Modularized learning method and system for bid inviting and purchasing laws and regulations

Abstract

The invention is suitable for the field of modular learning, and provides a modular learning method and system for bid and purchase laws and regulations, and the method comprises the steps: decomposing bid and purchase legal terms into basic element modules and application scene modules, forming an initial module library, loading laws and regulation module versions in different periods and regions, and carrying out the multi-dimensional space-time adaptation; collecting module calling combination operation of a user, verifying compliance in real time based on association rules and generating combination operation data; a user operation track is recorded, module association degree parameters are dynamically adjusted in combination with related data, an evolutionary knowledge network is constructed, and association rules are updated; and synchronously outputting the visual knowledge graph to display the module relationship and the learning progress. According to the invention, refined learning and multi-dimensional adaptation of laws and regulations are realized, individual cognitive features can be reflected, learning efficiency and pertinence are improved, and the method is suitable for the field of bid procurement laws and regulations learning.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of modular learning, and particularly relates to a modular learning method and system for bidding procurement law. BACKGROUND

[0002] Bidding procurement involves a large number of legal provisions and is highly professional. With the continuous development of the industry, the standardization requirements of bidding procurement activities are increasingly improved, and relevant laws and regulations are continuously updated and improved. The contents of the regulations in different periods and different regions are different, and the learning needs of practitioners for bidding procurement regulations are increasingly urgent, and efficient and accurate learning methods and systems are needed to meet the learning needs in actual application.

[0003] At present, the existing bidding procurement regulation learning scheme mainly presents the overall text of the provisions, and some schemes will classify and organize the regulations to form a collection of materials divided by domain or level of effectiveness. Some learning systems also provide query and retrieval functions for regulation provisions to assist users in finding specific provisions. However, these schemes mainly focus on the display and management of the regulation text itself, and do not perform deep disassembly and modularization of the regulation provisions. They also lack effective adaptation of different versions and different regional regulations and dynamic tracking and personalized guidance of the user learning process.

[0004] The existing technology cannot divide the bidding procurement legal provisions into independently accessible modules, making it difficult to achieve multi-dimensional spatiotemporal adaptation of bidding procurement modules in different periods and regions. This results in difficulties for users to accurately obtain regulation content adapted to specific scenarios during the learning process. At the same time, the technology cannot verify the logical compliance in real time based on user operation combinations and dynamically adjust knowledge associations, cannot form a knowledge network reflecting individual cognitive characteristics, and cannot improve user learning efficiency and help users systematically master the associated logic between regulations and their own learning progress. SUMMARY

[0005] The present application aims to provide a bidding procurement modular learning method and system to solve the technical problems of the existing technology identified in the background.

[0006] The present application is implemented as follows: a bidding procurement modular learning method, the method comprising: dividing the bidding procurement legal provisions into independently accessible basic element modules and application scenario modules to form an initial module library, loading modules of different versions of different periods and regions, performing multi-dimensional spatiotemporal adaptation through version branch management and regional parameter injection, and synchronizing version difference data and conflict annotation results to an interactive interface; collecting user calling combination operations for the initial module library and different version modules, verifying the logical compliance of the combination operations in real time based on the association rules of the initial module library, and feeding back the results to generate combination operation data; Record the operation trajectory of the user during the combination operation, generate a learning trajectory log, collect combination operation data, user subsequent correction data and the learning trajectory log, dynamically adjust the correlation degree parameters between the modules, build an evolutionary knowledge network reflecting individual cognitive characteristics, and update the correlation rules in real time; Synchronously output a visual knowledge graph, dynamically display the module relationship and learning progress in the form of node links based on the knowledge network correlation strength, learning trajectory data and version difference information.

