An intelligent auxiliary examination and approval system and method based on natural resource business

Abstract

This invention discloses an intelligent auxiliary approval system and method based on natural resource business, belonging to the field of business approval technology. The key technical points include the following steps: obtaining basic information of the target approval item; extracting approval data of similar historical approval items based on the basic information of the target approval item; if the material completeness of the approval data of similar historical approval items is unstable at different approval stages, then extracting the impact of material completeness changes on approval efficiency to obtain a first approval correlation coefficient; if the material completeness of the approval data of similar historical approval items is stable at different approval stages, then extracting the impact of different approval stages on the accuracy of the approval result to obtain a second approval correlation coefficient; and extracting the impact of different approval standard adaptability on approval compliance to obtain a third approval correlation coefficient. The effect is to improve approval efficiency and quality.

Description

Technical Field

[0001] This invention relates to the field of business approval technology, and more specifically, to an intelligent auxiliary approval system and method based on natural resource business. Background Technology

[0002] The traditional approval model in the field of full-service natural resource approval has many drawbacks. Data accumulated from similar approval matters in the past is often simply stored without in-depth analysis or effective utilization, failing to provide valuable reference for current approval work. This makes each approval process feel like a completely new undertaking, lacking the ability to learn from historical experience and patterns, which is detrimental to improving approval quality and efficiency. Furthermore, there is a lack of analysis and response mechanisms for changes in the completeness of materials at different stages of the approval process. Approval strategies cannot be adjusted accordingly based on these changes, thus hindering the optimization and development of the approval process. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of this invention is to provide an intelligent auxiliary approval system and method based on natural resource business.

[0004] To achieve the above objectives, the present invention provides the following technical solution: An intelligent assisted approval method based on natural resource business, the method includes the following steps: Obtain basic information about the target approval item, and extract approval data of similar historical approval items based on the basic information of the target approval item; If the completeness of materials for similar approval items in the past is unstable at different approval stages, the impact of changes in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient. If the completeness of materials for similar approval items in history is stable at different approval stages, then the impact of different approval stages on the accuracy of approval results is extracted to obtain the second approval correlation coefficient, and the impact of the adaptability of different approval standards on approval compliance is extracted to obtain the third approval correlation coefficient. Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, and combined with the completeness of materials and the status of different approval stages in the approval process of the target approval item, the approval status value is obtained. The approval process for the target approval item is adjusted based on the approval status value to obtain an optimized approval execution plan.

[0005] Preferably, the method further includes the following steps: Receive target approval items uploaded by users through the existing approval system; Automatically identify and verify the compliance of target approval items to determine whether the content of the documents is consistent with the requirements of the application section; Structured approval data is obtained by extracting content from target approval items that have undergone standardized verification. The structured approval data is checked for consistency and compliance with the pre-set digital review rules to generate auxiliary review opinions.

[0006] Preferably, the target approval items are automatically identified and their compliance is checked to determine whether the document content is consistent with the requirements of the application section. This specifically includes the following steps: Use image recognition and / or text analysis technologies to identify the substantive content of the target approval items; The identified document content is matched with the preset document types for the application section to determine whether the document content meets the section requirements.

[0007] Preferably, the impact of changes in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient, which specifically includes the following steps: Under the condition that the completeness of materials at different stages of the approval process for similar historical approval items is unstable and fluctuating, the approval efficiency data for the same type of approval stage in the historical approval process is obtained. The first approval correlation coefficient is obtained by extracting the correlation between changes in material completeness and approval efficiency based on approval efficiency data and the degree of change in material completeness.

[0008] Preferably, the second approval correlation coefficient is obtained by extracting the impact of different approval stages on the accuracy of the approval result, specifically including the following steps: To obtain accurate data on the approval results of the same type of approval at different stages of the approval process for similar historical approval items, given that the completeness of materials at different approval stages remains stable. The second approval correlation coefficient is obtained by extracting the impact of different approval stages on the approval results based on the accuracy of the approval results data and the completeness and stability of the materials.

[0009] Preferably, the third approval correlation coefficient is obtained by extracting the impact of the adaptability of different approval standards on approval compliance, specifically including the following steps: Collect the set of approval standards applicable to each approval stage in historical similar approval items and the corresponding approval compliance judgment results, and classify the approval compliance judgment results into fully compliant, partially compliant and non-compliant. Adaptability vector coding is applied to the set of approval standards. The coding dimensions include the matching degree between the standards and the applicable scenario parameters of the current approval items, the constraint threshold of standard elements, the fit of the application data, and the degree of coordination of related approvals. A mapping model is constructed based on the results of adaptive vector coding and the results of approval compliance determination; The set of approval standards for the target approval items is input into the trained mapping model to obtain the influence weight value of each standard on approval compliance. Based on the influence weight value, the comprehensive influence coefficient of the adaptability of different approval standards on approval compliance is extracted to obtain the third approval correlation coefficient.

