Document compliance judgment method based on violation traceability path score

Abstract

The invention discloses a document compliance judgment method based on violation traceability path scoring, and relates to the technical field of data compliance review, and the method comprises the following steps: carrying out structured analysis on a to-be-detected document, splitting the document content into semantic units, and identifying sensitive information entities contained in the semantic units; constructing a violation traceability path from the sensitive information entity to the regulation terms; performing scoring calculation on the violation tracing path, and determining a violation risk level of the path based on attributes of each node and edge in the path; on the basis of a path scoring result, matching corresponding regulation clause contents, extracting original text contents, clause numbers, application conditions, law domain classification information and punishment suggestions of the regulation clauses from the regulation knowledge graph, and generating an interpretable causal chain description; and outputting a violation result report. According to the method, the problems of non-traceable compliance basis, opaque violation judgment, lack of explanation support of risk grading and the like in the existing document review technology are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data compliance review, and in particular to a document compliance determination method based on violation tracing path scoring. Background Art

[0002] With increasingly stringent data security and privacy requirements, many industries face increasingly complex compliance audits in document management, content sharing, and cross-departmental information flow. For example, regulations such as GDPR, HIPAA, and the Personal Information Protection Act clearly restrict the handling of sensitive personal, health, and financial information in documents.

[0003] Current document compliance reviews primarily rely on rule-based or keyword-based recognition methods, with some systems employing entity recognition and document classification technologies to detect sensitive information. However, these methods typically only determine whether risky content exists, but struggle to clearly explain the basis for violations, particularly by failing to trace them back to specific regulatory provisions or the chain of actions that triggered them. This results in a lack of transparency and auditability.

[0004] Furthermore, different regulations have multiple definitions and processing requirements for similar data, making it difficult for traditional methods to achieve fine-grained matching and personalized risk assessments. Therefore, a traceable, scorable, and explainable violation identification mechanism is urgently needed to improve the accuracy and credibility of document compliance assessments. Summary of the Invention

[0005] The present invention aims to solve the problems existing in existing document review technologies, such as the non-traceability of compliance basis, the opaqueness of violation determination, and the lack of explanatory support for risk grading, and provides a document compliance determination method based on violation tracing path scoring.

[0006] The present invention provides a document compliance determination method based on violation tracing path scoring, which solves the above technical problems using the following technical solutions:

[0007] A document compliance determination method based on violation tracing path scoring includes the following steps:

[0008] S1. Perform structural analysis on the document to be inspected, split the document content into semantic units, and identify the sensitive information entities contained therein to form the basic data layer for compliance review;

[0009] S2. Construct a violation tracing path from the sensitive information entity to the regulatory clause, where the violation tracing path includes content segments, entity types, rule triggering conditions, and regulatory clause nodes;

[0010] S3. Score and calculate the violation tracing path, and determine the violation risk level of the path based on the attributes of each node and edge in the path;

[0011] S4. Based on the scoring results of the violation traceability path, the corresponding regulatory provisions are matched and the original content, clause number, applicable conditions, legal jurisdiction classification information, and penalty recommendations of the regulatory provisions are extracted from the regulatory knowledge graph to provide a clear legal basis for violation identification and generate an interpretable causal chain description;

[0012] S5. Output a violation result report, which includes the location information of the illegal content, the traceability path structure, the scoring level, the matching legal basis and the handling suggestions.

[0013] Optionally, step S1 specifically includes:

[0014] S1.1. Receive various documents to be tested, parse them, and complete content extraction and structural processing;

[0015] S1.2. Divide the parsed document content into logically clear basic semantic units using a text segmentation algorithm.

[0016] S1.3. Apply the entity recognition model to scan the text in the basic semantic unit, identify sensitive information entities, add a label to each identified entity, and record the basic semantic unit in which it is located;

[0017] S1.4. Label the basic semantic unit set of sensitive information entities to form an "entity-location-type" mapping table, providing an initial node for subsequent violation path construction.

[0018] Preferably, the documents to be detected include three types: structured documents, semi-structured documents and image documents;

[0019] a) For structured and semi-structured documents, directly parse the document format, extract the text content and format information, and output structured text data that retains the original layout.

[0020] b) For image-type documents, the OCR module is first called to perform text recognition on the image to generate editable text content. Then, layout analysis technology is used to restore the document layout, distinguish the main text, header, footer and table areas, and finally output the text data with coordinate positions and layout structure information.

