Agricultural product whole-process tracing method and system based on block chain

Abstract

The invention relates to the technical field of agricultural product tracing, in particular to an agricultural product full-process tracing method and system based on a block chain, and the method comprises the following steps: S1, receiving the information generated by agricultural products in each link of a supply chain; s2, establishing association between the converted data records based on a predetermined rule, allowing a user to examine, modify or create the association between the data records, and defining explanatory association to obtain the data records containing the explanatory association; s3, displaying an evidence network formed by data records containing explanatory association in a mode of nodes and connecting lines, and allowing a user to select, organize and confirm one or more evidence paths; and S4, according to the evidence path confirmed by the user, extracting related data records and explanatory association thereof, and generating a compliance evidence packet with a predetermined structure. Diversified data and atypical operations can be effectively processed, structured compliance evidences are generated, and the reliability and credibility of a traceability system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product traceability, and in particular to a blockchain-based full-process agricultural product traceability method and system. Background Art

[0002] In a blockchain-based, end-to-end agricultural product traceability system, ensuring the authenticity and integrity of operational records and environmental data at every stage is crucial. However, data collection and submission often rely on participants at different supply chain nodes, who use varying equipment and possess varying technical expertise. This poses challenges to the accuracy and timeliness of data entry. Even if subsequent records are accurate, inaccuracies in source information can still compromise the authenticity of the traceability chain if data entry is negligent or omitted, increasing risk to the entire system.

[0003] Especially for high-value certified agricultural products, such as those with organic or geographical indication certification, their standards require stringent recordkeeping throughout the entire production process. For example, organic product certification prohibits the use of synthetic pesticides and fertilizers. If a traceability system merely accepts submitted data and lacks proactive intervention and compliance verification mechanisms, it will be unable to effectively prevent omissions or non-compliance in data entry. For example, in tea production, if management personnel fail to promptly record the use of banned pesticides, the traceability system may fail to detect records that are inconsistent with actual conditions, resulting in problems that cannot be traced promptly or unclear responsibility.

[0004] Existing technologies have shortcomings in processing and verifying raw data and need to be improved. Summary of the Invention

[0005] The purpose of the present invention is to address the above-mentioned shortcomings and propose a blockchain-based full-process traceability method and system for agricultural products.

[0006] The present invention adopts the following technical solutions: A blockchain-based full-process agricultural product traceability method, the method comprising the following steps: S1: Receives operational records and environmental data generated by agricultural products at various stages of the supply chain, as well as multiple official certification standards that agricultural products must meet, unofficial certification standards with specific detailed requirements, and supplementary explanatory materials that indicate differences from conventional operations in operational records, and converts the received information into data records that conform to a predetermined format. S2: Establishes associations between the converted data records based on predetermined rules, allowing users to review, modify, or create associations between data records, and defines explanatory associations. Explanatory associations are used to explain how the differences from conventional operations in operational records meet the requirements of unofficial certification standards or do not violate the core principles of official certification standards, resulting in data records containing explanatory associations. S3: Displays an evidence network consisting of data records containing explanatory associations in the form of nodes and connecting lines, allowing users to select, organize, and confirm one or more evidence paths to prove that the agricultural products comply with all relevant certification standards and explain the atypical operations in the operational records. S4: Based on the evidence paths confirmed by the user, extracts relevant data records and their explanatory associations, and generates a compliance evidence package with a predetermined structure. This compliance evidence package presents the agricultural products' compliance with all relevant certification standards and an explanation of the differences from conventional operations in the operational records.

[0007] Through the above solution, diverse data and atypical operations can be effectively processed, and structured compliance evidence can be generated to improve the reliability and trust of the traceability system.

[0008] Furthermore, the present application also proposes that step S2 also includes the following steps: matching the defined explanatory association with a preset probative force evaluation knowledge base, the probative force evaluation knowledge base is used to store historical certification cases and their corresponding certification standard combinations, the probative force evaluation knowledge base includes the association patterns of atypical operations and certification standards and their evaluation results, and evaluates the strength and probative force of the explanatory association based on historical cases; based on the matching results, generating and presenting expected probative force evaluation information to help users evaluate the probative force of the explanatory association and decide whether to adopt the explanatory association to support agricultural product compliance certification.

[0009] Through the above scheme, the probative force of explanatory associations can be evaluated to assist users in decision-making.

[0010] Furthermore, the present application also proposes that the steps of matching the defined explanatory association with the preset probative force evaluation knowledge base include: obtaining the user-defined explanatory association, the explanatory association containing information on the combination of atypical operation types and certification standards; retrieving historical cases or evaluation standards that directly correspond to the combination of atypical operation types and certification standards in the user-defined explanatory association in the preset probative force evaluation knowledge base; if no directly corresponding historical cases or evaluation standards are retrieved, extracting the key elements in the explanatory association, and searching the probative force evaluation knowledge base for historical cases or evaluation standards that are similar to the key elements through the preset approximate matching logic to obtain approximate matching candidates; if no match is found, performing inference analysis based on the association rules or meta-knowledge in the certification field to generate inference matching candidates; outputting the matching results to generate expected probative force evaluation information about the user-defined explanatory association.

[0011] Through the above scheme, the accuracy and coverage of the evidentiary force evaluation can be improved through multiple matching methods.

[0012] Furthermore, the present application also proposes that the steps of generating expected probative force evaluation information about user-defined explanatory associations include: extracting historical case features or evaluation standard clauses from the matching results; comparing the user-defined explanatory associations with the extracted historical case features or evaluation standard clauses to identify the points of conformity and differences between the user-defined explanatory associations and the extracted historical case features or evaluation standard clauses; determining the expected probative force conclusion of the user-defined explanatory associations based on the matching results, the identified points of conformity and the identified points of difference; combining the expected probative force conclusion, the extracted historical case features or evaluation standard clauses, the identified points of conformity and the identified points of difference to generate expected probative force evaluation information about the user-defined explanatory associations.

[0013] Through the above scheme, structured and detailed information on the assessment of the probative force can be provided.

[0014] Furthermore, the present application also proposes that the steps of determining the expected probative force conclusion of the user-defined explanatory association based on the matching results, the identified conforming points and the identified difference points include: obtaining the matching results, the matching results include their source information, the source information indicates that the matching results are derived from historical cases or evaluation criteria, and provides statistical significance data related to historical cases or the scope of application and universality of the evaluation criteria; evaluating the reliability of each source information in the matching results, and the evaluation is based on the statistical significance of historical cases or the universality of the evaluation criteria to obtain the reliability index of each source information; obtaining the identified conforming points and the identified difference points; for each identified conforming point, determining its support strength value according to the degree of correlation between its content and the corresponding certification requirements and the importance of the certification requirements; for each identified difference point, determining the potential impact value of the difference point according to the degree of deviation of its content from the corresponding certification requirements and the importance of the certification requirements; obtaining the matching results, the identified conforming points and the identified difference points, the reliability index of each source information obtained by evaluation, and the reliability index of all conforming points The support strength value and the potential impact value of all difference points are used to set weight coefficients for the reliability indicators of the obtained source information, the support strength values ​​of all conforming points and the potential impact value of all difference points. According to the set weight coefficients, the reliability indicators of the obtained source information, the support strength values ​​of all conforming points and the potential impact value of all difference points are weighted to obtain weighted index values. Algebraic operations are performed on the obtained weighted index values ​​to calculate the basic expected probative force value. According to the overall reliability level of the assessed source information and the calculated basic expected probative force value, a confidence assessment level or a probability interval range is determined, wherein when the overall reliability level of the source information decreases, the generated probability interval range is widened or the confidence assessment level is reduced. The calculated basic expected probative force value is combined with the determined confidence assessment level or probability interval range to generate an expected probative force conclusion of the user-defined explanatory association, which is the expected probative force conclusion determined based on the matching results, the identified conforming points and the identified difference points.

[0015] Through the above scheme, a more reliable and quantitative conclusion on the evaluation of the force of proof can be provided.

[0016] Furthermore, the present application also proposes that the steps for setting the weight coefficient include: obtaining dynamic change information of the certification standard system, including information on newly added certification standard types and information on adjustments to the importance of existing standard clauses; obtaining current certification target combination information of specific agricultural products, indicating the certification standards that need to be met; based on the dynamic change information of the certification standard system, setting the initial weight coefficient, adjusting the reliability index of the source information, the support strength value of the compliance point and the potential impact value of the difference point; and adjusting the weight coefficient of the relevant certification standards according to the current certification target combination information of agricultural products.

