Service interaction method, apparatus, device, medium, and product

Abstract

The present disclosure provides a service interaction method, device, equipment, medium and product, and relates to the fields of artificial intelligence and intelligent customer service. The method comprises: in response to a service processing request input in a first interaction area, processing the service processing request by using a target model to determine a target service function matched with the service processing request semantics; displaying an operation view corresponding to the target service function in a second interaction area different from the first interaction area; and in response to an operation behavior of a target object on the operation view, outputting operation prompt information corresponding to the operation behavior through the first interaction area, the operation prompt information being used to guide the target object to complete an operation process corresponding to the target service function.

Description

Technical Field

[0001] This disclosure relates to the fields of artificial intelligence and intelligent customer service, and more specifically, to a service interaction method, apparatus, device, medium, and product. Background Technology

[0002] Currently, government service self-service terminals mainly rely on single-screen manual retrieval or basic voice commands, requiring users to manually browse or search for target functions using keywords. While some related technologies support simple voice command recognition, they struggle to understand natural language context, and the questions and answers are disconnected from the actual service scenarios.

[0003] In the process of realizing the concept disclosed herein, it was found that at least the following problems exist in the relevant technology: the separation between function retrieval and scenario-based question and answer causes users to repeatedly switch between operation and consultation interfaces, resulting in relatively low service efficiency. Summary of the Invention

[0004] In view of the above, this disclosure provides a service interaction method, apparatus, device, medium and product.

[0005] One aspect of this disclosure provides a service interaction method, comprising: responding to a service processing request input in a first interaction area, processing the service processing request using a target model, and determining a target service function semantically matching the service processing request; displaying an operation view corresponding to the target service function in a second interaction area different from the first interaction area; and responding to an operation behavior of a target object on the operation view, outputting operation prompt information corresponding to the operation behavior through the first interaction area, the operation prompt information being used to guide the target object to complete the operation process corresponding to the target service function.

[0006] According to embodiments of this disclosure, in response to a service processing request input in a first interactive area, the service processing request is processed using a target model to determine a target service function that semantically matches the service processing request. This includes: in response to receiving a service processing request in the form of voice in the touch trigger area of ​​the first interactive area, converting the service processing request into service processing text; inputting the service processing text into the target model for semantic parsing, so as to associate and match the service processing text with multiple preset service descriptions to determine the target service function.

[0007] According to embodiments of this disclosure, in response to a service processing request input in a first interaction area, the service processing request is processed using a target model to determine a target service function that semantically matches the service processing request. The method further includes: in response to receiving a service processing request in the form of a keyword in a second interaction area, performing fuzzy string matching on the service processing request to determine the target service function.

[0008] According to embodiments of this disclosure, displaying an operation view corresponding to a target service function in a second interaction area different from the first interaction area includes: displaying at least one service card corresponding to the target service function in the second interaction area; and displaying an operation view corresponding to the selected service card in the second interaction area in response to a selection operation of any service card by the target object.

[0009] According to embodiments of this disclosure, in response to the operation behavior of the target object on the operation view, operation prompt information corresponding to the operation behavior is output through the first interactive area, including: matching the corresponding operation prompt information from a preset knowledge base according to the operation type of the operation behavior, wherein the preset knowledge base includes a preset mapping relationship between operation types and operation prompt information; outputting the operation prompt information in the first interactive area by a virtual image in the form of voice broadcast, and / or displaying text bubbles including operation prompt information in the first interactive area.

[0010] According to embodiments of this disclosure, the method further includes: in response to a target object initiating a service query request in a first interaction area, obtaining historical operation information generated by the target object operating the operation view; inputting the service query request and historical operation information into a target model, generating response guidance information, and outputting it through the first interaction area.

[0011] According to embodiments of this disclosure, the method further includes: determining the current process node in the target service function based on historical operation information; retrieving multiple pending operations semantically associated with the service query request from a preset knowledge base, with the current process node as the scope constraint; inputting the service query request, historical operation information, and operation attribute information of each pending operation into the target model to generate predictive guidance information for each pending operation, and outputting it through the first interactive area.

[0012] According to embodiments of this disclosure, the method further includes: in response to a target object triggering a question mark in a second interactive area, reading explanatory text corresponding to the question mark from a preset knowledge base; and displaying the explanatory text through the second interactive area.

[0013] Another aspect of this disclosure provides a service interaction device, comprising: a service determination module, configured to respond to a service processing request input in a first interaction area, process the service processing request using a target model, and determine a target service function semantically matching the service processing request; an operation display module, configured to display an operation view corresponding to the target service function in a second interaction area different from the first interaction area; and an information output module, configured to respond to the operation behavior of a target object on the operation view, and output operation prompt information corresponding to the operation behavior through the first interaction area, the operation prompt information being used to guide the target object to complete the operation process corresponding to the target service function.

[0014] Another aspect of this disclosure provides an electronic device comprising:

[0015] One or more processors;

[0016] Memory, used to store one or more programs.

[0017] Specifically, when one or more programs are executed by one or more processors, the one or more processors implement the above method.