[0007] As a further scheme of the present application, the forming of the initial module library specifically comprises: Performing semantic analysis on the tender procurement legal clauses, identifying the minimum compliance units in the tender procurement legal clauses, and extracting the indivisible elements as basic element modules; Dividing application scenarios based on procurement methods, project types and subject roles, and generating application scenario modules containing module activation conditions and constraint rules; Adding time-space tags to each basic element module and application scenario module, wherein the time-space tags contain regulation version numbers and regional codes; Establishing an initial correlation rule library between the basic element modules and the application scenario modules, and defining module dependency relationships and conflict detection logic; Combining the basic element module set, the application scenario module set and the initial correlation rule library into the initial module library.

[0008] As a further scheme of the present application, the loading of the law module versions of different periods and regions specifically comprises: Creating independent version libraries for different periods / regions, and storing the basic element module set and the application scenario module set under the independent version libraries; Modifying the region-sensitive parameters in the basic element modules through a regional parameter injection engine; Comparing the basic element modules and the application scenario modules with the same tags in different version libraries to generate version difference data; Adding conflict identifiers to the modules with logical conflicts to form a conflict annotation result.

[0009] As a further scheme of the present application, the modification of the region-sensitive parameters in the basic element modules specifically comprises: ; Wherein, the region-sensitive parameter is, the indivisible element in the basic element module, the regional code in the time-space tag, the time-space tag contains a regulation version number, the module set stored under the independent version library, injecting engine for area parameters.

[0010] As a further scheme of the present application, the real-time verification combination operation logic compliance specifically includes: capture the combination sequence of the basic element module and the application scenario module called by the user from the initial module library; call the initial correlation rule library to check three types of logic: module dependency, conflict exclusion, and scene constraint compliance; output the check results containing the basic element module / application scenario module ID and legal basis of the conflict; record the basic element module / application scenario module call timestamp, verification result, and user correction action, and generate combination operation data.

[0011] As a further scheme of the present application, the output of the check results containing the basic element module / application scenario module ID and legal basis of the conflict: ; wherein, the basic element module / application scenario module ID containing the conflict, the article index of the conflict basis, the version weight factor, the total number of basic element modules / application scenario modules containing conflicts detected in a single verification.

[0012] As a further scheme of the present application, the construction of the evolutionary knowledge network reflecting individual cognitive characteristics specifically includes: statistically generate the basic element module co-occurrence frequency by counting the number of times the basic element module appears in the same combination, and generate the application scenario module error rate by calculating the proportion of the application scenario module verification results being wrong; calculate the correlation degree parameter value between the modules according to the basic element module co-occurrence frequency and the application scenario module error rate; when the correlation degree parameter exceeds the adaptive threshold, establish a new connection between the corresponding module nodes in the evolutionary knowledge network; write the established new connection relationship into the dynamic verification rule library, and cover the corresponding entries of the initial correlation rule library.

[0013] As a further scheme of the present application, the calculation of the correlation degree parameter value between the modules: ; wherein, represents the real-time correlation degree of the basic element module and the application scenario module , represents the basic element module Application Scenario Module Co-occurrence frequency in the combination Represents basic element modules Total number of occurrences Application scenario module Error rate in validation These are the weighting coefficients.

[0014] Another object of the present invention is to provide a modular learning system for bidding and procurement regulations, the system comprising: The version management module is used to decompose the legal terms of bidding and procurement into basic element modules and application scenario modules that can be accessed independently, forming an initial module library. At the same time, it loads the legal module versions from different periods and regions, and performs multi-dimensional spatiotemporal adaptation through version branch management and regional parameter injection. Version difference data and conflict annotation results are synchronized to the interactive interface. The operation combination verification module is used to collect user call combination operations for the initial module library and different version modules, and verify the compliance of the combined operation logic in real time based on the association rules of the initial module library and return the results, generating combined operation data. The operation trajectory recording module is used to record the user's operation trajectory during the combination operation process, generate learning trajectory logs, collect combination operation data, user subsequent correction data and learning trajectory logs, dynamically adjust the correlation parameters between modules, construct an evolutionary knowledge network that reflects individual cognitive characteristics, and update the correlation rules in real time. The knowledge graph output module is used to synchronously output a visualized knowledge graph. Based on the knowledge network association strength, learning trajectory data, and version difference information, it dynamically displays the module relationships and learning progress in the form of node links.

