A method and system for approval of government affairs based on intelligent automated planning processes

Abstract

This invention provides a method and system for intelligent automated planning and approval processes in government affairs, belonging to the technical field of intelligent input recommendation. The method includes acquiring material documents and form data issued by users, converting the material documents and form data into mixed data; acquiring a pre-trained government affairs big data model, extracting key information from the mixed data through the government affairs big data model; using the government affairs big data model and the MCP protocol to perform omission and completion checks, logical judgment calculations, and qualification verification on the key information to obtain target data; performing multi-dimensional analysis on the target data through the government affairs big data model and outputting multi-dimensional results; and planning an approval path based on the multi-dimensional results. This application can solve the problems of cumbersome, inefficient, insufficient automation and intelligence, and data silos in existing government affairs approval processes.

Description

Technical Field

[0001] This invention belongs to the technical field of automated process optimization, specifically relating to a method and system for approval of government intelligent automated planning processes. Background Technology

[0002] With the deepening development of "digital government" and "smart government," more and more government affairs are gradually shifting from offline window processing to online government service halls and self-service terminals. Users can submit application materials via the internet or self-service devices, while relevant departments rely on back-end business systems for approval and processing. This model greatly facilitates users, but the following prominent problems still exist: 1. Issues in the user application process: (1) Heavy burden of form filling: When handling matters, users need to fill in a large number of form fields, including identity information, enterprise information, property information, etc., which are prone to omissions and format errors.

[0003] (2) Insufficient intelligent verification: Existing systems mostly rely on basic format verification (such as ID number length, email format, and required field detection), and cannot perform in-depth logical verification. For example, it is often impossible to automatically determine whether a user meets the application requirements or whether the business scope filled in complies with industry policies.

[0004] (3) Complex material submission: Applicants need to upload multiple types of supporting materials. The existing system has difficulty in judging whether the materials are authentic and consistent with the content filled in the form, resulting in applications being frequently returned for correction.

[0005] 2. Issues in the department's back-end approval process: (1) Manual verification is time-consuming: Approval personnel need to verify the application materials item by item, compare the contents of the forms, and also call external systems to verify identity and qualifications, which consumes a lot of manpower.

[0006] (2) Cross-departmental data barriers: Data involving multiple departments such as industry and commerce, taxation, public security, and civil affairs lacks an effective interoperability mechanism in the existing system, often requiring manual offline inquiries or inter-departmental document transfers, which is inefficient.

[0007] (3) Inconsistent approval standards: Different approvers have different understandings of the policies, which may lead to different approval results for the same matter, affecting fairness and transparency.

[0008] (4) Fixed process lacks flexibility: Most government systems adopt a fixed serial process, and all applications must go through the same steps, making it impossible to dynamically adjust the path according to the completeness of materials and risk level.

[0009] 3. User experience and social impact: (1) Repeated submissions and long cycles: Users repeatedly modify and submit their work due to format errors or missing materials, which greatly prolongs the approval cycle.

[0010] (2) High pressure on the window: Although “online and mobile” services have been implemented, due to the lack of intelligence of the online system, a large number of users still need to go to the offline window for consultation and modification of materials, which increases the pressure on the window.

[0011] (3) High social costs: The manual review process consumes a lot of administrative resources. The number of approvals for high-frequency items (such as business registration, household registration certificate, and tax filing) is huge, resulting in low approval efficiency and insufficient public satisfaction.

[0012] 4. Existing intelligent systems are insufficient: Although some local government systems have introduced functions such as electronic certificate databases and OCR recognition, the following problems still exist: (1) Most of them are still at the level of auxiliary verification and have failed to truly form an automatic approval closed loop; (2) Lack of intelligent interpretation of complex policy conditions; (3) Cross-departmental data access is not smooth, making it difficult to form a unified intelligent approval system. Summary of the Invention

[0013] To address the aforementioned technical problems, this invention provides a method and system for approving intelligent and automated planning processes in government affairs, thereby resolving the issues described in the background section.

