A service requirement processing method and apparatus

Abstract

The application provides a service demand processing method and device, and the method comprises the following steps: performing semantic analysis on a service demand initiated by a user, and obtaining a scene label corresponding to the service demand based on a semantic analysis result and a pre-constructed government affair scene library; extracting each handling matter corresponding to the scene label from a government affair knowledge hub, and performing process arrangement on each handling matter according to a process rule corresponding to each handling matter; and generating a handling guidance scheme corresponding to the service demand based on a process arrangement result. According to the embodiment, the corresponding handling guidance scheme can be generated according to different service demands, so that the user can handle the corresponding service according to the handling process, required materials, handling entrance and the like indicated in the handling guidance scheme, thereby not only meeting the individualized demand of the user, but also improving the service handling efficiency.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method and apparatus for processing business requirements. Background Technology

[0002] Currently, handling cross-departmental business matters mainly requires users to check the requirements for each individual matter through the official website or offline windows, resulting in low efficiency. Furthermore, since different users have different business needs, they need to integrate the processing procedures themselves based on the business they want to handle. In cross-departmental business, there may be issues such as untimely coordination between multiple departments and differences in required materials. Users cannot promptly perceive these potential obstacles to the progress of their business, which not only fails to meet their personalized business needs but also further reduces efficiency. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide at least one business demand processing method, apparatus, electronic device, and storage medium, which can generate corresponding processing guidance schemes according to different business demands, enabling users to process corresponding businesses according to the processing procedures, required materials, and processing entry points indicated in the processing guidance schemes. This not only meets the personalized needs of users but also improves the efficiency of business processing.

[0004] In a first aspect, embodiments of the present invention provide a business requirement processing method, including: Semantic parsing is performed on user-initiated business requests, and the scene tags corresponding to the business requests are matched in a pre-built government scenario library based on the semantic parsing results. Extract each service item corresponding to the scenario tag from the government knowledge center, and arrange the process of each service item according to the process rules corresponding to each service item; Based on the process orchestration results, a processing guidance plan corresponding to business needs is generated.

[0005] Optionally, semantic parsing is performed on the user-initiated business request, and based on the semantic parsing results, scene tags corresponding to the business request are matched in a pre-built government scenario database, including: Standardize business requirements; Semantic parsing is performed on the standardized business requirements to obtain the demand subject, behavioral target, user location and user identity type in the business requirements, and intent recognition is performed on the business requirements to determine the demand classification. Based on the demand subject, behavioral goal, user location, user identity type, and demand category, the system matches the scenario tags corresponding to the business needs from a pre-built government scenario database.

[0006] Optionally, based on the process rules corresponding to each processing item, the process is arranged, including: Identify the first items with pre-conditions from all the items to be processed, determine the pre-conditions and pre-materials corresponding to each first item according to the process rules, and generate a serial processing path for each first item based on the pre-conditions, pre-materials and the corresponding departmental approval logic. Identify the second items from all the items that do not have any prerequisite conditions, and generate a parallel processing item group based on each second item; Based on the serial processing path and the parallel processing item group, the process orchestration result is generated.

[0007] Optionally, based on the process orchestration results, a processing guidance plan corresponding to business needs is generated, including: Extract the handling rules, the departments to which the matters belong, and the list of required materials corresponding to each matter from the government affairs knowledge center; Generate access links for each service item, and generate service guidance plans based on the workflow layout, service rules, department to which the service item belongs, list of required materials, and access links.

[0008] Optionally, after generating the processing guidance plan corresponding to business needs, it also includes: Call the processing synchronization interface to determine the processing progress of each item, and update the processing guidance plan based on the processing progress; Receive user inquiries regarding the guidance plan and determine the business type, issue level, department, and processing progress of each item in the inquiry. Based on the business type, issue level, department, and processing progress of each matter, the party responsible for handling the inquiry is determined, and the corresponding business knowledge base of the party responsible is used to generate the answer to the inquiry.

[0009] Optionally, the method further includes: If the business knowledge base of the processing party does not contain the answer information for the inquiry, the inquiry question, user information, scenario tags and processing progress will be pushed to the human agent terminal of the processing party according to the business type and problem level of the inquiry question. The data returned by the human agent terminal is pushed to the user as the answer to the inquiry.