[0017] Through the above scheme, the evaluation of evidentiary power can be adapted to dynamically changing standards and specific product objectives.

[0018] Furthermore, the present application also proposes that the steps for determining the support strength value of the compliance point include: obtaining the compliance point content and the corresponding certification requirements; identifying and parsing the explanatory association path connecting the compliance point content and the certification requirements, and extracting the evidence entry type and association type on the path; based on the association rules or meta-knowledge in the proof evaluation knowledge base, evaluating the association support strength of the association path for the association between the compliance point content and the certification requirements; determining the degree of association between the compliance point content and the certification requirements based on the evaluated support strength; obtaining and considering the importance of the corresponding certification requirements; and determining the support strength value of the compliance point based on the degree of association and importance.

[0019] Through the above scheme, it is possible to quantify the support strength of the compliance points.

[0020] Furthermore, the present application also proposes that the steps for determining the potential impact value of the difference point include: obtaining the content of the difference point and the corresponding certification requirements; identifying the type of the difference point and the corresponding certification requirement type; determining the initial deviation between the content of the difference point and the corresponding certification requirement based on the identified type of the difference point and the corresponding certification requirement type through preset quantification rules; analyzing the correlation between the difference point in the evidence network to obtain the contextual information of the difference point; adjusting the initial deviation based on the contextual information and preset adjustment rules to obtain the adjusted deviation; obtaining the importance of the corresponding certification requirement; and determining the potential impact value of the difference point using the preset calculation logic based on the adjusted deviation and the obtained importance.

[0021] Through the above scheme, the potential impact of differences on compliance can be quantified.

[0022] Furthermore, the present application also proposes a blockchain-based full-process traceability system for agricultural products, which includes: a data receiving module for receiving operation records and environmental data generated by agricultural products in various links of the supply chain, as well as multiple official certification standards that agricultural products must meet, unofficial certification standards with specific detail requirements, and supplementary explanatory materials that differ from conventional operations in operation records, and converting the received information into data records that conform to a predetermined format; an association building module for establishing associations between converted data records based on predetermined rules, allowing users to review, modify or create associations between data records, and define explanatory associations, which are used to explain how the differences between operation records and conventional operations conform to the standards. The system complies with the requirements of non-official certification standards or does not violate the core principles of official certification standards to obtain data records containing explanatory associations; an evidence display module is used to display the evidence network composed of data records containing explanatory associations in the form of nodes and connecting lines, and allows users to select, organize and confirm one or more evidence paths to prove that agricultural products comply with all relevant certification standards and explain atypical operations in operation records; an evidence package generation module is used to extract relevant data records and their explanatory associations based on the evidence path confirmed by the user, and generate a compliance evidence package with a predetermined structure, which presents the compliance proof of agricultural products to all relevant certification standards and an explanation of the operation records that are different from conventional operations.

[0023] Through the above solution, a system for implementing the above method is provided.

[0024] Furthermore, the present application also proposes that the system also includes a probative force evaluation module for matching the defined explanatory associations with a preset probative force evaluation knowledge base. The probative force evaluation knowledge base is used to store historical certification cases and their corresponding certification standard combinations. The probative force evaluation knowledge base includes association patterns between atypical operations and certification standards and their evaluation results, and evaluates the strength and probative force of explanatory associations based on historical cases, generates and presents expected probative force evaluation information, helps users evaluate the probative force of explanatory associations, and decides whether to adopt the explanatory associations to support agricultural product compliance certification.

[0025] Through the above scheme, a system module is provided to realize the above-mentioned proof evaluation function.

[0026] To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only for reference and illustration and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of the method of the present invention; Figure 2Schematic diagram of the overall structure of the system of the present invention. DETAILED DESCRIPTION

[0028] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only for simple schematic illustrations and are not depicted according to actual dimensions. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0029] This embodiment provides a blockchain-based agricultural product full-process traceability method and system, combined with Figure 1 and Figure 2 shown.

[0030] refer to Figure 1 A blockchain-based agricultural product full-process traceability method includes the following steps: S1: Receives operational records and environmental data generated by agricultural products at various stages of the supply chain, as well as multiple official certification standards that agricultural products must meet, unofficial certification standards with specific detailed requirements, and supplementary explanatory materials that indicate differences from conventional operations in operational records, and converts the received information into data records that conform to a predetermined format. S2: Establishes associations between the converted data records based on predetermined rules, allowing users to review, modify, or create associations between data records, and defines explanatory associations. Explanatory associations are used to explain how the differences from conventional operations in operational records meet the requirements of unofficial certification standards or do not violate the core principles of official certification standards, resulting in data records containing explanatory associations. S3: Displays an evidence network consisting of data records containing explanatory associations in the form of nodes and connecting lines, allowing users to select, organize, and confirm one or more evidence paths to prove that the agricultural products comply with all relevant certification standards and explain the atypical operations in the operational records. S4: Based on the evidence paths confirmed by the user, extracts relevant data records and their explanatory associations, and generates a compliance evidence package with a predetermined structure. This compliance evidence package presents the agricultural products' compliance with all relevant certification standards and an explanation of the differences from conventional operations in the operational records.

[0031] Receiving operational records and environmental data generated throughout the supply chain, as well as the multiple official certification standards agricultural products must meet, unofficial certification standards with specific details, and supplementary explanations of operational differences from conventional practices, and converting this information into data records conforming to a predetermined format, involves acquiring various types of information generated at every stage of agricultural product production and distribution, including but not limited to field operation logs, storage temperature and humidity, transportation routes, quality inspection reports, and various product-related certification requirements (such as organic certification and geographical indication certification) and explanatory documents for atypical operations. This raw information may originate from different devices or be manually input in a variety of formats. Through the data reception and conversion process, this heterogeneous information is unified into structured data units that conform to the system's internal processing specifications, such as using a unified data model or data dictionary for description. The goal is to achieve standardized collection and preliminary processing of massive, multi-source, heterogeneous traceability data, laying the foundation for subsequent data integration and analysis. Among them, the supplementary explanatory materials in the operation records that are different from routine operations refer to additional explanatory documents or data provided for those behaviors or events that are not part of the standard operating procedures but actually occurred and may affect product compliance. For example, temporary protective measures taken due to sudden weather changes, emergency response after equipment failure, etc. Its purpose is to record and explain these atypical situations and provide a basis for subsequent compliance judgments. Data records that conform to the predetermined format are traceability information units that have been standardized and have a unified structure, field definition, and data type. They can be stored in the form of database records, structured files (such as JSON, XML), etc. Their purpose is to ensure that all traceability information is consistent within the system to facilitate management, query, and association.

[0032] This solution systematically handles compliance explanations for atypical operations by standardizing the reception of raw traceability information, constructing a data association graph, and introducing explanatory associations. Through visualizing the evidence network and user-organized evidence paths, a structured compliance evidence package is ultimately generated, effectively improving the integrity, interpretability, and compliance-proving power of agricultural product traceability data.

[0033] In one specific embodiment, operational records, environmental data, and other information generated by agricultural products at various stages of the supply chain are received and aggregated into a data processing platform via APIs, file uploads, or manual input. Data records are converted to a predetermined format using a predefined JSON Schema or Protobuf format, mapping data from different sources into a unified data structure. For example, fields such as "fertilizer name," "application amount," and "application date" in field fertilization records can be standardized into unified key-value pairs. Associations between the converted data records are established based on predetermined rules. Associations can be automatically established based on information such as timestamps, product batch numbers, and geographic locations. For example, tea picking records for a batch of tea on a specific date can be associated with the weather and environmental data for that day. Users are allowed to review, modify, or create associations between data records. A graphical interface displays data record nodes and their association lines, allowing users to adjust associations by dragging or clicking. To define explanatory associations, users can select an atypical operational record node, then select one or more certification standard nodes, and enter text or upload a file as an explanation. The system then establishes a specific type of association between the explanation and the operational record and the certification standard. The evidence network composed of data records with explanatory associations is displayed in the form of nodes and connecting lines. Graph database technology can be used to store data records and associations, and the evidence network diagram can be rendered through a front-end visualization library (such as D3.js). Users are allowed to select, organize, and confirm one or more evidence paths. Users can click on nodes and connecting lines on the evidence network diagram to select the data records and explanatory associations that constitute the evidence chain. The system highlights the selected path, and the user saves the path after confirmation. Based on the evidence path confirmed by the user, the relevant data records and their explanatory associations are extracted, and a compliance evidence package with a predetermined structure is generated. The system traverses all nodes and associations on the path confirmed by the user, extracts the corresponding data content, and generates a structured compliance evidence package file according to the preset XML or PDF template. The file contains the original data, association relationships, and explanatory association content.