[0014] Firstly, this invention provides the following technical solution: a method for approving government affairs processes based on intelligent automated planning, comprising: Obtain the material files and form data sent by the user, and convert the material files and form data into mixed data; Obtain a pre-trained government affairs big data model, and extract key information from the mixed data using the government affairs big data model; The key information is checked for omissions and deficiencies, logically judged and calculated, and eligibility verified through the aforementioned government affairs big data model and MCP protocol to obtain the target data. The government affairs big data model is used to perform multi-dimensional analysis on the target data and output multi-dimensional results. Based on the multi-dimensional results, the approval path is planned.

[0015] Compared to existing technologies, the beneficial effects of this application are as follows: This application achieves intelligent parsing, verification, and decision generation of forms and materials through a large-scale government affairs model, reducing manual verification steps and shortening the approval cycle, especially suitable for batch processing of high-frequency, standardized matters; based on a rule engine and process orchestration engine, it realizes automatic planning and execution of approval paths, supports dynamic diversion and parallel processing, significantly improving the overall approval throughput, supports natural language input and intelligent form completion, reducing the burden on users and error rates; through material completeness scoring and intelligent correction guidance, it achieves "one-time notification, one-time correction," avoiding repeated submissions and waiting for users; it provides real-time tracking of the entire process progress, improving the transparency of government affairs and user satisfaction. It enhances the standardization and policy consistency of approvals, achieving intelligent interpretation and consistency judgment of complex policy conditions based on the semantic understanding capabilities of the large-scale model, reducing inconsistencies in approval results caused by differences in human understanding; and it solidifies approval standards through a rule engine, ensuring the standardization and uniformity of the approval process for similar matters. Break down cross-departmental data barriers and achieve intelligent collaboration. Relying on the MCP protocol, it enables unified access and context assembly of data interfaces from multiple departments, supports data sharing and exemption from material submission, and reduces duplicate submissions. Under the premise of compliance, it realizes automatic data verification and condition exemption, and promotes the implementation of "reducing materials and reducing procedures".

[0016] Preferably, the step of obtaining the material files and form data issued by the user and converting the material files and form data into mixed data specifically includes: Obtain the form fields and uploaded material files submitted by the user, and extract and transform the form fields and uploaded material files according to the prmopt prompt word rules to obtain mixed structured and unstructured data in JSON format.

[0017] Preferably, the step of extracting key information from the mixed data through the government affairs big data model includes: The government affairs big data model is used to perform semantic understanding of the context of the mixed data and extract key information from the form to obtain key information.

[0018] Preferably, the step of performing omission and completion checks, logical judgment calculations, and qualification verification on the key information through the government affairs big data model and the MCP protocol to obtain the target data includes: The key information is compared semantically and in terms of key form fields with the policy and regulation corpus using the aforementioned government affairs big data model to obtain the comparison results; If the comparison result indicates that necessary data is missing, the shared data corresponding to the missing data is obtained by calling the MCP protocol through the government affairs big data model. The missing data is then used to fill in the missing data to obtain the supplementary data. Obtain the item form field association rules in the key information, perform association calculations on the related items based on the item form field association rules and output the calculation results, and supplement the calculation structure into the completed data; Obtain the qualification verification conditions, determine whether the content in the completed data meets the qualification verification conditions, and if it does, directly output the target data.

[0019] Preferably, the multi-dimensional results include field compliance markers, material integrity scores, and risk levels.