[0010] Secondly, embodiments of the present invention provide a business demand processing apparatus, including: The parsing module is used to perform semantic parsing on the business requests initiated by users, and to match the scene tags corresponding to the business requests in a pre-built government scenario library based on the semantic parsing results. The orchestration module is used to extract each handling item corresponding to the scenario tag from the government knowledge center, and to orchestrate the process of each handling item according to the process rules corresponding to each handling item. The generation module is used to generate processing guidance plans that correspond to business needs based on the process orchestration results.

[0011] Thirdly, embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the first aspect or any optional implementation of the first aspect are performed.

[0012] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the first aspect or any optional implementation thereof.

[0013] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0014] In any of the above-mentioned aspects or any implementation methods, when a user submits a business request, natural language processing technology can be used to semantically analyze the user's input business request. This identifies key information such as the target of the service, the type of business, the applicant, the region, and the purpose of the service, and extracts corresponding semantic features. These semantic features are then matched with a pre-built government service scenario database to determine the scenario label corresponding to the current business request, such as scenarios related to business establishment, social security, housing security, and tax services, thereby accurately locating the user's relevant government service area. After determining the scenario label, further information such as the corresponding processing items, dependencies between items, processing conditions, required materials, processing departments, processing channels, online and offline processing entry points, processing time limits, and relevant policy basis can be extracted from the government service knowledge center. The process is then arranged according to the corresponding process rules for each processing item. When a business requires multiple prerequisites, a complete processing flow can be generated based on the sequential dependencies between items. When differences in user identity, region, or processing conditions lead to variations in the processing path, the corresponding processing branch is dynamically selected according to the process rules to form a processing flow that suits the user's current situation. Finally, based on the workflow arrangement, a processing guidance plan corresponding to the business needs can be generated. This guidance plan not only lists each processing step in sequence but also clarifies the required materials, processing conditions, processing departments, processing portals, processing methods, and precautions for each step. It also provides prompts for the next processing requirements, allowing users to complete the business process step-by-step by following the guidance plan without having to search for and organize large amounts of policy information themselves. Compared to the traditional method that relies on users manually navigating the process, this method generates targeted processing guidance plans based on the different business needs of different users. It matches government knowledge, process rules, and user needs, not only meeting the personalized processing needs of different users and reducing the understanding costs during business consultation and processing but also reducing duplicate processing caused by missing materials, process errors, or improper processing order, thus improving the efficiency and service quality of government services.

[0015] The beneficial effects of the aforementioned business requirement processing device, electronic equipment, and storage medium are described in the description of the aforementioned business requirement processing method, and will not be repeated here. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to the present invention and, together with the specification, serve to explain the technical solutions of the present invention. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 A flowchart of a business requirement processing method provided by an embodiment of the present invention is shown; Figure 2 A flowchart illustrating a business requirement processing method provided by an embodiment of the present invention is shown. Figure 3 A schematic diagram of a business demand processing device provided in an embodiment of the present invention is shown; Figure 4 An exemplary system architecture in which embodiments of the present invention can be applied is shown; Figure 5 A schematic diagram of the structure of a computer system used to implement embodiments of the present invention is shown. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations, and require notification to users and obtaining their consent or authorization. When applicable, user personal information is subjected to de-identification and / or anonymization and / or encryption technical processing.

[0020] The above problems and solutions are the result of the inventor's practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be considered as the inventor's contribution to the invention.

[0021] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0022] To facilitate understanding of this embodiment, a detailed description of a business requirement processing method disclosed in this invention will be provided first. The execution entity of the business requirement processing method provided in this invention is generally a computer device with certain computing capabilities. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, this business requirement processing method can be implemented by a processor calling computer-readable instructions stored in memory.

[0023] See Figure 1 The diagram shown is a flowchart of a business requirement processing method provided in an embodiment of the present invention. The method includes steps S101 to S103, wherein: S101: Perform semantic parsing on the business requests initiated by users, and match the scene tags corresponding to the business requests in a pre-built government affairs scene library based on the semantic parsing results.

[0024] In this embodiment of the invention, the service request initiated by the user can be any service request input by the user through natural language, such as "I want to register my newborn's birth," "What procedures are needed to start a business," "Apply for public rental housing," "Apply for retirement," "Apply for unemployment insurance," "Company deregistration," etc., or it can be a more colloquial expression, such as "What certificates are needed for a newborn child," "I want to open a restaurant," "I want to open a convenience store," etc. Alternatively, the user can also input the service request by voice. This embodiment of the invention does not specifically limit the input form of the service request. In addition, users can initiate service requests through government service applications, mini-programs, web pages, and self-service terminals.

