Full-period management platform and management method for novel agricultural operation main body

Abstract

The invention provides a full-period management platform and management method for a novel agricultural operation subject, and relates to the technical field of agricultural management, and the method comprises the steps: carrying out the risk prediction of a target agricultural operation subject; inputting the basic information of the agricultural subject into a full-cycle agricultural supply chain; performing same-level node risk propagation prediction on the target agricultural operation subject based on the agricultural subject node; performing different-level node risk propagation prediction on the target agricultural operation subject based on the agricultural subject node; and performing risk early warning on the target agricultural operation subject based on the agricultural subject risk first coefficient, the agricultural subject risk second coefficient and the agricultural subject risk third coefficient. According to the method and the device, the technical problem that the early warning and coping capability of an agricultural operation subject to unnatural factor risks in a complex supply chain is poor due to the fact that monitoring and analysis depend on a single factor in the prior art can be solved, and the technical effect of improving the early warning capability and coping efficiency of the agricultural subject when facing various risks is achieved.

Description

Technical Field

[0001] The present application relates to the field of agricultural management technology, and in particular to a full-cycle management platform and management methods for new agricultural business entities. Background Art

[0002] In the process of modern agricultural production, with the development of agricultural scale and industrialization, risk management and prediction are becoming more and more important in agricultural operations. Agricultural operators usually face a variety of complex risks, which come not only from traditional risk factors such as natural disasters, pests and diseases, but also from new risks such as market price fluctuations and supply chain disruptions.

[0003] However, existing agricultural risk management methods mainly rely on the monitoring and analysis of a single factor. For example, many agricultural operators use meteorological monitoring equipment and crop health monitoring systems to keep abreast of weather conditions and crop growth, and these data can help predict short-term natural disaster risks. However, the limitation of this method is that although it can better cope with the direct risks brought about by climate change, it is difficult to deal with multi-dimensional risk transmission and superposition effects. In addition, the impact of non-natural factors such as market price fluctuations and logistics disruptions is usually difficult to warn in advance through existing technical means, and these factors have occupied an increasingly important position in the modern agricultural supply chain. Taking market risk as an example, the price of agricultural products is affected by multiple factors such as global market supply and demand, policy changes, and international trade. It is difficult to effectively deal with the risks brought about by price fluctuations by analyzing local weather and crop conditions alone.

[0004] To sum up, existing technologies have technical problems such as reliance on monitoring and analysis of a single factor, which makes it difficult to deal with multi-dimensional risk transmission and superposition effects, further affecting the ability of agricultural operators to warn and respond to risks of non-natural factors in complex supply chains, such as market price fluctuations, logistics disruptions, etc. Summary of the invention

[0005] The purpose of this application is to provide a full-cycle management platform and management methods for new agricultural operators, in order to solve the technical problems in the existing technology that rely on the monitoring and analysis of a single factor, resulting in difficulty in handling multi-dimensional risk transmission and superposition effects, further affecting the agricultural operators' ability to warn and respond to risks of non-natural factors in complex supply chains such as market price fluctuations, logistics disruptions, etc.

[0006] In view of the above-mentioned problems, this application provides a full-cycle management platform and management methods for new agricultural operators.

[0007] In the first aspect, the present application provides a full-cycle management platform for new agricultural business entities, including: a first agricultural risk prediction module, the first agricultural risk prediction module is used to predict the risks of target agricultural business entities and determine the first agricultural entity risk coefficient; a supply chain node analysis module, the supply chain node analysis module is used to input the basic agricultural entity information of the target agricultural business entity into the full-cycle agricultural supply chain to determine the agricultural entity node; a second agricultural risk prediction module, the second agricultural risk prediction module is used to predict the risk propagation of nodes at the same level for the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate a second agricultural entity risk coefficient; a third agricultural risk prediction module, the third agricultural risk prediction module is used to predict the risk propagation of nodes at different levels for the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate a third agricultural entity risk coefficient; an agricultural risk warning module, the agricultural risk warning module is used to warn the target agricultural business entity of risks based on the first agricultural entity risk coefficient, the second agricultural entity risk coefficient and the third agricultural entity risk coefficient, combined with the agricultural entity risk grading warning table.

[0008] On the second aspect, the present application also provides a full-cycle management method for new agricultural business entities, including: conducting risk prediction for target agricultural business entities and determining the first risk coefficient of agricultural entities; inputting the basic agricultural entity information of the target agricultural business entity into the full-cycle agricultural supply chain to determine the agricultural entity node; based on the agricultural entity node, predicting the risk propagation of the target agricultural business entity at the same level node according to the full-cycle agricultural supply chain, and generating the second risk coefficient of the agricultural entity; based on the agricultural entity node, predicting the risk propagation of the target agricultural business entity at the different level node according to the full-cycle agricultural supply chain, and generating the third risk coefficient of the agricultural entity; based on the first risk coefficient of the agricultural entity, the second risk coefficient of the agricultural entity and the third risk coefficient of the agricultural entity, combined with the agricultural entity risk grading warning table, issuing risk warnings for the target agricultural business entity.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By predicting the risks of the target agricultural business entities, the first agricultural entity risk coefficient is determined; the agricultural entity basic information of the target agricultural business entities is input into the full-cycle agricultural supply chain to determine the agricultural entity nodes; based on the agricultural entity nodes, the risk propagation prediction of the same-level nodes of the target agricultural business entities is performed according to the full-cycle agricultural supply chain to generate the second agricultural entity risk coefficient; based on the agricultural entity nodes, the risk propagation prediction of the different-level nodes of the target agricultural business entities is performed according to the full-cycle agricultural supply chain to generate the third agricultural entity risk coefficient; based on the first agricultural entity risk coefficient, the second agricultural entity risk coefficient and the third agricultural entity risk coefficient, combined with the agricultural entity risk grading warning table, the target agricultural business entities are given a risk warning, so as to achieve the technical goal of comprehensive prediction and management of multi-dimensional risks of agricultural business entities, and achieve the technical effect of improving the early warning ability and response efficiency of agricultural entities when facing various risks such as natural disasters, market fluctuations, and supply chain interruptions.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a schematic diagram of the structure of the full-cycle management platform for new agricultural business entities in this application;