[0034] This program improves the integrity and availability of traceability information through standardized data processing and explanatory association construction; combines evidence networks and path mechanisms to enhance the explainability of atypical operations, simplify the review process, systematically support agricultural product certification and verification, and improve the credibility and practicality of the traceability system.

[0035] However, relying solely on user-defined explanatory associations is susceptible to subjective judgment and lacks objective evaluation criteria, resulting in insufficient persuasiveness of compliance evidence packages and making it difficult to effectively support compliance proof of agricultural products in complex certification scenarios.

[0036] In this regard, the present application further proposes that step S2 also includes the following steps: matching the defined explanatory association with a preset proof strength evaluation knowledge base, the proof strength evaluation knowledge base is used to store historical certification cases and their corresponding certification standard combinations, the proof strength evaluation knowledge base includes the association patterns of atypical operations and certification standards and their evaluation results, and evaluates the strength and proof strength of the explanatory association based on historical cases; based on the matching results, generating and presenting expected proof strength evaluation information to help users evaluate the proof strength of the explanatory association and decide whether to adopt the explanatory association to support agricultural product compliance certification.

[0037] Explanatory associations can be represented through text, structured data, or association rules. The system then matches these associations against a pre-built knowledge base for probative force assessment, which includes information such as historical cases, certification clauses, operating models, and expert rules. Matching can be achieved based on keywords, semantic similarity, or reasoning, and the probative force is assessed through statistics, machine learning, or expert rules. The resulting expected probative force assessment information, such as a score, confidence level, or case summary, helps users determine whether the explanation is sufficiently persuasive.

[0038] This solution introduces an evaluation mechanism based on historical certification experience, objectively evaluates the probative value of explanatory associations, and presents the results to users, thereby improving the reliability of the compliance evidence package and the ability of traceability information to support certification standards.

[0039] In some preferred embodiments, after a user defines an explanatory association, the system extracts information about atypical operations and certification standards and matches it with historical cases in the knowledge base. The system then assesses the expected probative value of similar cases based on statistical results and generates assessment information, including a score, case summary, and assessment rationale, for the user to consider and decide whether to adopt the association for inclusion in the compliance evidence package.

[0040] This solution reduces subjectivity and uncertainty in interpretive correlations by introducing an objective assessment mechanism based on historical experience, thereby improving the reliability of compliance interpretations for atypical operations. The assessment information generated by the system helps users optimize their choices, build more convincing compliance evidence packages, and enhance the effectiveness of traceability systems in certification and regulatory oversight.

[0041] However, direct matching may not be able to find completely matching historical cases or evaluation criteria, resulting in inaccurate evaluation results or the inability to conduct evaluation.

[0042] In this regard, the present application further proposes that the steps of matching the defined explanatory association with the preset probative force evaluation knowledge base include: obtaining the user-defined explanatory association, the explanatory association containing information on the combination of atypical operation types and certification standards; retrieving historical cases or evaluation standards that directly correspond to the combination of atypical operation types and certification standards in the user-defined explanatory association in the preset probative force evaluation knowledge base; if no directly corresponding historical cases or evaluation standards are retrieved, the key elements in the explanatory association are extracted, and historical cases or evaluation standards that are similar to the key elements are searched in the probative force evaluation knowledge base through the preset approximate matching logic to obtain approximate matching candidates. If no match is found, reasoning analysis is performed based on the association rules or meta-knowledge in the certification field to generate inferential matching candidates; the matching results are output to generate expected probative force evaluation information about the user-defined explanatory association.

[0043] Among them, obtaining user-defined explanatory associations, which include information on the combination of atypical operation types and certification standards, refers to receiving user-input association information used to explain how the atypical aspects of agricultural product operation records comply with or do not violate certification standards. This information clearly indicates the specific atypical operation types involved and the set of certification standards that need to be evaluated with reference, with the purpose of providing clear input and evaluation basis for subsequent probative force evaluation; extracting key elements from explanatory associations refers to identifying and extracting core information points that have an important impact on the probative force evaluation from the text description of the user-defined explanatory associations, such as operating behaviors, environmental conditions, causes, results, or remedial measures taken. Specifically, this can be achieved through natural language processing technologies such as keyword extraction, entity recognition, or semantic analysis. Its purpose is to convert complex explanatory associations into structured or semi-structured information that can be used for matching and analysis; the preset approximate matching logic refers to an algorithm or rule set used to measure the degree of similarity between the extracted key elements and historical cases or evaluation standard descriptions in the probative force evaluation knowledge base. Specifically, it can be achieved based on text similarity calculation, feature vector matching, or concept association analysis. Its purpose is to identify key elements that have an important impact on the probative force evaluation when there is no complete direct correspondence. Approximate matching candidates refer to historical cases or evaluation criteria found in the probative force evaluation knowledge base through approximate matching logic that have a certain similarity with the user-defined explanatory association. They are not completely consistent, but can serve as a reference for evaluating the probative force of the user-defined explanatory association. Association rules or meta-knowledge in the certification field refer to the principles, logic or experience summaries generally accepted in the specific agricultural product certification field for judging whether operational behavior complies with the standards. Specifically, they can include industry norms, expert experience, logical reasoning rules or ontology models, and their purpose is to provide a domain knowledge foundation for reasoning analysis. Reasoning analysis refers to the process of using association rules or meta-knowledge in the certification field to logically deduce user-defined explanatory associations to determine whether they are likely to comply with or not violate relevant certification standards. Its purpose is to make a principled judgment on the probative force of explanatory associations based on domain knowledge in the absence of direct or similar cases. Reasoning matching candidates refer to the conclusions or bases generated through the reasoning analysis process that indicate that the user-defined explanatory association is likely to comply with or not violate relevant certification standards. They are possibility judgments or principled guidance derived from domain knowledge.

[0044] This scheme improves the accuracy and adaptability of explanatory association evaluation by combining a multi-level strategy of direct matching, approximate matching and inference matching, and enhances the system's ability and robustness to cope with complex and atypical operations.

[0045] In some preferred embodiments, specifically, suppose a user defines an explanatory association to explain that, after picking, a batch of organic tea leaves were temporarily left outdoors for one hour due to sudden heavy rain, followed by a withering process with enhanced ventilation. The user believes this operation meets the flexibility requirements for fresh leaf handling in the organic certification standards. The system first obtains this explanatory association and identifies the atypical operation type as "fresh leaves left outdoors" and the certification standard combination as "Organic Certification Standard (Fresh Leaf Handling)." The system then attempts to directly search the probative force assessment knowledge base for cases or standards that exactly match "fresh leaves left outdoors" and "Organic Certification Standard (Fresh Leaf Handling)." Assuming no direct matching items are found, the system further extracts key elements from the explanatory association, such as "left outdoors," "fresh leaves," "one hour," "heavy rain," "withering," "organic certification," "force majeure," and "enhanced ventilation." The system then uses pre-defined approximate matching logic, such as a text similarity algorithm, to search the knowledge base for historical cases similar to these elements. A close match may be found, such as a case in which organic vegetables were temporarily stacked after harvest due to transportation delays, and the case was accepted by the certification body by documenting the cause and implementing remedial measures. If a close match is not found, the system infers based on association rules within the certification domain. For example, the rule base contains a rule that states: "Temporary operational deviations due to force majeure may not affect the final certification result if they are well documented and reasonable remedial measures are taken." The system analyzes the user-defined explanatory associations and identifies "heavy rain" as force majeure, "open-air storage" as a deviation, and "withering treatment with enhanced ventilation" as a remedial measure. The system then uses other data records (such as weather records) to corroborate the occurrence of "heavy rain." Based on this rule, the system concludes that "this operational deviation may comply with organic certification principles" and generates an inferred match candidate. Ultimately, the system outputs the close match candidate and / or inferred match candidate to generate information for the subsequent generation of an assessment of the expected probative value of the user-defined explanatory association.

[0046] This solution improves the matching success rate of explanatory associations through a multi-level matching strategy. Even if there is a lack of direct corresponding items, evaluation basis can be obtained through similarity search or knowledge reasoning, ensuring the continuity and comprehensiveness of the evaluation and improving the effectiveness of agricultural product compliance certification.