[0021] Further optionally, step S2 specifically includes:

[0022] S2.1. Based on the recognition results of the document to be detected, extract the entities marked as sensitive information and the content fragments in which they are located;

[0023] S2.2. Retrieve predefined regulatory rule sets based on sensitive entity types, match corresponding compliance rule conditions, and combine contextual semantics to determine whether the rule triggering conditions are met;

[0024] S2.3. Based on the matched rule trigger conditions, query the predefined compliance knowledge graph, locate the corresponding regulatory clause node, parse the regulatory clause content, extract structured information, and verify its compatibility with the current violation scenario;

[0025] S2.4. Concatenate “content fragment → entity type → rule trigger condition → regulatory clause” in logical order to form a structured traceability path, supplement the contextual semantic features in the traceability path, and ensure that the path is semantically closed and logically reasonable.

[0026] Further optionally, step S3 specifically includes:

[0027] S3.1. For the constructed violation traceability path, extract five node and edge attributes: content sensitivity of content segments in the path, entity confidence of entity types, rule matching degree between rule triggering conditions and path semantics, mandatory nature of regulatory clauses, and contextual coordination degree of the entity context, and generate a vector containing multidimensional features.

[0028] S3.2. Comprehensively calculate the feature vectors using a preset weighted scoring function, incorporate confidence interval modeling to handle fuzzy semantic scenarios, and support manual parameter adjustment or automatic optimization through reinforcement learning to achieve quantitative risk assessment.

[0029] S3.3. Based on the set risk threshold, the calculation results are divided into three levels: "high risk", "medium risk" and "low risk". A detailed report is then generated, including risk scores, factor contribution analysis and regulatory references, and a confidence level description is added to the fuzzy path to assist decision-making.

[0030] Further optionally, step S4 specifically includes:

[0031] S4.1. Search the regulatory knowledge graph for the end node of the violation traceability path to obtain the regulatory content corresponding to the end node.

[0032] S4.2. In-depth analysis of the semantic information contained in the violation tracing path and the rule information of the regulatory clauses in the regulatory knowledge graph. Through careful comparison, intelligent alignment of the violation tracing path and the regulatory content is achieved, accurately identifying the regulatory clause corresponding to the end node of the path;

[0033] S4.3. Extract detailed information related to the clause from the regulatory knowledge graph, including the original text of the regulatory clause, clause number, applicable conditions, jurisdiction classification information, and penalty recommendations, to provide reference for subsequent handling of violations;

[0034] S4.4. When a violation tracing path corresponds to multiple regulatory clauses, multiple candidate clauses are output simultaneously and ranked based on the path score and the degree of match between the rule and the path;

[0035] S4.5. Use the constructed violation traceability path and the matched regulatory provisions to generate an interpretable causal chain description.

[0036] Further optionally, step S5 specifically includes:

[0037] S5.1. Collect risk scoring results, regulatory matching information, violation traceability paths, and related compliance judgment information, organize and categorize them to prepare for subsequent report generation;

[0038] S5.2. Encapsulate the collected and organized information according to the set structure;

[0039] S5.3. Generate the specific contents of the violation result report based on the structured and encapsulated information. The report includes the location information of the violation content, the traceability path structure, the scoring level, the matching regulatory basis and the handling suggestions.

[0040] Preferably, step S5 is executed to output the violation result report in the following manner:

[0041] a) Display the report content directly on the human-computer interface;

[0042] b) Automatically generate PDF reports for easy storage and distribution;

[0043] c) Provide a structured data interface to connect to the audit system, business process system, risk control platform or automatic processing engine to achieve data sharing and interaction.

[0044] Compared with the prior art, the document compliance determination method based on violation tracing path scoring of the present invention has the following beneficial effects:

[0045] 1. This invention constructs a traceability violation path from document content fragments to regulatory provisions, and scores this path based on multiple factors such as content features, entity matching degree, rule condition complexity, and contextual semantic relevance. It then determines whether the document content constitutes a violation and the level of violation, and generates regulatory traceability information and disposal recommendations, thus achieving risk highlighting, violation location, and explainable compliance review in the process of handling sensitive document information.