[0020] Preferably, the step of planning the approval path based on the multi-dimensional results includes: If a field is marked as valid, the document review process begins. If a field is marked as invalid, the corresponding form rules or filling guidelines are returned to the front end through the rule engine in the government affairs big data model to remind the user to fill in the form correctly. If a field is marked as needing correction, the target form field data is obtained by calling the shared database using the MCP protocol and recommended to the user for correction. If the material completeness score is not less than the first preset score, the application will proceed to the automated approval submission node. If the material completeness score is less than the first preset score but not less than the second preset score, the application will be compared with the material list uploaded by the user and the material list required for the application, and the missing materials will be output. The missing materials will be retrieved by calling the shared database through the MCP protocol. If the missing materials can be retrieved, the application will be automatically submitted for approval. If the missing materials cannot be retrieved, the user will be prompted to upload them. If the material completeness score is less than the second preset score, the application will be deemed unqualified and the user will be informed of the list of missing materials and instructions on how to obtain them. If the risk level is low, the entire approval process will be completed automatically. If the risk level is medium, the auxiliary manual review service will be called through the MCP protocol. If the risk level is high, the compliance risk handling process will be triggered.

[0021] Secondly, the invention provides the following technical solution: a government affairs intelligent automated planning process approval system, the system comprising: The conversion module is used to obtain material files and form data issued by the user, and convert the material files and form data into mixed data. The extraction module is used to obtain the pre-trained government affairs big data model and extract key information from the mixed data through the government affairs big data model; The processing module is used to perform omission and completion checks, logical judgments and calculations, and qualification verification on the key information through the government affairs big data model and the MCP protocol to obtain the target data; The planning module is used to perform multi-dimensional analysis on the target data through the government affairs big data model and output multi-dimensional results, and plan the approval path based on the multi-dimensional results.

[0022] Preferably, the conversion module is used for: Obtain the form fields and uploaded material files submitted by the user, and extract and transform the form fields and uploaded material files according to the prmopt prompt word rules to obtain mixed structured and unstructured data in JSON format.

[0023] Thirdly, the present invention provides the following technical solution: a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for approving government affairs intelligent automated planning processes.

[0024] Fourthly, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described method for approving government affairs intelligent automated planning processes. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of the government affairs intelligent automation planning process approval method provided in Embodiment 1 of the present invention; Figure 2 This is a structural block diagram of the government affairs intelligent automated planning process approval system provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the hardware structure of a computer provided for another embodiment of the present invention.

[0027] The present invention will be further described below with reference to the accompanying drawings and description. Detailed Implementation

[0028] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain embodiments of the present invention, and should not be construed as limiting the present invention.

[0029] In the description of the embodiments of the present invention, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention.

[0030] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0031] In the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present invention according to the specific circumstances.

[0032] Example 1 In one embodiment of the present invention, such as Figure 1 As shown, a method for approval of government affairs based on intelligent automation planning processes includes: S1. Obtain the material files and form data issued by the user, and convert the material files and form data into mixed data; Specifically, step S1 is as follows: Obtain the form fields and uploaded material files submitted by the user, and extract and transform the form fields and uploaded material files according to the prmopt prompt word rules to obtain mixed structured and unstructured data in JSON format; For step S1 above, it can be implemented through a large-scale government affairs model. The large-scale government affairs model in this application is based on the Transformer architecture, with a total model parameter size of approximately 2.6 billion (2.6B). It uses mixed-precision training (FP16 + INT8) to improve inference efficiency and adopts a hybrid encoder-decoder structure design. It supports three types of tasks: Natural Language Understanding (NLU), Natural Language Generation (NLG), and structured data reasoning. The composition of its training data is shown in the table below:

[0033] All user-submitted form fields and uploaded material files (PDF, images) are converted into a mixed structured and unstructured data input. The specific conversion algorithm is as follows: the user input text is extracted by the government big data model according to the prmopt prompt word rules and then converted into the following structured JSON format. The prmopt prompt word rules are: the user will enter the form information required to handle the current matter or upload material files. Please convert the input text or materials into the following structured example format according to the input text or materials. If a user enters information into a form stating "My name is A, my ID number is B, and I live in C," the following content will be retrieved: "formItem":[ { "label": "Name", value: "A" }, { "label": "ID card number", "value": "B }, { "label": "address", value: "C" } ] }; The submitted materials can be extracted in the following format: [ { "name": "ID card", "base64": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII5" }, { "name": "Business License", "base64": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII2" }, { "name": "Tax Clearance Certificate", "base64": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYI4" } ].