[0025] To accurately identify the various forms of business needs mentioned above, a government service scenario database can be pre-built as a bridge between business needs and government knowledge. Specifically, based on the national and local "efficient completion of one task" reform item lists, high-frequency processing item statistics from government service platforms at all levels, and typical events in the life cycle of individuals and enterprises, government service scenarios with unified processing goals can be sorted out to determine the business scenarios that need to be included in management. Each scenario is assigned a unique scenario identifier, and standard information such as scenario category, life cycle stage, applicable objects, and applicable regions are also marked. Then, all processing items involved in completing the scenario can be extracted from the cross-departmental and cross-level item database, and categorized and aggregated according to legally mandatory items, optional items, and canceled items to form the association between scenarios and processing items. On this basis, standard definitions can be established for each scenario, including scenario name, standard description, commonly used user expressions, a thesaurus, and slot constraint information such as identity, region, and enterprise type involved in the processing process. Furthermore, a mapping relationship between user intent and scenario, synonym matching rules, and disambiguation rules can be established, enabling the execution entity of this embodiment to accurately locate the corresponding government service scenario according to different user expressions. Finally, a unified referencing relationship can be established between scenario tags and five types of knowledge bases: the item database, the processing rule database, the authority and responsibility database, the material list database, and the consultation routing database. This ensures that each scenario corresponds to a complete set of government affairs knowledge, forming a government affairs scenario database capable of supporting intelligent retrieval, process arrangement, and processing guidance. Furthermore, scenario content, thesaurus, and matching rules can be updated based on policy adjustments, item changes, and historical matching records, thereby improving the accuracy and timeliness of scenario matching.

[0026] In this embodiment of the invention, semantic parsing is performed on the business requests initiated by users, and scene tags corresponding to the business requests are matched in a pre-built government service scenario database based on the semantic parsing results. This includes: standardizing the business requests; performing semantic parsing on the standardized business requests to obtain the request subject, behavioral target, user location, and user identity type in the business requests, and performing intent recognition on the business requests to determine the request category; and matching the scene tags corresponding to the business requests in the pre-built government service scenario database based on the request subject, behavioral target, user location, user identity type, and request category.

[0027] In practice, the process begins by acquiring user-initiated business requests, such as "Recent graduates applying for local residency," "I want to open a restaurant," and "Apply for public rental housing." After obtaining these requests, they can be standardized. This includes converting different input formats, such as voice and images, into text data; standardizing special symbols, meaningless stop words, repetitive characters, and colloquial expressions within the text; and mapping different expressions like "residency registration," "household registration transfer," and "relocation" to standard business terms using a thesaurus, thus obtaining standardized business requests. Natural language processing (NLP) techniques can then be used to semantically analyze these standardized requests. Specifically, this can be achieved through word segmentation, part-of-speech tagging, and named entity recognition to extract entity information, including the requesting entity, the target behavior, the user's location, and the user's identity type. The system uses several key elements: the demand subject (representing the recipient of the service, such as individuals, businesses, or sole proprietorships), the behavioral objective (describing the government service matter the user wishes to complete, such as settling down, starting a business, or deregistering a business), the user's location (determining the administrative region to which the service pertains), and the user's identity type (identifying the user's status, such as recent graduates, veterans, self-employed individuals, or corporate entities). After extracting the entity information, the system further combines contextual semantics to perform intent recognition, determining the service demand's category, such as administrative approval, public services, social security, housing security, or enterprise services. Subsequently, the demand subject, behavioral objective, user location, user identity type, and demand category are used as multi-dimensional matching conditions. Scene matching is performed within a pre-built government service scenario database. Using the intent-scenario mapping relationship, thesaurus, slot constraints, and disambiguation rules established in the database, multiple candidate scenarios are matched and scored. The scenario with the highest matching degree is selected as the target scenario, and the corresponding scenario label is output. For example, when a user inputs "recent graduate household registration," the execution entity of this embodiment can first perform standardization processing, normalizing the business requirement to "recent graduates applying for local household registration." Then, it parses the requirement to identify the subject as "individual," the behavioral goal as "applying for household registration," the user's location as their current region (e.g., Beijing), and the user's identity type as "recent graduate," classifying the requirement as "public service." Subsequently, the above parsing results can be matched with the government service scenario database. By matching synonyms such as "graduate household registration" and "university graduate household registration transfer," and combining constraints such as "recent graduate," "applying for household registration," and the corresponding geographical restrictions of Beijing, the scenario tag corresponding to this business requirement is ultimately determined to be "university graduate household registration."