[0015] The beneficial effects of this invention are: This invention decomposes legal provisions related to bidding and procurement into basic element modules and application scenario modules, forming an initial module library and loading versions from different periods and regions. This achieves refined breakdown of regulatory content and multi-dimensional spatiotemporal adaptation, allowing users to easily access regulatory modules suitable for specific scenarios and solving the problems of inconsistent regulatory versions and difficulty in addressing regional differences. By collecting user module call combinations and verifying compliance in real time, and combining user operation trajectories to construct an evolutionary knowledge network, it can dynamically reflect individual cognitive characteristics of users, update association rules in real time, and help users promptly identify logical errors in their learning, gradually forming a systematic understanding of regulations. Simultaneously, the synchronous output of a visualized knowledge graph displays module relationships and learning progress in an intuitive node-linked format, facilitating users' grasp of the knowledge structure and learning status. This overall improves the efficiency and relevance of learning bidding and procurement regulations, better meeting the learning needs of different users in different scenarios. Attached Figure Description

[0016] Figure 1 A flowchart illustrating the modular learning method for bidding and procurement regulations provided in this embodiment of the invention; Figure 2 A flowchart for forming an initial module library is provided for embodiments of the present invention; Figure 3 A flowchart for loading regulatory module versions from different periods and regions provided in this embodiment of the invention; Figure 4 A flowchart for real-time verification of the compliance of combined operation logic provided in an embodiment of the present invention; Figure 5 A flowchart for constructing an evolutionary knowledge network that reflects individual cognitive characteristics, provided in an embodiment of the present invention; Figure 6 The structural block diagram of the modular learning system for bidding and procurement regulations provided in the embodiments of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] Figure 1 A flowchart of the modular learning method for bidding and procurement regulations provided in this embodiment of the invention is shown below. Figure 1 As shown, the method includes: S100 decomposes the legal terms of bidding and procurement into basic element modules and application scenario modules that can be accessed independently, forming an initial module library. At the same time, it loads legal module versions from different periods and regions, and performs multi-dimensional spatiotemporal adaptation through version branch management and regional parameter injection. Version difference data and conflict annotation results are synchronized to the interactive interface. This step systematically breaks down the legal provisions of bidding and procurement, dividing them into basic element modules and application scenario modules to form an initial module library. At the same time, considering the time-sensitive and regional characteristics of regulations, different versions of regulations from different periods and regions will be loaded. Multi-dimensional spatiotemporal adaptation will be achieved through version branch management and regional parameter injection. The difference data and conflict annotation results between versions will be synchronized to the interactive interface in real time, allowing users to intuitively perceive the changes in regulations and regional differences.

[0019] like Figure 2 As shown, the formation of the initial module library specifically includes: S110 performs semantic analysis on the legal clauses of bidding and procurement, identifies the smallest compliant unit in the legal clauses of bidding and procurement, and extracts indivisible elements as basic element modules. By employing semantic parsing technology to deeply process legal clauses related to bidding and procurement, the smallest compliant units within the clauses are identified, and indivisible elements are extracted as basic element modules. This process requires the use of natural language processing tools for word segmentation, entity recognition, and semantic understanding of the legal text. The aim is to break down massive and complex legal clauses into atomic basic units, ensuring that each module is irreplaceable and independently compliant. This lays the foundation for flexible combinations later on, avoiding logical loopholes in combination due to overly coarse module breakdown, or redundancy due to overly fine breakdown.

[0020] S120, based on the procurement method, project type and subject role, divides application scenarios and generates application scenario modules containing module activation conditions and constraint rules; For example, based on the procurement method, it can be divided into scenarios such as open bidding, invited bidding, and competitive negotiation; based on the project type, it can be divided into scenarios such as goods procurement, engineering procurement, and service procurement; based on the subject role, it can be divided into scenarios such as purchaser, bidding agency, and bidder. Each scenario module will have clear activation conditions. For example, the activation conditions for the competitive negotiation scenario may be that the procurement needs are uncertain and the budget amount is lower than a certain standard. It also includes constraint rules, such as the number of people in the negotiation team must not be less than 3.