[0046] 2. The present invention can improve the accuracy and semantic depth of violation identification through structured traceability modeling of violations; support quantitative scoring and classification of the risks of illegal content, meeting the needs of different organizations, industries or regions for refined compliance management and controllable risks; can clearly output information such as "which rule the illegal content triggered, which regulation is applicable, and why it constitutes a violation", support clause-level regulatory traceability, and provide legal support and process transparency for regulatory audits, compliance appeals and manual reviews; can automatically complete the compliance closed-loop processing from identification, judgment, interpretation to recommendation, support content screening, document blocking or rewriting processes without human intervention, reduce corporate compliance costs, and improve organizational risk response efficiency;

[0047] 3. The present invention realizes closed-loop control of the entire process from document semantic understanding to intelligent comparison of regulations, and from violation judgment to interpretation output. It is particularly suitable for practical application scenarios with high requirements for content security and compliance, complex text structure, and flexible application of regulations. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Attachment Figure 1 This is a flow chart of the method of embodiment 1 of the present invention. DETAILED DESCRIPTION

[0049] In order to make the technical solution, the technical problems solved and the technical effects of the present invention more clear, the technical solution of the present invention is clearly and completely described below in conjunction with specific embodiments.

[0050] Example 1:

[0051] Reference Attachment Figure 1 This embodiment proposes a document compliance determination method based on violation tracing path scoring, which includes the following steps:

[0052] S1. Perform structural analysis on the document to be inspected, split the document content into semantic units, and identify the sensitive information entities contained therein to form the basic data layer for compliance review, including:

[0053] S1.1. Receive various documents to be tested, parse them, and complete content extraction and structural processing.

[0054] S1.2. Use the text segmentation algorithm to divide the parsed document content into logically clear basic semantic units, such as paragraphs, sentences, table units, title blocks, etc.

[0055] S1.3. Apply the entity recognition model to scan the text in the basic semantic units to identify sensitive information entities such as name, address, contact information, identity information, health data, etc., add a label to each identified entity, and record the basic semantic unit in which it is located.

[0056] S1.4. Label the basic semantic unit set of sensitive information entities to form an "entity-location-type" mapping table, providing an initial node for subsequent violation path construction.

[0057] It should be added that the documents to be detected are not limited to the three types of structured documents (such as Word, PDF), semi-structured documents (such as HTML, email body) and image documents (such as scanned documents);

[0058] a) For structured and semi-structured documents, directly parse the document format, extract the text content and format information, and output structured text data that retains the original layout.

[0059] b) For image-type documents, the OCR module is first called to perform text recognition on the image to generate editable text content. Then, layout analysis technology is used to restore the document layout, distinguish the main text, header, footer and table areas, and finally output the text data with coordinate positions and layout structure information.

[0060] S2. Construct a violation tracing path from the sensitive information entity to the regulatory clause. The violation tracing path includes content segments, entity types, rule triggering conditions, and regulatory clause nodes, specifically including:

[0061] S2.1. Based on the recognition results of the document to be tested, extract entities marked as sensitive information (such as name, ID number, health data, financial account information, etc., these sensitive information entities are the starting point for the subsequent construction of the violation tracing path) and the content fragments (such as the sentences and paragraphs in which they are located); for example, if "Zhang San's ID number is 123456789012345678" in the document is identified as containing sensitive information, then "Zhang San" and "123456789012345678" are sensitive information entities, and "Zhang San's ID number is 123456789012345678" is the corresponding content fragment.

[0062] S2.2. Retrieve the predefined regulatory rule set based on the sensitive entity type, match the corresponding compliance rule conditions, and combine the context semantics to determine whether the rule triggering conditions are met.

[0063] In this step, the predefined regulatory rule set is a series of regulatory-related rules stored in the system. These rules specify the compliance requirements for different types of sensitive information in different scenarios. By searching the regulatory rule set based on the type of sensitive entity, you can find the corresponding compliance rule conditions. For example, if the sensitive entity type is "personally identifiable information," you may find the rule "Processing of personally identifiable information requires explicit user authorization."

[0064] Contextual semantics include the purpose of sensitive information use, processing methods, and the parties involved. For example, in a document, "Zhang San's ID number is 123456789012345678, which is used for employee registration and has been authorized by Zhang San," the context indicates that although sensitive information is present, the rule triggering condition of "processing personal identity information requires explicit user authorization" is met. If the authorization information is not mentioned, this condition may not be met.

[0065] S2.3. Based on the matched rule trigger conditions, query the predefined compliance knowledge graph, locate the corresponding regulatory clause node, parse the regulatory clause content, extract structured information, and verify the match with the current violation scenario.