[0010] Preferably, based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, and combined with the completeness of materials and the status of different approval stages in the approval process for the target approval item, an approval status value is derived, specifically including the following steps: Configure dynamic weight coefficients for the correlation coefficients of the first approval, the second approval, and the third approval, respectively; An approval status value calculation model is established. The approval status value calculation model adopts a multi-dimensional weighted fusion algorithm. The first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient are multiplied by their respective dynamic weight coefficients and then introduced into the scenario adaptation correction factor for calibration. The scenario adaptation correction factor is calculated based on the matching degree between the resource type of the target approval item and the type of similar historical items. The initial approval status value is output through the approval status value calculation model, and the initial approval status value is then processed by interval mapping: the initial value is mapped to the quantization interval; The mapped approval status value is validated. The validation process incorporates real-time feedback data from the approval process. If the real-time feedback data exceeds a preset dynamic threshold, the approval status value is iteratively corrected. The correction magnitude is positively correlated with the degree of abnormality in the real-time feedback data. Finally, the validated approval status value is output.

[0011] Preferably, the optimized approval execution plan is obtained by adjusting the approval process for the target approval item based on the approval status value, specifically including the following steps: Based on the quantitative range matching of approval status values, corresponding basic adjustment strategies are implemented. Input the approval node ID, resource usage parameters, and standard reference number involved in each adjustment strategy into the strategy conflict detection model to obtain the logical conflict index between strategies, and verify the synergy of the basic adjustment strategies based on the logical conflict index; After the basic adjustment strategy is verified for collaboration, an approval execution plan is generated, which includes a process node sequence diagram, a resource configuration list, and a standard adaptation comparison table.

[0012] An intelligent auxiliary approval system based on natural resource business includes: Acquisition module: Acquires basic information about the target approval item and extracts approval data of similar historical approval items based on the basic information of the target approval item; First processing module: If the completeness of materials for the approval data of similar historical approval items is unstable and fluctuating at different approval stages, the impact of the change in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient. The second processing module: If the completeness of materials for the approval data of similar historical approval items is stable and fluctuating at different approval stages, then the impact of different approval stages on the accuracy of the approval results is extracted to obtain the second approval correlation coefficient, and the impact of the adaptability of different approval standards on the approval compliance is extracted to obtain the third approval correlation coefficient. The third processing module: Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, combined with the completeness of materials and the status of different approval stages in the approval process of the target approval item, the approval status value is obtained; Output module: Adjusts the approval process of the target approval item based on the approval status value to obtain an optimized approval execution plan.

[0013] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent auxiliary approval method based on natural resource business.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention, at the level of data utilization and correlation analysis, acquires basic information about the target approval item and extracts historical similar approval data. This allows for the full exploration of past approval experiences and patterns, providing strong data support for current approvals. Different approval correlation coefficients are extracted for different changes in material completeness, enabling refined analysis of approval influencing factors. If the material completeness of historical similar approval items shows unstable changes, the impact of material completeness changes on approval efficiency is extracted to obtain the first approval correlation coefficient, which can effectively optimize approval efficiency. If material completeness shows stable changes, the impact of different approval stages on the accuracy of approval results is extracted to obtain the second approval correlation coefficient, and the impact of different approval standard adaptability on approval compliance is extracted to obtain the third approval correlation coefficient, comprehensively improving approval quality from dimensions such as the accuracy and compliance of approval results. Based on these approval correlation coefficients, an approval status value is obtained, which comprehensively and accurately reflects the overall situation of the target approval item during the approval process due to material completeness and different approval stages, providing a basis for subsequent adjustments to the approval process. The approval process for target approval items is adjusted based on the approval status value to obtain an optimized approval execution plan, which improves the intelligence and efficiency of the approval process, reduces errors and inefficiencies that may be caused by manual intervention, promotes a more standardized and smoother operation of the entire natural resource business approval process, improves approval efficiency and quality, and provides strong support for the digital transformation of administrative approval. Attached Figure Description

[0015] Figure 1 This invention provides a schematic diagram illustrating the steps of an intelligent assisted approval method based on natural resource business. Figure 2 This invention presents a schematic diagram of a module for an intelligent auxiliary approval system based on natural resource business. Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0016] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0020] Reference Figures 1-3 As shown.