[0028] S102: Extract each handling item corresponding to the scenario tag from the government knowledge center, and arrange the process of each handling item according to the process rules corresponding to each handling item.

[0029] In this embodiment of the invention, the government knowledge hub is a knowledge center obtained by uniformly aggregating various knowledge resources in the field of government services. It is not a single database, but rather a comprehensive knowledge system formed by standardizing and integrating government information scattered across different departments and levels, using scenario tags as a unified index. After a user's business needs are matched to a specific scenario, they can quickly locate all government knowledge related to that scenario based on the scenario tags, without needing to access multiple business systems separately, thus improving knowledge retrieval efficiency and the accuracy of processing guidance. Specifically, the government knowledge hub may include the following types of knowledge bases: (1) Item Database. This database stores basic information on various government affairs matters, including item name, item number, item type, competent department, processing level, processing method, processing time limit, fee standard, and processing result, and records the relationships between different items. For example, the scenario of "university graduates settling down" can be associated with multiple matters such as household registration transfer, employment registration, and social insurance relationship transfer.

[0030] (2) Processing Rule Base. This is used to store the business rules and process rules corresponding to each processing item, including processing conditions, eligibility restrictions, processing order, prerequisite dependencies, parallel processing relationships, mutual exclusion relationships, processing time constraints, and regionally differentiated rules. For example, household registration transfers in some areas can only be processed after the user has completed employment registration, or different processing procedures are used in different regions.

[0031] (3) Departmental authority and responsibility database. This database stores the scope of responsibilities, approval authority, and division of labor information of each government department, approval agency, and window unit, clarifying which department should be responsible for accepting, reviewing, and completing each matter, thereby ensuring that matters can be accurately routed to the corresponding handling agency.

[0032] (4) Document List Database. This database stores the application materials required for each application, including the document name, type, whether it is a required document, document format requirements, validity period, acquisition method, and whether it supports automatic retrieval of electronic certificates. For example, materials such as graduation certificates, ID cards, employment contracts, and proof of residence, along with their specific requirements.

[0033] (5) Consultation routing database. This database stores the consultation channels corresponding to each service item, including consultation departments, contact numbers, online customer service, government service hall windows, self-service terminals, and frequently asked questions. When users encounter questions during the service process, it can automatically recommend the corresponding consultation entry point, improving consultation efficiency.

[0034] In addition, the government knowledge hub can further include extended knowledge resources such as policy and regulation databases, service guide databases, historical case databases, electronic certificate databases, and service portal databases. These various knowledge databases can establish relationships through a unified data model and be organized and managed using scenario tags as a unified index. This allows the implementing entity of this invention to obtain all necessary processing items, rules, materials, access points, and related policy information for a given scenario based on the scenario tags matched by the user.

[0035] In embodiments of the present invention, such as Figure 2 As shown, after extracting all processing items corresponding to a scenario from the government knowledge hub based on scenario tags, the processing items can be further arranged according to the process rules corresponding to each processing item to generate a processing flow that conforms to the actual business processing logic. Specifically, the process arrangement for each processing item according to the process rules corresponding to each processing item includes: identifying each first item with preconditions from the processing items; determining the preconditions and pre-requisite materials corresponding to each first item according to the process rules; and generating a serial processing path for each first item based on the preconditions, pre-requisite materials, and corresponding departmental approval logic; identifying each second item without preconditions from the processing items; and generating a parallel processing item group based on each second item; and generating the process arrangement result based on the serial processing path and the parallel processing item group.