[0014] Figure 2 This is a flowchart of the full-cycle management method for new agricultural business entities for this application.

[0015] Description of reference numerals:

[0016] The first module of agricultural risk prediction is 11, the supply chain node analysis module is 12, the second module of agricultural risk prediction is 13, the third module of agricultural risk prediction is 14, and the agricultural risk early warning module is 15. DETAILED DESCRIPTION

[0017] This application provides a full-cycle management platform and management methods for new agricultural operators, solving the technical problem that the existing technology relies on the monitoring and analysis of a single factor, which makes it difficult to handle multi-dimensional risk transmission and superposition effects, further affecting the agricultural operators' ability to warn and respond to non-natural factors in complex supply chains, such as market price fluctuations, logistics disruptions, and other risks. The technical goal of achieving comprehensive prediction and management of multi-dimensional risks of agricultural operators is to achieve the technical effect of improving the early warning ability and response efficiency of agricultural operators in the face of natural disasters, market fluctuations, supply chain disruptions and other risks.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For example, please refer to the attached Figure 1 This application provides a full-cycle management platform for new agricultural operators, including:

[0020] The first agricultural risk prediction module 11 is used to predict the risks of target agricultural business entities and determine the first risk coefficient of the agricultural entity.

[0021] Specifically, the target agricultural business entities refer to agricultural production entities that carry out business activities in the form of farmer cooperatives, family farms, agricultural enterprises, and farmer professional cooperatives. Risk prediction for the target agricultural business entity means estimating the risks that the agricultural entity may face by analyzing relevant data and models. By collecting various types of information related to agricultural operations, such as crop growth conditions, soil characteristics, climate change, and market conditions. For example, if the main crop of an agricultural business entity is wheat, and the rainfall in the area in the past year is 80 mm, and the rainfall required for normal growth of wheat is 300 mm, then it can be predicted that the future output of the farm may be affected, thereby increasing the risk. Next, by comprehensively analyzing these data, a quantitative risk assessment indicator can be obtained, namely the first risk coefficient of the agricultural entity, which is used to measure the risk level of the agricultural business entity. For example, if the first risk coefficient is calculated to be 0.8, it means that the agricultural entity is at a high risk under current conditions and needs to take corresponding risk management measures, such as increasing irrigation or selecting more drought-resistant crop varieties. Therefore, risk prediction can not only help agricultural operators identify potential risks, but also provide a scientific basis for formulating response strategies.

[0022] The supply chain node parsing module 12 is used to input the basic agricultural entity information of the target agricultural business entity into the full-cycle agricultural supply chain to determine the agricultural entity node.

[0023] Specifically, inputting the basic information of the target agricultural operator into the full-cycle agricultural supply chain means integrating and incorporating the basic information of the agricultural operator, such as farmland location, crop types, production scale and business model, into a supply chain management system covering the entire process of agricultural production, clarifying the position and role of the agricultural operator in the entire supply chain, and determining the agricultural operator node. Among them, the agricultural operator node is the agricultural supply chain node where the target agricultural operator is located. For example, assuming that a farm focuses on producing 20 acres of organic vegetables, the basic information includes the types of vegetables, expected output and sales channels, etc. By inputting this information, the full-cycle agricultural supply chain can identify the node of the agricultural operator in the supply chain, such as providing organic vegetables to supermarkets or restaurants as a supplier. In this way, the agricultural operator can not only clearly understand its role in the full-cycle agricultural supply chain, but also optimize the production process and improve efficiency through the data provided by the system, thereby enhancing market competitiveness. Therefore, inputting basic information into the full-cycle agricultural supply chain not only helps the management of agricultural operators, but also promotes collaboration and information flow between various links.

[0024] The second agricultural risk prediction module 13 is used to predict the risk propagation of nodes at the same level of the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate a second agricultural entity risk coefficient.

[0025] Specifically, relevant information of agricultural subject nodes, such as geographical location, production type, historical risk data, etc., is used as the basis for analysis. Next, according to the full-cycle agricultural supply chain, analysis is conducted through each link in the entire agricultural supply chain, from planting, processing to sales, to ensure that the risk prediction covers the possibility of the entire cycle. Then, the risk propagation of nodes at the same level is predicted for the target agricultural business entity, and the risk propagation between other agricultural nodes at the same supply chain level as the target agricultural business entity is predicted. For example, assuming that there are multiple farms in a certain area growing the same crops, if one of the farms faces a high risk due to pests and diseases, other farms may also face similar threats. The second risk coefficient of the agricultural entity is generated, which quantifies the comprehensive risk faced by the target agricultural business entity taking into account the entire supply chain and nodes at the same level.