[0021] The embodiments further illustrate the intelligent auxiliary approval system and method based on natural resource business proposed in this invention.

[0022] An intelligent assisted approval method based on natural resource business, the method includes the following steps: Obtain basic information about the target approval item, and extract approval data of similar historical approval items based on the basic information of the target approval item; The basic information includes the approval business line identifier, item code and processing level, and initial status identifier for the item. The approval business line identifier clearly identifies the business area to which the target approval item belongs, such as construction land approval, new mining rights approval, surveying and mapping qualification application, and farmland protection project filing. The item code and processing level include the official unique code and processing level of the approval item, ensuring that the extracted historical data is consistent with the current approval's processing authority and process standards. The initial status identifier for the item includes the initial status information for new applications, resubmissions after corrections, and objection reviews.

[0023] If the completeness of materials for similar approval items in the past is unstable at different approval stages, the impact of changes in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient. If the completeness of materials for similar approval items in history is stable at different approval stages, then the impact of different approval stages on the accuracy of approval results is extracted to obtain the second approval correlation coefficient, and the impact of the adaptability of different approval standards on approval compliance is extracted to obtain the third approval correlation coefficient. Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, and combined with the completeness of materials and the status of different approval stages in the approval process of the target approval item, the approval status value is obtained. The approval process for the target approval item is adjusted based on the approval status value to obtain an optimized approval execution plan.

[0024] It also includes the following steps: Receive target approval items uploaded by users through the existing approval system; Automatically identify and verify the compliance of target approval items to determine whether the content of the documents is consistent with the requirements of the application section; Structured approval data is obtained by extracting content from target approval items that have undergone standardized verification. The structured approval data is checked for consistency and compliance with the pre-set digital review rules to generate auxiliary review opinions.

[0025] The first step involves receiving target approval items uploaded by users through existing approval systems. Existing natural resource approval systems, such as the BPMS-based integrated platform, already support online applications. When an applicant submits a construction land planning permit application, they upload electronic materials online, including the construction land planning permit application form, business license, and planned land boundary map, and fill in basic form information. At this point, the unified access gateway receives these electronic materials and task data for target approval items in real time through a standardized API interface. Simultaneously, using message queues or HTTP callback mechanisms, it synchronizes the data to the AI ​​intelligent assistance system, ensuring timely and complete data transmission and avoiding information gaps caused by data silos between systems. The automatic identification and standardization verification of target approval items is led by a standardization verification engine. This engine incorporates multiple material recognition models, conducting verification from three dimensions: document type matching, content clarity, and completeness of key elements. Taking the review of legal representative's ID card materials as an example, the engine initially locates the material type based on the catalog tags of the uploaded materials, such as the legal person identity certificate section. Then, it uses image recognition technology to determine whether the actual content of the document is an ID card, such as recognizing the front and back features and anti-counterfeiting marks. At the same time, it checks whether the image clarity meets the requirements for subsequent OCR recognition, whether the ID card validity period is within the valid range, and whether it contains key elements such as name and ID number. If it finds that the uploaded image is an incorrect company logo image or the ID card image is blurry or does not meet the clarity standards, the engine will automatically mark it as non-standard and highlight the warning in the auxiliary decision-making interaction interface. This step can reduce the workload of manual review by about 60%, effectively improve the quality of received documents, and avoid subjective bias and omissions in manual review.

[0026] Structured approval data is obtained by extracting content from target approval items that have passed standardization verification. This process is completed collaboratively by a document parsing engine and an information extraction and filling engine, resolving the bottleneck of the existing system's heavy reliance on manual data entry. The document parsing engine first categorizes and processes the materials that have passed standardization verification. For scanned documents, such as the planning land boundary map title block, it uses OCR services to extract text information. For structured documents, such as PDF business licenses, it directly parses the content and identifies non-text elements such as tables and seals. Subsequently, the information extraction and filling engine, based on pre-configured field mapping rules (such as mapping the company name in the business license to the applicant unit field in the approval form), and combined with natural language understanding technology, accurately extracts key information. This includes extracting the unified social credit code and legal representative's name from the business license, the approval document number and project name from the project approval document, and even identifying the land area and drawing number from the planning land boundary map title block. This extracted information is then backfilled into the form fields of the original approval system in a structured format, such as JSON. This step can reduce the manual data entry time for a single transaction by more than 80%, eliminating data errors caused by manual input from the source.

