A multi-subject collaborative operation and effectiveness management and control system for cross-regional fruit farming aid

Abstract

The application discloses a cross-regional fruit farmer-aiding support multi-subject collaborative operation and effect management and control system, relates to the technical field of digital agriculture, and comprises a multi-subject identity and permission management module, a fruit industry supply and demand data middle platform module, a multi-subject collaborative operation full-link subsystem, a support effect whole-cycle management and control and quantitative examination subsystem, an intelligent decision and early warning module, a block chain storage and security management and control module and a multi-terminal adaptation module which are connected in communication. The system effectively solves the pain points such as data islands, low efficiency of collaboration, difficult traceability of product control and effect fraud in cross-regional fruit support. The multi-subject collaborative operation subsystem realizes online collaboration of the whole process of production and sales connection, product control traceability and cold chain scheduling; the effect management and control subsystem automatically accounts relying on business original data and supports multi-level penetration supervision. With the aid of the data middle platform and the block chain storage, the support operation efficiency and the examination fairness are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of digital agriculture technology, specifically to a cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system. Background Technology

[0002] With the continuous advancement of the rural revitalization strategy, cross-regional counterpart assistance has become an important path to boost the development of the specialty forestry and fruit industry and drive stable income growth for farmers. Fruit products have inherent characteristics such as dispersed production areas, high perishability, high requirements for distribution timeliness and temperature control, and long quality control chains. Cross-regional assistance involves multiple entities, including farmers in the production areas, assisting units, logistics providers, distributors, testing institutions, and financial institutions.

[0003] However, in the existing approach, the business systems of each participating entity are independent, and data standards are inconsistent, forming data silos. Information such as production capacity, quality, logistics, and market demand cannot be efficiently exchanged, making it difficult to achieve accurate matching of production and sales. At the same time, links such as production and sales docking, order fulfillment, quality control traceability, and cold chain scheduling rely on manual offline management, lacking standardized automatic fulfillment mechanisms and full-process data encryption and evidence storage methods, resulting in low collaboration efficiency, high circulation losses, and inaccurate traceability of quality control responsibilities. In addition, the existing management of assistance effectiveness generally adopts a model of manual summarization, offline reporting, and post-event statistics. The statistical standards of assessment indicators are inconsistent, and the data sources lack consistency and uniqueness, making it easy for data tampering and the falsification of effectiveness. Moreover, the effectiveness management is disconnected from the actual assistance business, making it impossible to achieve dynamic process supervision, multi-level data penetration query, and full-cycle closed-loop management. At the same time, it lacks refined access control and intelligent risk warning mechanisms, making it difficult to guarantee the objectivity of assessment results and the security of assistance operations. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-entity collaborative operation and effectiveness management system for cross-regional fruit farmer assistance, in order to solve the problems mentioned in the background.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system, including a multi-entity identity and permission management module, a fruit industry supply and demand data platform module, a multi-entity collaborative operation full-link subsystem, an assistance effectiveness full-cycle management and quantitative assessment subsystem, an intelligent decision-making and early warning module, a blockchain evidence storage and security management module, and a multi-terminal adaptation module; The multi-entity identity and permission management module is used to perform unified identity authentication, hierarchical role configuration and differentiated permission control for the participating entities in the entire chain of cross-regional fruit farmer assistance. The participating entities include farmers / agricultural cooperatives in the production area, regional assistance units, cold chain logistics service providers, sales channel providers, financial service institutions, agricultural product quality testing institutions and industry regulatory departments. The fruit industry supply and demand data platform module communicates with the multi-entity identity and permission management module to collect, clean, de-identify and manage cross-regional fruit industry full-dimensional basic data, build a standardized production capacity database at the production site and a demand database at the sales site, and realize intelligent matching and dynamic updating of supply and demand data based on AI algorithms. The multi-entity collaborative operation full-link subsystem is connected to the multi-entity identity and permission management module and the fruit industry supply and demand data platform module, respectively, to realize cross-regional fruit farmer assistance from production and sales docking, full-link quality control and traceability, cold chain logistics warehousing and scheduling to financial and agricultural technology support services. The subsystem for full-cycle management and quantitative assessment of the effectiveness of assistance is connected to the multi-entity collaborative operation full-link subsystem and the fruit industry supply and demand data platform module to build a multi-level customizable indicator system for the effectiveness of assistance, so as to realize dynamic management and control of the entire process of assistance projects, automatic calculation of effectiveness data, quantitative assessment and traceability audit. The intelligent decision-making and early warning module is connected to all the above modules and is used to intelligently identify and classify the various risks in the entire process of helping farmers based on full-link business data and AI algorithm models, and generate intelligent decision-making suggestions for optimizing the allocation of assistance resources and adjusting operational strategies. The blockchain evidence storage and security management module communicates with all the above modules and is used to store core business data, performance evaluation data and fund flow data on the blockchain for evidence storage throughout the entire process, while realizing end-to-end data encryption, privacy protection and compliance management. The multi-terminal adaptation module is communicatively connected to all the above modules and is used to provide multi-terminal access points adapted to the usage scenarios of different participating entities.