[0026] The third module 14 for predicting agricultural risks is used to predict the risk propagation of nodes at different levels for the target agricultural business entity based on the agricultural entity node and the full-cycle agricultural supply chain, and generate a third coefficient of agricultural entity risk.

[0027] Specifically, it is based on the relevant information of the target agricultural business entity, such as its production, position in the supply chain, business scale and other data. Then, according to the full-cycle agricultural supply chain, all links of the agricultural supply chain are considered, and a comprehensive analysis is conducted from production to sales to ensure that the possible risks of the entire process are covered. Then, the target agricultural business entity is predicted to carry out heterogeneous node risk propagation, and the relevant nodes at different supply chain levels are analyzed to predict how the risks of these nodes affect the target agricultural entity. For example, a farm's seed supplier, fertilizer supplier or acquirer may affect the operation of the farm due to logistics disruptions or shortages of raw materials, generating the third coefficient of agricultural entity risk, which represents the overall risk level faced by the target agricultural entity after comprehensively considering the heterogeneous node risks.

[0028] The agricultural risk warning module 15 is used to provide risk warning for the target agricultural business entity based on the agricultural entity risk first coefficient, the agricultural entity risk second coefficient and the agricultural entity risk third coefficient, combined with the agricultural entity risk classification warning table.

[0029] Specifically, the first risk coefficient of agricultural entities calculated through the depth and breadth risk prediction channels, the second risk coefficient of agricultural entities obtained through the risk propagation analysis of the same-level nodes, and the third risk coefficient of agricultural entities obtained through the risk propagation prediction of different-level nodes are used to conduct comprehensive risk assessment and early warning for the target agricultural business entities using the agricultural entity risk classification early warning table. The early warning table sets corresponding warning levels according to different risk levels. For example, if the coefficient is high, it triggers a high-risk early warning, prompting agricultural operators to take emergency measures. Risk early warning is to comprehensively evaluate the overall risk level that the target agricultural entity may face in the future based on various risk coefficients, and help it respond to potential threats in advance.

[0030] The full-cycle management platform for new agricultural operators can achieve the technical goal of comprehensive prediction and management of multi-dimensional risks of agricultural operators, and achieve the technical effect of improving the early warning ability and response efficiency of agricultural operators when facing various risks such as natural disasters, market fluctuations, and supply chain disruptions.

[0031] Furthermore, the present application also includes:

[0032] Based on the target agricultural business entity, real-time status parameter collection is performed to obtain agricultural entity status data; based on the target agricultural business entity, deep learning is performed to build a dual channel for agricultural risk prediction, and the dual channel for agricultural risk prediction is embedded into the first module of agricultural risk prediction, wherein the dual channel for agricultural risk prediction includes an agricultural risk depth prediction channel and an agricultural risk breadth prediction channel; the agricultural entity status data is input into the agricultural risk depth prediction channel to obtain an agricultural risk depth prediction coefficient; the agricultural entity status data is input into the agricultural risk breadth prediction channel to obtain an agricultural risk breadth prediction coefficient; based on the agricultural risk prediction weight condition, the agricultural risk depth prediction coefficient and the agricultural risk breadth prediction coefficient are weightedly calculated to obtain the first coefficient of agricultural entity risk.

[0033] Specifically, by collecting real-time status parameters of the target agricultural business entities, real-time status data about the agricultural entities can be obtained. The status data of agricultural entities include specific indicators such as soil moisture, temperature, climate conditions, and crop growth conditions, which help to fully grasp the current operating status of agricultural entities. Through the continuous collection of agricultural entity status data, changes in the environment and production process can be captured in a timely manner, thereby providing accurate input information for subsequent risk prediction.

[0034] Next, based on the obtained agricultural subject status data, a dual-channel agricultural risk prediction dual channel is built using deep learning technology. The dual channels of agricultural risk prediction include a deep prediction channel for agricultural risks and a broad prediction channel for agricultural risks. The deep prediction channel focuses more on detailed individual variables, such as crop health or water resources in a specific area, while the broad prediction channel focuses on larger macro factors, such as global climate change trends or market supply and demand fluctuations. Through the combination of depth and breadth, possible agricultural risks can be predicted more comprehensively.

[0035] Then, the collected data on the status of agricultural entities are input into the agricultural risk depth prediction channel. The agricultural risk depth prediction channel calculates a depth prediction coefficient based on detailed historical data and current status. For example, based on the meteorological change data in a specific time period, it predicts the drought or pest risk that a certain piece of farmland will face in the future. Similarly, the same data is input into the agricultural risk breadth prediction channel, which will calculate the agricultural risk breadth prediction coefficient based on the macro-environment or systemic factors, such as the risks that the global food supply chain disruption may bring to agricultural operators.

[0036] Next, the agricultural risk prediction weight condition is used to perform weighted calculation on the agricultural risk depth prediction coefficient and the agricultural risk breadth prediction coefficient. By setting weights for different prediction coefficients and combining various prediction information, a comprehensive agricultural risk evaluation value is obtained, which is the first risk coefficient of the agricultural subject. For example, if the market volatility risk in the breadth prediction channel is considered more important, then this coefficient may be given a higher weight, ultimately generating a higher comprehensive risk coefficient.