[0018] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the methods described above.

[0019] Another aspect of this disclosure provides a computer program product including computer-executable instructions that, when executed, are used to implement the methods described above.

[0020] According to embodiments of this disclosure, a user's service processing request is received through a first interactive area, and semantic matching is performed using a target model to accurately locate the target service function. The corresponding operation view is displayed in a second interactive area to achieve linkage. In response to the user's operation behavior on the operation view, operation prompt information matching the operation behavior is automatically output through the first interactive area to actively guide the user to complete the subsequent operation process. This constructs a service interaction method that integrates semantic retrieval and operation perception guidance under dual-screen collaboration, solving the problems of low retrieval efficiency and lack of operation guidance in traditional government all-in-one machines, and effectively improving service efficiency. Attached Figure Description

[0021] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0022] Figure 1 The illustrations depict application scenarios of service interaction methods, apparatuses, devices, media, and products according to embodiments of this application.

[0023] Figure 2 A flowchart illustrating a service interaction method according to an embodiment of this application is shown schematically.

[0024] Figure 3A The diagram illustrates an operation homepage according to an embodiment of this application;

[0025] Figure 3B This illustration shows a schematic diagram of a service card display according to an embodiment of this application;

[0026] Figure 4A This illustration schematically shows a diagram of how a question mark triggers the generation of an explanation according to an embodiment of this application;

[0027] Figure 4B This illustration schematically shows a large model assistance triggered by a question mark according to an embodiment of this application;

[0028] Figure 5A This illustration schematically shows a diagram of an explanation generation triggered by a question mark according to another embodiment of this application;

[0029] Figure 5B This illustration schematically shows a large model assistance triggered by a question mark according to another embodiment of this application;

[0030] Figure 6 This schematic diagram illustrates a structural block diagram of a service interaction device according to an embodiment of this application;

[0031] Figure 7 A block diagram schematically illustrates an electronic device suitable for implementing a service interaction method according to an embodiment of this application. Detailed Implementation

[0032] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0033] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0034] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0035] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0036] In the embodiments disclosed herein, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0037] In the embodiments disclosed herein, user authorization or consent is obtained before acquiring or collecting user personal information.

[0038] Embodiments of this disclosure provide a service interaction method, including: responding to a service processing request input in a first interaction area, processing the service processing request using a target model, and determining a target service function semantically matching the service processing request; displaying an operation view corresponding to the target service function in a second interaction area different from the first interaction area; and responding to the operation behavior of a target object on the operation view, outputting operation prompt information corresponding to the operation behavior through the first interaction area, wherein the operation prompt information is used to guide the target object to complete the operation process corresponding to the target service function.

[0039] Figure 1 The illustration schematically depicts application scenarios of service interaction methods, apparatuses, devices, media, and products according to embodiments of this application. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0040] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0041] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social media platform software, etc. (for example only).

[0042] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0043] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0044] It should be noted that the service interaction method provided in this embodiment can generally be executed by server 105. Correspondingly, the service interaction device provided in this embodiment can generally be located in server 105. The service interaction method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the service interaction device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Alternatively, the service interaction method provided in this embodiment can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the service interaction device provided in this embodiment may also be located in the first terminal device 101, the second terminal device 102 or the third terminal device 103, or in other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0045] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0046] Figure 2 A flowchart illustrating a service interaction method according to an embodiment of this application is shown schematically.

[0047] like Figure 2 As shown, the method includes operations S210~S230.

[0048] In operation S210, in response to a service processing request input in the first interaction area, the service processing request is processed using the target model to determine the target service function that semantically matches the service processing request.

[0049] During operation S220, an operation view corresponding to the target service function is displayed in a second interaction area, which is different from the first interaction area.

[0050] In operation S230, in response to the target object's operation behavior on the operation view, operation prompt information corresponding to the operation behavior is output through the first interaction area. The operation prompt information is used to guide the target object to complete the operation process corresponding to the target service function.

[0051] According to embodiments of this disclosure, in the first interactive area (e.g., an AI digital human interactive interface deployed on the left screen of a government affairs all-in-one machine), users can process requests through voice or text input services. For voice input, voice data is first collected via a microphone and converted into text. For text input, the input text is directly obtained.

[0052] The service processing request text is input into a pre-trained or deployed target model. This target model can employ a large language model architecture, enabling deep semantic understanding of the user input. The target model performs semantic association matching between the user request and predefined service function descriptions (such as tags, keywords, or operation paths for various government services), thereby accurately determining the target service function that matches the user's intent, such as "migrant population registration" or "social security inquiry."

[0053] After determining the target service function, an operation view corresponding to that target service function is displayed in a second interactive area (such as the right screen of a government affairs all-in-one machine), which is different from the first interactive area. Specifically, one or more service cards can be displayed in the second interactive area. Each service card corresponds to a specific business entry point, and the service card can contain visual information such as the business name and a brief icon.