[0047] However, simply outputting matching results is not enough to guide users in evaluating the probative force of explanatory associations. There is an urgent need to provide a method to convert matching results into user-understandable and applicable expected probative force assessment information to improve the practicality and effectiveness of the assessment.

[0048] In this regard, the present application further proposes the steps of generating expected probative force evaluation information about user-defined explanatory associations, including: extracting historical case features or evaluation standard clauses from the matching results; comparing the user-defined explanatory associations with the extracted historical case features or evaluation standard clauses to identify the points of conformity and differences between the user-defined explanatory associations and the extracted historical case features or evaluation standard clauses; determining the expected probative force conclusion of the user-defined explanatory associations based on the matching results, the identified points of conformity and the identified points of difference; combining the expected probative force conclusion, the extracted historical case features or evaluation standard clauses, the identified points of conformity and the identified points of difference to generate expected probative force evaluation information about the user-defined explanatory associations.

[0049] Among them, the matching result refers to the output information obtained after matching the user-defined explanatory association with the preset probative force evaluation knowledge base, which may include directly matched historical cases, evaluation standards, approximate matching candidates or inferential matching candidates; historical case features refer to key information extracted from the matched historical cases, such as the atypical operation types involved in the case, certification standard combinations, proof processes, evaluation conclusions, etc.; evaluation standard clauses refer to specific regulations, requirements or evaluation details extracted from the matched evaluation standards; conformity points refer to the consistency or similarity between the user-defined explanatory association and the extracted historical case features or evaluation standard clauses; difference points refer to the difference or deviation between the user-defined explanatory association and the extracted historical case features or evaluation standard clauses; expected probative force conclusion refers to a comprehensive evaluation result of the probative force of the user-defined explanatory association based on the matching results, conformity points and difference points, which can be a score, grade or probability range; expected probative force evaluation information refers to the evaluation report or summary presented to the user, which is composed of the expected probative force conclusion, extracted historical case features or evaluation standard clauses, identified conformity points and identified difference points.

[0050] This solution compares user-defined explanatory connections with historical case characteristics or evaluation criteria, identifying points of agreement and discrepancies, and assessing their probative force. It comprehensively considers the matching results, the positive impact of points of agreement, and the negative impact of points of discrepancy to form a comprehensive probative force assessment conclusion, presenting key information to the user along with the assessment results. This process enhances the credibility and usability of explanatory connections within the traceability system, providing users with a clearer understanding of their probative force.

[0051] In some preferred embodiments, it can be specifically implemented as follows: suppose the user defines an explanatory association to explain that the withering time of a batch of tea leaves was extended by 2 hours compared to normal due to unexpected weather conditions after picking. The user believes that this meets the requirement that "the organic processing standard allows the adjustment of process parameters under specific environmental conditions to ensure product quality." The system retrieves a historical case through matching. In this case, an organic tea garden also extended the withering time due to similar weather conditions. The final product passed the organic certification and the evaluation conclusion was "strong proof." At the same time, the system also matches an evaluation standard clause, which stipulates that "under the influence of force majeure or specific environmental factors, it is allowed to fine-tune some process parameters on the premise of ensuring product quality and complying with core principles. Detailed records and reasonable explanations must be provided." The system extracts features such as weather conditions, adjustment time, subsequent processing, and final certification results from historical cases, and extracts relevant clauses from the evaluation standards. The system then compares the user-defined explanatory associations with the extracted historical case features and evaluation criteria clauses, identifying points of agreement. For example, the extended withering time in the user-defined explanatory associations is similar to that in historical cases, the weather emergency causes are consistent with the environmental factors described in historical cases and the evaluation criteria, and the user-defined explanatory associations mentioning compliance with organic processing standards are consistent with the evaluation criteria clauses. The system also identifies discrepancies. For example, the user-defined explanatory associations may not provide detailed follow-up measures or provide insufficient justification. Based on these matching results, points of agreement, and points of disagreement, the system conducts a comprehensive assessment and determines that the expected probative strength of the user-defined explanatory associations may be "medium to high probative strength, with recommendation for additional follow-up information." Finally, the system combines this conclusion with the extracted historical case features, evaluation criteria clauses, and identified points of agreement and disagreement to generate an expected probative strength assessment, such as an assessment report or a user interface display of detailed assessment results, including reference cases, relevant standards, points of agreement, points of disagreement, and the final probative strength assessment conclusion and improvement recommendations.

[0052] Through the above technical solution, the matching results can be effectively utilized and converted into expected probative force evaluation information that can be understood and used by users, so that users can clearly understand the basis, process and conclusions of the evaluation, and thus better evaluate and utilize user-defined explanatory associations and judge their reliability and validity.

[0053] This proposal points out that if we only rely on simple rules or quantitative comparisons to judge the probative force, ignoring the reliability of the source of the matching results and the actual influence and mutual relationship between the points of conformity and difference, it will easily lead to inaccurate evaluation and difficulty in coping with complex and changing application scenarios.

[0054] In this regard, the present application further proposes the steps of determining the expected probative force conclusion of the user-defined explanatory association based on the matching results, the identified conforming points and the identified difference points, including: obtaining the matching results, the matching results including their source information, the source information indicating that the matching results are derived from historical cases or evaluation criteria, and providing statistical significance data related to historical cases or the scope of application and universality of the evaluation criteria; evaluating the reliability of each source information in the matching results, and the evaluation is based on the statistical significance of historical cases or the universality of the evaluation criteria to obtain the reliability index of each source information; obtaining the identified conforming points and the identified difference points; for each identified conforming point, determining its support strength value according to the degree of correlation between its content and the corresponding certification requirements and the importance of the certification requirements; for each identified difference point, determining the potential impact value of the difference point according to the degree of deviation between its content and the corresponding certification requirements and the importance of the certification requirements; obtaining the matching results, the identified conforming points and the identified difference points, the reliability index of each source information obtained by evaluation, and the reliability index of all conforming points. The support strength value and the potential impact value of all difference points are used to set weight coefficients for the reliability indicators of the obtained source information, the support strength values ​​of all conforming points and the potential impact value of all difference points. According to the set weight coefficients, the reliability indicators of the obtained source information, the support strength values ​​of all conforming points and the potential impact value of all difference points are weighted to obtain weighted index values. Algebraic operations are performed on the obtained weighted index values ​​to calculate the basic expected probative force value. According to the overall reliability level of the assessed source information and the calculated basic expected probative force value, a confidence assessment level or a probability interval range is determined, wherein when the overall reliability level of the source information decreases, the generated probability interval range is widened or the confidence assessment level is reduced. The calculated basic expected probative force value is combined with the determined confidence assessment level or probability interval range to generate an expected probative force conclusion of the user-defined explanatory association, which is the expected probative force conclusion determined based on the matching results, the identified conforming points and the identified difference points.

[0055] Among them, source information refers to metadata used to identify the origin of the matching result, which can specifically indicate that the matching result comes from a case record in the historical certification case database, or from an official or unofficial evaluation standard text, and its purpose is to provide a basis for the subsequent evaluation of the reliability of the matching result; the reliability index refers to a quantitative expression of the trustworthiness of the source information, which can be a numerical score, a grade classification or a confidence interval, and its purpose is to distinguish the reference value of different source information for the evaluation of the probative force; the support strength value refers to a quantitative expression of the degree of positive contribution of a single conforming point to the probative force of the explanatory association, and its It can be a positive value, the purpose of which is to measure the extent to which the conformity point enhances the credibility of the explanatory association; the potential impact value refers to the quantitative expression of the negative impact of a single difference point on the probative force of the explanatory association, which can be a negative value or a value indicating risk, the purpose of which is to measure the extent to which the difference point weakens the credibility of the explanatory association; the weight coefficient refers to the relative importance factor given to different input indicators in the weighted operation, which can be a set of values, the purpose of which is to adjust the contribution ratio of different factors in the comprehensive evaluation; the weighted operation refers to multiplying each indicator with its corresponding weight coefficient The process of summing or performing other combined calculations, which can adopt weighted average, weighted summation, etc., is aimed at comprehensively considering the influence of multiple factors; algebraic operation refers to further mathematical calculation of the index value obtained by weighted operation, which may include summation, difference, product, ratio or more complex function calculation, and its purpose is to convert the weighted comprehensive index into a basic probative value; the basic expected probative value refers to the preliminary probative value obtained after comprehensively considering the reliability of the source, the support of the conformity point and the influence of the difference point, which can be a continuous value or a discrete level, and its purpose is to provide a core The result of the probative force assessment; the overall reliability level refers to the overall trustworthiness judgment obtained after a comprehensive assessment of the reliability indicators of all source information. It can be a summarized reliability score or grade, the purpose of which is to reflect the reliability of the overall basis supporting the matching result; the confidence assessment level refers to the qualitative grading of the trustworthiness of the basic expected probative force value, which can include "high confidence", "medium confidence", "low confidence", etc., the purpose of which is to provide an easy-to-understand reliability judgment; the probability interval range refers to a possible value range given around the basic expected probative force value, which can be expressed as "[minimum value, maximum value]" or "base value ± deviation", the purpose of which is to quantify the uncertainty of the probative force assessment result; the expected probative force conclusion of the user-defined explanatory association refers to the assessment result of the probative force of the explanatory association finally presented to the user, which can be a text description or structured data that combines the basic expected probative force value with the confidence information, the purpose of which is to provide the user with a comprehensive probative force judgment that contains uncertainty information.