[0037] Through data collection, the real-time status information of agricultural entities is ensured, and then the possible risks are comprehensively evaluated through the risk prediction system in two dimensions, depth and breadth. Finally, a comprehensive risk coefficient is obtained through weighted calculation to help agricultural operators better manage and respond to production and market risks that may arise in the future and ensure the continued stability of operations. For example, if the forecast coefficient indicates that the rainfall in the next week is too low, resulting in an increased risk of drought, farmers can take irrigation measures in advance to avoid losses.

[0038] Furthermore, the present application also includes:

[0039] A risk record search is performed according to the target agricultural business entity to obtain an agricultural entity status record set, an agricultural risk depth record set and an agricultural risk breadth record set; the residual neural network is trained with the agricultural entity status record set as input data and the agricultural risk depth record set as output data, and an agricultural risk depth prediction loss coefficient is obtained after each predetermined number of trainings; if the agricultural risk depth prediction loss coefficient is less than the agricultural risk depth prediction loss threshold, the agricultural risk depth prediction channel is generated; supervised learning is performed on the BP neural network based on the agricultural entity status record set and the agricultural risk breadth record set to generate the agricultural risk breadth prediction channel; the agricultural risk depth prediction channel and the agricultural risk breadth prediction channel are connected to generate the agricultural risk prediction dual channel.

[0040] Specifically, risk record retrieval is performed based on the target agricultural business entity to obtain the agricultural entity status record set, agricultural risk depth record set and agricultural risk breadth record set, and to obtain a variety of important data sets about the entity.

[0041] The agricultural subject status record set contains real-time information related to agricultural production, such as soil moisture, crop growth and climate conditions, while the agricultural risk depth record set focuses on specific risk event records, such as past pests and diseases and their impact on yields, and the agricultural risk breadth record set considers more macro factors, such as global climate change, market fluctuations and policy adjustments. These data sets include historical risk data and status information, and the integration lays the foundation for subsequent analysis and model building, ensuring the accuracy and reliability of predictions, and helping researchers and agricultural managers understand past risk events and current agricultural production conditions.

[0042] Next, the residual neural network is trained using the agricultural subject status record set as input data and the agricultural risk depth record set as output data. In this process, the residual neural network can learn the pattern of agricultural risk depth prediction, and when the predetermined number of training times is reached, the agricultural risk depth prediction loss coefficient is calculated. The agricultural risk depth prediction loss coefficient reflects the difference between the model prediction value and the actual value. For example, if the loss coefficient is smaller during the training process, the prediction error of the residual neural network is smaller and it has better prediction ability. Among them, the predetermined number of training times is obtained by customized settings by technical personnel in this field according to actual conditions.

[0043] Then, if the obtained agricultural risk depth prediction loss coefficient is less than the set agricultural risk depth prediction loss threshold, the residual neural network will be considered to have achieved acceptable prediction accuracy, thereby generating an agricultural risk depth prediction channel, indicating that the agricultural risk depth prediction channel has reliability and can be used in practical applications to predict possible agricultural risks in the future, thereby helping agricultural operators make reasonable decisions. Among them, the agricultural risk depth prediction loss threshold is obtained by a technician in this field according to the actual situation.

[0044] Next, based on the agricultural subject status record set and the agricultural risk breadth record set, supervised learning is performed on the back propagation (BP) neural network to generate an agricultural risk breadth prediction channel. At this stage, the BP neural network can identify the impact of the macro environment on agricultural risks by learning the relationship between multiple inputs and outputs. For example, the BP neural network will analyze historical data to discover the impact of climate change on crop production, thereby generating an accurate breadth prediction model.

[0045] Finally, the agricultural risk depth prediction channel and the agricultural risk breadth prediction channel are connected to form a comprehensive agricultural risk prediction dual channel. By integrating the prediction capabilities of the two dimensions of depth and breadth, the agricultural risk prediction dual channel can provide a more comprehensive agricultural risk assessment, enabling agricultural operators to manage risks more effectively and make more scientific decisions.

[0046] Through data retrieval, model training, loss threshold judgment, supervised learning and channel integration, a comprehensive dual-channel for agricultural risk prediction is constructed, which can combine detailed depth risks and macro breadth risks to provide agricultural operators with scientific risk assessment and response strategies.

[0047] Furthermore, the present application also includes:

[0048] Based on the agricultural main node, the same-level node identification is performed according to the full-cycle agricultural supply chain to determine multiple agricultural main nodes at the same level; risk identification is performed based on the multiple agricultural main nodes at the same level to obtain multiple agricultural node risk identification results; risk propagation characteristics of the target agricultural business entity are predicted based on the multiple agricultural node risk identification results to obtain multiple same-level node risk propagation coefficients; it is determined whether the multiple same-level node risk propagation coefficients are greater than / equal to the same-level node risk propagation threshold, and a same-level node risk propagation characteristic distribution that is greater than / equal to the same-level node risk propagation threshold is established; based on the same-level node risk propagation characteristic distribution, a centralized value calculation is performed to obtain the second coefficient of the agricultural entity risk.

