Government affair business consultation response method and device, electronic equipment and storage medium

Abstract

The invention discloses a response method and device for government affair business consultation, electronic equipment and a storage medium. According to the method, a knowledge base including an item situation database, an item handling information database and an item consultation information database is pre-constructed, and the knowledge base is retrieved according to a consultation request to actively query a user, or a recommended handling item is provided for the user, or the user is prompted to check a demand material for service handling. According to the technical scheme, the response accuracy and comprehensiveness of the consultation request of the user are improved, so that the government affair business handling efficiency of the user is improved, and the business handling complexity is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a government affair business consultation response method and device, electronic equipment and storage medium. BACKGROUND

[0002] The current government service platform usually only provides simple search function or "dumb" simple point selection consultation service. Because the name of government affairs is usually not easy to understand, the public is difficult to clearly know which or which matters they want to handle, and the interaction mode is relatively simple, usually only supporting text input. The province, city and district usually have their own government platforms, and many business data are not interconnected. The matter information is synchronized from the province, and the update is not timely. In addition, if the materials are missing when handling a certain matter, it may be found in the middle of the process, and other matters may need to be handled to supplement the materials. For the public, the process is long and complex. SUMMARY

[0003] The present application provides a government affair business consultation response method, device, electronic equipment and storage medium, to improve the response accuracy and comprehensiveness of user consultation requests, thereby improving the efficiency of user government affair business handling and reducing the complexity of business handling.

[0004] According to one aspect of the present application, a government affair business consultation response method is provided, which comprises:

[0005] In response to the current consultation request of the current user, user intention recognition classification is performed to determine the intention category of the current user;

[0006] In the case where the intention category belongs to government affair business handling, a pre-constructed knowledge base is retrieved according to the current consultation request to obtain a retrieval result; the pre-constructed knowledge base includes a matter situation database, a matter handling information database and a matter consultation information database; the matter situation database includes a corresponding relationship file of situation questions and situation answers; the matter handling information database includes matter handling information files classified by matters; the matter consultation information database includes associated knowledge files constructed according to historical consultation;

[0007] A response result to the current consultation request is determined according to the retrieval result; the type of the response result includes active inquiry, recommended matter and material inspection prompt.

[0008] According to another aspect of the present application, a government affair business consultation response device is provided, which comprises:

[0009] An intention category determination module for, in response to the current consultation request of the current user, performing user intention recognition classification to determine the intention category of the current user;

[0010] The retrieval result obtaining module is configured to, in the case that the intention category belongs to government affair handling, retrieve a pre-constructed knowledge base according to the current consultation request to obtain a retrieval result; the pre-constructed knowledge base comprises a matter situation database, a matter handling information database and a matter consultation information database; the matter situation database comprises a corresponding relationship file of situation questions and situation answers; the matter handling information database comprises matter handling information files classified according to matters; and the matter consultation information database comprises associated knowledge files constructed according to historical consultations.

[0011] The answer result first determining module is configured to determine an answer result to the current consultation request according to the retrieval result; and the type of the answer result comprises active inquiry, recommended matter and prompt material inspection.

[0012] According to another aspect of the present application, an electronic device is provided, which comprises:

[0013] at least one processor; and

[0014] a memory connected to the at least one processor in communication; wherein,

[0015] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the government affair consultation answering method according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to execute the government affair consultation answering method according to any one of the embodiments of the present application when executed by the processor.

[0017] The technical solution of the embodiments of the present application adopts the technical means of pre-constructing a knowledge base comprising a matter situation database, a matter handling information database and a matter consultation information database, and retrieving the knowledge base to actively inquire the user, or provide the user with a recommended handling matter, or prompt the user to check the required material for business handling, thereby solving the problem that the user cannot obtain accurate business handling information through consultation before handling the business, leading to a long and complex business handling process, improving the accuracy and comprehensiveness of the answer to the user's consultation request, thereby improving the efficiency of the user's government affair handling and reducing the complexity of the business handling.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without any creative effort.