[0054] When a user clicks on a service card, the second interactive area switches to the detailed operation view corresponding to that service card. This operation view can include interactive elements such as forms to be filled out for business processing, confirmation instructions, and progress bars, thus providing the user with a complete business processing interface.

[0055] During the user's operation on the operation view of the second interaction area, the user's operation behavior is collected in real time through touch event listening, page jump detection, and input box content editing awareness, such as clicking form fields, triggering question indicators, submitting information, or switching pages.

[0056] In response to these actions, the system matches corresponding prompts from a pre-defined mapping library or knowledge base based on the action type. This pre-defined mapping library stores the correspondence between action types and guiding prompts. The prompts are then output through the first interactive area, either via voice broadcast from an AI digital human avatar or in conjunction with text bubbles displayed in either the first or second interactive area.

[0057] For example, when a user is redirected to the form filling page, the first interactive area will automatically announce, "Please fill out the form next. If you have any questions, please feel free to ask me." This proactively guides the user through the subsequent steps, achieving a seamless interactive experience where the user is guided as they perform the task.

[0058] The system receives user service requests in the first interactive area and uses the target model for semantic matching to accurately locate the target service function. The corresponding operation view is displayed in the second interactive area to achieve linkage. In response to the user's operation behavior in the operation view, the system automatically outputs operation prompts that match the operation behavior through the first interactive area to actively guide the user to complete the subsequent operation process. This creates a service interaction method that integrates semantic retrieval and operation perception guidance under dual-screen collaboration, which solves the problems of low retrieval efficiency and lack of operation guidance in traditional government all-in-one machines, and effectively improves service efficiency.

[0059] According to embodiments of this disclosure, in response to a service processing request input in a first interactive area, the service processing request is processed using a target model to determine a target service function that semantically matches the service processing request. This includes: in response to receiving a service processing request in the form of voice in the touch trigger area of ​​the first interactive area, converting the service processing request into service processing text; inputting the service processing text into the target model for semantic parsing, so as to associate and match the service processing text with multiple preset service descriptions to determine the target service function.

[0060] To enable voice-based service request input, a touch trigger area is set up in the first interactive area (such as the left screen of the government service kiosk). When the user clicks this trigger area, the microphone is activated to collect voice data. The collected analog voice signal is processed by analog-to-digital conversion and a speech recognition engine, converting it into text-based service processing text. To avoid environmental noise interference, a noise reduction algorithm can be deployed at the voice acquisition front end, and an end-to-end model based on deep neural networks is used in the speech recognition stage to improve transcription accuracy.

[0061] The transformed service processing text is then input into the target model, which employs a large language model architecture and possesses semantic understanding capabilities. The target model performs semantic parsing on the service processing text, first identifying intent and extracting keywords, and then, if necessary, rewriting and enhancing the user input through prompt word engineering to eliminate ambiguity or redundant information in colloquial expressions.

[0062] The parsed semantic features are then matched against multiple pre-stored service descriptions. These pre-stored service descriptions consist of business tags for government service items, keywords for processing conditions, and common question templates; these descriptions are pre-vectorized and stored to form a vector database. During matching, the target model employs a strategy combining semantic retrieval and keyword retrieval. On one hand, it calculates the cosine similarity between the vector of the service processing text and the vectors of each pre-stored service description; on the other hand, it uses a fuzzy string matching algorithm to match keywords.

[0063] The model determines the target service function that best matches the user's intent based on the comprehensive matching score. For example, when a user says "I want to apply for a residence permit", the model will output the service function "Application for Residence Permit for Migrant Population".

[0064] Voice requests are received through the touch-triggered area of ​​the first interactive zone. After semantic parsing by the target model, the requests are associated with and matched with preset service descriptions to achieve accurate retrieval of function cards based on natural language.

[0065] According to embodiments of this disclosure, in response to a service processing request input in a first interaction area, the service processing request is processed using a target model to determine a target service function that semantically matches the service processing request. The method further includes: in response to receiving a service processing request in the form of a keyword in a second interaction area, performing fuzzy string matching on the service processing request to determine the target service function.

[0066] In the second interactive area (such as the right screen of a government service kiosk), a text input box is provided, allowing users to directly enter service requests in keyword form using the touchscreen keyboard or an external keyboard. Once the user types text into the input box and submits it (e.g., by clicking the "Search" button or pressing the Enter key), the keyword string is immediately retrieved.

[0067] To improve fault tolerance and user experience, instead of strict exact keyword matching, a fuzzy string matching algorithm is used to process user input. Specifically, the similarity between user input and each preset service description is calculated based on edit distance, allowing a certain number of characters to be inserted, deleted, or replaced, while enhancing robustness against synonyms, typos, or reversed word order.

[0068] In addition, the system can segment user-input keywords and compare them one by one with a keyword tag library of preset service descriptions, calculating a comprehensive score based on the number and weight of matched words. During matching, all preset service descriptions are sorted from highest to lowest matching score, and the one or more with the highest scores are selected as candidate target service functions.

[0069] If the highest-scoring item significantly outperforms the others, it is directly designated as the final target service function. If multiple high-scoring items exist, they can be displayed as a list of service cards in the second interactive area for users to further select from.