[0006] Preferably, the multi-subject identity and permission management module adopts an RBAC+ABAC hybrid permission model, including an identity authentication unit, a role permission configuration unit, and an operation log auditing unit; The identity authentication unit is used to connect to the official authoritative identity verification system to complete the real-name registration and qualification authenticity verification of the participating entities, and generate a unique digital identity identifier for the entity. The role permission configuration unit is used to preset standard role templates for different participating entities, supports custom role function operation permissions, data access scope and territorial management boundaries, and also supports temporary authorization and hierarchical approval process configuration for cross-regional collaborative tasks. The operation log auditing unit is used to record the system operation behavior of all participating entities in a structured manner throughout the entire process and store the evidence on the blockchain in real time, supporting the full-process retrospective audit and responsibility positioning of regulatory authorities.

[0007] Preferably, the fruit industry supply and demand data platform module adopts a lake warehouse integrated architecture, and builds a four-layer data governance architecture consisting of a source layer, a cleaning layer, a standard layer, and an application layer, including an industry basic data management unit, a data processing unit, and a supply and demand intelligent matching unit; The data processing unit is used to automatically clean and standardize multi-source heterogeneous data, and integrates a federated learning privacy computing framework to achieve secure sharing of cross-subject data that is available but not visible. The supply and demand intelligent matching unit has a built-in dual-tower deep neural network model based on an attention mechanism, which is used to automatically generate an optimal production and sales matching recommendation list based on the multi-dimensional features of the production and sales areas.

[0008] Preferably, the multi-entity collaborative operation full-chain subsystem includes a production and sales docking collaboration unit, a full-chain quality control and traceability collaboration unit, a cold chain logistics and warehousing collaboration scheduling unit, and a financial and supporting service collaboration unit; The production and sales docking and coordination unit adopts a dual-drive mechanism of electronic contract + blockchain smart contract, writes the core terms of the order into the smart contract, and automatically triggers the settlement process when all performance conditions are met. The full-chain quality control and traceability collaborative unit adopts a national cryptographic encryption system with one item and one code. Quality control data at all stages is stored on the blockchain through a hash root constructed by a Merkle tree, enabling full-chain traceability and precise identification of responsibility. The cold chain logistics and warehousing collaborative scheduling unit has a built-in multi-objective vehicle route optimization model with time window, shelf life and temperature control constraints. It generates the optimal scheduling scheme with the optimization objectives of the lowest total logistics cost, the highest temperature control compliance rate and the shortest delivery time. The financial and supporting service coordination unit has a built-in credit assessment model that integrates multi-source data, which is used to provide online agricultural financial services and agricultural technology support services to farmers / cooperatives in the production area.

[0009] Preferably, the subsystem for full-cycle management and quantitative assessment of assistance effectiveness constructs a full-cycle management model of "indicator preset - data source consistency - automatic calculation - traceability audit - closed-loop optimization", including an effectiveness indicator system management unit, a dynamic management and control unit for the assistance process, an automatic calculation and visualization unit for effectiveness data, and an effectiveness assessment and traceability audit unit. The automatic performance data calculation and visualization unit directly retrieves raw data from business modules through the data platform API interface, automatically completes the performance indicator calculation according to the preset formula, and leaves a full trace of the calculation process and uploads the data to the blockchain for evidence in real time. It does not support manual modification. The performance evaluation and traceability audit unit supports multi-level penetrating supervision from the provincial region to individual farmers, and all evaluation data can be traced and verified through blockchain.