[0021] This step closely integrates abstract legal provisions with practical application scenarios, allowing users to quickly locate relevant modules based on their specific situations, reducing interference from irrelevant information, improving the relevance and practicality of learning, and transforming legal knowledge from textbook provisions into actionable scenarios.

[0022] S130, add spatiotemporal tags to each basic element module and application scenario module, the spatiotemporal tags including the regulatory version number and the regional code; This step embeds tag fields into the module's attribute information and uses database association technology to bind the tags to the module content. The purpose of this is to assign spatiotemporal attributes to the module, enabling it to be accurately located to a specific period and region. This provides a foundation for subsequently loading different versions of the module, injecting regional parameters, and comparing version differences, ensuring that users can quickly call the spatiotemporal version of the module that meets their needs.

[0023] S140, Establish an initial association rule base between the basic element module and the application scenario module, and define module dependency relationships and conflict detection logic; For example, the bid opening process module depends on the bid document receiving completion module, and the two have a sequential dependency relationship; the single-source procurement module and the mandatory public bidding module have logical conflicts and cannot be activated simultaneously. This process requires sorting out the inherent logic between the legal provisions and transforming the dependencies and conflict rules into computer-recognizable logical expressions. The purpose is to standardize the interaction logic between modules in advance, provide a basis for compliance verification of subsequent user combination operations, and reduce compliance risks caused by users' incorrect module combination from the source.

[0024] S150, the basic element module set, application scenario module set and initial association rule base are combined into the initial module base.

[0025] S200 collects user calls to the initial module library and different version modules, and verifies the compliance of the combined operation logic in real time based on the association rules of the initial module library and returns the results, generating combined operation data. To address the unique characteristics of regulations across different periods and regions, an independent version management system is established to ensure that regulatory modules from various regions and periods can be accurately accessed. Simultaneously, user operations on the initial module library and different version modules are captured in real time, and their logical compliance is verified based on association rules. Ultimately, combined operation data reflecting user operation characteristics is generated, laying the foundation for subsequent knowledge network evolution.

[0026] like Figure 3 As shown, loading different versions of regulatory modules from different periods and regions specifically includes: S210 creates independent version repositories for different periods / regions, storing the basic element module set and application scenario module set under the independent version repository; S220, Modify the region-sensitive parameters in the basic element module through the region parameter injection engine; When a user calls a module for a specific region, the engine automatically reads the regional code and regulatory version number from the module's spatiotemporal tag. If this combination exists in the preset regional rule base, the corresponding regional parameter is used to replace the default parameter; otherwise, the default parameter is retained. This step solves the learning difficulties caused by regional differences in regulations. For example, different regions may have different regulations on procurement limits and bid bond ratios. By adjusting parameters, the basic element modules can accurately reflect local requirements. This transforms modules from general templates to regionally customized versions, eliminating the need for users to memorize regional differences during learning. The modules themselves present content that conforms to local realities, significantly reducing misunderstandings caused by regional differences.

[0027] S230: Compare the basic element modules and application scenario modules with the same tags in different version libraries to generate version difference data; S240: Add conflict identifiers to modules with logical conflicts to form conflict annotation results.

[0028] By scanning the constraint rules of modules in different versions or the same version using a conflict detection algorithm, when two modules are found to have irreconcilable contradictions in terms of applicable conditions, operational requirements, etc., a visual conflict marker is automatically added and the conflict reason is associated with it.

[0029] Early warnings of logical inconsistencies between modules prevent users from making erroneous judgments due to overlooking conflicts when performing combined operations. Its advantage lies in making potential logical risks explicit, allowing users to proactively focus on conflict points and explore the causes of conflicts during the learning process, thereby improving their ability to grasp the complexity and particularity of regulations.