[0070] This fuzzy string matching mechanism can still correctly identify and recommend the required service functions even if the user input is incomplete, contains spelling errors, or uses non-standard terms (e.g., inputting "residence permit" when the actual service name is "migrant population residence registration"), thus making up for the lack of accuracy in keyword retrieval.

[0071] According to embodiments of this disclosure, displaying an operation view corresponding to a target service function in a second interaction area different from the first interaction area includes: displaying at least one service card corresponding to the target service function in the second interaction area; and displaying an operation view corresponding to the selected service card in the second interaction area in response to a selection operation of any service card by the target object.

[0072] After identifying the target service function that semantically matches the user's request, an operable function entry point needs to be provided to the user in the second interaction area (e.g., the right screen of the government service terminal). Specifically, one or more service cards are first displayed in the second interaction area, with each service card corresponding to a specific government service.

[0073] During the service card generation process, the target service function's name, icon, brief description, category, and other attribute information are retrieved from a pre-defined service function database and dynamically rendered into a card-style visual component. These components are then sorted and displayed according to recommendation level or business relevance. The service cards can be laid out in a grid or list format and may include a business title, a brief summary, and guiding icons (such as an "Apply Now" arrow) to help users quickly identify the required function.

[0074] When the target object (i.e., the user) selects any service card in the second interaction area via touch or mouse click, the front-end interaction module captures the selection event and loads the detailed operation interface corresponding to that service from the back-end based on the business identifier or Uniform Resource Locator (URL) bound to the selected card. The operation view can be a page containing a multi-step form, a confirmation page for processing conditions, a materials list, or a progress tracking bar.

[0075] Switch the display content of the current second interaction area from the card list to the specific operation view of the service. At the same time, it can link the first interaction area (such as the digital human on the left screen) to output prompt information, such as "The migrant population registration form has been opened for you. Please fill it in according to the prompts".

[0076] Through this card overview and click-to-enter interactive mode, users can freely choose among multiple recommended services and quickly enter the formal processing procedure after confirming the required service, achieving a clear presentation of function entry points and smooth switching of operation paths.

[0077] Figure 3A A schematic diagram of the operation homepage according to an embodiment of this application is shown.

[0078] like Figure 3A As shown, the first interactive area 301 of the government service kiosk is used to deploy an AI digital human virtual avatar to display dialogue content through text bubbles. At the bottom of the first interactive area 301, there is also an interactive box for receiving keywords input by the user. The second interactive area 302 displays multiple function entry cards, including "Public Utility Payment," "Personal Services," "Business Services," and "Policy Disclosure." Each card has a "Click to View" button below it to access the corresponding service details page or processing procedure.

[0079] Figure 3B The illustration shows a schematic diagram of a service card display according to an embodiment of this application.

[0080] like Figure 3B As shown, when a user enters a keyword in the interaction box at the bottom of the first interaction area, or clicks the "Click to view" button in the second interaction area, multiple service cards 303 are dynamically displayed on the second interaction area. Each service card 303 corresponds to a government service function, which the user can select to enter the specific service process.

[0081] According to embodiments of this disclosure, in response to the operation behavior of the target object on the operation view, operation prompt information corresponding to the operation behavior is output through the first interactive area, including: matching the corresponding operation prompt information from a preset knowledge base according to the operation type of the operation behavior, wherein the preset knowledge base includes a preset mapping relationship between operation types and operation prompt information; outputting the operation prompt information in the first interactive area by a virtual image in the form of voice broadcast, and / or displaying text bubbles including operation prompt information in the first interactive area.

[0082] In the second interactive area, all user touch or mouse operations are captured in real time through the front-end event listening interface, including page navigation, button clicks, input box editing, question icon triggering, bubble closing, etc., and the operation type of the current operation is identified (e.g., "entering the form filling page", "clicking the submit button", "triggering the field question icon").

[0083] A pre-built knowledge base is established, the core of which is the pre-defined mapping relationship between operation types and operation prompts. Specifically, for each possible operation type, business experts or by analyzing historical operation logs, write corresponding guiding messages as operation prompts, and store the two in the pre-built knowledge base in the form of key-value pairs.

[0084] Once the operation perception engine identifies a specific operation type, it immediately uses that operation type as the search key to perform a precise match in the preset knowledge base and extract the pre-bound operation prompt information text.

[0085] For example, if the user's action type is "jump to form filling page", the corresponding operation prompt in the knowledge base will be "Please fill in the form next. If you have any questions, you can click the form filling assistant on the right or consult the AI ​​digital human". If the action type is "click the option with the question mark", the prompt will be a brief explanation of that option.

[0086] After receiving the operation prompt information, the information is output to the user through the first interaction area. The first interaction area features an AI digital human virtual avatar with speech synthesis and text display capabilities. The matched operation prompt text is sent to the speech synthesis module and the text rendering module respectively.