[0066] The predefined compliance knowledge graph is a structured knowledge representation method that organizes information such as regulatory clauses, rule conditions, entity types, etc. in the form of a graph to facilitate query and reasoning.

[0067] For example, if the rule trigger condition is "processing personal identity information without obtaining explicit authorization from the user", locate the relevant regulatory provisions in the "Personal Information Protection Law"; parse the content of the regulatory provisions and extract structured information, such as the scope of application, liability provisions, and punishment measures; compare and verify the extracted structured information with the current violation scenario to determine whether the regulatory provisions are truly applicable to the current scenario. For example, the scope of application stipulated in the regulatory provisions is "enterprises processing personal information in commercial activities", and the current scenario is "non-profit organizations processing personal information in public welfare activities", then it is necessary to further determine whether the regulatory provisions can fully cover the current scenario.

[0068] S2.4. Concatenate “content snippet → entity type → rule trigger condition → regulatory clause” in a logical order to form a structured traceability path. For example, “Zhang San’s ID number is 123456789012345678 (content snippet) → personal identity information (entity type) → processing personal identity information without explicit user authorization (rule trigger condition) → Article XX of the Personal Information Protection Law (regulatory clause)”;

[0069] Supplement the contextual semantic features of the traceability path (such as the purpose of use of sensitive information, processing methods, and involved entities) to ensure that the path is semantically closed and logically sound. For example, adding contextual semantics such as "used for employee registration but not authorized" to the above path will make the logic of the entire path clearer.

[0070] S3. Score the violation tracing path and determine the violation risk level of the path based on the attributes of each node (content segment, entity type, rule trigger condition, regulatory clause) and edge (semantic association between nodes) in the path, specifically including:

[0071] S3.1. For the constructed violation tracing path, extract five node and edge attributes: content sensitivity of content segments in the path, entity confidence of entity types, rule matching degree between rule triggering conditions and path semantics, mandatory nature of regulatory clauses, and contextual coordination degree of the context in which the entity is located, and generate a vector containing multi-dimensional features.

[0072] Content sensitivity: Assigns values based on the type of sensitive information and the risk of leakage, such as ID number (10 points), name (6 points), and health data (9 points), and dynamically adjusts based on the form of content exposure (plaintext transmission +3 points, encrypted storage 0 points).

[0073] Entity confidence: Evaluates the accuracy of entity recognition, with the OCR / NER model outputting probability values (e.g., ID card number recognition confidence of 0.92, fuzzy name recognition confidence of 0.75).

[0074] Rule matching degree: Determines the degree of fit between the rule triggering conditions and the path semantics. A complete match with a mandatory rule (such as "cross-border transmission requires security assessment") is scored 10 points, while a partial match or exception scenario is scored 4-7 points.

[0075] Mandatory nature of clauses: graded according to the effectiveness of regulations, such as the mandatory level of laws (such as the Personal Information Protection Law) is 10 points, administrative regulations (such as the Data Security Management Regulations) are 8 points, and industry standards are 5 points.

[0076] Contextual collaboration: Analyzes the compliance risks of entity usage scenarios, such as the collaboration degree of "cross-border transmission of health data" is 10 points (high-risk scenario), and the collaboration degree of "internal archive encrypted storage" is 3 points (low-risk scenario).

[0077] After the five attributes are quantified into numerical values, they are combined into a multidimensional feature vector (such as [9, 0.92, 8, 10, 10]), providing a data basis for subsequent scoring.

[0078] S3.2. Comprehensively calculate the feature vectors through a preset weighted scoring function, integrate confidence interval modeling to process fuzzy semantic scenarios, and support manual adjustment of parameters or automatic optimization through reinforcement learning to achieve quantitative assessment of risk levels.

[0079] In this step, the weighting logic is as follows: weights are assigned according to business compliance priorities, for example, content sensitivity (40%) > clause mandatory (30%) > rule matching (20%) > context coordination (8%) > entity confidence (2%). Example formula: Risk score = 0.4 × sensitivity + 0.3 × clause mandatory + 0.2 × rule matching + 0.08 × context coordination + 0.02 × entity confidence.

[0080] S3.3. Based on the set risk thresholds (e.g., high risk ≥ 80 points, medium risk 60-79 points, low risk < 60 points), the calculation results are divided into three levels: "high risk", "medium risk" and "low risk". A detailed report is then generated containing risk scores, factor contribution analysis and regulatory references, and a confidence level description is added to the fuzzy path to assist decision-making.