[0030] In this step, modifying the region-sensitive parameters in the basic element module specifically involves: ; in, As a region-sensitive parameter, Indivisible elements in the basic element module For the geographic encoding in the spatiotemporal label, The spatiotemporal label includes the regulatory version number. To store a collection of modules in an independent version control repository, Inject engine into region parameters.

[0031] S300 records the user's operation trajectory during the combined operation process, generates learning trajectory logs, collects combined operation data, user subsequent correction data and learning trajectory logs, dynamically adjusts the correlation parameters between modules, constructs an evolutionary knowledge network that reflects individual cognitive characteristics, and updates the correlation rules in real time. The system tracks user calls and combinations in the initial module library and different version modules in real time. It verifies the logical compliance of these operations in real time through preset association rules and provides feedback on the results. During this process, the system records the user's operation trajectory, the conflict information generated during verification, and the user's subsequent correction actions in detail, forming a complete combination operation data and learning trajectory log. Based on this data, the system dynamically adjusts the association parameters between modules, gradually building an evolutionary knowledge network that reflects the user's individual cognitive habits, and updates the association rules in sync to ensure that the system's verification logic can be continuously optimized as the user learns.

[0032] By capturing users' module combination sequences, the system can gain a deeper understanding of users' cognitive paths, rather than just focusing on the final result. The real-time execution of three types of logical checks enables immediate interception of errors during the learning process, preventing users from forming incorrect knowledge associations. The clear presentation of conflicting results provides users with precise cognitive calibration points, shifting learning from blind trial to targeted correction. The accumulation and application of combination operation data allows the system to continuously adapt to users' cognitive characteristics. When users frequently make mistakes in a certain type of module combination, the system will strengthen the prompts of related modules by adjusting the correlation parameters. When users improve their mastery of a certain type of combination, the system will weaken unnecessary verification interventions. This personalized adaptation significantly improves learning efficiency.

[0033] like Figure 4 As shown, the compliance of the real-time verification combined operation logic specifically includes: S310, capture the combination sequence of basic element modules and application scenario modules called by the user from the initial module library; By recording user clicks, drags, and selections through front-end interaction logs, the system parses the IDs, call order, and combination methods of the invoked modules in real time, forming structured sequence data. The purpose of this is to fully reconstruct the user's module combination thought process during learning, providing original evidence for subsequent logical verification. It accurately tracks the user's cognitive associations between different modules, capturing both intentional logical combinations and unintentional errors, thus laying the foundation for understanding the user's knowledge mastery and cognitive blind spots.

[0034] S320, the initial association rule base is called to check three types of logic: module dependency, conflict exclusion, and scenario constraint compliance; Module dependency checks primarily verify whether there are modules that must exist simultaneously, conflict exclusion checks focus on modules that cannot coexist, and scenario constraint compliance checks confirm whether the module combination meets the activation conditions of the current application scenario. This design aims to ensure the logical rigor of user operations from multiple dimensions. Its advantage lies in transforming abstract legal logic into quantifiable checking rules, enabling the timely identification of logical flaws during user learning, preventing the accumulation of misconceptions, and helping users establish a correct legal logic framework.

[0035] S330 outputs the inspection results, including the IDs of the conflicting basic element modules / application scenario modules and the legal basis. This allows users to clearly understand which specific module has a problem in the combined operation, which legal clause is violated, and the degree of impact of the conflict under different versions. It transforms vague logical errors into specific legal basis, provides users with clear directions for correction, enhances the pertinence and effectiveness of the learning process, and avoids users wasting time on incorrect logical paths. S340 records the call timestamps, verification results, and user correction actions of the basic element module / application scenario module, and generates combined operation data.

[0036] In this step, the output includes the check results of the conflicting basic element module / application scenario module ID and legal basis: ; in, For the basic element module / application scenario module ID containing the conflict, Index of legal provisions used as the basis for conflict of laws Version weighting factor This represents the total number of basic element modules / application scenario modules that contain conflicts detected in a single verification.