[0034] S2. Obtain the pre-trained government affairs big data model, and extract key information from the mixed data through the government affairs big data model; Step S2 includes: The government affairs big data model is used to perform semantic understanding of the context of the mixed data and extract key information from the form to obtain key information.

[0035] Among them, the big model performs semantic understanding in the context of user input data and automatically extracts key information from the form (such as "operator" and "unified social credit code" in the establishment of individual business households). The government big model base is trained by learning from sample forms of the corresponding form fields, and has the ability to automatically identify form fields and their corresponding values ​​from the entire text entered by the user.

[0036] S3. The key information is checked for omissions and deficiencies, logically judged and calculated, and eligibility verified through the aforementioned government affairs big data model and MCP protocol to obtain the target data; Step S3 includes: S31. The key information is compared with the policy and regulation corpus using the aforementioned government affairs big data model, and the comparison results are obtained by semantic and key form fields. S32. If the comparison result indicates that necessary data is missing, the government affairs big data model calls the MCP protocol to obtain shared data corresponding to the missing data, and uses the shared data to fill in the missing key data to obtain the supplementary data. S33. Obtain the item form field association rules in the key information, perform association calculation on the related items based on the item form field association rules and output the calculation results, and supplement the calculation structure into the completed data; Specifically, for example, comparing the fields extracted from the above form with the corresponding form items in the corpus, the required fields are missing information such as gestational age, place of household registration, and place of permanent residence. The missing fields are supplemented in the following order: 1. At this point, the large model will prioritize obtaining the corresponding shared data by calling the corresponding MCP protocol after analysis. In this example, the data from the public security department should be called to complete the place of household registration. Specifically, the MCP protocol defines a unified data call interface, connecting heterogeneous databases from departments such as industry and commerce, taxation, public security, and civil affairs into a unified context. It also converts this cross-departmental data into context chunks, injecting them into the large model's inference input in real time. If a match is found in a user's key form field, the information is automatically corrected; if a match is found in the user's submitted materials, the material list is automatically completed. Simultaneously, it assists in automated path planning, determining which conditions have been automatically met through data sharing (e.g., a certificate of no criminal record can automatically exempt the user from uploading materials), dynamically generating "skippable steps" to reduce redundant approval processes, and providing feedback to the large model as a decision-making basis to help it plan the optimal approval path. As the context protocol layer, MCP interfaces the semantic judgment results of the large model with the business system's process orchestration engine. When external services (such as material comparison interfaces or cross-departmental data sharing interfaces) need to be called, MCP dynamically selects the microservice module to call based on the context semantics generated by the large model, ensuring a closed-loop integration between the large model's decision-making and the system's execution layer.

[0037] 2. Perform logical calculations based on the association rules of the fields in the form; for example, gestational age can be determined by the current time and the due date. 3. If the missing information cannot be completed, the system will send a feedback message to the user, who will then enter the missing information again.

[0038] S34. Obtain the qualification verification conditions, determine whether the content in the completed data meets the qualification verification conditions, and if the qualification verification conditions are met, directly output the target data. Specifically, for example, the large-scale model can enhance the retrieval of policy and regulatory guidelines, and verify the eligibility of user-input forms. For instance, for the senior citizen allowance, which requires recipients to be over 80 years old, the system will determine whether the user meets the requirements based on the information in the form. If the form cannot determine eligibility, it will call upon services corresponding to the MCP protocol to assist in the determination. For example, it can obtain ID card information through the MCP protocol to obtain information such as the user's age to assist in the determination of eligibility. The collaboration and automation of user input and services corresponding to the MCP protocol are achieved by the large-scale model automatically collaborating on the user input information to complete the eligibility review.