[0010] Preferably, the intelligent decision-making and early warning module incorporates an XGBoost multi-class gradient boosting tree risk identification model, which extracts feature indicators for six major categories of core risks: market, quality control, logistics, performance, project execution, and fund utilization, thereby enabling real-time risk identification, graded early warning, and intelligent handling.

[0011] Preferably, the blockchain evidence storage and security management module adopts a consortium blockchain architecture, with the core nodes being the provincial rural revitalization bureau, the agricultural and rural affairs department, and the counterpart assistance leading unit. All core data uploaded to the chain is encrypted and hashed using the national cryptographic SM2 / SM3 algorithm to ensure data confidentiality, integrity, and immutability.

[0012] Preferably, the multi-terminal adaptation module includes a PC-based management backend, a mobile app, a WeChat mini-program, and an H5 page, respectively adapting to the refined management, mobile office, and lightweight usage scenarios of different participating entities.

[0013] Compared with the prior art, the beneficial effects of the present invention are: 1. In this invention, the multi-entity collaborative operation full-chain subsystem specifically addresses the core pain points of existing technologies: independent business systems among participating entities, data silos formed by inconsistent data standards, inefficient information exchange between production capacity and market demand leading to production-sales imbalance, and reliance on manual offline management in production-sales matching, order fulfillment, quality control traceability, and cold chain scheduling, resulting in low collaborative efficiency, high circulation losses, and inaccurate traceability of quality control responsibilities. Simultaneously, relying on a multi-entity identity and permission management module to achieve hierarchical authorization and security auditing, a fruit industry supply and demand data platform to provide a unified data foundation and intelligent supply and demand matching, a blockchain evidence storage module to ensure the credibility of data throughout the entire process, and an intelligent decision-making module to achieve risk warning, collectively constructing a cross-entity, full-process online collaborative system, significantly improving operational efficiency, reducing fresh produce losses, and protecting farmers' rights.

[0014] 2. In this invention, the subsystem for full-cycle management and quantitative assessment of poverty alleviation effectiveness effectively solves the prominent problems in existing technologies, such as the manual aggregation, offline reporting, and post-event statistics model for poverty alleviation effectiveness management; inconsistent statistical standards for assessment indicators; lack of consistency and uniqueness in data sources leading to tampering and falsification of effectiveness; and the disconnect between effectiveness management and actual business operations, making it impossible to achieve dynamic process supervision, multi-level data penetration query, and full-cycle closed-loop management. Simultaneously, it integrates a data platform to automatically capture native business data, blockchain notarization to ensure the immutability of assessment data, a multi-terminal adaptation module to support convenient access for all stakeholders, and an intelligent decision-making module to provide operational optimization suggestions, forming a two-way closed loop between business and management. This technically eliminates fraudulent agricultural assistance and achieves precise full-cycle management and objective, fair assessment of poverty alleviation projects. Attached Figure Description

[0015] Figure 1This invention presents a master diagram of the overall business flow and data closed loop of a multi-entity collaborative operation and effectiveness management system for cross-regional fruit farmer assistance. Figure 2 This invention provides a flowchart of a multi-entity collaborative operation subsystem within a cross-regional fruit farmer assistance and support system, which is a multi-entity collaborative operation and effectiveness management system. Figure 3 This is a flowchart of the subsystem for full-cycle management and quantitative assessment of the effectiveness of cross-regional fruit farmer assistance and multi-entity collaborative operation and effectiveness management system of the present invention; Figure 4 This is a flowchart of the blockchain evidence storage and security management module in a cross-regional fruit farmer assistance and multi-entity collaborative operation and effectiveness management system of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example: Refer to Figures 1-4 As shown: A cross-regional fruit-farming assistance system with multi-entity collaborative operation and effectiveness management is deployed on a government cloud server, developed using a microservice architecture, and supports high-concurrency access and elastic scaling. The consortium blockchain uses the national cryptographic SM2 / SM3 algorithm to ensure encryption security, and the consensus mechanism adopts the Practical Byzantine Fault Tolerance (PBFT) algorithm. It connects to official platforms such as the National Government Service Platform, the Agricultural Product Quality and Safety Traceability Platform of the Ministry of Agriculture and Rural Affairs, the National Enterprise Credit Information Publicity System, and the Citizen Network Identity Recognition System (eID) of the Ministry of Public Security through standardized API interfaces to achieve data interoperability and qualification verification.