[0049] Specifically, based on the agricultural subject nodes, the same-level node identification is carried out according to the full-cycle agricultural supply chain, which means that in the entire supply chain, other agricultural subjects at the same level as the target agricultural business subject, or other agricultural subjects similar to or adjacent to the target agricultural business subject, are identified. Among them, by classifying the functions, scales and product types of each agricultural subject, agricultural subject nodes of the same level with similar characteristics as the target subject are found. For example, if the target agricultural business subject is a rice farm producing fifty acres, other rice farms of the same scale and product type are identified as same-level nodes to facilitate subsequent risk analysis and resource integration.

[0050] Next, risk identification is performed based on multiple agricultural subject nodes at the same level to obtain multiple agricultural node risk identification results. Among them, by analyzing the relevant data of agricultural subject nodes at the same level, such as climate conditions, market demand, and historical risk events, the risks that each agricultural subject node at the same level may face are evaluated. For example, if a rice farm at the same level has suffered two severe production cuts due to climate reasons in the past three years, by incorporating this information into risk identification, specific risk assessment results are formed to help decision makers understand the risk status of the entire node at the same level.

[0051] Then, based on the risk identification results of multiple agricultural nodes, the risk propagation characteristics of the target agricultural business entity are predicted, and the risk propagation coefficients of multiple nodes at the same level are obtained to evaluate the possibility of risk propagation between nodes at the same level, and analyze the process of certain risk factors affecting agricultural entities in the entire supply chain. For example, if the risk propagation coefficient of a node is calculated to be 0.6, it means that the risk of the node is more likely to spread between nodes at the same level.

[0052] Next, it is determined whether the risk propagation coefficients of multiple peer nodes are greater than or equal to the risk propagation threshold of peer nodes, and the nodes with more serious risk propagation are screened out to establish the risk propagation characteristic distribution of peer nodes greater than or equal to the risk propagation threshold of peer nodes, that is, the risk propagation coefficients of peer nodes greater than or equal to the risk propagation threshold of peer nodes are added to the risk propagation characteristic distribution of peer nodes. If the value of the risk propagation coefficient is higher than or equal to the preset threshold, the characteristics of these nodes in the risk propagation process are identified, thereby providing a basis for risk management.

[0053] Finally, the concentration value is calculated based on the distribution of risk propagation characteristics of nodes at the same level to obtain the second risk coefficient of the agricultural entity. The process of concentration value calculation can integrate the risk characteristics of all relevant nodes and provide a more comprehensive risk assessment standard for the target agricultural business entity. The second risk coefficient of the agricultural entity can quantify the overall risk level of the target agricultural business entity after considering the risk propagation characteristics of nodes at the same level. For example, if the calculated second risk coefficient is 0.7, it means that the agricultural business entity has a high risk level in the risk propagation between nodes at the same level, and corresponding countermeasures need to be formulated.

[0054] Through the identification of peer nodes, risk assessment, risk propagation feature prediction and concentration value calculation, it helps agricultural operators to comprehensively analyze potential risks and their propagation effects, thereby improving the effectiveness of risk management. For example, if the target farm is found to have multiple high-risk peer nodes in the risk propagation feature distribution, measures can be taken in advance, such as increasing irrigation or adjusting planting plans, to reduce the impact of risks on its own operations.

[0055] Furthermore, the present application also includes:

[0056] Traverse the multiple agricultural node risk identification results and extract the first agricultural node risk identification result; predict the risk spread probability of the target agricultural business entity based on the first agricultural node risk identification result to determine a first risk propagation probability coefficient; predict the risk spread impact of the target agricultural business entity based on the first agricultural node risk identification result to obtain a first risk propagation impact coefficient; perform weighted calculation on the first risk propagation probability coefficient and the first risk propagation impact coefficient based on the same-level node risk propagation weight condition to obtain a first same-level node risk propagation coefficient, and add the first same-level node risk propagation coefficient to the multiple same-level node risk propagation coefficients.

[0057] Specifically, all identified agricultural node risk data are checked one by one, and the risk information of one specific node is randomly extracted, and then by focusing on a specific agricultural node, a specific basis is provided for subsequent risk analysis.

[0058] Next, the risk spread probability of the target agricultural business entity is predicted based on the risk identification results of the first agricultural node, the first risk transmission probability coefficient is determined, and the possibility of risk spread from the first agricultural node to the target agricultural business entity is evaluated. If the risk identification results of the first agricultural node show that the node faces a 30% probability of pest occurrence, then the risk transmission probability coefficient of the target agricultural business entity may also be predicted to be at a similar level, reflecting the risk impact that the target agricultural entity may be subject to.

[0059] Then, based on the risk identification results of the first agricultural node, the risk spread impact prediction is carried out on the target agricultural business entity to obtain the first risk transmission impact coefficient, and the actual loss that may be caused when the risk spreads from the first agricultural node to the target agricultural business entity is evaluated. For example, if the risk identification results of the first agricultural node show that the occurrence of pests may cause a 50% reduction in crop yield at the node, then the target agricultural business entity may face the same risk impact, and the corresponding impact coefficient is obtained.

[0060] Next, based on the risk propagation weight conditions of the same-level nodes, the first risk propagation probability coefficient and the first risk propagation impact coefficient are weighted and calculated, and a comprehensive risk propagation coefficient is formed by combining the evaluation of probability and impact to obtain the first peer node risk propagation coefficient. For example, if the first risk propagation probability coefficient is 0.3 and the first risk propagation impact coefficient is 0.4, then after weighted calculation, the first peer node risk propagation coefficient may be 0.35, which more accurately reflects the risk impact of the node on the target agricultural business entity.