[0039] S4. Perform multi-dimensional analysis on the target data through the government affairs big data model and output multi-dimensional results, and plan the approval path based on the multi-dimensional results.

[0040] The multi-dimensional results include field compliance markers, material integrity scores, and risk levels.

[0041] Specifically, the aforementioned multi-dimensional results can be used for decision-making output through a large-scale government affairs model.

[0042] Step S4 includes: S41. If a field is marked as valid, the material review process will begin. If a field is marked as invalid, the corresponding form rules or filling guidelines will be returned to the front end through the rule engine in the government big data model to remind the user to fill in the correct form. If a field is marked as needing correction, the target form field data will be obtained by calling the shared database using the MCP protocol and recommended to the user for correction. Specifically, when a field is deemed invalid, the system uses a large-scale model-enhanced retrieval vector library to find the corresponding form rule. The rule engine then determines the field is invalid. At this point, the corresponding form rule or filling guide can be returned to the front end to remind the user of the correct filling method. During the model training phase, the word vector model performs vectorized embedding processing on the form rule document. The following document is a sample document summarizing the corresponding form field rules. After the user enters a question, the form field JSON is extracted, and the corresponding field validation rule is queried from the vector library based on the field name. This generates the corresponding user correction guide. For example, if the user enters: "My home address is No. 32, Zumiao Road, Chancheng District", the large model performs a structured transformation to obtain: { My registered residence is No. 32, Zumiao Road, Chancheng District. "formItem": [ { "label": "address", "value": No. 32, Zumiao Road, Chancheng District } ] } After querying the vector library, the corresponding rule is that the South China Sea region is required. Therefore, a correction guide will be generated to prompt the user that "the address contains the South China Sea region", and the front end will be returned to prompt the user to enter the information again. Meanwhile, if the data needs to be corrected, the "rule base service" and "data comparison service" are scheduled through MCP to generate a recommended correction scheme, reducing the cost of secondary input for users. The correction scheme is to use the MCP protocol to call the shared database to obtain the form field data, which is a case where the user form data is exempt from filling in, and the field values ​​conform to the corresponding rules. Specifically, for the rules engine, it internally establishes an automated approval rules library based on the Drools / JSON rules set. The output results of the large model (compliance labels, scores, risk levels) will be used as input conditions for the rules engine to automatically trigger predefined approval paths.

[0043] S42. If the material completeness score is not less than the first preset score, the application will proceed to the automated approval submission node. If the material completeness score is less than the first preset score but not less than the second preset score, the application will be compared with the material list uploaded by the user and the material list required for the application, and the missing materials will be output. The missing materials will be retrieved by calling the shared database through the MCP protocol. If the missing materials can be retrieved, the application will be automatically submitted for approval. If the missing materials cannot be retrieved, the user will be prompted to upload them. If the material completeness score is less than the second preset score, the application will be deemed unqualified and the user will be informed of the list of missing materials and instructions on how to obtain them. Specifically, when the score is not less than 95 points (out of 100), the system will enter the automated approval submission stage. When the score is between 70 and 95 points (excluding 95), the system will enter the material supplementation pending process. The large model will automatically generate a list of missing materials and predict whether the materials can be obtained through data exchange based on the resource sharing interface of the government department. If they can be obtained, the system will automatically supplement them. If not, the user will be notified to correct and supplement the materials. Specifically, the large model has been trained and learned for the list of materials required for the application. Combining the material list uploaded by the user with the list of materials required for the application, it can automatically output the missing materials. At this time, the system will first call the data sharing interface through the MCP service to retrieve the user's missing materials. If they can be obtained, the system will automatically submit the application for approval. If they cannot be obtained, the user will be reminded to upload the missing materials again. When the score is less than 70 points, the application will be judged as "unqualified". The user will be informed of the "missing list + retrieval instructions" in one go through the front end to avoid repeated submissions.

[0044] S43. If the risk level is low, the entire approval process will be completed automatically. If the risk level is medium, the auxiliary manual review service will be called through the MCP protocol. If the risk level is high, the compliance risk handling process will be triggered.