[0037] The S400 synchronously outputs a visualized knowledge graph, dynamically displaying module relationships and learning progress in the form of node links based on the knowledge network correlation strength, learning trajectory data, and version difference information.

[0038] By analyzing user learning behavior data, an evolutionary knowledge network reflecting individual cognitive characteristics is constructed. This network is then visualized in the form of a knowledge graph, intuitively displaying module relationships and learning progress. This allows users to deepen their understanding of regulations within a dynamically adjusted knowledge system. The system calculates the correlation parameters between modules by statistically analyzing the co-occurrence frequency and error rate of modules in user operation data. When the correlation reaches a threshold, new module connections are established in the knowledge network. These new connections are then updated to the dynamic verification rule base, replacing the initial rules. Simultaneously, based on the correlation strength, learning trajectory, and version differences of the knowledge network, a visual graph is output in the form of node links, achieving the co-evolution of the knowledge system and user cognition.

[0039] like Figure 5 As shown, the construction of an evolutionary knowledge network reflecting individual cognitive characteristics specifically includes: S410, count the number of times basic element modules appear simultaneously in the same combination to generate the co-occurrence frequency of basic element modules, and calculate the proportion of application scenario module verification results that are incorrect to generate the error rate of application scenario modules. The module combination sequences recorded in the logs are analyzed using data statistics tools: Co-occurrence frequency statistics require traversing all combination operations, recording the number of times two basic element modules in the same combination appear simultaneously, and calculating the ratio of this number to the total number of times any one module appears; error rate calculation requires filtering the verification results of application scenario modules and calculating the proportion of times marked as errors to the total number of calls to that module. The purpose of this is to transform users' implicit cognitive habits into quantifiable data indicators. Co-occurrence frequency reflects users' inherent cognitive tendencies regarding module associations, while error rate reflects users' weaknesses in mastering specific application scenario modules. Its advantage lies in providing a solid quantitative basis for subsequent calculation of association parameters, allowing the strength of associations between modules to no longer depend on initial presets but to be dynamically generated based on users' actual learning behavior, thus better aligning with individual cognitive patterns.

[0040] S420, calculate the correlation parameter value between modules based on the co-occurrence frequency of the basic element modules and the error rate of the application scenario modules; The obtained co-occurrence frequency (i.e., basic element module) Application Scenario Module Co-occurrence frequency and The ratio of total occurrences) and error rate (i.e., application scenario module) Substituting the error rate into the correlation formula, where the weight coefficients... The focus of the study of regulations can be adjusted according to the specific circumstances (when more emphasis is placed on the actual co-occurrence patterns of modules). Taking a higher value, with more attention paid to the user's level of mastery. Take the lower value).

[0041] The purpose of this approach is to use an algorithm to fuse two data indicators into a single correlation parameter, enabling a comprehensive assessment of the strength of the correlation between modules. A higher co-occurrence frequency indicates that users are more inclined to use the two modules in conjunction, thus increasing the correlation. Conversely, a lower error rate indicates a more solid understanding of the application scenario module by the user, further strengthening its correlation with the basic element modules. Its advantage lies in allowing the correlation parameter to reflect both the inherent connections between modules in actual legal logic and the individual user's cognitive habits and level of mastery, making the subsequent construction of the knowledge network more personalized and practical.

[0042] S430, when the correlation parameter exceeds the adaptive threshold, a new connection is established between the corresponding module nodes of the evolutionary knowledge network; When the calculated correlation parameter exceeds the current threshold, the system automatically adds connecting lines to the corresponding module nodes in the knowledge network. The thickness of the lines can initially reflect the strength of the correlation. The purpose of this is to allow the knowledge network to proactively expand as the user learns, transforming implicit connections between modules that the user frequently associates and has a good grasp of into explicit connections. Its advantage lies in making the structure of the knowledge network more aligned with the user's cognitive path, avoiding the problem of traditional static knowledge systems being disconnected from the user's actual cognition. This allows users to more intuitively discover potential connections between modules during learning, thereby expanding their knowledge horizons and building a more complete legal cognitive framework.

