component in the message component according to the global visualization information, and add the local visualization information to a first component template corresponding to the target display component adapted thereto; Based on the nested relationship, the second component template and the at least one first component template, the message component and at least one target display component are rendered to display the at least one target display component in the message component on a third page to display at least one sub-message through the at least one target display component.

4. The method according to claim 1, characterized in that: The multiple display components include at least: a rich text component, a phone component, a picture component, a video component and a card component.

5. The method according to claim 1, characterized in that The multiple display components further include an input box component, the input box component is used to input new service requirement description information, wherein the service requirement description information is displayed on the third page via a text component; The method further comprises: If it is detected that the third page has not received any new message within the set time, the topic component is displayed on the third page through a dynamic effect; and / or When the third page includes a topic component, in response to a trigger operation on the topic component, the AI ​​intelligent customer service returns random topic information for the user based on the user portrait and displays it.

6. The method according to claim 1, characterized in that The plurality of display components further include a time component; the method further includes: In response to the message component being displayed on the third page, the current time is obtained through the time component, and the current time is passed to the message component through the time component, so that the message component uses the current time as its display time.

7. The method according to claim 1, characterized in that The third page also includes a loading component; the method further includes: When the service requirement description information is provided to the AI ​​intelligent customer service and the service result information corresponding to the service requirement description information is not received, the loading component is displayed, and when the service result information is received, the loading component is canceled.

8. The method according to any one of claims 1 to 7, characterized in that: A connection is established between the server device and the terminal device via a server push event SSE; Receiving the service result information includes: In the case where the server device sends the service result information to the terminal device through the SSE protocol, the terminal device monitors the service result information sent by the server device based on the SSE interface.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to implement the steps in the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the processor is caused to implement the steps in the method of any one of claims 1-7.

Images