[0036] In practice, the process can begin by traversing the set of processing items and reading the corresponding process rules from the processing rule base. This includes information such as dependencies between items, processing conditions, departmental approval logic, material requirements, and processing order. From this, the first items with preconditions can be identified. For each first item, its corresponding preconditions and required materials can be further analyzed. For example, a certain item may require the approval of another item before it can be processed, or specific supporting documents may be required before entering the approval process. After identifying the preconditions and required materials, the dependencies between items can be sorted based on the departmental approval logic for each item. Items with sequential dependencies are then connected in sequence to generate a corresponding serial processing path, ensuring that subsequent items can only proceed after the preconditions are completed and met. Simultaneously, the remaining processing items can be analyzed to identify second items without preconditions or dependencies. Since there are no sequential restrictions between these second items, they can be grouped into parallel processing groups, allowing multiple items to be initiated simultaneously, thereby reducing overall processing time. After constructing the serial processing path and the parallel processing item group, the generated processing process can be further validated based on the departmental responsibilities, policy constraints, and process legality rules in the processing rule base. This verifies that there are no conflicts, omissions, or violations of approval regulations among the processing items. Finally, the serial processing path and the parallel processing item group are merged to generate a complete process orchestration result.

[0037] Taking the "recent graduate household registration" application as an example, after matching the "college graduate household registration" scenario, the system can extract processing items such as household registration transfer application, employment registration, social insurance relationship transfer, and housing provident fund account transfer from the government affairs knowledge center. Among these, the household registration transfer application requires completion of employment registration and supporting documents such as graduation certificate and ID card as prerequisites. Therefore, employment registration can be identified as a prerequisite for the household registration transfer application, and a sequential processing path of "employment registration - household registration transfer application" can be generated by combining the approval logic of the public security department and the human resources department. The social insurance relationship transfer and the housing provident fund account transfer do not have a sequential dependency; both can be processed independently after meeting the basic processing conditions. Therefore, they can be grouped into the same parallel processing item group, allowing users to initiate processing simultaneously. Finally, the generated sequential processing path and the parallel processing item group can be integrated to form a process arrangement result that conforms to government affairs processing standards. This allows users to clearly understand the processing order of each item and know which items can be processed simultaneously, effectively reducing redundant trips and waiting time, and improving overall business processing efficiency.

[0038] S103: Based on the process orchestration results, generate a processing guidance plan that corresponds to business needs.

[0039] In this embodiment of the invention, after the process arrangement of each handling item is completed, a handling guidance plan corresponding to the user's business needs can be generated based on the generated process arrangement results. Specifically, generating a handling guidance plan corresponding to business needs based on the process arrangement results includes: extracting the handling rules, the department to which the item belongs, and the list of required materials corresponding to each handling item from the government knowledge center; generating a handling entry jump link corresponding to each handling item; and generating a handling guidance plan based on the process layout results, handling rules, department to which the item belongs, list of required materials, and handling entry jump link.

[0040] In practical implementation, based on the processing items in the workflow arrangement results, scenario tags can be used as indexes to extract the corresponding processing rules, the relevant departments, and the required materials list from the government knowledge center. The processing rules can include processing conditions, processing time limits, fee standards, processing methods, processing results, and precautions; the relevant departments can be used to identify the competent department or window unit responsible for accepting, reviewing, and completing the matter; the required materials list can include the name of the application materials, whether they are required, the required format, whether electronic certificates are supported, and the method of obtaining the materials. Then, the processing entry database can be further queried to generate a corresponding processing entry link for each processing item. The processing entry can be a link to the government service platform webpage, a mobile mini-program, the government service application's processing page, a self-service terminal entry, or an offline appointment window, allowing users to directly access the corresponding processing page without having to search for the processing entry again. After extracting the above information, the processing items can be organized and displayed according to the processing order determined by the workflow arrangement. For items with sequential dependencies, they can be arranged sequentially according to the serial processing path, with the corresponding prerequisites displayed in subsequent items. For items that can be processed simultaneously, they can be categorized and displayed as parallel processing groups, guiding users to process multiple items at the same time to shorten the overall processing cycle. Based on this, a complete processing guidance plan can be generated by integrating the workflow arrangement results, item processing rules, the department to which the item belongs, the list of required materials, and the entry links. This processing guidance plan not only intuitively displays the processing flow, department, materials, and entry point for each business, but also dynamically prompts the next pending items and related precautions based on the user's current processing progress, enabling users to complete the business processing item by item according to the guidance plan.