[0045] Specifically, under low-risk conditions, the system automatically completes the entire approval process (zero human intervention) and synchronizes the approval opinions to the business system. Under medium-risk conditions, the system coordinates and calls the "assisted manual review service" through MCP to highlight some fields or materials that need to be manually reviewed, allowing approvers to quickly confirm them and reducing the scope of manual judgment. The highlighted fields or materials that need to be manually reviewed are generated as follows: each time the large model analyzes user input and automatically approves, if there are cases where the compliance of a field or material cannot be automatically determined, the current field or material entered by the user will be stored in the background database. When the user completes all the steps, a risk assessment report will be generated, and non-compliant fields or materials will be retrieved from the database and marked for subsequent manual review and approval by the business department system. Under high-risk conditions, the "compliance risk handling process" is automatically triggered, pushing the case to a dedicated risk review team and attaching a risk explanation report generated by the large model (e.g., suspected forgery of materials, logical conflicts in fields, abnormalities in historical applications, etc.). For the entire approval process, after selecting a path, a "process tracking business ID" will be automatically generated. The approval results (approved, corrected, manually reviewed, risk-reviewed) will be automatically returned to the front end, allowing users to track the progress in real time and avoid the problem of "blindly waiting" in traditional approvals.

[0046] In summary, the government affairs intelligent automation planning and approval process method provided in this embodiment achieves intelligent parsing, verification, and decision generation of forms and materials through a large government affairs model, reducing manual verification steps and shortening the approval cycle. It is particularly suitable for batch processing of high-frequency, standardized matters. Based on a rule engine and process orchestration engine, it realizes automatic planning and execution of approval paths, supports dynamic diversion and parallel processing, significantly improving the overall approval throughput. It supports natural language input and intelligent form completion, reducing the burden on users and the error rate. Through material completeness scoring and intelligent correction guidance, it achieves "one-time notification and one-time correction," avoiding repeated submissions and waiting for users. It provides real-time tracking of the entire process progress, improving the transparency of government affairs and user satisfaction. It enhances the standardization and policy consistency of approval. Based on the semantic understanding capabilities of the large model, it realizes intelligent interpretation and consistency judgment of complex policy conditions, reducing inconsistencies in approval results caused by differences in human interpretation. Through the rule engine, it solidifies approval standards, ensuring the standardization and uniformity of the approval process for similar matters. Break down cross-departmental data barriers and achieve intelligent collaboration. Relying on the MCP protocol, it enables unified access and context assembly of data interfaces from multiple departments, supports data sharing and exemption from material submission, and reduces duplicate submissions. Under the premise of compliance, it realizes automatic data verification and condition exemption, and promotes the implementation of "reducing materials and reducing procedures".

[0047] Example 2 like Figure 2As shown, in Embodiment 2 of the present invention, a government affairs intelligent automated planning process approval system is provided, the system comprising: Conversion module 1 is used to obtain material files and form data issued by the user, and convert the material files and form data into mixed data; Extraction module 2 is used to obtain the pre-trained government affairs big data model and extract key information from the mixed data through the government affairs big data model; Processing module 3 is used to perform omission and completion checks, logical judgment calculations, and qualification verification on the key information through the government affairs big data model and the MCP protocol to obtain the target data; Planning module 4 is used to perform multi-dimensional analysis on the target data through the government affairs big data model and output multi-dimensional results, and plan the approval path based on the multi-dimensional results.

[0048] Wherein, the conversion module 1 is used for: Obtain the form fields and uploaded material files submitted by the user, and extract and transform the form fields and uploaded material files according to the prmopt prompt word rules to obtain mixed structured and unstructured data in JSON format.

[0049] The extraction module 2 is used for: The government affairs big data model is used to perform semantic understanding of the context of the mixed data and extract key information from the form to obtain key information.