[0056] This solution evaluates the reliability of matching results, quantifies the impact of conformity points and discrepancy points, and performs weighted calculations based on weight coefficients to derive the basic expected probative force value, ultimately determining the confidence level and forming a comprehensive probative force conclusion, thereby improving the accuracy and credibility of the compliance explanation of atypical operations.

[0057] In some preferred embodiments, specifically, after obtaining the matching results and their source information, the system can evaluate the reliability of the source information based on the statistical significance P value of the historical case or the authority level of the evaluation standard. For example, for historical cases with a statistical significance P value less than 0.05, the reliability index can be set to 0.9; for P values ​​between 0.05 and 0.1, the reliability index is set to 0.7; for P values ​​greater than 0.1, the reliability index is set to 0.5. For evaluation standards, the reliability index of national mandatory standards can be set to 1.0; the reliability index of industry recommended standards is set to 0.8; and the reliability index of internal enterprise standards is set to 0.6. After obtaining the conforming points and difference points, the system can determine the support strength value and potential impact value based on the preset rule base. For example, for a conforming point, if its content directly corresponds to the key mandatory clauses in the certification standard and the degree of correlation is high, its support strength value can be set to +10; if it corresponds to a non-key recommended clause, the support strength value is set to +3. For a difference point, if the deviation violates a key mandatory clause and the degree of deviation is significant, the potential impact value can be set to -15; if the deviation only violates a non-key recommended clause, the potential impact value is set to -5. Weighting coefficients can be set based on the type of certification standard, the characteristics of the agricultural product, or user configuration. For example, the reliability of the source information can be weighted as 0.4, the total support strength of the conforming points as 0.4, and the total potential impact of the difference points as 0.2. The basic expected probative force value can be calculated using a weighted summation, for example: basic value = sum of source reliability indicators * 0.4 + sum of support strength of conforming points * 0.4 + sum of potential impact of difference points * 0.2. Finally, the basic value is mapped to a confidence level or probability interval based on the overall reliability level of the source information (e.g., the average of all source reliability indicators). For example, if the overall reliability average is greater than 0.8, the confidence level is "high"; if it is between 0.6 and 0.8, it is "medium"; and if it is less than 0.6, it is "low." The final conclusion can be expressed as "Expected probative force: [base value], confidence level: [level]."

[0058] This technical solution comprehensively evaluates the source reliability of the matching results, the supporting role of the matching points and the negative impact of the difference points, and combines weighted calculation with confidence assessment to generate more accurate, reliable and probative conclusions that contain uncertainty information, effectively improving the assessment accuracy of explanatory associations.

[0059] However, if the weight coefficient is fixed, it will not be able to adapt to the dynamic changes of the certification standard system and the diversity of agricultural product certification objectives, which may lead to distorted evaluation results.

[0060] In this regard, the present application further proposes that the steps for setting the weight coefficient include: obtaining dynamic change information of the certification standard system, including information on newly added certification standard types and information on adjustments to the importance of existing standard clauses; obtaining current certification target combination information for specific agricultural products, indicating the certification standards that need to be met; based on the dynamic change information of the certification standard system, setting the initial weight coefficient, adjusting the reliability index of the source information, the support strength value of the compliance point and the potential impact value of the difference point; and adjusting the weight coefficient of the relevant certification standards according to the current certification target combination information of agricultural products.

[0061] Among them, the dynamic change information of the certification standard system refers to the changes in the certification standard system, which may include information on newly added certification standard types and information on adjustments to the importance of existing standard clauses, with the purpose of obtaining changes in the external environment that affect the evaluation results; information on newly added certification standard types refers to the types of certification standards newly added to the certification system, which can be achieved by receiving external update data packages or monitoring official information releases, with the purpose of identifying new evaluation dimensions; information on adjustments to the importance of existing standard clauses refers to information on changes in the weight or degree of influence of certain clauses in the existing certification standards in the evaluation, which can be achieved by receiving standard update notifications or parsing standard revision texts, with the purpose of reflecting changes in the emphasis of internal requirements of the standards; information on the current certification target combination of specific agricultural products refers to information on which specific sets of certification standards need to be met for a specific agricultural product, which can be achieved by user input or automatic matching by the system according to product type, with the purpose of clarifying the scope and focus of the evaluation; certification standards that need to be met refer to the specific list of certification standards that specific agricultural products need to meet The table can be expressed in the form of a list of standard identifiers or standard names, and its purpose is to provide a basis for evaluation; the reliability index of source information refers to the quantitative value of the trust level of the matching result source information, which can be determined based on historical data statistics or expert evaluation, and its purpose is to measure the effectiveness of the source of evidence; the support strength value of the compliance point refers to the quantitative value of the contribution of the identified compliance point to the proof of compliance of agricultural products with the certification requirements, which can be determined by a calculation method based on the degree of correlation between the content of the compliance point and the certification requirements and the importance of the certification requirements, and its purpose is to measure the strength of positive evidence; the potential impact value of the difference point refers to the quantitative value of the negative impact of the identified difference point on the proof of compliance of agricultural products with the certification requirements, which can be determined by a calculation method based on the degree of deviation between the content of the difference point and the certification requirements and the importance of the certification requirements, and its purpose is to measure the risk of negative evidence; the weight coefficient of the relevant certification standard refers to the proportion of the certification standard related to the specific agricultural product certification target in the overall evaluation, which can be expressed in the form of a number or proportion, and its purpose is to highlight the influence of key certification standards.

[0062] This plan dynamically adjusts the weight coefficients, combines changes in certification standards and agricultural product certification goals, and implements a flexible and adaptive evaluation mechanism to improve the accuracy and adaptability of the expected proof force assessment and avoid evaluation distortion caused by fixed weights.

[0063] In some preferred embodiments, specifically, assuming that a compliance assessment needs to be conducted on a batch of organic tea exported to the European Union, the system can dynamically adjust the weight coefficient according to changes in the certification standards, such as increasing the weight of data related to key testing items, to ensure that the assessment results accurately reflect the degree of compliance under different standards.

[0064] Through the above technical solution, the weights of various factors in the evaluation model can be flexibly adjusted according to the dynamic changes of the certification standard system and the certification objectives of specific agricultural products, so that the evaluation process of the expected probative force conclusion can adapt to changes in the external environment and internal needs, thereby improving the accuracy and reliability of the evaluation results.

[0065] However, it is difficult to accurately assess the strength of the association between compliance points and certification requirements by relying solely on literal matching and fixed weights. The lack of in-depth analysis of the chain of evidence leads to inaccurate assessment of support strength values, affecting the reliability of compliance judgments.

[0066] In this regard, the present application further proposes that the steps for determining the support strength value of the compliance point include: obtaining the compliance point content and the corresponding certification requirements; identifying and parsing the explanatory association path connecting the compliance point content and the certification requirements, and extracting the evidence entry type and association type on the path; based on the association rules or meta-knowledge in the proof evaluation knowledge base, evaluating the association support strength of the association path for the association between the compliance point content and the certification requirements; determining the degree of association between the compliance point content and the certification requirements based on the evaluated support strength; obtaining and considering the importance of the corresponding certification requirements; and determining the support strength value of the compliance point based on the degree of association and importance.