[0041] In embodiments of the present invention, such as Figure 2As shown, after generating a processing guidance plan corresponding to business needs, the user's processing process can be continuously tracked, and intelligent consultation services can be provided. Specifically, after generating a processing guidance plan corresponding to business needs, the process also includes: calling the processing synchronization interface to determine the processing progress of each item, and updating the processing guidance plan based on the processing progress; receiving user inquiries about the processing guidance plan, and determining the business type, problem level, department, and processing progress of each item in the inquiry; determining the party responsible for handling the inquiry based on the business type, problem level, department, and processing progress of each item, and generating answer information for the inquiry using the corresponding business knowledge base of the party responsible.

[0042] In practice, the latest processing status of each matter can be obtained in real time by calling the processing synchronization interface provided by the government service platform, various business departments, or the unified approval platform. This includes information such as "pending submission," "materials under review," "approved," "approved but rejected," and "completed." The processing guidance plan is then dynamically updated based on this information. When a matter is completed, it is automatically marked as completed, and subsequent matters meeting the processing conditions are updated to "pending processing." If a matter cannot be processed due to missing materials or failed review, the processing guidance plan will indicate the corresponding reasons and supplementary requirements, guiding users to complete the rectification and continue processing, ensuring that the processing guidance plan always aligns with the user's actual processing progress. Users can also initiate inquiries via text or voice while viewing the processing guidance plan or during the actual processing process. For example, during the "university graduate household registration" process, users can ask questions such as "When can I process my household registration transfer?" or "What materials do I need to submit after my employment registration is approved?" The executing entity in this embodiment of the invention can first perform semantic parsing on the consultation question to identify the corresponding business type, question level, department, and current processing progress of each matter. The business type can include policy consultation, processing procedure consultation, material consultation, and processing progress consultation. The question level can be divided into general consultation, professional consultation, or difficult consultation based on the complexity of the question. The department is matched to the corresponding competent authority such as public security, human resources and social security, and housing provident fund based on the consultation content. Simultaneously, a comprehensive analysis can be performed in conjunction with the current processing progress. For example, when a user's employment registration is not yet completed, for a consultation on "when can I apply for household registration transfer," it can be identified that household registration transfer is still subject to prerequisites. Therefore, the consultation question is routed to the business knowledge base of the public security department, and an answer is generated based on the current processing progress and the public security department's processing rules, such as "The current employment registration is not yet completed. Please complete the employment registration and pass the review first, and then submit the household registration transfer application. You need to prepare materials such as your ID card, graduation certificate, and employment certificate." If a user inquires about "how to transfer housing provident fund," the question can be routed to the housing provident fund business knowledge base to generate a corresponding answer based on the business type and department. This not only avoids providing users with generic answers irrelevant to the current stage of the process, but also provides users with more accurate and timely business guidance, improving the quality of consultation services and the overall efficiency of business processing.

[0043] In this embodiment of the invention, the method further includes: responding to the fact that the business knowledge base corresponding to the processing party does not contain answer information for the consultation question, pushing the consultation question, user information, scenario tags and processing progress to the processing party's human agent terminal according to the business type and question level of the consultation question; and pushing the data returned by the human agent terminal as answer information for the consultation question to the user.

[0044] In practice, after determining the handling party based on the business type, issue level, department, and processing progress of the inquiry, the corresponding business knowledge base of the handling party can be used to retrieve a standard answer matching the inquiry. If no corresponding answer is found in the business knowledge base, or if the confidence level of the knowledge base matching result is lower than a preset threshold, the current inquiry is determined to be unsolvable through the knowledge base, and a manual collaborative processing mechanism is initiated. Specifically, the inquiry can be routed to the corresponding department's human agent terminal based on the department to which it belongs, while simultaneously pushing relevant contextual information to the human agent, including basic user information, the scenario tag corresponding to the current business, the generated processing guidance plan, the processing progress of each item, and historical inquiry records. For example, during the process of "registering a college graduate's household registration," a user might inquire, "Do I need to transfer my social security contributions paid in another province before I can register my household registration?" Since this question involves local policy differences and there is no standard answer in the business knowledge base, the inquiry and the user's current processing progress ("employment registration completed, household registration application pending submission, social security relationship not transferred") can be simultaneously pushed to the human resources and social security department's customer service terminal. A human agent will then provide a manual response based on local policies. After processing, the human agent will return the response to the system in real time. The system will then push this response back to the user's terminal as the answer to the inquiry, and simultaneously guide the subsequent processing steps based on the current processing guidance plan, such as reminding the user that they need to complete the social security relationship transfer before proceeding to the next step. Simultaneously, information such as the inquiry question, processing department, processing time, human agent response content, and processing stage can be recorded to form an inquiry processing log, facilitating subsequent querying, auditing, and service quality analysis. Furthermore, verified human agent responses can be added to the corresponding department's business knowledge base, further improving the business knowledge base and thus increasing the coverage of intelligent Q&A.