[0027] The system performs consistency checks and compliance checks on structured approval data against pre-defined digital review rules to generate auxiliary review opinions. These are executed separately by a consistency check engine and a compliance screening engine, addressing the difficulties in consistency checks and the lack of digitization of key review points in existing systems. The consistency check engine calls upon an expandable consistency rule library, automatically comparing the same key information in different materials. Taking the approval of a construction land planning permit as an example, the engine executes rules such as the project name in the application form must be equal to the project name in the project approval document, and the land area in the application form must be substantially consistent with the land area in the red line map label, allowing for minor calculation errors. If it finds that the project name in the application form is Project A while the project approval document also lists Project A, it automatically marks the difference and lists details. The compliance screening engine connects to a structured review key point knowledge base, matching extracted project attributes such as land use nature (Class II residential land) and plot ratio ≤ 2.5 with digital rules. For example, it calls the construction land planning permit - residential land rule library to check whether the land use nature is within the Class I or Class II residential land range and whether the plot ratio is ≤ 3.0. Information not extracted, such as building density, is marked as pending review. The system integrates the results of two verification checks to generate an intelligent auxiliary review report, which clearly lists the approved items, warning items, and items requiring manual review. This provides decision-making basis for approvers. This step can improve the accuracy of consistency review to over 95% and the coverage of core review points to 100%, effectively avoiding review omissions caused by personnel's lack of business knowledge or negligence.

[0028] The system automatically identifies and verifies the compliance of target approval items to determine whether the content of the documents is consistent with the requirements of the application section. This includes the following steps: Use image recognition and / or text analysis technologies to identify the substantive content of the target approval items; The identified document content is matched with the preset document types for the application section to determine whether the document content meets the section requirements.

[0029] Image recognition and text analysis technologies are used to identify the substantive content of the target approval items. The identification results are then matched with the preset document types in the application section to determine whether the document content meets the requirements. When a company submits materials including an application form, business license, and planning red line map, image recognition technology is used to process the scanned copy of the business license to extract key information such as the company name and unified social credit code. Text analysis technology is used to parse the title page content of the planning red line map to obtain information such as land area and drawing number. The identified document content is then matched with the preset document types in the construction land planning permit application section. For example, if the enterprise qualification certificate section requires a business license, the identified business license information matches, indicating that the material meets the requirements. Similarly, if the project planning drawings section requires planning red line maps and other related drawings, the identified planning red line map information also matches successfully, thus confirming that the document content meets the requirements.

[0030] The impact of changes in material completeness on approval efficiency is then extracted to obtain the first approval correlation coefficient, which specifically includes the following steps: Under the condition that the completeness of materials at different stages of the approval process for similar historical approval items is unstable and fluctuating, the approval efficiency data for the same type of approval stage in the historical approval process is obtained. The first approval correlation coefficient is obtained by extracting the correlation between changes in material completeness and approval efficiency based on approval efficiency data and the degree of change in material completeness.

[0031] When the completeness of materials for similar historical approval matters fluctuates at different approval stages, we obtain approval efficiency data for the same type of approval stage in historical similar approval matters. Based on this approval efficiency data and the degree of change in material completeness, we extract the correlation between changes in material completeness and approval efficiency, thus obtaining the first approval correlation coefficient. Assuming that historically, in the material review stage of such applications, some cases submitted complete materials from the outset, resulting in quick approval; while others required multiple supplementary materials, leading to longer approval times—that is, the completeness of materials fluctuated. In this case, we obtain the approval efficiency data for all historical construction land planning permit applications at the material review stage, such as the time spent at this stage for each case. Then, we determine the degree of change in material completeness in these cases, such as the number of times materials were supplemented and the key content involved in the supplementary materials. Combining this with the approval efficiency data, we explore how changes in material completeness affect approval efficiency; for example, do cases with more supplementary materials take longer to approve? We extract the correlation between changes in material completeness and approval efficiency, ultimately obtaining the first approval correlation coefficient. The first approval correlation coefficient reflects the degree of correlation between changes in material completeness and approval efficiency, providing a basis for efficiency evaluation of subsequent related approval work.

[0032] The second approval correlation coefficient is obtained by extracting the impact of different approval stages on the accuracy of the approval results. This involves the following steps: To obtain accurate data on the approval results of the same type of approval at different stages of the approval process for similar historical approval items, given that the completeness of materials at different approval stages remains stable. The second approval correlation coefficient is obtained by extracting the impact of different approval stages on the approval results based on the accuracy of the approval results data and the completeness and stability of the materials.