[0087] The speech synthesis module employs neural network-based text-to-speech technology to convert text into natural and fluent speech, which is then broadcast through the speaker in the first interaction area. Simultaneously, the mouth animation of the digital human avatar is synchronized with the speech to enhance the realism of the interaction. The text rendering module displays the same operation prompt text in a dialog bubble or designated text area within the first interaction area. The bubble can be designed to be semi-transparent or have a white background and supports automatic closing or user click-to-close.

[0088] In addition, depending on the scenario, you can choose to only broadcast the voice, only display the text bubble, or both at the same time to suit the preferences of different users (for example, people with poor eyesight can rely on the voice broadcast, while users can read the text in noisy environments).

[0089] By using this rapid matching method based on preset mapping relationships and multimodal output of virtual avatars, targeted guidance can be proactively provided the moment the user operates, without requiring the user to manually trigger the help function, thereby significantly improving the smoothness and intelligence of the process.

[0090] According to embodiments of this disclosure, the service interaction method further includes: in response to a target object initiating a service query request in a first interaction area, obtaining historical operation information generated by the target object operating the operation view; inputting the service query request and historical operation information into a target model, generating response guidance information, and outputting it through the first interaction area.

[0091] During the service interaction process, in addition to initiating the initial service processing request through the first interaction area, users may also have new questions or require additional guidance during the process. At this time, users can initiate service inquiry requests in the first interaction area (such as the AI ​​digital human interaction interface on the left screen) in the form of voice or text, such as asking "What format is required for this material?" or "What is the next step?"

[0092] Upon receiving the service request, it is first converted into text (or processed through speech recognition if it is voice input). Simultaneously, it is necessary to obtain historical operation information generated by the user's actions on the operation view within the current service flow.

[0093] During the historical operation information collection process, the front end records every operation event of the user on the second interaction area (right screen) in real time, including page jump records, names of clicked buttons or options, changes in the content of input boxes, triggered question indicators and their corresponding explanations, and the sequence number of completed steps, etc., and stores these events in a session context in chronological order.

[0094] When a user initiates a service query request, the system extracts the operation information from the most recent few steps (e.g., the most recent two or three steps) from the session context to form historical operation information. Then, the text of the service query request and the historical operation information are used as input and passed to the target model.

[0095] The target model can employ a large language model, guided by designed prompts to generate targeted responses based on context. Specifically, the prompts clearly inform the target model of the user's current situation, previously performed actions, and the current interface state, requiring the model to answer the user's questions based on this information and provide suggestions for the next step.

[0096] To enhance the accuracy of responses, before inputting information into the target model, relevant processing guidelines, material requirements, and frequently asked questions can be retrieved from an external knowledge base. These search results can then be used as supplementary context and input into the target model. After processing, the target model outputs response guidance information, which not only directly answers the user's current question but may also include hints or precautions for subsequent steps.

[0097] The response guidance information is output through the first interactive area. Specifically, it is delivered via voice by an AI digital human virtual avatar, while the response content is displayed in a text bubble within the first interactive area. For example, when a user fills out a form and asks "How do I obtain a residence certificate?", the historical operation information shows that the user is currently on the "Upload Residence Certificate" page. The response guidance information generated by the target model is: "You can obtain a residence certificate from the community neighborhood committee, or you can use a screenshot of your electronic residence permit. After filling in this section, please click Next to confirm your contact information."

[0098] By combining historical operational information with context-aware question answering, accurate answers closely related to the user's current task can be provided, reducing ineffective guidance caused by generic responses.

[0099] According to embodiments of this disclosure, the service interaction method further includes: determining the current process node in the target service function based on historical operation information; retrieving multiple pending operations semantically related to the service query request from a preset knowledge base, with the current process node as the scope constraint; inputting the service query request, historical operation information, and operation attribute information of each pending operation into the target model to generate predictive guidance information for each pending operation, and outputting it through the first interaction area.

[0100] After a user initiates a service inquiry request through the first interaction area, in addition to generating response guidance information for the current problem, predictive operation guidance can also be provided. Specifically, based on the acquired historical operation information, the specific process node where the user is in the current target service function is determined.

[0101] Historical operation information records the steps the user has completed, the current page identifier, and the form fields that have been filled in. By analyzing this information, the user's current stage can be inferred, such as the "fill in residence information" node in the "migrant population registration" business process, or the "select query year" node in the "social security inquiry" process. The definition of process nodes can be pre-described in the business process configuration file in the form of a directed graph or state machine.

[0102] After determining the current process node, constraint retrieval is performed in a preset knowledge base. This preset knowledge base differs from the simple mapping library used for operation type mapping mentioned above; instead, it is a structured process knowledge base that organizes and stores multiple pending operations that may be involved in each business process node.

[0103] Pending operations refer to the steps that users are expected to take after the current node, such as "upload materials," "confirm information," and "submit application." Each pending operation is also associated with operation attribute information, such as operation name, operation sequence number, required materials prompts, and precautions text.