[0081] S4. Based on the scoring results of the violation tracing path, the corresponding regulatory clauses are matched, and the original content, clause number, applicable conditions, legal domain classification information and penalty recommendations of the regulatory clauses are extracted from the regulatory knowledge graph to provide a clear legal basis for violation identification and generate an explainable causal chain description.

[0082] This step specifically includes:

[0083] S4.1. Search the regulatory knowledge graph for the end node of the violation traceability path to obtain the regulatory content corresponding to the end node.

[0084] S4.2. In-depth analysis of the semantic information contained in the violation tracing path and the rule information of the regulatory clauses in the regulatory knowledge graph. Through careful comparison, intelligent alignment of the violation tracing path and the regulatory content is achieved, accurately identifying the regulatory clause corresponding to the end node of the path;

[0085] S4.3. Extract detailed information related to the clause from the regulatory knowledge graph, including the original text of the regulatory clause, clause number, applicable conditions, jurisdiction classification information, and penalty recommendations, to provide reference for subsequent handling of violations;

[0086] S4.4. When a violation tracing path corresponds to multiple regulatory clauses, multiple candidate clauses are output simultaneously and ranked based on the path score and the degree of match between the rule and the path;

[0087] S4.5. Use the constructed violation traceability path and the matched regulatory provisions to generate an interpretable causal chain description.

[0088] S5. Output the violation result report, including:

[0089] S5.1. Collect risk scoring results, regulatory matching information, violation traceability paths, and related compliance judgment information. This includes the specific location of the violation (e.g., page number, paragraph, specific sentence), the attributes of each node and edge in the path (used to generate the traceability path structure), the risk score level, the matching regulatory clause number, the original text summary, and the corresponding handling recommendations. Organize and categorize the collected information in preparation for subsequent report generation.

[0090] S5.2. Encapsulate the collected and organized information according to the set structure;

[0091] S5.3. Generate the specific contents of the violation result report based on the structured and encapsulated information. The report includes the location information of the violation content, the traceability path structure, the scoring level, the matching regulatory basis and the handling suggestions.

[0092] Preferably, step S5 is executed to output the violation result report in the following manner:

[0093] a) Display the report content directly on the human-computer interface;

[0094] b) Automatically generate PDF reports for easy storage and distribution;

[0095] c) Provide a structured data interface to connect to the audit system, business process system, risk control platform or automatic processing engine to achieve data sharing and interaction.

[0096] In summary, the document compliance determination method based on violation tracing path scoring of the present invention can improve the interpretability and accuracy of compliance judgments, and is particularly suitable for scenarios with high requirements for data compliance, such as enterprise document management, cross-border data review, and medical finance.

[0097] The above specific examples are used to illustrate the principles and implementation methods of the present invention in detail. These examples are only used to help understand the core technical content of the present invention. Based on the above specific embodiments of the present invention, any improvements and modifications made by those skilled in the art without departing from the principles of the present invention should fall within the scope of patent protection of the present invention.

Claims

1. A document compliance determination method based on violation tracing path scoring, characterized in that: The steps include: S1. Perform structural analysis on the document to be inspected, split the document content into semantic units, and identify the sensitive information entities contained therein to form the basic data layer for compliance review; S2. Construct a violation tracing path from the sensitive information entity to the regulatory clause, where the violation tracing path includes content segments, entity types, rule triggering conditions, and regulatory clause nodes; S3. Score and calculate the violation tracing path, and determine the violation risk level of the path based on the attributes of each node and edge in the path; S4. Based on the scoring results of the violation traceability path, the corresponding regulatory provisions are matched and the original content, clause number, applicable conditions, legal jurisdiction classification information, and penalty recommendations of the regulatory provisions are extracted from the regulatory knowledge graph to provide a clear legal basis for violation identification and generate an interpretable causal chain description; S5. Output a violation result report, which includes the location information of the illegal content, the traceability path structure, the scoring level, the matching legal basis and the handling suggestions.

2. A document compliance determination method based on violation tracing path scoring according to claim 1, characterized in that: The step S1 specifically includes: S1.

1. Receive various documents to be tested, parse them, and complete content extraction and structural processing; S1.

2. Divide the parsed document content into logically clear basic semantic units using a text segmentation algorithm. S1.

3. Apply the entity recognition model to scan the text in the basic semantic unit, identify sensitive information entities, add a label to each identified entity, and record the basic semantic unit in which it is located; S1.