[0020] Figure 1a A flow chart of a government affair business consulting response method provided by the embodiment of the present application;

[0021] Figure 1b A situation file schematic diagram provided by the embodiment;

[0022] Figure 1c A specific schematic diagram of a matter handling information file provided by the embodiment;

[0023] Figure 1d A key setting schematic diagram of a pre-constructed knowledge base provided by the embodiment;

[0024] Figure 1e An active inquiry schematic diagram under an enterprise information change business scenario provided by the embodiment;

[0025] Figure 1f A recommended matter and material inspection schematic diagram under an enterprise information change business scenario provided by the embodiment;

[0026] Figure 2 A structural schematic diagram of a government affair business consulting response device provided by the embodiment of the present application;

[0027] Figure 3 A structural schematic diagram of an electronic device for implementing the government affair business consulting response method of the embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the personnel in the technical field better understand the present application, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should belong to the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Figure 1a This is a flowchart illustrating a method for responding to government affairs inquiries according to an embodiment of the present invention. This embodiment is applicable to responding to user inquiries. The method can be executed by a government affairs inquiries response device, which can be implemented in hardware and / or software and can be configured in a server. Figure 1a As shown, the method includes:

[0031] S110. In response to the current user's current consultation request, perform user intent identification and classification to determine the current user's intent category.

[0032] The current consultation request refers to the consultation request information entered by the current user through the intelligent agent's human-computer interaction interface. The current consultation request can be in the form of text, voice, images, etc. The intent category can include government service processing, greeting scenarios, and refusal-to-answer scenarios; that is, the user's consultation can be about government service processing, a greeting-like input request, or a sensitive, non-government-related input request.

[0033] In one optional implementation, in response to a current user's current consultation request, performing user intent identification and classification to determine the current user's intent category may include: in response to the current consultation request, identifying semantic information of the current consultation request; performing user intent identification and classification based on the semantic information to determine the current user's intent category; the intent category includes government business processing, greeting scenarios, and refusal to answer scenarios.

[0034] In this embodiment, in response to the current user's current consultation request, the user's intent can be identified based on its semantics and the corresponding intent category can be determined.

[0035] S120, in the case that the intent category belongs to government affair handling, retrieving a pre-constructed knowledge base according to the current consultation request to obtain a retrieval result; the pre-constructed knowledge base comprises a matter situation database, a matter handling information database and a matter consultation information database; the matter situation database comprises a corresponding relationship file of situation questions and situation answers; the matter handling information database comprises matter handling information files classified according to matters; and the matter consultation information database comprises associated knowledge files constructed according to historical consultations.

[0036] In the matter situation database, the situation questions and the situation answers can be constructed as a tree structure relationship, for example, a situation question 1 answer 1, a situation question 2 answer 2, a leaf node under the situation question can also be a specific matter associated with the situation question. There can be multiple situations under a certain business subject matter. The data for constructing the matter situation database can be derived from the matter situations pre-processed by business personnel and the matter situations extracted from the prescribed documents. Figure 1b A situation file diagram is provided for the embodiment.

[0037] Each matter handling information file in the matter handling information database can be a description file of the whole process of matter handling, for example, including acceptance conditions, application materials, results, basis for prescribed documents, handling process, handling window, basic information and charging information, etc. The data for constructing the matter handling information database can be derived from the existing matter systems of various cities and districts. Figure 1c A specific matter handling information file diagram is provided for the embodiment.

[0038] Each associated knowledge file in the matter consultation information database can be a knowledge file derived from the common questions themselves and the extension of the common questions according to historical user consultations, and can also include knowledge files derived from various affair handling guidelines of various cities and districts. For example, a basic information table of various affair handling points, a characteristic service (reservation, weekend, noon) information table, a matter list of the government affair service network, a self-service terminal (self-service machine) matter list, a video affair matter list of village and community government affair service, a summary table of industry department government affair service matter knowledge questions and answers, etc.

[0039] Optionally, the corresponding relationship file, the matter handling information file and the associated knowledge file in the pre-constructed knowledge base are processed by segment vectorization with a specified identifier; and the pre-constructed knowledge base supports keyword retrieval and / or vector retrieval.

[0040] The embodiment can realize file segmentation through segment identifiers in the pre-constructed knowledge base, and vector processing is performed on the corresponding relationship file of the matter situation database, the matter handling information file of the matter handling information database, and the associated knowledge file of the matter consultation information database. There are three retrieval methods for the pre-constructed knowledge base (keyword retrieval, vector retrieval, keyword and vector retrieval). Figure 1d The key settings of the pre-constructed knowledge base provided in the embodiment are shown in the schematic diagram, for example, segment settings (such as setting segment identifiers, segment maximum length, and segment overlap length), retrieval settings (vector retrieval, full-text keyword retrieval, and mixed retrieval), and recall strategy settings (TopK, score threshold), and the like.