[0067] Among them, the explanatory association path refers to a series of evidence items and association relationships that connect the content of the compliance point and the corresponding certification requirements. It can be specifically composed of multiple data record nodes and association lines connecting these nodes. Its purpose is to show how the content of the compliance point supports or explains the satisfaction of the certification requirements; Among them, the evidence item type refers to the category of data record nodes contained in the explanatory association path, which can specifically include operation records, environmental data, supplementary explanatory materials, etc., and its purpose is to distinguish evidence information of different sources and natures; Among them, the association type refers to the category of the relationship between the evidence items on the explanatory association path, which can specifically include proof relationship, explanation relationship, causal relationship, etc., and its purpose is to describe the logical or factual connection between the evidence items; Among them, the knowledge of probative force assessment is the key to the effectiveness of the assessment. A knowledge base refers to a collection of knowledge stored for evaluating the reliability and validity of evidence. Specifically, it may include historical certification case data, expert experience rules, statistical analysis models, etc. Its purpose is to provide a basis for evaluating the support strength of association paths; wherein, association rules or meta-knowledge refer to the rules or advanced knowledge used for reasoning and evaluating the support strength of association paths in the probative force evaluation knowledge base. Specifically, it may be a pattern obtained by summarizing and analyzing a large number of historical cases or an evaluation standard set by domain experts. Its purpose is to guide the quantitative evaluation of the probative force of a specific association path; wherein, the association support strength refers to the quantitative evaluation result of the degree to which the association path supports the certification requirements for the content of the compliance point. Specifically, it may be a numerical value or a grade. Its purpose is to measure the effectiveness of the association path in proving compliance.

[0068] This solution systematically evaluates the strength of the association between compliance points and certification requirements by combining evidence chain analysis with association rules in the knowledge base, avoiding subjective judgment, improving the objectivity and accuracy of support strength value assessment, and combining the importance of certification requirements to provide a reliable basis for the expected proof force assessment and enhance the reliability of agricultural product compliance assessment.

[0069] In some preferred embodiments, for example, assume that the content of a compliance point is "a certain biological pesticide is used" and the corresponding certification requirement is the requirement of "prohibiting the use of chemical synthetic pesticides" in the organic certification standard. The process of determining the support strength value of the compliance point can be carried out as follows: First, obtain the content of the compliance point and the corresponding certification requirement. Then, identify and parse the explanatory association path connecting the compliance point content of "a certain biological pesticide is used" and the certification requirement of "prohibiting the use of chemical synthetic pesticides." This path may include: the compliance point (a certain biological pesticide is used) is connected to the evidence item (biological pesticide purchase record) through a proof relationship, the purchase record is connected to the evidence item (biological pesticide use record) through a proof relationship, and the use record is connected to the certification requirement (prohibiting the use of chemical synthetic pesticides) through a compliance relationship. In this process, the evidence item type (e.g., supplementary explanatory materials, operation records) and the association type (e.g., proof relationship, compliance relationship) on the path are extracted. Next, based on the association rules or meta-knowledge in the probative force evaluation knowledge base, for example, the knowledge base may contain the rule that "the use of certified biological pesticides with complete purchase and use records usually has a high probative force for organic certification", the association path is evaluated for the association support strength between the compliance point content and the certification requirements, for example, the evaluation result is a high support strength. Based on the high support strength of the evaluation, the degree of association between the compliance point content and the certification requirements is determined to be high. At the same time, the importance of the corresponding certification requirements is obtained and considered. For example, "the prohibition of the use of chemical synthetic pesticides" is a core requirement of organic certification and its importance is high. Finally, combined with the high degree of association and high importance, the support strength value of the compliance point is determined to be a high value, indicating that the compliance point provides strong support for meeting this important certification requirement.

[0070] This solution analyzes the explanatory association path between compliance points and certification requirements, and combines the knowledge base of evidentiary assessment and the importance of certification requirements to accurately quantify the support strength value, thereby improving the accuracy and credibility of agricultural product compliance assessment. It is particularly suitable for complex scenarios such as atypical operations, and solves the technical difficulties of support strength assessment in complex evidence networks.

[0071] This issue points out that relying solely on setting weight coefficients to adjust the impact of difference points lacks in-depth analysis of the content of the difference points and their specific relationship with certification requirements in the evidence network, resulting in insufficient assessment granularity and incomplete risk reflection, which may affect the accuracy of compliance assessment.

[0072] In this regard, the present application further proposes that the steps for determining the potential impact value of the difference point include: obtaining the content of the difference point and the corresponding certification requirements; identifying the type of the difference point and the corresponding certification requirement type; determining the initial deviation between the content of the difference point and the corresponding certification requirement based on the identified type of the difference point and the corresponding certification requirement type through preset quantification rules; analyzing the correlation between the difference point in the evidence network to obtain the contextual information of the difference point; adjusting the initial deviation based on the contextual information and preset adjustment rules to obtain the adjusted deviation; obtaining the importance of the corresponding certification requirement; and determining the potential impact value of the difference point using the preset calculation logic based on the adjusted deviation and the obtained importance.

[0073] Among them, the preset quantitative rules refer to the rules for converting the qualitative or semi-quantitative deviation between the content of the difference point and the certification requirements into numerical values, which can be implemented by a scoring table based on expert experience, a statistical model based on historical data, or a quantitative function based on specific standards; the evidence network refers to a graph structure composed of data records and the associations between them, with nodes representing data records and edges representing associations; the association relationship refers to the way and type of connection between nodes in the evidence network, which can represent causal, support, contradiction, explanation and other relationships; contextual information refers to the position of the difference point in the evidence network, its connection with other nodes and associations, and the meaning represented by these connections, which may include other evidence directly or indirectly related to the difference point, the type and strength of explanatory associations, etc.; the preset adjustment rules refer to the rules for correcting the initial deviation based on contextual information, which can enhance or weaken the impact of the initial deviation based on contextual information; the preset calculation logic refers to a mathematical model or algorithm that calculates the final potential impact value based on the adjusted deviation and the importance of the certification requirements, which can adopt a weighted average, multiplication model or other functional relationship.

[0074] This solution preliminarily quantifies the degree of deviation by identifying the difference points and the types of certification requirements, and makes adjustments based on the contextual relationship of the difference points in the evidence network to further improve the accuracy of the deviation assessment. Finally, the importance of the certification requirements is integrated to calculate the potential impact value of the difference points, thereby achieving a refined assessment of the actual risk level of the difference points in a specific environment. This series of steps is organically combined to make the assessment of the potential impact of the difference points more comprehensive and accurate. The potential impact value of the difference points determined in this way serves as a key input for the subsequent calculation of the expected probative force conclusion and the setting of the weight coefficient, which can significantly improve the reliability of the overall compliance assessment. By comprehensively considering the specific nature of the difference points, the type and importance of the certification requirements violated, and the position and relationship of the difference points in the entire evidence system, this solution can more accurately quantify the potential negative impact of non-compliant operations on the compliance of agricultural product certification, and provide a more reliable basis for users to evaluate the probative force of explanatory associations.

[0075] In some preferred embodiments, specifically, suppose a discrepancy is discovered in the traceability system. For example, the picking records for a batch of tea indicate a picking date earlier than the local harvest date, while organic certification standards have specific requirements for picking times. First, the system retrieves the discrepancy (picking date earlier than specified) and the corresponding certification requirement (the organic certification standard's requirements for picking time). Next, the system identifies the discrepancy type as "operation time discrepancy" and the corresponding certification requirement type as "organic standard - time requirement." Based on pre-set quantification rules, for example, based on the number of days or degree of deviation, an initial deviation is determined. A picking date earlier than specified may be quantified as a higher initial deviation value. The system then analyzes the discrepancy's relationships within the evidence network, for example, to determine whether there are explanatory links explaining the reason for early picking (e.g., rushing harvest due to sudden weather changes), whether other evidence (e.g., weather records, rushing harvest application records) supports this explanation, or whether other evidence (e.g., picking records from other tea gardens during the same period) contradicts the discrepancy. Based on this contextual information, the system adjusts the initial deviation according to the preset adjustment rules. For example, if there is a reasonable explanation and supporting evidence, the initial deviation may be lowered; if there is contradictory evidence or no explanation, the initial deviation may be increased or maintained unchanged. At the same time, the system obtains the importance of the corresponding certification requirements. The provisions on picking time in the organic certification standards may be marked as medium or high importance. Finally, based on the adjusted deviation and the obtained importance, the preset calculation logic is applied, for example, multiplying the adjusted deviation by the importance or calculating through other functions to determine the potential impact value of the difference point. This value reflects the potential negative impact of the early picking operation on the final organic certification compliance.