[0043] S440, the newly established connection relationship is written into the dynamic verification rule base, overriding the corresponding entry in the initial association rule base.

[0044] The module dependencies or constraints reflected by new connections are transformed into structured rule entries, replacing conflicting or duplicated content in the initial rule base. This allows the system's verification logic to be updated synchronously with the evolution of the knowledge network, ensuring that subsequent verification of user-defined operations no longer relies on rigid initial rules, but rather on user-formed, practice-tested relational logic. Its advantage lies in making verification rules more adaptable and accurate, better matching users' learning progress and cognitive depth, avoiding unnecessary verification interference caused by rules lagging behind user cognition, and improving the smoothness of the learning process.

[0045] In this step, the correlation parameter values ​​between the calculation modules are: ; in, Represents basic element modules Application Scenario Module Real-time correlation Represents basic element modules Application Scenario Module Co-occurrence frequency in the combination Represents basic element modules Total number of occurrences Application scenario module Error rate in validation These are the weighting coefficients.

[0046] Figure 6 The structural block diagram of the modular learning system for bidding and procurement regulations provided in the embodiments of the present invention is as follows: Figure 6 As shown, the system includes: Version management module 100 is used to decompose the legal terms of bidding and procurement into basic element modules and application scenario modules that can be accessed independently, forming an initial module library. At the same time, it loads the legal module versions from different periods and regions, performs multi-dimensional spatiotemporal adaptation through version branch management and regional parameter injection, and synchronizes version difference data and conflict annotation results to the interactive interface. The operation combination verification module 200 is used to collect user call combination operations for the initial module library and different version modules, and verify the compliance of the combination operation logic in real time based on the association rules of the initial module library and return the results, generating combination operation data. The operation trajectory recording module 300 is used to record the user's operation trajectory during the combined operation process, generate learning trajectory logs, collect combined operation data, user subsequent correction data and learning trajectory logs, dynamically adjust the correlation parameters between modules, construct an evolutionary knowledge network that reflects individual cognitive characteristics, and update the correlation rules in real time. The knowledge graph output module 400 is used to synchronously output a visualized knowledge graph. Based on the knowledge network association strength, learning trajectory data, and version difference information, it dynamically displays the module relationships and learning progress in the form of node links.

[0047] 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.

[0048] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. 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 modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A modular learning method for bidding and procurement regulations, characterized by: The method includes: The legal provisions of bidding and procurement are broken down into basic element modules and application scenario modules that can be accessed independently, forming an initial module library. At the same time, different versions of legal modules from different periods and regions are loaded. Multi-dimensional spatiotemporal adaptation is achieved through version branch management and regional parameter injection. Version difference data and conflict annotation results are synchronized to the interactive interface. Collect user calls to the initial module library and different version modules, and verify the compliance of the combined operation logic in real time based on the association rules of the initial module library and provide feedback on the results, generating combined operation data; Record the user's operation trajectory during the combination operation process, generate learning trajectory log, collect combination operation data, user subsequent correction data and learning trajectory log, dynamically adjust the correlation parameters between modules, construct an evolutionary knowledge network that reflects individual cognitive characteristics, and update the correlation rules in real time; It synchronously outputs a visualized knowledge graph, which dynamically displays module relationships and learning progress in the form of node links based on the knowledge network correlation strength, learning trajectory data and version difference information.

2. The method according to claim 1, characterized in that, The formation of the initial module library specifically includes: Semantic analysis is performed on the legal clauses of bidding and procurement to identify the smallest compliant unit in the legal clauses of bidding and procurement and extract indivisible elements as basic element modules. Based on the procurement method, project type, and main role, application scenarios are divided, and application scenario modules containing module activation conditions and constraint rules are generated. Add spatiotemporal tags to each basic element module and application scenario module. The spatiotemporal tags include the regulatory version number and the regional code. Establish an initial association rule base between the basic element module and the application scenario module, and define module dependency relationships and conflict detection logic; The basic element module set, the application scenario module set, and the initial association rule base are combined into the initial module base.