[0033] When the completeness of materials for similar historical approval matters remains relatively stable across different approval stages, we obtain the accuracy data of approval results for the same type of approval stage within those same historical approval matters. Based on this accuracy data and the stability of material completeness, we extract the impact of different approval stages on the approval results to obtain a second approval correlation coefficient. Assuming that historically, the completeness of materials for such applications has remained relatively stable across different approval stages (material review, on-site verification, etc.), for example, the material review stage mainly involves supplementing incomplete forms, while the on-site verification stage mainly involves supplementing explanatory materials that do not match the actual site, and the changes are relatively stable. In this case, we obtain the accuracy data of approval results for all historical construction land planning permit applications at the same type of approval stage, such as the material review stage and the on-site verification stage. For example, we obtain the number of cases where the approval judgment was accurate at the material review stage and the number of cases where the approval judgment was accurate at the on-site verification stage. We then combine this with the stability of material completeness to determine how different approval stages affect the accuracy of the approval results, such as the degree of influence of the material review stage on the accuracy of subsequent approval results, and the role of the on-site verification stage. By this determination, we extract the impact of different approval stages on the approval results to obtain the second approval correlation coefficient, which reflects the correlation between different approval stages and the accuracy of approval results.

[0034] The impact of different approval standard adaptability on approval compliance is extracted to obtain the third approval correlation coefficient, which specifically includes the following steps: Collect the set of approval standards applicable to each approval stage in historical similar approval items and the corresponding approval compliance judgment results, and classify the approval compliance judgment results into fully compliant, partially compliant and non-compliant. Adaptability vector coding is applied to the set of approval standards. The coding dimensions include the matching degree between the standards and the applicable scenario parameters of the current approval items, the constraint threshold of standard elements, the fit of the application data, and the degree of coordination of related approvals. A mapping model is constructed based on the results of adaptive vector coding and the results of approval compliance determination; The set of approval standards for the target approval items is input into the trained mapping model to obtain the influence weight value of each standard on approval compliance. Based on the influence weight value, the comprehensive influence coefficient of the adaptability of different approval standards on approval compliance is extracted to obtain the third approval correlation coefficient.

[0035] The system collects the set of approval standards applicable to each stage of similar historical approval items, along with the corresponding approval compliance judgment results. These compliance judgment results are categorized as fully compliant, partially compliant, and non-compliant. The set of approval standards is then subjected to adaptability vector coding, with coding dimensions covering the matching degree between the standards and the applicable scenario parameters of the current approval item, the standard element constraint thresholds, the suitability of the submitted data, and the degree of synergy between related approvals. A mapping model is constructed based on the adaptability vector coding results and the approval compliance judgment results. The set of approval standards for the target approval item is input into the trained mapping model to obtain the influence weight values ​​of each standard on approval compliance. Based on these influence weight values, a comprehensive influence coefficient of the adaptability of different approval standards on approval compliance is extracted, thus obtaining the third approval correlation coefficient.

[0036] This process involves collecting a set of approval standards applied to such applications throughout history, covering stages such as document review and on-site verification. For example, standards for application form completion and business license validity during document review, and standards for land use consistency with planning boundaries and site construction conditions during on-site verification. Corresponding compliance judgments are also collected; some applications fully comply with all standards and are deemed fully compliant, some have minor issues and are deemed partially compliant, and others have serious discrepancies and are deemed non-compliant. Adaptability vector coding is applied to these sets of approval standards. For instance, the matching degree between the application form completion standards during document review and applicable scenario parameters such as the current application project's location and scale is analyzed. The constraint thresholds for the completeness and accuracy of the information provided, the fit between the submitted application data and the standards, and the synergy with subsequent planning and construction permit approvals are also coded. Based on these coding results and approval compliance judgment results, a mapping model is constructed. The current set of approval standards is input into the trained mapping model to obtain the influence weight values ​​of each standard on approval compliance, such as application form completion specifications and business license validity. For example, the standard of consistency between planning red lines and land use scope has a high influence weight, indicating its significant impact on approval compliance. Finally, based on these influence weight values, a comprehensive influence coefficient on approval compliance of different approval standard adaptability is extracted, resulting in the third approval correlation coefficient. This coefficient reflects the overall influence of the adaptability of various approval standards on approval compliance, providing a basis for the compliance assessment of the current application.