[0076] This solution achieves a refined assessment of the potential impact of difference points by comprehensively considering the difference point type, certification requirement type and its contextual information in the evidence network. It can accurately reflect its actual risk level in a specific environment, thereby improving the accuracy and reliability of compliance assessment results.

[0077] However, only having methodological processes but lacking corresponding system implementation makes it difficult to ensure their effective implementation in actual agricultural product traceability scenarios, affecting the smooth execution of key links such as data recording, association construction, information display, and evidence package generation, as well as the overall traceability efficiency.

[0078] refer to Figure 2 In this regard, the present application further proposes a blockchain-based full-process traceability system for agricultural products, which is applied to a blockchain-based full-process traceability method for agricultural products. The system includes: a data receiving module for receiving operation records and environmental data generated by agricultural products in various links of the supply chain, as well as multiple official certification standards that agricultural products need to meet, unofficial certification standards with specific detail requirements, and supplementary explanatory materials in operation records that are different from conventional operations, and converting the received information into data records that conform to a predetermined format; an association construction module for establishing associations between converted data records based on predetermined rules, allowing users to review, modify or create associations between data records, and define explanatory associations, which are used to explain the associations in operation records with How the differences in routine operations meet the requirements of non-official certification standards or do not violate the core principles of official certification standards, and derive data records containing explanatory associations; an evidence display module is used to display the evidence network composed of data records containing explanatory associations in the form of nodes and connecting lines, and allow users to select, organize and confirm one or more evidence paths to prove that agricultural products comply with all relevant certification standards and explain the atypical operations in the operation records; an evidence package generation module is used to extract relevant data records and their explanatory associations based on the evidence path confirmed by the user, and generate a compliance evidence package with a predetermined structure, which presents the proof of compliance of agricultural products to all relevant certification standards and an explanation of the differences from routine operations in the operation records.

[0079] The data receiving module refers to the component used to collect various raw information generated during the agricultural product traceability process. Specifically, it can be a data acquisition interface, a data parser, or a data format converter. Its purpose is to unify heterogeneous raw data into standardized data records, laying the foundation for subsequent processing. The association building module refers to a component used to establish logical connections between standardized data records. Specifically, it can be a graph database builder, a rule engine, or a user interface. Its purpose is to build a data network that reflects the agricultural product traceability chain and compliance proof logic, and allows users to intervene, adjust, and supplement interpretations. The evidence display module refers to the component used to present the constructed data network to the user in a visual manner. It can be a graphics rendering engine, a web front-end component, or a data visualization tool. Its purpose is to enable users to intuitively understand the relationship between data and conveniently select and organize proof paths; The evidence package generation module refers to a component used to extract relevant information from the data network according to the user-specified proof path and package and output it according to specific specifications. It can be a document generator, a data export tool or a report generation service. Its purpose is to integrate complex traceability and compliance information into a format that is easy to audit and verify.

[0080] Structured data records received by the data receiving module are simultaneously submitted to the blockchain system for storage. Based on pre-set policies, the system can choose to upload the complete data record or its summary information (such as a hash value) to the blockchain, balancing on-chain storage burden and security requirements. Preferably, the blockchain platform can adopt a consortium chain structure, using a blockchain framework such as Hyperledger Fabric or FISCO BCOS, to support multi-party data co-management and auditing. All uploaded data will be accompanied by a system-generated timestamp and verified through a digital signature mechanism to ensure the authenticity and immutability of the data source.

[0081] This solution establishes a complete system architecture by setting up modules for data reception, association building, evidence presentation, and evidence package generation, providing full support for the entire process, from unified data processing to compliance evidence output. The collaborative work of these modules not only improves the efficiency of data processing and presentation, but also enhances the ability to interpret atypical operations and the credibility of traceability results, effectively addressing key issues in the practical application of agricultural product traceability.

[0082] In some preferred embodiments, the blockchain-based agricultural product traceability system can be deployed on a server cluster. The data receiving module can be implemented as a set of API interfaces and data parsing services, responsible for receiving data uploaded by farms, processing plants, logistics companies, and other parties, and storing it in a structured database. The association building module can be implemented as a standalone software service, which reads data records from the database and automatically establishes associations based on preset rules (e.g., based on timestamps, batch numbers, geographic locations, etc.). It also provides a user interface that allows certification experts or administrators to manually adjust associations or add explanatory associations, which can be stored in the association database. The evidence presentation module can be implemented as the front-end of a web application, which retrieves data records and association information by calling back-end services and uses a graph visualization library (e.g., D3.js or Cytoscape.js) to present the evidence network in a user interface. Users can select and organize evidence paths by clicking on nodes and connecting lines. The evidence package generation module can be implemented as another back-end service, which receives the evidence path information confirmed by the user, extracts the corresponding original data records and explanatory associated text from the database, and formats and packages them for output in a predetermined compliant evidence package format (for example, a PDF document or a JSON file).

[0083] Through the above technical solution, a system is provided that can realize the full-process traceability method of agricultural products. Through modular design, the system can effectively receive, process, display and generate traceability information of agricultural products, thereby ensuring the quality, safety and compliance of agricultural products. It solves the problems of data recording, association, display and evidence package generation in the full-process traceability of agricultural products, and enables the traceability method to be effectively applied in actual scenarios.

[0084] However, relying solely on manually defined explanatory associations may be subjective and uncertain, and lack objective evaluation criteria, making it difficult for users to accurately judge the probative value of explanatory associations, thereby affecting the reliability of agricultural product compliance certification.

[0085] In this regard, the present application further proposes that the system also includes a probative force evaluation module for matching the defined explanatory associations with a preset probative force evaluation knowledge base. The probative force evaluation knowledge base is used to store historical certification cases and their corresponding certification standard combinations. The probative force evaluation knowledge base includes association patterns between atypical operations and certification standards and their evaluation results, and evaluates the strength and probative force of explanatory associations based on historical cases, generates and presents expected probative force evaluation information, helps users evaluate the probative force of explanatory associations, and decides whether to adopt the explanatory associations to support agricultural product compliance certification.

[0086] The probative force assessment module is a software or hardware unit in the system used to assess the probative force of explanatory associations. It supports implementation in the form of independent modules, integrated functions, or dedicated hardware. It relies on a pre-set probative force assessment knowledge base, which stores the combination of historical certification cases and relevant certification standards, the association patterns between atypical operations and standards, and their assessment results. The data format includes structured data tables, case libraries, or knowledge graphs. The assessment can be completed based on rules, expert experience, or machine learning models. Ultimately, the system will generate the expected probative force assessment information, presented in the form of scores, grades, or text, to provide a reference for users to judge the effectiveness of explanatory associations.

[0087] This solution introduces a probative force assessment module, which objectively evaluates user-defined explanatory associations by matching them with historical certification cases and rules, generates expected probative force information, and provides decision support before the evidence package is generated, thereby improving the quality control of explanatory associations and the reliability of traceability results.

[0088] In a preferred embodiment, when a user defines an explanatory association (e.g., a justification for an unconventional operation) in the system, the probative strength assessment module is triggered. It receives the operation type and relevant certification standard information and matches it to corresponding historical cases or rules in the knowledge base. After comparison, the system generates an assessment result, such as "moderate probative strength, additional materials recommended," and presents it to the user, who can then decide whether to adopt, modify, or supplement the explanatory association, thereby supporting the construction of the final compliance evidence package.

[0089] This solution introduces a probative force assessment module and knowledge base to objectively evaluate user-defined explanatory associations, reducing the subjectivity of manual judgment. The system generates and presents expected probative force assessment information, helping users accurately judge its probative force, thereby improving the objectivity and reliability of agricultural product compliance certification.

[0090] The contents disclosed above are only preferred feasible embodiments of the present invention and do not limit the scope of protection of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention description and drawings are included in the scope of protection of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A blockchain-based full-process agricultural product traceability method, characterized in that: The method comprises the following steps: S1: Receives operational records and environmental data generated by agricultural products at various stages of the supply chain, as well as multiple official certification standards that agricultural products must meet, unofficial certification standards with specific detailed requirements, and supplementary explanatory materials that differ from conventional operations in operational records, and converts the received information into data records that conform to a predetermined format; S2: Establish associations between converted data records based on predetermined rules, allowing users to review, modify, or create associations between data records, and define explanatory associations. Explanatory associations are used to explain how the differences in operation records from conventional operations comply with the requirements of unofficial certification standards or do not violate the core principles of official certification standards, thereby deriving data records containing explanatory associations. S3: Displays an evidence network consisting of data records with explanatory associations in the form of nodes and connecting lines, and allows users to select, organize and confirm one or more evidence paths to prove that agricultural products meet all relevant certification standards and explain atypical operations in the operation records; S4: Based on the evidence path confirmed by the user, relevant data records and their explanatory associations are extracted, and a compliance evidence package with a predetermined structure is generated. The compliance evidence package presents the proof of compliance of agricultural products to all relevant certification standards and an explanation of the differences between the operation records and conventional operations.