[0018] The technical principles and implementation details of each core module are as follows: The multi-entity identity and access control module employs a hybrid access control model combining RBAC (Role-Based Access Control) and ABAC (Attribute-Based Access Control). It interfaces with an official authoritative identity verification system at the underlying level, enabling dual access management through static role authorization and dynamic attribute control. The RBAC layer pre-defines eight standard role templates, each with fixed functional operation permissions and basic data access scopes. The ABAC layer dynamically controls access based on four dimensions: the entity's location, project affiliation, business process, and data security level, preventing access violations. Operation logs are formatted in a structured format, including the operation entity ID, timestamp, operation content, operation terminal IP, and operation result. All logs are fully recorded and uploaded to the blockchain in real-time for evidence storage, supporting full-process backtracking and auditing.

[0019] The fruit industry supply and demand data platform module adopts a lake-warehouse integrated architecture, building a four-layer data governance architecture: source aggregation layer, cleaning layer, standardization layer, and application layer. The source aggregation layer gathers multi-source heterogeneous data through multiple channels; the cleaning layer uses a rule engine and an isolated forest anomaly detection algorithm to automate data cleaning; the standardization layer constructs a unified data dictionary following the national standard "Data Elements for Agricultural Product Circulation Information"; the application layer uses a dual-tower deep neural network model based on an attention mechanism to embed and encode supply and demand features, calculates matching degree using cosine similarity, and outputs an optimal matching recommendation list. Simultaneously, it integrates a federated learning privacy computing framework to achieve secure sharing of data across entities, ensuring that data is usable but not visible.

[0020] Multi-entity collaborative operation full-chain subsystem: Four collaborative units are built specifically for the characteristics of fresh fruit products. Details are as follows: The production and sales coordination unit adopts a dual-drive mechanism of electronic contracts and blockchain smart contracts. The core terms of the assistance orders are written into the blockchain smart contracts, and the state machine mechanism realizes the automatic control of the entire order fulfillment process. When all the fulfillment conditions are met, the smart contract automatically triggers the settlement process, eliminating the risk of human intervention and ensuring that farmers receive their payments in a timely manner. The transition formula for the smart contract performance state machine is as follows: ; In the formula: The order's fulfillment status at time t (pending contract signing / pending shipment / pending inspection / inspected / settled / default). The result of the performance condition verification at time t, with a value of "satisfied / not satisfied"; This is a state transition function. The order state will advance only if it is "satisfied". Otherwise, the current state will be locked and an alert will be triggered.

[0021] The conditions for triggering automatic settlement of smart contracts are: ; In the formula: This is the settlement trigger condition, with a value of "satisfied / not satisfied"; The quantity of fruit that passed inspection; Specify the purchase quantity for the order; The minimum acceptable percentage threshold is set at 95%; This refers to the actual delivery time; Agree on the latest delivery time for the order; This indicates that the quality control inspection has passed the verification result.

[0022] The end-to-end quality control and traceability collaborative unit adopts a one-item-one-code system with "national cryptographic SM2 encryption, batch association and unique identification". Each traceability code corresponds to the smallest sales unit of fruit. Quality control data at all stages is stored on the blockchain through a hash root constructed by a Merkle tree, realizing end-to-end traceability and precise positioning of responsibility. The source code encoding and encryption formulas are as follows: ; In the formula; A unique encrypted traceability code for each item; A unique batch number for each fruit harvesting batch; A unique serial number for the smallest sales unit; This refers to the harvesting time; Codes are used to identify fruit varieties and quality grades. This is a public key encryption function based on the Chinese national cryptographic standard SM2. Only authorized entities can decrypt and read the full data using their private key.

[0023] The entire process of tracing the source data is used to construct a binary Merkle tree, generating a unique Merkle root which is then stored on the blockchain for data integrity verification. The formula for generating the Merkle root from the traceability data is as follows: ; In the formula: The Merkle tree root hash value for tracing the source data; This is a data block for quality control and traceability at each stage of the entire supply chain; When data is tampered with at any stage, the corresponding leaf node hash value changes, and eventually the Merkle root and the on-chain evidence value become inconsistent, thus identifying data tampering.