3. The method according to claim 2, characterized in that, The loading of different versions of regulations from different periods and regions specifically includes: Create independent repositories for different periods / regions, and store the basic element module set and application scenario module set under the independent repository; Modify the region-sensitive parameters in the basic element module by using the region parameter injection engine; Compare the basic element modules and application scenario modules with the same tags in different version libraries to generate version difference data; Add conflict identifiers to modules with logical conflicts to generate conflict annotation results.

4. The method according to claim 3, characterized in that, The modification of the region-sensitive parameters in the basic element module specifically involves: ； in, As a region-sensitive parameter, Indivisible elements in the basic element module For the geographic encoding in the spatiotemporal label, The spatiotemporal label includes the regulatory version number. To store a collection of modules in an independent version control repository, Inject engine into region parameters.

5. The method according to claim 3, characterized in that, The compliance of the real-time verification combined operation logic specifically includes: Capture the combined sequence of basic element modules and application scenario modules invoked by the user from the initial module library; The initial association rule base is invoked to check three types of logic: module dependency, conflict exclusion, and scenario constraint compliance; Output the inspection results, including the IDs of the conflicting basic element modules / application scenario modules and their legal basis; Record the timestamps of calls to the basic elements module / application scenario module, verification results, and user correction actions to generate combined operation data.

6. The method according to claim 5, characterized in that, The output includes the IDs of the conflicting basic element modules / application scenario modules and the results of the legal basis checks: ； in, For the basic element module / application scenario module ID containing the conflict, Index of legal provisions used as the basis for conflict of laws As a version weighting factor, This represents the total number of basic element modules / application scenario modules that contain conflicts detected in a single verification.

7. The method according to claim 5, characterized in that, The construction of an evolutionary knowledge network that reflects individual cognitive characteristics specifically includes: The co-occurrence frequency of basic element modules is generated by counting the number of times basic element modules appear simultaneously in the same combination, and the error rate of application scenario modules is generated by calculating the proportion of application scenario module verification results that are incorrect. The correlation parameter value between modules is calculated based on the co-occurrence frequency of the basic element modules and the error rate of the application scenario modules. When the correlation parameter exceeds the adaptive threshold, a new connection is established between the corresponding module nodes of the evolutionary knowledge network; The newly established connection relationship is written into the dynamic verification rule base, overriding the corresponding entry in the initial association rule base.

8. The method according to claim 7, characterized in that, The correlation parameter values ​​between the calculation modules are: ； in, Represents basic element modules Application Scenario Module Real-time correlation Represents basic element modules Application Scenario Module Co-occurrence frequency in the combination Represents basic element modules Total number of occurrences Application scenario module Error rate in validation These are the weighting coefficients.

9. A modular learning system for bidding and procurement regulations, characterized in that: The system includes: The version management module is used to decompose the legal terms of bidding and procurement into basic element modules and application scenario modules that can be accessed independently, forming an initial module library. At the same time, it loads the legal module versions from different periods and regions, and performs multi-dimensional spatiotemporal adaptation through version branch management and regional parameter injection. Version difference data and conflict annotation results are synchronized to the interactive interface. The operation combination verification module is used to collect user call combination operations for the initial module library and different version modules, and verify the compliance of the combined operation logic in real time based on the association rules of the initial module library and return the results, generating combined operation data. The operation trajectory recording module is used to record the user's operation trajectory during the combination operation process, generate learning trajectory logs, collect combination operation data, user subsequent correction data and learning trajectory logs, dynamically adjust the correlation parameters between modules, construct an evolutionary knowledge network that reflects individual cognitive characteristics, and update the correlation rules in real time. The knowledge graph output module is used to synchronously output a visualized knowledge graph. Based on the knowledge network association strength, learning trajectory data, and version difference information, it dynamically displays the module relationships and learning progress in the form of node links.

Images