[0061] Finally, the risk propagation coefficient of the first peer node is added to the risk propagation coefficients of multiple peer nodes, and the newly calculated risk propagation coefficient is integrated into the risk propagation analysis of the entire peer node to form a more comprehensive risk view, allowing agricultural operators to comprehensively assess their risk status in the entire supply chain.

[0062] By traversing the risk identification results of agricultural nodes, predicting the probability of spread and impact, weighted calculation, and coefficient integration, a comprehensive risk propagation assessment system was constructed to help agricultural operators clearly identify the risk relationship with other nodes of the same level, so as to better manage risks and respond to strategies. For example, if the risk propagation coefficient of a certain node is found to have increased significantly, agricultural operators can adjust management strategies in a timely manner, such as adding pest control measures, to reduce potential losses.

[0063] Furthermore, the present application also includes:

[0064] According to the full-cycle agricultural supply chain, heterogeneous nodes of the agricultural subject nodes are identified to determine a plurality of heterogeneous agricultural subject nodes; based on the plurality of heterogeneous agricultural subject nodes, association analysis is performed on the target agricultural business entity to determine a set of associated heterogeneous agricultural nodes; risk propagation prediction is performed on the target agricultural business entity based on the set of associated heterogeneous agricultural nodes to obtain a plurality of heterogeneous node risk propagation coefficients; it is determined whether the plurality of heterogeneous node risk propagation coefficients are greater than / equal to a heterogeneous node risk propagation threshold, and a heterogeneous node risk propagation characteristic distribution greater than / equal to the heterogeneous node risk propagation threshold is established; a centralized value is calculated based on the heterogeneous node risk propagation characteristic distribution to obtain the third coefficient of the agricultural subject risk.

[0065] Specifically, the agricultural subject nodes are identified at different levels according to the full-cycle agricultural supply chain. In the entire agricultural supply chain, agricultural nodes that are in different links from the target agricultural subject nodes are identified, and multiple agricultural subject nodes at different levels are determined. Among them, agricultural subject nodes at different levels are in the upstream or downstream links of the supply chain, such as agricultural material suppliers, processing plants or distributors in the supply chain. For example, a farm that grows wheat may be connected to heterogeneous nodes such as flour processing plants or wheat seed suppliers. By identifying heterogeneous agricultural subject nodes, other nodes associated with the target agricultural subject can be found, thus laying the foundation for subsequent risk analysis.

[0066] Next, we conduct an association analysis on the target agricultural business entity based on multiple heterogeneous agricultural subject nodes, determine the associated heterogeneous agricultural node set, and analyze the degree of association between the heterogeneous nodes and the target agricultural entity, including supply and demand relationships, logistics dependence or other interactions. For example, the association between a wheat farm and a seed supplier, a fertilizer company, and a flour mill is determined through supply records or contractual relationships, forming an associated heterogeneous agricultural node set, which helps to understand which heterogeneous nodes may have an important impact on the operation of the target agricultural entity.

[0067] Then, the risk propagation of the target agricultural business entity is predicted based on the associated heterogeneous agricultural node set, and multiple heterogeneous node risk propagation coefficients are obtained to evaluate how the risk of the associated nodes is propagated to the target agricultural entity. For example, if the seed supply of the seed supplier is interrupted, which in turn affects the production of the wheat farm, the risk degree of the risk transmission faced by the seed supplier is taken as the heterogeneous node risk propagation coefficient.

[0068] Next, determine whether the risk propagation coefficients of multiple heterogeneous nodes are greater than or equal to the heterogeneous node risk propagation threshold, screen out heterogeneous nodes with more serious risk propagation, and add the heterogeneous node risk propagation coefficients greater than or equal to the heterogeneous node risk propagation threshold to the heterogeneous node risk propagation characteristic distribution. If the risk propagation coefficient of a node exceeds the set threshold, the node is considered to have a significant risk propagation impact. By obtaining the heterogeneous node risk propagation characteristic distribution, these key nodes can be analyzed collectively to evaluate their risk impact on the entire supply chain.

[0069] Finally, the concentration value is calculated based on the distribution of risk propagation characteristics of heterogeneous nodes to obtain the third risk coefficient of the agricultural entity. The risk propagation characteristics of all heterogeneous nodes are integrated to calculate the comprehensive risk faced by the target agricultural entity in the entire supply chain.

[0070] By identifying heterogeneous nodes, conducting correlation analysis, predicting risk propagation, judging thresholds, and calculating concentration values, a comprehensive risk assessment system for target agricultural operators can be formed to reduce the risk of possible production interruptions.

[0071] Furthermore, the present application also includes:

[0072] Traverse the set of associated heterogeneous agricultural nodes and extract the first associated heterogeneous agricultural node; perform risk prediction based on the first associated heterogeneous agricultural node to obtain a first heterogeneous node risk prediction result; perform risk contagion analysis on the target agricultural business entity based on the first heterogeneous node risk prediction result to obtain a first risk contagion probability coefficient and a first risk contagion influence coefficient; perform weighted calculation on the first risk contagion probability coefficient and the first risk contagion influence coefficient according to a heterogeneous node risk propagation weight condition to generate a first heterogeneous node risk propagation coefficient, and add the first heterogeneous node risk propagation coefficient to the multiple heterogeneous node risk propagation coefficients.