[0024] The cold chain logistics and warehousing collaborative scheduling unit, targeting the characteristics of fresh fruits that are easily perishable, have high temperature control requirements, and have strict delivery time constraints, constructs a multi-objective vehicle route optimization model (VRPTW) with time windows, shelf life, and temperature control constraints. The optimization objectives are "lowest total logistics cost, highest temperature control compliance rate, and shortest delivery time". The optimal cold chain scheduling scheme is solved by genetic algorithm. The VRPTW model variables are defined as follows: ; The multi-objective optimization objective function is: ; In the formula: To find the minimum value of the overall objective function; The objective function is the total logistics cost. Let be the objective function for cold chain temperature control compliance rate, be the transportation time, and be the indicator function, which takes the value 1 if the condition is met and 0 otherwise. Let the objective function be the total transportation time; , , The weight coefficients for each sub-objective satisfy the following conditions: The priority of the assistance projects is preset.

[0025] The constraints are as follows: Load constraints: ; Flow conservation constraint: ; Time window constraint: ; Shelf life constraints: ; Temperature control constraints: ; 0-1 integer constraint: .

[0026] The financial and supporting services collaboration unit constructs a credit scoring system for farmers / cooperatives through a credit assessment model that integrates multi-source data, thereby achieving a closed-loop online financial service process to support agriculture.

[0027] The subsystem for full-cycle management and quantitative assessment of poverty alleviation effectiveness constructs a full-cycle management model with preset indicators, consistent data sources, automatic calculation, traceability auditing, and closed-loop optimization. It presets primary, secondary, and tertiary indicators, fully aligning with national standards for assessing the effectiveness of rural revitalization poverty alleviation. Effectiveness data is directly retrieved from business modules via the data platform's API interface, automatically calculated according to preset formulas, with the entire calculation process traceable and data uploaded to the blockchain in real time for evidence storage. Manual modification is not supported. It also supports multi-level drill-down analysis from provincial regions to individual farmers, achieving penetrating supervision.

[0028] Specifically, for assessment indicators with different dimensions and trends, the extreme value method is used for standardization to eliminate the influence of dimensions and provide a unified basis for comprehensive accounting. ; In the formula: For the serial number of the assessment object ( =1,2,..., (This corresponds to different levels of assessment entities, such as supporting units, counties, townships, cooperatives, and farmers); For the assessment indicator serial number ( =1,2,..., ); For the first The first assessment target, the first The original business accounting values ​​of each performance indicator; For the first The first assessment target, the first The dimensionless standardized values ​​of the assessment indicators are fixed in the range of [0,1]. The standardized data can be directly used for subsequent weighted calculations. , The first The maximum and minimum values ​​of each indicator across all assessed subjects; Positive indicators: The higher the value, the better the assistance effect, including the number of farmers covered by assistance, the proportion of households with income growth / monitored households, the average increase in income per farmer household, the rate of increase in industry output value, the order fulfillment rate, and the increase in the rate of high-quality fruit, etc. Negative indicators: The smaller the value, the better the assistance effect, including cold chain circulation loss rate, order default rate, fund usage violation rate, project progress delay rate, etc.

[0029] To ensure fairness in the assessment of government assistance, the CRITIC (Criteria Importance Through Intercriteria Correlation) method is used to assign weights to indicators. This method comprehensively considers the comparative strength (standard deviation) and conflict (correlation coefficient) of indicators, calculating weights entirely based on the objective characteristics of the data itself, avoiding biases caused by subjective weighting. The objective weighting formula for indicators based on the CRITIC method is as follows: The standard deviation of the indicator comparison strength reflects the dispersion of the indicator values. The greater the dispersion, the higher the indicator's discriminative power, and the greater its weight. ; Where: Where: The total number of assessment subjects under the same assessment dimension; , for the first The arithmetic mean of the standardized values ​​of all assessment objects for each indicator.