[0104] During the retrieval process, the current process node serves as a scope constraint, extracting a list of all pending operations corresponding to that process node from a pre-defined knowledge base. Simultaneously, the user's service query text (e.g., "What should I do next?") is semantically matched with the operation descriptions in the pending operation list. The semantic similarity between the user's query intent and each pending operation is calculated, and one or more pending operations with the highest relevance are selected. Matching methods can employ vector similarity calculation or keyword-based text matching.

[0105] The service inquiry request, historical operation information, and operation attribute information (including operation name, sequence, and guidance script template) of each selected pending operation are input into the target model. The target model is a large language model. Through specific prompt word design, the target model is required to generate predictive guidance information for these pending operations based on the user's current process node, the history of completed operations, and the attributes of candidate pending operations.

[0106] The generation of predictive guidance information is not simply a repetition of the name of the operation to be processed, but rather uses natural language to proactively prompt the user with the possible next steps and precautions.

[0107] For example, when a user asks, "What's next after filling this out?", if the current process node is determined to be "filling in residential information" based on historical operation information, and the retrieved pending operations are "uploading identity verification" and "confirming residential address," then the target model generates the following predictive guidance information: "After filling in your residential information, you will need to upload photos of the front and back of your ID card and confirm that your residential address is correct. We suggest you prepare an electronic copy of your ID card in advance." This predictive guidance information not only answers the user's current question but also proactively provides anticipatory guidance for subsequent steps, allowing the user to understand the next steps without having to ask again.

[0108] The predicted guidance information is output through the first interactive area, in the same manner as the response guidance information. It is delivered by an AI digital human virtual avatar and displayed as a text bubble in the first interactive area. The predicted guidance information can be output separately or combined with the generated response guidance information (e.g., answering the current question first, then supplementing with the predicted content).

[0109] In this way, proactive anticipation capabilities are achieved beyond passive responses, enabling users to be informed of subsequent operations in advance before they have even asked a specific question, thereby further improving efficiency and user experience.

[0110] According to embodiments of this disclosure, the service interaction method further includes: in response to a target object triggering a question mark in a second interaction area, reading explanatory text corresponding to the question mark from a preset knowledge base; and displaying the explanatory text through the second interaction area.

[0111] In the second interactive area (such as the right screen of the government affairs all-in-one machine), next to each form item, option button or key term in the operation view (such as the form filling page or service guide page), there is a pre-set question mark. The mark is usually presented as a circular question mark "?" icon, a circled question mark or dotted text with an underline. The color can be light gray or bright blue to distinguish it from ordinary text, and it can be triggered by touch click or mouse hover.

[0112] When the target object (user) clicks or touches the question icon, the front-end interaction module captures the trigger signal through the event listener interface and obtains the business field identifier bound to the question icon. It then initiates a query request to a pre-defined knowledge base, which is a structured static knowledge base that stores pre-stored explanatory text corresponding to each business field or function option.

[0113] The pre-defined knowledge base can be implemented using a key-value database or a local embedded database, where the key is a field identifier and the value is a pre-stored explanatory text string. The explanatory text is pre-written by business experts and includes a concise definition of the field or option, a filling example, and precautions. For example, for the "Residence Permit Type" option, the explanatory text would be: "Residence permits are divided into two types: 'Residence Registration' and 'Residence Permit Application'. Residence Registration is applicable to those who have been newly arrived in the area for less than 6 months; Residence Permit Application is applicable to those who have been registered for more than 6 months."

[0114] After retrieving the corresponding explanatory text from the preset knowledge base, the text is displayed to the user through the second interactive area. The display method can be an opaque or semi-transparent white bubble, which dynamically pops up near the trigger indicator (below or to the right). The bubble contains the explanatory text content, and the text supports line breaks and scrolling.

[0115] To avoid obscuring form content, the bubble's position can be automatically adjusted based on screen space. For example, when the trigger indicator is near the bottom of the screen, the bubble pops up; when it's near the right edge, the bubble shifts to the left. The bubble also supports multiple closing rules: the bubble automatically closes when the user clicks on any area outside the bubble, or closes by clicking the close button ("×") inside the bubble, or automatically fades out and closes after a preset time (e.g., 10 seconds).

[0116] In addition, for longer explanatory texts (e.g., exceeding 100 words), they can be displayed in a sidebar pop-up instead of the entire text in the bubble. Specifically, after clicking the question icon, a sidebar panel slides out from the right side of the second interaction area, displaying detailed explanatory text, which may include mixed text and images or step-by-step instructions. After reading, the user can click to close or continue filling out the form.

[0117] With this pre-stored interpretation mechanism, users can quickly obtain authoritative explanations for specific form items or options without leaving the current operation interface. This reduces the response delay caused by calling the large model for each question and meets the need for instant answers to common and simple questions. It is especially suitable for questions about explanations of a large number of standardized fields in form filling scenarios.

[0118] Figure 4A The illustration shows a schematic diagram of how a question mark triggers the generation of an explanation according to an embodiment of this application.