[0073] Specifically, the associated heterogeneous agricultural node sets are checked one by one, and the first associated heterogeneous agricultural node is randomly extracted to obtain for detailed analysis.

[0074] Next, risk prediction is performed based on the first associated heterogeneous agricultural node to predict the risk type and severity that the node may face, and obtain the risk prediction result of the first heterogeneous node. For example, it is analyzed whether the seed supplier has production problems or logistics interruption risks, and it is concluded that the risk of insufficient supply in the next six months is 40%.

[0075] Then, according to the risk prediction results of the first heterogeneous node, the target agricultural business entity is subjected to risk contagion analysis. By analyzing the potential impact of the risk of the heterogeneous node on the target agricultural entity, the first risk contagion probability coefficient and the first risk contagion impact coefficient are obtained to evaluate the possibility and severity of the risk contagion to the target entity. For example, if the seed supplier has supply problems, the farm's planting plan may be delayed, so the calculated risk contagion probability coefficient may be 0.6, and the expected impact of this impact on the yield may be 30%, which is the risk contagion impact coefficient.

[0076] Next, the first risk spread probability coefficient and the first risk spread influence coefficient are weighted according to the risk propagation weight conditions of heterogeneous nodes. By combining the probability and the influence, a comprehensive risk propagation coefficient is obtained to generate the first heterogeneous node risk propagation coefficient. For example, if the risk spread probability coefficient is 0.6 and the influence coefficient is 0.3, after weight calculation, it may be concluded that the first heterogeneous node risk propagation coefficient is 0.5, which further reflects the risk spread of the node. The first heterogeneous node risk propagation coefficient is added to the risk propagation coefficients of multiple heterogeneous nodes, that is, according to the method of obtaining the first heterogeneous node risk propagation coefficient, the heterogeneous node risk propagation coefficients of the remaining associated heterogeneous agricultural nodes are continued to be calculated. The propagation coefficients of all heterogeneous nodes can eventually form an overall assessment to judge the overall risk level of the supply chain.

[0077] By traversing the associated heterogeneous node sets, performing risk prediction, contagion analysis, weighted calculation and result integration, a detailed risk propagation assessment system for target agricultural entities can be constructed. For example, if the risk propagation coefficient of seed suppliers and fertilizer suppliers is high, agricultural operators can look for alternative suppliers in advance to reduce the impact of supply chain disruptions on production.

[0078] In summary, the full-cycle management platform for new agricultural business entities provided by this application has the following technical effects:

[0079] By predicting the risks of the target agricultural business entities, the first agricultural entity risk coefficient is determined; the agricultural entity basic information of the target agricultural business entities is input into the full-cycle agricultural supply chain to determine the agricultural entity nodes; based on the agricultural entity nodes, the risk propagation prediction of the same-level nodes of the target agricultural business entities is performed according to the full-cycle agricultural supply chain to generate the second agricultural entity risk coefficient; based on the agricultural entity nodes, the risk propagation prediction of the different-level nodes of the target agricultural business entities is performed according to the full-cycle agricultural supply chain to generate the third agricultural entity risk coefficient; based on the first agricultural entity risk coefficient, the second agricultural entity risk coefficient and the third agricultural entity risk coefficient, combined with the agricultural entity risk grading warning table, the target agricultural business entities are given a risk warning, so as to achieve the technical goal of comprehensive prediction and management of multi-dimensional risks of agricultural business entities, and achieve the technical effect of improving the early warning ability and response efficiency of agricultural entities when facing various risks such as natural disasters, market fluctuations, and supply chain interruptions.

[0080] Embodiment 2: Based on the full-cycle management platform for new agricultural business entities in the previous embodiment, the present application also provides a full-cycle management method for new agricultural business entities, please refer to the attached Figure 2 ,include:

[0081] Conduct risk prediction for the target agricultural business entity and determine the first risk coefficient of the agricultural entity; input the agricultural entity basic information of the target agricultural business entity into the full-cycle agricultural supply chain to determine the agricultural entity node; based on the agricultural entity node, conduct the same-level node risk propagation prediction for the target agricultural business entity according to the full-cycle agricultural supply chain to generate the second risk coefficient of the agricultural entity; based on the agricultural entity node, conduct the different-level node risk propagation prediction for the target agricultural business entity according to the full-cycle agricultural supply chain to generate the third risk coefficient of the agricultural entity; based on the first risk coefficient of the agricultural entity, the second risk coefficient of the agricultural entity and the third risk coefficient of the agricultural entity, conduct risk warning for the target agricultural business entity in combination with the agricultural entity risk grading warning table.

[0082] Furthermore, the first module of agricultural risk prediction in the full-cycle management method for new agricultural business entities is used to predict the risk of target agricultural business entities and determine the first risk coefficient of agricultural entities, including:

[0083] Based on the target agricultural business entity, real-time status parameter collection is performed to obtain agricultural entity status data; based on the target agricultural business entity, deep learning is performed to build a dual channel for agricultural risk prediction, and the dual channel for agricultural risk prediction is embedded into the first module of agricultural risk prediction, wherein the dual channel for agricultural risk prediction includes an agricultural risk depth prediction channel and an agricultural risk breadth prediction channel; the agricultural entity status data is input into the agricultural risk depth prediction channel to obtain an agricultural risk depth prediction coefficient; the agricultural entity status data is input into the agricultural risk breadth prediction channel to obtain an agricultural risk breadth prediction coefficient; based on the agricultural risk prediction weight condition, the agricultural risk depth prediction coefficient and the agricultural risk breadth prediction coefficient are weightedly calculated to obtain the first coefficient of agricultural entity risk.