[0037] Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, and combined with the completeness of materials and the status of different approval stages in the approval process for the target approval item, the approval status value is derived, specifically including the following steps: Configure dynamic weight coefficients for the correlation coefficients of the first approval, the second approval, and the third approval, respectively; An approval status value calculation model is established. The approval status value calculation model adopts a multi-dimensional weighted fusion algorithm. The correlation coefficients of the first approval, the second approval, and the third approval are multiplied by their respective dynamic weight coefficients and then introduced into the scenario adaptation correction factor for calibration. The scenario adaptation correction factor is calculated based on the matching degree between the resource type of the target approval item and the type of similar historical items. The initial approval status value is output through the approval status value calculation model, and the initial approval status value is then processed by interval mapping: the initial value is mapped to the quantization interval; The mapped approval status value is validated. The validation process incorporates real-time feedback data from the approval process. If the real-time feedback data exceeds a preset dynamic threshold, the approval status value is iteratively corrected. The correction magnitude is positively correlated with the degree of abnormality in the real-time feedback data. Finally, the validated approval status value is output.

[0038] First, dynamic weight coefficients are configured for the first, second, and third approval correlation coefficients. Next, an approval status value calculation model is established. This model uses a multi-dimensional weighted fusion algorithm to multiply each of the three approval correlation coefficients by its respective dynamic weight coefficient, and introduces a scenario adaptation correction factor for calibration. This scenario adaptation correction factor is calculated based on the type matching degree between the resource type of the target approval item and similar historical items. Then, the approval status value calculation model outputs an initial approval status value, which is then subjected to interval mapping to a specific quantification range. The mapped approval status value is validated, incorporating real-time feedback data from the approval process. If the real-time feedback data exceeds a preset dynamic threshold, the approval status value is iteratively corrected. The correction magnitude is positively correlated with the degree of anomaly in the real-time feedback data. Finally, the validated approval status value is output.

[0039] Dynamic weight coefficients are assigned to the first, second, and third approval correlation coefficients. For example, a higher dynamic weight coefficient is assigned to the first approval correlation coefficient, which is related to approval efficiency, based on the current priority of the approval task. A multi-dimensional weighted fusion algorithm is used to multiply each of the three correlation coefficients by its respective dynamic weight coefficient, and then a scenario adaptation correction factor is introduced for calibration. This scenario adaptation correction factor is calculated by comparing the type matching degree between the current application for construction land and historical applications for residential land planning permits. After obtaining the initial approval status value through the approval status value calculation model, it is mapped to a quantization range, for example, from 0 to 100. Real-time feedback data from the approval process is introduced for verification. If real-time feedback data during the material review stage shows that the frequency of supplementary materials is much higher than the preset dynamic threshold, it indicates an anomaly. The approval status value is iteratively corrected according to the degree of anomaly; the higher the degree of anomaly, the greater the correction. Finally, a verified approval status value is output, thus more accurately reflecting the status of the current approval matter.

[0040] The optimized approval execution plan is obtained by adjusting the approval process for the target approval item based on the approval status value, which includes the following steps: Based on the quantitative range matching of approval status values, corresponding basic adjustment strategies are implemented. Input the approval node ID, resource usage parameters, and standard reference number involved in each adjustment strategy into the strategy conflict detection model to obtain the logical conflict index between strategies, and verify the synergy of the basic adjustment strategies based on the logical conflict index; After the basic adjustment strategy is verified for collaboration, an approval execution plan is generated, which includes a process node sequence diagram, a resource configuration list, and a standard adaptation comparison table.

[0041] First, the corresponding basic adjustment strategy is matched based on the quantitative range of the approval status value. Next, the approval node ID, resource usage parameters, and standard reference number involved in each adjustment strategy are input into the strategy conflict detection model to obtain the logical conflict index between strategies. Then, the basic adjustment strategies are validated for synergy based on this logical conflict index. After the basic adjustment strategies pass the synergy validation, an approval execution plan is generated, including a process node sequence diagram, a resource configuration list, and a standard adaptation comparison table.