[0050] The processing module 3 is used for: The key information is compared semantically and in terms of key form fields with the policy and regulation corpus using the aforementioned government affairs big data model to obtain the comparison results; If the comparison result indicates that necessary data is missing, the shared data corresponding to the missing data is obtained by calling the MCP protocol through the government affairs big data model. The missing data is then used to fill in the missing data to obtain the supplementary data. Obtain the item form field association rules in the key information, perform association calculations on the related items based on the item form field association rules and output the calculation results, and supplement the calculation structure into the completed data; Obtain the qualification verification conditions, determine whether the content in the completed data meets the qualification verification conditions, and if it does, directly output the target data.

[0051] The multi-dimensional results include field compliance markers, material integrity scores, and risk levels.

[0052] The planning module 4 is used for: If a field is marked as valid, the document review process begins. If a field is marked as invalid, the corresponding form rules or filling guidelines are returned to the front end through the rule engine in the government affairs big data model to remind the user to fill in the form correctly. If a field is marked as needing correction, the target form field data is obtained by calling the shared database using the MCP protocol and recommended to the user for correction. If the material completeness score is not less than the first preset score, the application will proceed to the automated approval submission node. If the material completeness score is less than the first preset score but not less than the second preset score, the application will be compared with the material list uploaded by the user and the material list required for the application, and the missing materials will be output. The missing materials will be retrieved by calling the shared database through the MCP protocol. If the missing materials can be retrieved, the application will be automatically submitted for approval. If the missing materials cannot be retrieved, the user will be prompted to upload them. If the material completeness score is less than the second preset score, the application will be deemed unqualified and the user will be informed of the list of missing materials and instructions on how to obtain them. If the risk level is low, the entire approval process will be completed automatically. If the risk level is medium, the auxiliary manual review service will be called through the MCP protocol. If the risk level is high, the compliance risk handling process will be triggered.

[0053] In other embodiments of the present invention, the present invention provides the following technical solution: a computer, including a memory 102, a processor 101, and a computer program stored on the memory 102 and executable on the processor 101, wherein the processor 101 executes the computer program to implement the above-described government affairs intelligent automated planning process approval method.

[0054] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0055] The memory 102 may include a large-capacity memory for data or instructions. For example, and not limitingly, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include removable or non-removable (or fixed) media. Where appropriate, the memory 102 may be internal or external to a data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0056] The memory 102 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101.

[0057] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the above-mentioned approval method based on the intelligent automation planning process of government affairs.

[0058] In some embodiments, the computer may further include a communication interface 103 and a bus 100. For example, Figure 3 As shown, the processor 101, memory 102, and communication interface 103 are connected through bus 100 and communicate with each other.

[0059] The communication interface 103 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0060] Bus 100 includes hardware, software, or both, that couples components of a computer device together. Bus 100 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although specific buses are described and illustrated in the embodiments of the present invention, the present invention is contemplated by any suitable bus or interconnect.

[0061] The computer can obtain the approval method based on the intelligent and automated planning process of government affairs based on the approval system, and execute the approval method based on the intelligent and automated planning process of government affairs of this invention, thereby realizing the approval based on the intelligent and automated planning process of government affairs.

[0062] In some further embodiments of the present invention, in conjunction with the above-described method for approving government affairs based on intelligent automated planning processes, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described method for approving government affairs based on intelligent automated planning processes.

[0063] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0064] More specific examples of readable media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0065] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0066] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for approving government affairs processes based on intelligent automation planning, characterized in that: include: Obtain the material files and form data sent by the user, and convert the material files and form data into mixed data; Obtain a pre-trained government affairs big data model, and extract key information from the mixed data using the government affairs big data model; The key information is checked for omissions and deficiencies, logically judged and calculated, and eligibility verified through the aforementioned government affairs big data model and MCP protocol to obtain the target data. The government affairs big data model is used to perform multi-dimensional analysis on the target data and output multi-dimensional results. Based on the multi-dimensional results, the approval path is planned.