[0030] The correlation coefficient of an indicator reflects the degree of information overlap between indicators. The lower the correlation coefficient, the higher the indicator conflict, the more independent information it contains, and the greater its weight. The formula for the conflict value Φg of the indicator is: ; In the formula: The total number of assessment indicators; The pairing index number (l=1,2,...,G) is used to calculate the correlation coefficient between the indicators; For the first Item and the first The Pearson correlation coefficient of the indicators (reflecting the degree of information overlap between indicators).

[0031] The comprehensive information content of an indicator is calculated by considering the comparative strength and conflict of the indicators. The comprehensive information content value of the g-th indicator is then obtained. The formula is: ; The final weight calculation of the indicators involves normalizing the comprehensive information content to obtain the final weight of each indicator. Final weighting coefficient of each assessment indicator : ; In the formula: Satisfy constraints It supports fine-tuning the weights of the objective calculations based on the focus of different assistance projects, balancing flexibility and fairness.

[0032] Based on the standardized indicator values ​​and objectively calculated weights, the final comprehensive effectiveness score of the assistance project is obtained through weighted summation. for: ; In the formula: The value range is fixed at [0, 100], corresponding to the official unified assessment and rating standard: ≥90 points: Excellent; 80-89 points: Good; 70-79 points: Pass; <70 points: Fail.

[0033] All core indicators strictly adhere to the official statistical standards for assessing the effectiveness of poverty alleviation efforts in key national rural revitalization counties. The calculation data comes from native data in the business system, with no manual intervention required. The standardized calculation formulas for the core assessment indicators are as follows: Percentage of households with income growth / monitored households: ; In the formula: To support the total number of farmers directly benefiting from the orders; To assist the number of households with increasing income / to prevent income decline; Average increase in income per farmer household: ; In the formula: For the first This year's income from poverty alleviation orders settled by farmers; This refers to the farmer's sales revenue of the same type of fruit in the previous year.

[0034] Contribution rate of farmers' income increase: ; In the formula: To help cover the total income of farmers from fruit planting this year; This represents the total revenue for the previous year.

[0035] Industrial output growth rate: ; In the formula: The total output value of the fruit industry in the project implementation area for this year; This represents the total output value of the previous year.

[0036] Order fulfillment rate: ; In the formula: The total number of orders delivered on time and with high quality; To help increase the total number of signed orders.

[0037] Cold chain loss rate: ; In the formula: Jreceive represents the total number of orders shipped; Jreceive represents the total number of items that have been successfully received and accepted by the end customer. Increase in the rate of high-quality fruit: ; In the formula: The percentage of Grade A and above fruits for this year; This represents the percentage from the previous year.

[0038] It supports a six-level penetrating supervision system, from provincial to municipal, county, township, cooperative, and individual farmer, enabling layer-by-layer traceability and precise positioning of poverty alleviation effectiveness data. The hierarchical data aggregation formula is as follows: ; In the formula: For the control level sequence number ( =1,2,..., This corresponds to a six-level penetrating supervision system: provincial level → municipal level → county level → township level → cooperative level → farmer level. The total number of control levels; For the first Aggregated values ​​of indicators at different control levels; For the first The next level The original values ​​of the indicators for each next-level unit; For the first The total number of lower-level units contained in the hierarchy.

[0039] Regulatory authorities can use this aggregation logic to drill down from the overall regional performance data to the details of individual farmers' income increases, order details, and settlement records. All data is stored on the blockchain, enabling transparent auditing and accountability.

[0040] Intelligent Decision-Making and Early Warning Module: The module adopts the XGBoost multi-class gradient boosting tree risk identification model, extracting 28 feature indicators for six core risk categories: market, quality control, logistics, performance, project execution, and fund utilization. The model is trained using historical risk case data, and the early warning level is divided into three levels: general, moderate, and severe, enabling real-time risk identification, graded early warning, and intelligent handling. At the same time, it realizes intelligent decision-making for optimizing the allocation of support resources based on machine learning algorithms.

[0041] Blockchain Evidence Storage and Security Management Module: Adopting a consortium blockchain architecture, the core nodes are the provincial rural revitalization bureau, the agricultural and rural affairs department, and the leading unit for counterpart assistance, responsible for consensus and ledger recording; ordinary nodes are various market participants, responsible for data uploading and querying. All core data uploaded to the chain uses the national cryptographic SM2 algorithm for asymmetric encryption, and the data hash value is generated using the national cryptographic SM3 algorithm, ensuring data confidentiality, integrity, and immutability.