2. A blockchain-based agricultural product full-process traceability method according to claim 1, characterized in that: Step S2 further includes the following steps: Match the defined explanatory associations with a pre-set probative force evaluation knowledge base. The probative force evaluation knowledge base is used to store historical certification cases and their corresponding certification standard combinations. The probative force evaluation knowledge base includes the association patterns between atypical operations and certification standards and their evaluation results, and evaluates the strength and probative force of the explanatory associations based on historical cases. Based on the matching results, expected probative force assessment information is generated and presented to help users evaluate the probative force of the explanatory association and decide whether to adopt the explanatory association to support agricultural product compliance certification.

3. A blockchain-based agricultural product full-process traceability method according to claim 2, characterized in that: The steps for matching the defined explanatory associations with the pre-built knowledge base for probative force assessment include: Obtain user-defined explanatory associations, which contain information about a combination of atypical operation types and certification standards; Retrieve historical cases or evaluation criteria that directly correspond to the atypical operation type and certification criteria combination in the user-defined explanatory association from a pre-set proof force evaluation knowledge base; If no directly corresponding historical cases or evaluation standards are retrieved, the key elements in the explanatory association are extracted, and historical cases or evaluation standards with similarities to the key elements are searched in the knowledge base of probative force assessment through the preset approximate matching logic to obtain approximate matching candidates. If no matching items are found, reasoning analysis is performed based on the association rules or meta-knowledge in the certification field to generate inferential matching candidates. The matching results are output to generate expected probative force assessment information about the user-defined explanatory associations.

4. A blockchain-based agricultural product full-process traceability method according to claim 3, characterized in that: The steps for generating information about the expected probative force assessment of a user-defined explanatory link include: Extract historical case features or evaluation criteria terms from matching results; Comparing the user-defined explanatory associations with the extracted historical case features or evaluation criteria clauses to identify points of agreement and points of discrepancy between the user-defined explanatory associations and the extracted historical case features or evaluation criteria clauses; Determine the expected probative force conclusion of the user-defined explanatory association based on the matching results, the identified points of agreement, and the identified points of difference; The expected probative force conclusions, the extracted historical case features or evaluation standard clauses, the identified conformity points, and the identified difference points are combined to generate the expected probative force evaluation information about the user-defined explanatory associations.

5. A blockchain-based agricultural product full-process traceability method according to claim 4, characterized in that: The steps for determining the expected probative force conclusion based on the matching results, the identified points of agreement, and the identified points of difference and the user-defined explanatory association include: Obtain matching results, which include source information indicating that the matching results are derived from historical cases or evaluation criteria, and provide statistically significant data related to the historical cases or the scope and universality of the evaluation criteria; Evaluate the reliability of each source of information in the matching results. This evaluation is based on the statistical significance of historical cases or the universality of the evaluation criteria, and obtain the reliability index of each source of information. Obtaining identified conforming points and identified diverging points; For each identified compliance point, determine its support strength value based on the degree of relevance between its content and the corresponding certification requirements and the importance of the certification requirements; For each identified difference, determine the potential impact value of the difference based on the degree of deviation between its content and the corresponding certification requirements and the importance of the certification requirements; Obtaining matching results, identified conforming points and identified differing points, reliability indicators of various source information obtained through evaluation, support strength values ​​of all conforming points, and potential impact values ​​of all differing points, setting weight coefficients for the obtained reliability indicators of various source information, support strength values ​​of all conforming points, and potential impact values ​​of all differing points, performing weighted operations on the obtained reliability indicators of various source information, support strength values ​​of all conforming points, and potential impact values ​​of all differing points based on the set weight coefficients to obtain weighted indicator values, performing algebraic operations on the obtained weighted indicator values, and calculating the basic expected probative force value; Determine a confidence level or a probability interval based on the assessed overall reliability level of each source information and the calculated basic expected probative force value. When the overall reliability level of the source information decreases, the generated probability interval widens or the confidence level decreases. The calculated basic expected probative force value is combined with the determined confidence assessment level or probability interval range to generate an expected probative force conclusion of the user-defined explanatory association, which is an expected probative force conclusion determined based on the matching results, identified compliance points and identified difference points.

6. A blockchain-based agricultural product full-process traceability method according to claim 5, characterized in that: The steps for setting the weight coefficient include: Obtain information on dynamic changes in the certification standard system, including new certification standard types and adjustments to the importance of existing standard clauses; Obtain information on the current certification target combination for a specific agricultural product, indicating the certification standards that need to be met; Based on the dynamic changes in the certification standard system, the initial weight coefficient is set to adjust the reliability index of the source information, the support strength value of the conforming points and the potential impact value of the difference points; Adjust the weight coefficients of relevant certification standards based on the current certification target combination information of agricultural products.

7. A blockchain-based agricultural product full-process traceability method according to claim 5 or 6, characterized in that: The steps for determining the support strength value of a matching point include: Obtain the content of the compliance points and corresponding certification requirements; Identify and parse the explanatory association paths that connect the content of the compliance points and the certification requirements, and extract the evidence item types and association types on the paths; Based on the association rules or meta-knowledge in the knowledge base of probative force evaluation, the strength of the association path in supporting the association between the content of the compliance point and the certification requirements is evaluated; Determine the degree of relevance between the content of the compliance points and the certification requirements based on the assessed support strength; Obtain and consider the importance of corresponding certification requirements; Combined with the degree of association and importance, the support strength value of the matching point is determined.

8. A blockchain-based agricultural product full-process traceability method according to claim 6, characterized in that: The steps for determining the potential impact value of a difference point include: Obtain the difference content and corresponding certification requirements; Identify the types of differences and corresponding certification requirements; Based on the identified difference type and the corresponding certification requirement type, the initial deviation between the difference content and the corresponding certification requirement is determined by using preset quantitative rules; Analyze the correlation between the difference points in the evidence network to obtain the contextual information of the difference points; Adjusting the initial deviation according to the context information and the preset adjustment rules to obtain an adjusted deviation; The importance of obtaining corresponding certification requirements; Based on the adjusted deviation and the obtained importance, the preset calculation logic is used to determine the potential impact value of the difference point.

9. A blockchain-based agricultural product full-process traceability system, which is applied to the blockchain-based agricultural product full-process traceability method according to claim 1, characterized in that: The system includes: A data receiving module is used to receive operation records and environmental data generated by agricultural products at various links in the supply chain, as well as multiple official certification standards that agricultural products must meet, unofficial certification standards with specific detailed requirements, and supplementary explanatory materials that distinguish operation records from conventional operations, and convert the received information into data records that conform to a predetermined format; An association building module is used to establish associations between transformed data records based on predetermined rules, allowing users to review, modify, or create associations between data records and define explanatory associations. Explanatory associations are used to explain how the differences in operation records from conventional operations comply with the requirements of unofficial certification standards or do not violate the core principles of official certification standards, thereby deriving data records containing explanatory associations. An evidence display module, which is used to display an evidence network consisting of data records with explanatory associations in the form of nodes and connecting lines, and allows users to select, organize and confirm one or more evidence paths to prove that agricultural products meet all relevant certification standards and explain atypical operations in the operation records; The evidence package generation module is used to extract relevant data records and their explanatory associations based on the evidence path confirmed by the user, and generate a compliance evidence package with a predetermined structure, which presents the agricultural products' compliance proof with all relevant certification standards and an explanation of the operation records that are different from routine operations.

10. The blockchain-based agricultural product full-process traceability system according to claim 9, characterized in that: The system also includes a strength of proof assessment module for matching the defined explanatory associations with a preset strength of proof assessment knowledge base. The strength of proof assessment knowledge base is used to store historical certification cases and their corresponding certification standard combinations. The strength of proof assessment knowledge base includes association patterns between atypical operations and certification standards and their evaluation results, and evaluates the strength and strength of the explanatory associations based on historical cases, generates and presents expected strength of proof assessment information, helps users evaluate the strength of the explanatory associations, and decides whether to adopt the explanatory associations to support agricultural product compliance certification.

Images