4. Label the basic semantic unit set of sensitive information entities to form an "entity-location-type" mapping table, providing an initial node for subsequent violation path construction.

3. A document compliance determination method based on violation tracing path scoring according to claim 2, characterized in that: The documents to be detected include three types: structured documents, semi-structured documents and image documents; a) For structured and semi-structured documents, directly parse the document format, extract the text content and format information, and output structured text data that retains the original layout. b) For image-type documents, the OCR module is first called to perform text recognition on the image to generate editable text content. Then, layout analysis technology is used to restore the document layout, distinguish the main text, header, footer and table areas, and finally output the text data with coordinate positions and layout structure information.

4. The document compliance determination method based on violation tracing path scoring according to claim 2 is characterized in that: The step S2 specifically includes: S2.

1. Based on the recognition results of the document to be detected, extract the entities marked as sensitive information and the content fragments in which they are located; S2.

2. Retrieve predefined regulatory rule sets based on sensitive entity types, match corresponding compliance rule conditions, and combine contextual semantics to determine whether the rule triggering conditions are met; S2.

3. Based on the matched rule trigger conditions, query the predefined compliance knowledge graph, locate the corresponding regulatory clause node, parse the regulatory clause content, extract structured information, and verify its compatibility with the current violation scenario; S2.

4. Concatenate "content fragment → entity type → rule trigger condition → regulatory clause" in a logical order to form a structured traceability path, supplement the contextual semantic features in the traceability path, and ensure that the path is semantically closed and logically reasonable.

5. The document compliance determination method based on violation tracing path scoring according to claim 4 is characterized in that: The step S3 specifically includes: S3.

1. For the constructed violation traceability path, extract five node and edge attributes: content sensitivity of content segments in the path, entity confidence of entity types, rule matching degree between rule triggering conditions and path semantics, mandatory nature of regulatory clauses, and contextual coordination degree of the entity context, and generate a vector containing multidimensional features. S3.

2. Comprehensively calculate the feature vectors using a preset weighted scoring function, incorporate confidence interval modeling to handle fuzzy semantic scenarios, and support manual parameter adjustment or automatic optimization through reinforcement learning to achieve quantitative risk assessment. S3.

3. Based on the set risk threshold, the calculation results are divided into three levels: "high risk", "medium risk" and "low risk". A detailed report is then generated, including risk scores, factor contribution analysis and regulatory references. Confidence levels are added to fuzzy paths to assist decision-making.

6. A document compliance determination method based on violation tracing path scoring according to claim 5, characterized in that: The step S4 specifically includes: S4.

1. Search the regulatory knowledge graph for the end node of the violation traceability path to obtain the regulatory content corresponding to the end node. S4.

2. In-depth analysis of the semantic information contained in the violation tracing path and the rule information of the regulatory clauses in the regulatory knowledge graph. Through careful comparison, intelligent alignment of the violation tracing path and the regulatory content is achieved, accurately identifying the regulatory clause corresponding to the end node of the path; S4.

3. Extract detailed information related to the clause from the regulatory knowledge graph, including the original text of the regulatory clause, clause number, applicable conditions, jurisdiction classification information, and penalty recommendations, to provide reference for subsequent handling of violations; S4.

4. When a violation tracing path corresponds to multiple regulatory clauses, multiple candidate clauses are output simultaneously and ranked based on the path score and the degree of match between the rule and the path; S4.

5. Use the constructed violation traceability path and the matched regulatory provisions to generate an interpretable causal chain description.

7. The method for determining document compliance based on violation tracing path scoring according to claim 6 is characterized in that: The step S5 specifically includes: S5.

1. Collect risk scoring results, regulatory matching information, violation traceability paths, and related compliance judgment information, organize and categorize them to prepare for subsequent report generation; S5.

2. Encapsulate the collected and organized information according to the set structure; S5.

3. Generate the specific contents of the violation result report based on the structured and encapsulated information. The report includes the location information of the violation content, the traceability path structure, the scoring level, the matching regulatory basis and the handling suggestions.

8. The method for determining document compliance based on violation tracing path scoring according to claim 7 is characterized in that: Execute step S5 to output the violation result report in the following manner: a) Display the report content directly on the human-computer interface; b) Automatically generate PDF reports for easy storage and distribution; c) Provide a structured data interface to connect to the audit system, business process system, risk control platform or automatic processing engine to achieve data sharing and interaction.

Images