[0119] like Figure 4A As shown, the second interactive area displays an explanation section, which shows pre-stored or dynamically generated answer text. Below this section is a "Still have questions" prompt or button. Below the explanation, there are three input boxes: a first input box, a second input box, and a third input box. Each input box contains multiple fields, such as the first field, second field, and third field in the first input box. Each field has a question mark icon to its right, which triggers the explanation of the corresponding field.

[0120] Figure 4B The illustration shows a schematic diagram of a question mark triggering a large model assistance according to an embodiment of this application.

[0121] like Figure 4B As shown, users can click the "?" icon to the right of each field to display the corresponding explanation. If users still have questions after viewing the explanation, they can click the microphone icon to initiate further interaction with the AI ​​digital human virtual avatar in the first interaction area, asking questions in natural language to obtain more detailed answers.

[0122] Figure 5A The illustration shows a diagram of an explanation generation triggered by a question mark according to another embodiment of this application.

[0123] like Figure 5A As shown, the second interactive area displays the form content area, with a "Form Filling Assistant" interactive entry point on its right or bottom. The form content contains multiple information items, including Question 1 and its corresponding "?" icon, Question 2 and its corresponding "?" icon, as well as options A, B, and C for the user to choose from. In addition, there is a "Fill in Information" input box for users to enter the required information.

[0124] Figure 5B A schematic diagram illustrating a large model assistance triggered by a question mark according to another embodiment of this application is shown.

[0125] like Figure 5B As shown, after a user clicks the "?" icon to the right of question 1 or question 2 in the "Form Filling Assistant" panel, the corresponding explanation will be displayed in the appropriate location. If the user still has questions after viewing the explanation, they can enter natural language (such as "Hello, may I ask...") in the bottom interactive box or click the microphone icon to initiate further interaction with the AI ​​digital human virtual avatar in the first interactive area to obtain more detailed answers.

[0126] Figure 6 A schematic block diagram of a service interaction device according to an embodiment of this application is shown.

[0127] like Figure 6 As shown, the service interaction device 600 includes a service determination module 610, an operation display module 620, and an information output module 630.

[0128] The service determination module 610 is used to respond to a service processing request input in the first interaction area, process the service processing request using the target model, and determine the target service function that semantically matches the service processing request.

[0129] The operation display module 620 is used to display the operation view corresponding to the target service function in a second interaction area that is different from the first interaction area.

[0130] The information output module 640 is used to respond to the operation behavior of the target object on the operation view and output operation prompt information corresponding to the operation behavior through the first interaction area. The operation prompt information is used to guide the target object to complete the operation process corresponding to the target service function.

[0131] According to embodiments of this disclosure, the service determination module 610 includes a text conversion submodule and an association matching submodule.

[0132] The text conversion submodule is used to convert a service processing request in the form of voice into service processing text in response to a touch trigger area received in the first interaction area.

[0133] The association matching submodule is used to input the service processing text into the target model for semantic parsing, so as to associate and match the service processing text with multiple preset service descriptions to determine the target service function.

[0134] According to embodiments of this disclosure, the service determination module 610 further includes a fuzzy matching submodule.

[0135] The fuzzy matching submodule is used to respond to a service processing request in the form of a keyword received in the second interaction area, perform fuzzy string matching on the service processing request, and determine the target service function.

[0136] According to embodiments of this disclosure, the operation display module 620 includes a card display submodule and a view display submodule.

[0137] The card display submodule is used to display at least one service card corresponding to the target service function in the second interactive area.

[0138] The view display submodule is used to respond to the target object's selection operation of any service card and display the operation view corresponding to the selected service card in the second interaction area.

[0139] According to embodiments of the present disclosure, the information output module 640 includes a prompt matching submodule and a prompt output submodule.

[0140] The prompt matching submodule is used to match the corresponding operation prompt information from the preset knowledge base according to the operation type of the operation behavior. The preset knowledge base includes a preset mapping relationship between operation types and operation prompt information.

[0141] The prompt output submodule is used to output operation prompt information in the first interaction area through a virtual image in the form of voice broadcast, and / or to display text bubbles including operation prompt information in the first interaction area.

[0142] According to embodiments of this disclosure, the service interaction device 600 further includes a history acquisition module and a guide generation module.

[0143] The history acquisition module is used to respond to a service query request initiated by the target object in the first interaction area and to obtain historical operation information generated by the target object's operation of the operation view.

[0144] The guidance generation module is used to input service query requests and historical operation information into the target model, generate response guidance information, and output it through the first interaction area.

[0145] According to embodiments of this disclosure, the service interaction device 600 further includes a node determination module, an operation retrieval module, and a prediction generation module.

[0146] The node determination module is used to determine the current process node in the target service function based on historical operation information.

[0147] The operation retrieval module is used to retrieve multiple pending operations that are semantically related to the service query request from a preset knowledge base, with the current process node as the scope constraint.

[0148] The prediction generation module is used to input service query requests, historical operation information, and operation attribute information of each pending operation into the target model, generate prediction guidance information for each pending operation, and output it through the first interaction area.

[0149] According to embodiments of this disclosure, the service interaction device 600 further includes an interpretation reading module and an interpretation display module.