[0045] According to a second aspect of the embodiments of the present invention, such as Figure 3 As shown, a business demand processing device 300 is provided, comprising: The parsing module 301 is used to perform semantic parsing on the business requirements initiated by the user, and to match the scene tags corresponding to the business requirements in a pre-built government scenario library based on the semantic parsing results. The orchestration module 302 is used to extract each handling item corresponding to the scenario tag from the government knowledge center, and to orchestrate the process of each handling item according to the process rules corresponding to each handling item. The generation module 303 is used to generate a processing guidance plan that corresponds to business needs based on the process orchestration results.

[0046] Optionally, the parsing module 301 is specifically used for: Standardize business requirements; Semantic parsing is performed on the standardized business requirements to obtain the demand subject, behavioral target, user location and user identity type in the business requirements, and intent recognition is performed on the business requirements to determine the demand classification. Based on the demand subject, behavioral goal, user location, user identity type, and demand category, the system matches the scenario tags corresponding to the business needs from a pre-built government scenario database.

[0047] Optionally, the orchestration module 302 is specifically used for: Identify the first items with pre-conditions from all the items to be processed, determine the pre-conditions and pre-materials corresponding to each first item according to the process rules, and generate a serial processing path for each first item based on the pre-conditions, pre-materials and the corresponding departmental approval logic. Identify the second items from all the items that do not have any prerequisite conditions, and generate a parallel processing item group based on each second item; Based on the serial processing path and the parallel processing item group, the process orchestration result is generated.

[0048] Optionally, the generation module 303 is specifically used for: Extract the handling rules, the departments to which the matters belong, and the list of required materials corresponding to each matter from the government affairs knowledge center; Generate access links for each service item, and generate service guidance plans based on the workflow layout, service rules, department to which the service item belongs, list of required materials, and access links.

[0049] Optionally, the device further includes a consultation module 304; the consultation module 304 is specifically used for: Call the processing synchronization interface to determine the processing progress of each item, and update the processing guidance plan based on the processing progress; Receive user inquiries regarding the guidance plan and determine the business type, issue level, department, and processing progress of each item in the inquiry. Based on the business type, issue level, department, and processing progress of each matter, the party responsible for handling the inquiry is determined, and the corresponding business knowledge base of the party responsible is used to generate the answer to the inquiry.

[0050] Optionally, the consultation module 304 is also used for: If the business knowledge base of the processing party does not contain the answer information for the inquiry, the inquiry question, user information, scenario tags and processing progress will be pushed to the human agent terminal of the processing party according to the business type and problem level of the inquiry question. The data returned by the human agent terminal is pushed to the user as the answer to the inquiry.

[0051] According to a third aspect of the present invention, an electronic device for processing business requirements is provided, comprising: one or more processors; and a storage device for storing 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 provided in the first aspect of the present invention.

[0052] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0053] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0054] Figure 4 An exemplary system architecture 400 is shown that can be applied to the business demand processing method or business demand processing apparatus of the present invention.

[0055] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, and 403, a network 404, and a server 405. Network 404 serves as the medium for providing communication links between terminal devices 401, 402, and 403 and server 405. Network 404 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0056] Users can use terminal devices 401, 402, and 403 to interact with server 405 via network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, and 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0057] Terminal devices 401, 402, and 403 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0058] Server 405 can be a server that provides various services, such as a backend management server that supports shopping websites browsed by users using terminal devices 401, 402, and 403 (for example only). The backend management server can process received business request processing requests and feed back the processing results (for example only) to the terminal devices.

[0059] It should be noted that the business requirement processing method provided in the embodiments of the present invention is generally executed by server 405, and correspondingly, the business requirement processing device is generally located in server 405. The business requirement processing method provided in the embodiments of the present invention can also be executed by terminal devices 401, 402, and 403, and correspondingly, the business requirement processing device can be located in terminal devices 401, 402, and 403.