[0041] The knowledge involved in the embodiment can be divided into matter information, handling information, common questions and answers, situation trees, and the like. A multi-level permission knowledge management platform is built, different areas of matters are divided into knowledge bases, and different tags are used for isolation. The knowledge base supports multiple formats of knowledge such as pdf, excel, txt, markdown, docx, and structured knowledge, and knowledge new policies or changes can be synchronized in real time to ensure the validity and timeliness. The files in the pre-constructed knowledge base of the embodiment can have corresponding identification tags, such as region tags (such as XX district, XX town, etc.), which facilitate accurate positioning of the files during knowledge retrieval.

[0042] In an optional implementation, in the case where the intent category belongs to government affair handling, retrieving the pre-constructed knowledge base according to the current consultation request to obtain a retrieval result can include: in the case where the intent category belongs to government affair handling, rewriting the current consultation request according to business-related words to obtain a rewritten consultation request; obtaining retrieval keywords and vector information matched by the rewritten consultation request; retrieving the pre-constructed knowledge base according to the retrieval keywords and / or the vector information to obtain a recall result; and determining the retrieval result according to the recall result.

[0043] In the embodiment, if it is determined that the current user consultation request belongs to the government affair handling category, the current user consultation can be rewritten as business-related words to improve the knowledge recall accuracy. The pre-constructed knowledge base is retrieved according to the retrieval keywords and / or vector information corresponding to the rewritten consultation request, and a recall result is obtained according to the recall strategy of the pre-constructed knowledge base. The recall result can be reordered to obtain a retrieval result.

[0044] S130, determining a response result to the current consultation request according to the retrieval result; the type of the response result includes active inquiry, recommended matter, and prompt material check.

[0045] In an optional implementation, determining the response result for the current consultation request according to the search result can include: determining a response type for the current consultation request according to the business handling association information in the search result; and determining the response result for the current consultation request according to a response strategy matched with the response type and in combination with the business handling association information.

[0046] The embodiment can determine which cases are met according to the search result, and determine whether to continue the next question, recommend an item, or perform material checking, etc. based on the cases and the business handling association information in the search result.

[0047] Based on the optional implementation, determining the response result for the current consultation request according to a response strategy matched with the response type and in combination with the business handling association information can include: in a case where the response type is active inquiry, determining inquiry content for the current user according to the business handling association information, and determining the inquiry content as the response result; in a case where the response type is recommended item, generating a recommended item list according to the business handling association information, and taking the recommended item list as the response result for user selection; and in a case where the response result is prompt material checking, generating a required material list according to the business handling association information, and taking the required material list as the response result for user checking.

[0048] An exemplary Figure 1e The embodiment provides an active inquiry schematic diagram in an enterprise information change business scenario. The embodiment can sort out a hierarchical knowledge graph of item handling cases based on user consultation requests, match and reason the theme of user consultation according to user question semantics, lock relevant hierarchical cases, and actively inquire about case problems that need to be determined. The embodiment also supports automatically obtaining data information such as licenses and enterprise types for determining cases when the user allows, and supports automatically skipping repeated questions or questions that can be reasoned out, so as to reduce the number of inquiries as much as possible.

[0049] Figure 1f The embodiment provides a recommended item and material checking schematic diagram in an enterprise information change business scenario. The embodiment can give recommended items based on user consultation, and support user package handling.

[0050] Reference Figure 1f The embodiment can perform material checking, obtain a material list for handling user consultation items, and identify items that can be handled to obtain missing materials for materials that do not exist.

[0051] Optionally, if the intent category belongs to the greeting scenario, the first response template is determined as the response result to the current consultation request; if the intent category belongs to the refusal scenario, the second response template is determined as the response result to the current consultation request.

[0052] In this embodiment, if the user's inquiry request belongs to the greeting scenario, the first response template (such as the greeting template) can be used to respond; if the user's inquiry request belongs to the refusal to answer scenario, the second response template (such as the "unable to recognize request" template) can be used to respond.

[0053] The technical solution of this embodiment adopts a pre-built knowledge base containing a database of matter circumstances, a database of matter handling information, and a database of matter consultation information. The knowledge base is retrieved to proactively inquire with users, or to provide users with recommended matters to be handled, or to prompt users to check the required materials for handling business. This solves the problem that users cannot obtain accurate business guidance information through consultation before handling business, resulting in a long and complicated business handling process. It improves the accuracy and comprehensiveness of responding to user consultation requests, thereby improving the efficiency of users' government business handling and reducing the complexity of business handling.