2. The method for approval of government intelligent automated planning processes according to claim 1, characterized in that, The step of obtaining the material files and form data sent by the user and converting the material files and form data into mixed data specifically involves: Obtain the form fields and uploaded material files submitted by the user, and extract and transform the form fields and uploaded material files according to the prmopt prompt word rules to obtain mixed structured and unstructured data in JSON format.

3. The method for approval of government intelligent automated planning processes according to claim 1, characterized in that, The steps for extracting key information from the mixed data using the government affairs big data model include: The government affairs big data model is used to perform semantic understanding of the context of the mixed data and extract key information from the form to obtain key information.

4. The method for approval of government intelligent automated planning processes according to claim 1, characterized in that, The steps of using the government affairs big data model and the MCP protocol to perform missing information verification, logical judgment calculations, and qualification verification to obtain the target data include: The key information is compared semantically and in terms of key form fields with the policy and regulation corpus using the aforementioned government affairs big data model to obtain the comparison results; If the comparison result indicates that necessary data is missing, the shared data corresponding to the missing data is obtained by calling the MCP protocol through the government affairs big data model. The missing data is then used to fill in the missing data to obtain the supplementary data. Obtain the item form field association rules in the key information, perform association calculations on the related items based on the item form field association rules and output the calculation results, and supplement the calculation structure into the completed data; Obtain the qualification verification conditions, determine whether the content in the completed data meets the qualification verification conditions, and if it does, directly output the target data.

5. The method for approval of government intelligent automated planning processes according to claim 1, characterized in that, The multi-dimensional results include field compliance markers, material integrity scores, and risk levels.

6. The method for approval of government intelligent automated planning processes according to claim 5, characterized in that, The steps for planning the approval path based on the multi-dimensional results include: If a field is marked as valid, the document review process begins. If a field is marked as invalid, the corresponding form rules or filling guidelines are returned to the front end through the rule engine in the government affairs big data model to remind the user to fill in the form correctly. If a field is marked as needing correction, the target form field data is obtained by calling the shared database using the MCP protocol and recommended to the user for correction. If the material completeness score is not less than the first preset score, the application will proceed to the automated approval submission node. If the material completeness score is less than the first preset score but not less than the second preset score, the application will be compared with the material list uploaded by the user and the material list required for the application, and the missing materials will be output. The missing materials will be retrieved by calling the shared database through the MCP protocol. If the missing materials can be retrieved, the application will be automatically submitted for approval. If the missing materials cannot be retrieved, the user will be prompted to upload them. If the material completeness score is less than the second preset score, the application will be deemed unqualified and the user will be informed of the list of missing materials and instructions on how to obtain them. If the risk level is low, the entire approval process will be completed automatically. If the risk level is medium, the auxiliary manual review service will be invoked through the MCP protocol. If the risk level is high, the compliance risk handling process will be triggered.

7. A government affairs intelligent automated planning and approval process system, characterized in that, The system includes: The conversion module is used to obtain material files and form data issued by the user, and convert the material files and form data into mixed data. The extraction module is used to obtain the pre-trained government affairs big data model and extract key information from the mixed data through the government affairs big data model; The processing module is used to perform omission and completion checks, logical judgments and calculations, and qualification verification on the key information through the government affairs big data model and the MCP protocol to obtain the target data; The planning module is used to perform multi-dimensional analysis on the target data through the government affairs big data model and output multi-dimensional results, and plan the approval path based on the multi-dimensional results.

8. The government affairs intelligent automated planning and approval process system according to claim 7, characterized in that, The conversion module is used for: Obtain the form fields and uploaded material files submitted by the user, and extract and transform the form fields and uploaded material files according to the prmopt prompt word rules to obtain mixed structured and unstructured data in JSON format.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the government affairs intelligent automation planning process approval method as described in any one of claims 1 to 6.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the government affairs intelligent automated planning process approval method as described in any one of claims 1 to 6.

Images