[0042] Multi-terminal adaptation module: It builds four terminal entry points: PC management backend, mobile APP, WeChat mini program and H5 page, and optimizes the adaptation for different users' usage scenarios to achieve lightweight access for all users.

[0043] In this embodiment, the multi-entity collaborative operation full-link subsystem and the assistance effectiveness full-cycle management and quantitative assessment subsystem work together to construct a two-way closed-loop mechanism of "business flow driving management flow, and management flow standardizing business flow". All native business data (orders, logistics, quality control, settlement) generated by the multi-entity collaborative operation full-link subsystem are synchronized to the assistance effectiveness management subsystem in real time. The assistance effectiveness management subsystem transforms national assessment standards into executable business rules and embeds them into every link of order fulfillment, fund use, and quality control management, realizing "business execution is data collection, and data collection is effectiveness calculation". This breaks the drawback of the traditional assistance "business and management are two separate things". The assistance effectiveness data comes entirely from native business data, with no manual entry point, which technically eliminates false agricultural assistance and data fraud. It realizes full-cycle closed-loop management of assistance projects from project initiation, execution, calculation to assessment. Regulatory departments can directly trace the income increase details of individual farmers from the overall regional effectiveness through multi-level penetrating supervision, thereby improving the efficiency of assistance project execution.

[0044] The fruit industry supply and demand data platform module is responsible for the aggregation, cleaning, standardization, and sharing of multi-source heterogeneous data across the entire supply chain, providing a unified data foundation for all business modules. The blockchain evidence storage and security management module is responsible for storing all core business data and performance accounting data output by the data platform on the blockchain, ensuring that the data is tamper-proof and traceable throughout the process. This builds a trustworthy foundation for the entire system and solves the problems of inconsistent data standards and data silos across regions and entities. All core data (electronic contracts, test reports, logistics documents, fund flows, and performance data) are encrypted and uploaded to the blockchain using national cryptographic algorithms, realizing "whoever uploads, is responsible, traceable, and accountable." This achieves secure sharing of "data usable but not visible" across entities, meeting the data needs of collaborative operations while protecting farmers' privacy and corporate trade secrets.

[0045] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system, characterized in that, It includes a multi-entity identity and permission management module with mutual communication and connection, a fruit industry supply and demand data platform module, a multi-entity collaborative operation full-link subsystem, a full-cycle management and quantitative assessment subsystem for assistance effectiveness, an intelligent decision-making and early warning module, a blockchain evidence storage and security management module, and a multi-terminal adaptation module; The system is deployed on a government cloud server and connects to the National Government Service Platform, the Agricultural Product Quality and Safety Traceability Platform of the Ministry of Agriculture and Rural Affairs, the National Enterprise Credit Information Publicity System, and the Citizen Network Identity Recognition System of the Ministry of Public Security through standardized API interfaces. The system achieves hierarchical identity authentication and differentiated permission management for all participants across the entire chain through a hybrid permission model combining role-based and attribute-based access control. It adopts a lake-warehouse integrated architecture to build a standardized data platform for the fruit industry, enabling the aggregation, governance, and sharing of multi-source heterogeneous data across regions. Through a multi-entity collaborative operation subsystem, it achieves full-process online collaboration in production and sales matching, full-chain quality control and traceability, cold chain logistics scheduling, and financial and agricultural technology services. It constructs a business flow-driven full-cycle management system for the effectiveness of assistance, enabling automatic calculation and traceability auditing of effectiveness based on native business data. It uses a national cryptographic algorithm consortium blockchain to achieve on-chain storage and encryption protection of core data throughout the entire process.

2. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The multi-entity identity and permission management module includes an identity authentication unit, a role and permission configuration unit, and an operation log auditing unit; The identity authentication unit is used to connect to the official authoritative identity verification system to complete the real-name registration and qualification verification of participating entities and generate a unique digital identity identifier for the entity; The role permission configuration unit is used to preset standard role templates for different participating entities, configure the functional operation permissions, data access scope and territorial management boundaries of custom roles, and configure the temporary authorization and hierarchical approval process for cross-regional collaborative tasks. The operation log auditing unit is used to record the system operation behavior of all participating entities in a structured format and synchronize the operation log to the blockchain evidence storage module in real time.

3. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The fruit industry supply and demand data platform module is built with a four-layer data governance architecture consisting of a source layer, a cleaning layer, a standard layer, and an application layer, including an industry basic data management unit, a data processing unit, and a supply and demand intelligent matching unit. The data processing unit is used to clean, deduplicatize, desensitize and standardize multi-source heterogeneous data using a rule engine and an isolated forest anomaly detection algorithm, and integrates a federated learning privacy computing framework to achieve collaborative computing of cross-subject data. The intelligent supply and demand matching unit incorporates a dual-tower deep neural network model based on an attention mechanism. It embeds and encodes the feature vectors of the production and sales ends and calculates the cosine similarity, outputting a production and sales matching recommendation list.

4. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The multi-entity collaborative operation full-chain subsystem includes a production and sales docking collaboration unit, a full-chain quality control and traceability collaboration unit, a cold chain logistics and warehousing collaboration scheduling unit, and a financial and supporting service collaboration unit. The production and sales docking and coordination unit is used to connect with the electronic contract service platform, write the core terms of the order into the blockchain smart contract, and realize the automatic flow of the order performance status and settlement triggering based on the state machine mechanism; The full-chain quality control and traceability collaboration unit is used to generate a one-item-one-code traceability identifier encrypted with the national cryptographic standard SM2, and to construct the hash root of the full-chain quality control data through a binary Merkle tree and store it on the chain for evidence. The cold chain logistics and warehousing collaborative scheduling unit has a built-in multi-objective vehicle route optimization model with time window, shelf life and temperature control constraints. The scheduling scheme is solved by genetic algorithm with total logistics cost, temperature control compliance rate and total transportation time as objective functions. The financial and supporting service collaboration unit has a built-in multi-source data fusion credit assessment model based on the entropy weight method, which connects to the business systems of financial institutions and agricultural technology service institutions.

5. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The subsystem for full-cycle management and quantitative assessment of assistance effectiveness includes an effectiveness indicator system management unit, a dynamic management and control unit for the assistance process, an automatic calculation and visualization unit for effectiveness data, and an effectiveness assessment and traceability audit unit. The performance indicator system management unit is used to configure multi-level assistance performance assessment indicators and corresponding calculation formulas. The dynamic control unit for the assistance process is used to capture the original data of the business module to verify the project execution progress and generate a supervision ledger. The automatic performance data calculation and visualization unit is used to obtain business native data through the data platform API interface, automatically complete indicator calculation according to preset formulas, and upload the calculated data to the blockchain for evidence storage in real time. The performance evaluation and traceability audit unit is used to generate evaluation and rating results based on accounting data, and supports multi-level data drilling from the provincial level to farmers.

6. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The intelligent decision-making and early warning module includes a risk early warning unit and an intelligent decision-making unit; The risk warning unit has a built-in XGBoost multi-class gradient boosting tree risk identification model, which extracts feature indicators of six types of risks: market, quality control, logistics, performance, project execution, and fund use, outputs the risk level, and pushes warning information in a targeted manner. The intelligent decision-making unit is used to generate a plan for allocating support resources and adjusting operational strategies based on historical operational data and machine learning algorithms.

7. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The blockchain evidence storage and security management module adopts a consortium blockchain architecture, sets the provincial rural revitalization bureau, the agricultural and rural affairs department, and the counterpart assistance leading unit as core consensus nodes, and uses a practical Byzantine fault-tolerant algorithm as the consensus mechanism. The module is used to store electronic contracts, quality control inspection reports, logistics documents, transaction records, assistance project execution data, and performance evaluation data on the blockchain. It uses the national cryptographic SM2 algorithm for asymmetric encryption and the national cryptographic SM3 algorithm to generate data hash values.

8. The cross-regional fruit farmer assistance multi-entity collaborative operation and effectiveness management system according to claim 1, characterized in that, The multi-terminal adaptation module includes a PC-based management backend, a mobile app, a WeChat mini-program, and an H5 page; The PC-based management backend is configured with refined management, data statistics, and auditing functions; The mobile app and WeChat mini-program are configured with functions such as production capacity reporting, order viewing, traceability management, access to agricultural technology services, and mobile office.

Images