[0054] The technical solution of this invention involves the collection, updating, analysis, processing, use, transmission, and storage of user personal information, all of which comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security.

[0055] Figure 2 This is a schematic diagram of a response device for government affairs inquiries provided in an embodiment of the present invention. Figure 2 As shown, the device includes: an intent category determination module 210, a search result acquisition module 220, and a response result first determination module 230. Wherein:

[0056] The intent category determination module 210 is used to perform user intent identification and classification in response to the current user's current consultation request to determine the intent category of the current user;

[0057] The retrieval result acquisition module 220 is used to retrieve retrieval results from a pre-built knowledge base based on the current consultation request when the intent category belongs to government affairs processing. The pre-built knowledge base includes a matter situation database, a matter processing information database, and a matter consultation information database. The matter situation database includes a correspondence file between situation questions and situation answers. The matter processing information database includes matter processing information files categorized by matter. The matter consultation information database includes related knowledge files constructed based on historical consultations.

[0058] The response result first determination module 230 is configured to determine a response result for the current consultation request according to the search result; and the response result includes active inquiry, recommended matter, and prompt material check.

[0059] The technical scheme of the embodiment adopts a pre-constructed knowledge base including a matter situation database, a matter handling information database, and a matter consultation information database, and uses a technical means of searching the knowledge base to actively inquire the user, or provide recommended matter handling for the user, or prompt the user to check the required material for business handling, thereby solving the problem that the user cannot obtain accurate business handling information through consultation before handling the business, and the long and complex business handling process, improving the response accuracy and comprehensiveness of the user's consultation request, thereby improving the efficiency of the user's government business handling and reducing the complexity of the business handling.

[0060] Optionally, the corresponding relationship file, the matter handling information file, and the associated knowledge file are processed by segment vectorization through a specified identifier in the pre-constructed knowledge base.

[0061] The pre-constructed knowledge base supports keyword search and / or vector search.

[0062] Optionally, the intent category determination module 210 can be specifically configured to:

[0063] In response to the current consultation request, the semantic information of the current consultation request is identified;

[0064] According to the semantic information, the user intent recognition classification is performed to determine the intent category of the current user;

[0065] The intent category includes government business handling, greeting scene, and refusal scene.

[0066] Optionally, the search result acquisition module 220 can be specifically configured to:

[0067] In the case where the intent category belongs to government business handling, the current consultation request is rewritten according to the business association word to obtain a rewritten consultation request;

[0068] The search keyword and vector information matched with the rewritten consultation request are acquired;

[0069] According to the search keyword and / or the vector information, the pre-constructed knowledge base is searched to obtain a recall result;

[0070] According to the recall result, the search result is determined.

[0071] Optionally, the response result first determination module 230 can include:

[0072] a response type determining unit configured to determine a response type of the current consultation request according to the service handling related information in the search result;

[0073] a response result determining unit configured to determine a response result of the current consultation request according to a response strategy matched with the response type and in combination with the service handling related information.

[0074] Optionally, the response result determining unit can be specifically configured to:

[0075] in a case where the response type is active inquiry, determine inquiry content of the current user according to the service handling related information, and determine the inquiry content as the response result;

[0076] in a case where the response type is recommended item, generate a recommended item list according to the service handling related information, and take the recommended item list as the response result for user selection;

[0077] in a case where the response result is a prompt for material checking, generate a required material list according to the service handling related information, and take the required material list as the response result for user checking.

[0078] Optionally, the response device for government affair service consultation further comprises a response result second determining module configured to:

[0079] in a case where the intention category belongs to the greeting scenario, determine a first response template as the response result of the current consultation request;

[0080] in a case where the intention category belongs to the refusal scenario, determine a second response template as the response result of the current consultation request.

[0081] The response device for government affair service consultation provided by the embodiment can execute the response method for government affair service consultation provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0082] Figure 3 A structural schematic diagram of an electronic device 300 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers or various forms of mobile devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0083] As Figure 3As shown, the electronic device 300 includes at least one processor 301, and a memory, such as a read-only memory (ROM) 302, a random access memory (RAM) 303, etc., connected to the at least one processor 301 in communication. The memory stores computer programs executable by the at least one processor, and the processor 301 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 302 or loaded from the storage unit 308 into the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The processor 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0084] A plurality of components in the electronic device 300 are connected to the I / O interface 305, including an input unit 306, such as a keyboard, a mouse, etc., an output unit 307, such as various types of displays, a speaker, etc., a storage unit 308, such as a magnetic disk, an optical disk, etc., and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0085] The processor 301 can be various general-purpose and / or special-purpose processing components having processing and computing capabilities. Some examples of the processor 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 301 performs various methods and processes described above, such as the response method of government service consultation.