[0042] When the approval status value falls within a certain quantitative range, a corresponding basic adjustment strategy is matched, such as adjusting the personnel configuration of the material review node or optimizing the resource scheduling of on-site verification. Then, the approval node IDs, resource occupancy parameters, and standard reference numbers involved in these adjustment strategies are input into the strategy conflict detection model. Here, the approval node IDs are the material review node IDs and on-site verification node IDs; the resource occupancy parameters are the number of personnel required for material review and the number of equipment required for on-site verification; and the standard reference numbers are the land use planning standard number and the architectural design standard number. The model analyzes whether there are logical conflicts between these strategies. For example, does the strategy of increasing personnel configuration at the material review node conflict with the strategy of equipment scheduling at the on-site verification node in terms of resource usage or time arrangement? This yields a logical conflict index. Based on the logical conflict index, the basic adjustment strategies are validated for synergy to ensure that the strategies can work together effectively. After the basic adjustment strategy passes the collaborative verification, an approval execution plan is generated. The process node sequence diagram clearly shows the order and time arrangement of material review, on-site inspection and final approval nodes; the resource allocation list lists the specific configuration of personnel, equipment and other resources required for each node; and the standard adaptation comparison table clarifies the applicable standards for each approval link and their compatibility with the application materials, thereby providing a clear, collaborative and executable plan for the approval of construction land planning permits.

[0043] An intelligent auxiliary approval system based on natural resource business includes: Acquisition module: Acquires basic information about the target approval item and extracts approval data of similar historical approval items based on the basic information of the target approval item; First processing module: If the completeness of materials for the approval data of similar historical approval items is unstable and fluctuating at different approval stages, the impact of the change in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient. The second processing module: If the completeness of materials for the approval data of similar historical approval items is stable and fluctuating at different approval stages, then the impact of different approval stages on the accuracy of the approval results is extracted to obtain the second approval correlation coefficient, and the impact of the adaptability of different approval standards on the approval compliance is extracted to obtain the third approval correlation coefficient. The third processing module: Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, combined with the completeness of materials and the status of different approval stages in the approval process of the target approval item, the approval status value is obtained; Output module: Adjusts the approval process of the target approval item based on the approval status value to obtain an optimized approval execution plan.

[0044] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements an intelligent auxiliary approval method based on natural resource business.

[0045] like Figure 3 As shown, the electronic device may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute an intelligent auxiliary approval method based on natural resource business.

[0046] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0047] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program that can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute an intelligent auxiliary approval method based on natural resource business.

[0048] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform an intelligent auxiliary approval method based on natural resource business.

[0049] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0050] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications 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.

Claims

1. An intelligent assistant approval method based on natural resource business, characterized in that, The method includes the following steps: Obtain basic information about the target approval item, and extract approval data of similar historical approval items based on the basic information of the target approval item; If the completeness of materials for similar approval items in the past is unstable at different approval stages, the impact of changes in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient. If the completeness of materials for similar approval items in history is stable at different approval stages, then the impact of different approval stages on the accuracy of approval results is extracted to obtain the second approval correlation coefficient, and the impact of the adaptability of different approval standards on approval compliance is extracted to obtain the third approval correlation coefficient. Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, and combined with the completeness of materials and the status of different approval stages in the approval process of the target approval item, the approval status value is obtained. The approval process for the target approval item is adjusted based on the approval status value to obtain an optimized approval execution plan.

2. The intelligent auxiliary approval method based on natural resource business as described in claim 1, characterized in that, It also includes the following steps: Receive target approval items uploaded by users through the existing approval system; Automatically identify and verify the compliance of target approval items to determine whether the content of the documents is consistent with the requirements of the application section; Structured approval data is obtained by extracting content from target approval items that have undergone standardized verification. The structured approval data is checked for consistency and compliance with the pre-set digital review rules to generate auxiliary review opinions.

3. The intelligent auxiliary approval method based on natural resource business as described in claim 1, characterized in that, The system automatically identifies and verifies the compliance of target approval items to determine whether the content of the documents is consistent with the requirements of the application section. This includes the following steps: Use image recognition and / or text analysis technologies to identify the substantive content of the target approval items; The identified document content is matched with the preset document types for the application section to determine whether the document content meets the section requirements.

4. The intelligent auxiliary approval method based on natural resource business as described in claim 1, characterized in that, The impact of changes in material completeness on approval efficiency is then extracted to obtain the first approval correlation coefficient, which specifically includes the following steps: Under the condition that the completeness of materials at different stages of the approval process for similar historical approval items is unstable and fluctuating, the approval efficiency data for the same type of approval stage in the historical approval process is obtained. The first approval correlation coefficient is obtained by extracting the correlation between changes in material completeness and approval efficiency based on approval efficiency data and the degree of change in material completeness.