[0150] The explanation reading module is used to read the explanation text corresponding to the question mark from the preset knowledge base in response to the question mark being triggered by the target object in the second interaction area.

[0151] The explanation display module is used to display explanatory text through the second interactive area.

[0152] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-a-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0153] For example, any plurality of the service determination module 610, operation display module 620, and information output module 630 may be combined into one module / unit / subunit, or any one of these modules / units / subunits may be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits may be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this disclosure, at least one of the service determination module 610, operation display module 620, and information output module 630 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the service determination module 610, operation display module 620, and information output module 630 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0154] It should be noted that the service interaction device part in the embodiments of this disclosure corresponds to the service interaction method part in the embodiments of this disclosure. For a detailed description of the service interaction device part, please refer to the service interaction method part, which will not be repeated here.

[0155] Figure 7 A block diagram schematically illustrates an electronic device suitable for implementing a service interaction method according to an embodiment of this application. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0156] like Figure 7 As shown, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage portion 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0157] RAM 703 stores various programs and data required for the operation of electronic device 700. Processor 701, ROM 702, and RAM 703 are interconnected via bus 704. Processor 701 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 702 and / or RAM 703. It should be noted that programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in one or more memories.

[0158] According to embodiments of this disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to a bus 704. The electronic device 700 may also include one or more of the following components connected to the input / output (I / O) interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0159] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by processor 701, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0160] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0161] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0162] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0163] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the service interaction methods provided in the embodiments of this disclosure.

[0164] When the computer program is executed by the processor 701, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0165] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 709, and / or installed from a removable medium 711. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0166] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0167] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0168] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A service interaction method, comprising: In response to a service processing request input in the first interaction area, the service processing request is processed using a target model to determine a target service function that semantically matches the service processing request. In a second interactive area, which is different from the first interactive area, an operation view corresponding to the target service function is displayed. In response to the target object's operation behavior on the operation view, operation prompt information corresponding to the operation behavior is output through the first interaction area. The operation prompt information is used to guide the target object to complete the operation process corresponding to the target service function.

2. The method according to claim 1, wherein, The process of responding to a service processing request input in the first interaction area, processing the service processing request using a target model, and determining a target service function semantically matching the service processing request includes: In response to receiving a service processing request in the form of voice in the touch trigger area of ​​the first interaction area, the service processing request is converted into service processing text; The service processing text is input into the target model for semantic parsing, so as to associate and match the service processing text with multiple preset service descriptions to determine the target service function.

3. The method according to claim 1, wherein, The step of responding to a service processing request input in the first interaction area, processing the service processing request using a target model, and determining a target service function semantically matching the service processing request, further includes: In response to receiving a service processing request in the form of a keyword in the second interaction area, fuzzy string matching is performed on the service processing request to determine the target service function.

4. The method according to claim 1, wherein, The step of displaying the operation view corresponding to the target service function in a second interaction area different from the first interaction area includes: At least one service card corresponding to the target service function is displayed in the second interactive area; In response to the target object's selection operation on any of the service cards, the operation view corresponding to the selected service card is displayed in the second interaction area.

5. The method according to claim 1, wherein, The response to the target object's operation behavior on the operation view, outputting operation prompt information corresponding to the operation behavior through the first interaction area, includes: Based on the operation type of the operation behavior, the corresponding operation prompt information is matched from the preset knowledge base, wherein the preset knowledge base includes a preset mapping relationship between operation types and operation prompt information; The operation prompt information is output in the first interactive area by a virtual avatar in the form of voice broadcast, and / or, a text bubble including the operation prompt information is displayed in the first interactive area.

6. The method according to claim 1 or 5, wherein, The method further includes: In response to a service query request initiated by a target object in the first interactive area, historical operation information generated by the target object's operation on the operation view is obtained. The service query request and the historical operation information are input into the target model to generate response guidance information, which is then output through the first interaction area.

7. The method according to claim 6, wherein, The method further includes: Based on the historical operation information, determine the current process node in the target service function; In the preset knowledge base, using the current process node as a scope constraint, multiple pending operations semantically related to the service query request are retrieved. The service query request, the historical operation information, and the operation attribute information of each operation to be processed are input into the target model to generate predictive guidance information for each operation to be processed, and output through the first interaction area.

8. The method according to claim 1, wherein, The method further includes: In response to the target object triggering a question marker in the second interaction area, the explanatory text corresponding to the question marker is read from a preset knowledge base; The explanatory text is displayed through the second interactive area.

9. A service interaction device, comprising: The service determination module is used to respond to a service processing request input in the first interaction area, process the service processing request using a target model, and determine the target service function that semantically matches the service processing request. An operation display module is used to display an operation view corresponding to the target service function in a second interaction area that is different from the first interaction area; The information output module is used to respond to the operation behavior of the target object on the operation view, and output operation prompt information corresponding to the operation behavior through the first interaction area. The operation prompt information is used to guide the target object to complete the operation process corresponding to the target service function.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 8.

11. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images