[0086] In some embodiments, the response method of government service consultation can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the processor 301, one or more steps of the response method of government service consultation described above can be performed. Alternatively, in other embodiments, the processor 301 can be configured to perform the response method of government service consultation by any other appropriate means (e.g., by means of firmware).

[0087] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0088] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0089] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0090] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0091] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0092] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0093] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0094] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method for responding to government affairs inquiries, characterized in that, include: In response to the current user's current inquiry request, user intent identification and classification are performed to determine the current user's intent category; When the intent category belongs to government affairs processing, a pre-built knowledge base is retrieved based on the current consultation request to obtain the search results; the pre-built knowledge base includes a matter situation database, a matter processing information database, and a matter consultation information database; the matter situation database includes a correspondence file between situation questions and situation answers; the matter processing information database includes matter processing information files distinguished by matter; the matter consultation information database includes related knowledge files constructed based on historical consultations; The response to the current inquiry request is determined based on the search results; The types of response results include proactive inquiries, recommendations, and prompts for material checks.

2. The method according to claim 1, characterized in that, The corresponding relationship file, the matter handling information file, and the associated knowledge file are segmented and vectorized in the pre-built knowledge base using specified identifiers. The pre-built knowledge base supports keyword retrieval and / or vector retrieval.

3. The method according to claim 1, characterized in that, In response to the current user's current inquiry request, user intent identification and classification are performed to determine the current user's intent category, including: In response to the current consultation request, identify the semantic information of the current consultation request; Based on the semantic information, user intent is identified and classified to determine the current user's intent category; The intent categories include government service processing, greeting scenarios, and refusal to answer scenarios.

4. The method according to claim 1, characterized in that, If the intent category belongs to government affairs processing, the pre-built knowledge base is searched according to the current consultation request to obtain search results, including: If the intent category belongs to government affairs processing, the current consultation request is rewritten based on business-related terms to obtain a rewritten consultation request; Obtain the search keywords and vector information matching the rewritten consultation request; Retrieve the pre-built knowledge base based on the search keywords and / or the vector information to obtain recall results; The search results are determined based on the recall results.

5. The method according to claim 1, characterized in that, Determining the response to the current inquiry request based on the search results includes: Based on the business processing association information in the search results, determine the response type for the current inquiry request; Based on the response strategy matching the response type and in conjunction with the business processing association information, the response result for the current inquiry request is determined.

6. The method according to claim 5, characterized in that, Based on the response strategy matching the response type and in conjunction with the business processing association information, the response result for the current inquiry request is determined, including: When the response type is an active inquiry, the inquiry content for the current user is determined based on the business processing association information, and the inquiry content is determined as the response result; When the response type is a recommended item, a list of recommended items is generated based on the business processing association information, and the list of recommended items is used as the response result for the user to select. If the response result prompts for material inspection, a list of required materials is generated based on the business processing related information, and the list of required materials is used as the response result for the user to check.

7. The method according to claim 3, characterized in that, Also includes: If the intent category belongs to the greeting scenario, the first response template is determined as the response result to the current consultation request; If the intent category belongs to the refusal scenario, the second response template is determined as the response result to the current consultation request.

8. A response device for government affairs inquiries, characterized in that, include: The intent category determination module is used to identify and classify user intent in response to the current user's current consultation request to determine the intent category of the current user; The search result acquisition module is used to retrieve search results from a pre-built knowledge base based on the current consultation request when the intent category belongs to government affairs processing. The pre-built knowledge base includes a matter situation database, a matter processing information database, and a matter consultation information database. The matter situation database includes a correspondence file between situation questions and situation answers. The matter processing information database includes matter processing information files categorized by matter. The matter consultation information database includes related knowledge files constructed based on historical consultations. The first response result determination module is used to determine the response result to the current consultation request based on the search results; The types of response results include proactive inquiries, recommendations, and prompts for material checks.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a method for responding to government affairs inquiries according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement a method for responding to government affairs inquiries according to any one of claims 1-7.

Images