5. The intelligent auxiliary approval method based on natural resource business as described in claim 4, characterized in that, The second approval correlation coefficient is obtained by extracting the impact of different approval stages on the accuracy of the approval results. This involves the following steps: To obtain accurate data on the approval results of the same type of approval at different stages of the approval process for similar historical approval items, given that the completeness of materials at different approval stages remains stable. The second approval correlation coefficient is obtained by extracting the impact of different approval stages on the approval results based on the accuracy of the approval results data and the completeness and stability of the materials.

6. The intelligent auxiliary approval method based on natural resource business as described in claim 5, characterized in that, The impact of different approval standard adaptability on approval compliance is extracted to obtain the third approval correlation coefficient, which specifically includes the following steps: Collect the set of approval standards applicable to each approval stage in historical similar approval items and the corresponding approval compliance judgment results, and classify the approval compliance judgment results into fully compliant, partially compliant and non-compliant. Adaptability vector coding is applied to the set of approval standards. The coding dimensions include the matching degree between the standards and the applicable scenario parameters of the current approval items, the constraint threshold of standard elements, the fit of the application data, and the degree of coordination of related approvals. A mapping model is constructed based on the results of adaptive vector coding and the results of approval compliance determination; The set of approval standards for the target approval items is input into the trained mapping model to obtain the influence weight value of each standard on approval compliance. Based on the influence weight value, the comprehensive influence coefficient of the adaptability of different approval standards on approval compliance is extracted to obtain the third approval correlation coefficient.

7. The intelligent auxiliary approval method based on natural resource business as described in claim 6, characterized in that, Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, and combined with the completeness of materials and the status of different approval stages in the approval process for the target approval item, the approval status value is derived, specifically including the following steps: Configure dynamic weight coefficients for the correlation coefficients of the first approval, the second approval, and the third approval, respectively; An approval status value calculation model is established. The approval status value calculation model adopts a multi-dimensional weighted fusion algorithm. The first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient are multiplied by their respective dynamic weight coefficients and then introduced into the scenario adaptation correction factor for calibration. The scenario adaptation correction factor is calculated based on the matching degree between the resource type of the target approval item and the type of similar historical items. The initial approval status value is output through the approval status value calculation model, and then the initial approval status value is processed by interval mapping: the initial value is mapped to the quantization interval; The mapped approval status value is validated. The validation process incorporates real-time feedback data from the approval process. If the real-time feedback data exceeds a preset dynamic threshold, the approval status value is iteratively corrected. The correction magnitude is positively correlated with the degree of abnormality in the real-time feedback data. Finally, the validated approval status value is output.

8. The intelligent auxiliary approval method based on natural resource business as described in claim 7, characterized in that, The optimized approval execution plan is obtained by adjusting the approval process for the target approval item based on the approval status value, which includes the following steps: Based on the quantitative range matching of approval status values, corresponding basic adjustment strategies are implemented. Input the approval node ID, resource usage parameters, and standard reference number involved in each adjustment strategy into the strategy conflict detection model to obtain the logical conflict index between strategies, and verify the synergy of the basic adjustment strategies based on the logical conflict index; After the basic adjustment strategy is verified for collaboration, an approval execution plan is generated, which includes a process node sequence diagram, a resource configuration list, and a standard adaptation comparison table.

9. An intelligent auxiliary approval system based on natural resource business, applied to the intelligent auxiliary approval method based on natural resource business as described in any one of claims 1 to 8, characterized in that, include: Acquisition module: Acquires basic information about the target approval item and extracts approval data of similar historical approval items based on the basic information of the target approval item; First processing module: If the completeness of materials for the approval data of similar historical approval items is unstable and fluctuating at different approval stages, the impact of the change in material completeness on approval efficiency is extracted to obtain the first approval correlation coefficient. The second processing module: If the completeness of materials for the approval data of similar historical approval items is stable and fluctuating at different approval stages, then the impact of different approval stages on the accuracy of the approval results is extracted to obtain the second approval correlation coefficient, and the impact of the adaptability of different approval standards on the approval compliance is extracted to obtain the third approval correlation coefficient. The third processing module: Based on the first approval correlation coefficient, the second approval correlation coefficient, and the third approval correlation coefficient, combined with the completeness of materials and the status of different approval stages in the approval process of the target approval item, the approval status value is obtained; Output module: Adjusts the approval process of the target approval item based on the approval status value to obtain an optimized approval execution plan.

10. An electronic device 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 program, it implements the intelligent assisted approval method based on natural resource business as described in any one of claims 1 to 8.

Images