[0060] It should be understood that Figure 4 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.

[0061] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing a terminal device of the present invention. Figure 5 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0062] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0063] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0064] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0065] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0066] 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 invention. 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.

[0067] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor. For example, a processor may include a parsing module, an orchestration module, and a generation module. The names of these modules do not necessarily limit the module itself. For instance, the parsing module can be described as "a module that performs semantic parsing on user-initiated business requests and matches the results of the semantic parsing against a pre-built government scenario database to obtain scenario tags corresponding to the business requests."

[0068] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device implements the following method: semantically parsing a user-initiated business request, and matching the scene tag corresponding to the business request with a pre-built government affairs scene library based on the semantic parsing result; extracting each handling item corresponding to the scene tag from the government affairs knowledge center, and arranging the process of each handling item according to the process rules corresponding to each handling item; and generating a handling guidance scheme corresponding to the business request based on the process arrangement result.

[0069] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for processing business requirements, characterized in that, include: The system performs semantic parsing on user-initiated business requests and matches the corresponding scenario tags in a pre-built government scenario database based on the semantic parsing results. Extract each handling item corresponding to the scenario label from the government knowledge center, and arrange the process of each handling item according to the process rules corresponding to each handling item; Based on the process orchestration results, a processing guidance plan corresponding to the business requirements is generated.

2. The method according to claim 1, characterized in that, The system performs semantic parsing on user-initiated business requests and, based on the semantic parsing results, matches the corresponding scenario tags in a pre-built government scenario database, including: The aforementioned business requirements are standardized. Semantic parsing is performed on the business requirements after the standardization process to obtain the demand subject, behavioral target, user location and user identity type in the business requirements, and intent recognition is performed on the business requirements to determine the demand category of the business requirements; Based on the demand subject, behavioral target, user location, user identity type, and demand category, the scenario tags corresponding to the business demand are matched in a pre-built government affairs scenario library.

3. The method according to claim 1, characterized in that, Based on the process rules corresponding to each matter, the process for each matter is arranged, including: From all the processing items, identify the first items that have prerequisite processing conditions, determine the prerequisite items and prerequisite materials corresponding to each first item according to the process rules, and generate a serial processing path for each first item based on the prerequisite items, prerequisite materials and corresponding departmental approval logic; Identify the second items from all the items that do not have any prerequisite conditions, and generate a parallel processing item group based on each second item; Based on the serial processing path and the parallel processing item group, a process orchestration result is generated.

4. The method according to claim 1, characterized in that, Based on the process orchestration results, a processing guidance plan corresponding to the aforementioned business requirements is generated, including: Extract the handling rules, the department to which the matter belongs, and the list of required materials corresponding to each matter from the government knowledge center; Generate access links for each service item, and generate the service guidance plan based on the process layout, service rules, department to which the service item belongs, list of required materials, and access links.

5. The method according to any one of claims 1-4, characterized in that, After generating the processing guidance plan corresponding to the aforementioned business requirements, the process also includes: The processing synchronization interface is called to determine the processing progress of each item, and the processing guidance plan is updated based on the processing progress. Receive inquiries from users regarding the processing guidance plan, and determine the business type, problem level, department, and processing progress of each matter in the inquiry; Based on the business type, issue level, department, and processing progress of each matter, the party responsible for handling the inquiry is determined, and the answer to the inquiry is generated using the business knowledge base corresponding to the party responsible.

6. The method according to claim 5, characterized in that, The method further includes: If the business knowledge base corresponding to the processing party does not contain the answer information for the consultation question, the consultation question, user information, scenario tags and processing progress are pushed to the human agent terminal of the processing party according to the business type and question level of the consultation question. The data returned by the human agent terminal is pushed to the user as the answer to the inquiry.

7. A method for processing business requirements, characterized in that, include: The parsing module is used to perform semantic parsing on the business requirements initiated by the user, and to match the scene tags corresponding to the business requirements in a pre-built government affairs scene library based on the semantic parsing results. The orchestration module is used to extract each handling item corresponding to the scenario tag from the government knowledge center, and to orchestrate the process of each handling item according to the process rules corresponding to each handling item. The generation module is used to generate a processing guidance plan corresponding to the business requirements based on the process orchestration results.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images