[0084] Furthermore, the full-cycle management method for new agricultural business entities conducts in-depth learning based on the target agricultural business entities and builds a dual channel for agricultural risk prediction, including:

[0085] A risk record search is performed according to the target agricultural business entity to obtain an agricultural entity status record set, an agricultural risk depth record set and an agricultural risk breadth record set; the residual neural network is trained with the agricultural entity status record set as input data and the agricultural risk depth record set as output data, and an agricultural risk depth prediction loss coefficient is obtained after each predetermined number of trainings; if the agricultural risk depth prediction loss coefficient is less than the agricultural risk depth prediction loss threshold, the agricultural risk depth prediction channel is generated; supervised learning is performed on the BP neural network based on the agricultural entity status record set and the agricultural risk breadth record set to generate the agricultural risk breadth prediction channel; the agricultural risk depth prediction channel and the agricultural risk breadth prediction channel are connected to generate the agricultural risk prediction dual channel.

[0086] Furthermore, the second module of agricultural risk prediction in the full-cycle management method for new agricultural business entities is used to predict the risk propagation of nodes at the same level for the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate the second coefficient of agricultural entity risk, including:

[0087] Based on the agricultural main node, the same-level node identification is performed according to the full-cycle agricultural supply chain to determine multiple agricultural main nodes at the same level; risk identification is performed based on the multiple agricultural main nodes at the same level to obtain multiple agricultural node risk identification results; risk propagation characteristics of the target agricultural business entity are predicted based on the multiple agricultural node risk identification results to obtain multiple same-level node risk propagation coefficients; it is determined whether the multiple same-level node risk propagation coefficients are greater than / equal to the same-level node risk propagation threshold, and a same-level node risk propagation characteristic distribution that is greater than / equal to the same-level node risk propagation threshold is established; based on the same-level node risk propagation characteristic distribution, a centralized value calculation is performed to obtain the second coefficient of the agricultural entity risk.

[0088] Furthermore, in the full-cycle management method for new agricultural business entities, risk propagation characteristics of the target agricultural business entities are predicted based on the risk identification results of the multiple agricultural nodes to obtain risk propagation coefficients of multiple nodes at the same level, including:

[0089] Traverse the multiple agricultural node risk identification results and extract the first agricultural node risk identification result; predict the risk spread probability of the target agricultural business entity based on the first agricultural node risk identification result to determine a first risk propagation probability coefficient; predict the risk spread impact of the target agricultural business entity based on the first agricultural node risk identification result to obtain a first risk propagation impact coefficient; perform weighted calculation on the first risk propagation probability coefficient and the first risk propagation impact coefficient based on the same-level node risk propagation weight condition to obtain a first same-level node risk propagation coefficient, and add the first same-level node risk propagation coefficient to the multiple same-level node risk propagation coefficients.

[0090] Furthermore, the third module of agricultural risk prediction in the full-cycle management method for new agricultural business entities is used to predict the risk propagation of nodes at different levels for the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate the third coefficient of agricultural entity risk, including:

[0091] According to the full-cycle agricultural supply chain, heterogeneous nodes of the agricultural subject nodes are identified to determine a plurality of heterogeneous agricultural subject nodes; based on the plurality of heterogeneous agricultural subject nodes, association analysis is performed on the target agricultural business entity to determine a set of associated heterogeneous agricultural nodes; risk propagation prediction is performed on the target agricultural business entity based on the set of associated heterogeneous agricultural nodes to obtain a plurality of heterogeneous node risk propagation coefficients; it is determined whether the plurality of heterogeneous node risk propagation coefficients are greater than / equal to a heterogeneous node risk propagation threshold, and a heterogeneous node risk propagation characteristic distribution greater than / equal to the heterogeneous node risk propagation threshold is established; a centralized value is calculated based on the heterogeneous node risk propagation characteristic distribution to obtain the third coefficient of the agricultural subject risk.

[0092] Furthermore, in the full-cycle management method for new agricultural business entities, risk propagation prediction is performed on the target agricultural business entity according to the associated heterogeneous agricultural node set to obtain multiple heterogeneous node risk propagation coefficients, including:

[0093] Traverse the set of associated heterogeneous agricultural nodes and extract the first associated heterogeneous agricultural node; perform risk prediction based on the first associated heterogeneous agricultural node to obtain a first heterogeneous node risk prediction result; perform risk contagion analysis on the target agricultural business entity based on the first heterogeneous node risk prediction result to obtain a first risk contagion probability coefficient and a first risk contagion influence coefficient; perform weighted calculation on the first risk contagion probability coefficient and the first risk contagion influence coefficient according to a heterogeneous node risk propagation weight condition to generate a first heterogeneous node risk propagation coefficient, and add the first heterogeneous node risk propagation coefficient to the multiple heterogeneous node risk propagation coefficients.

[0094] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The full-cycle management platform for new agricultural business entities and the specific examples in the aforementioned embodiment one are also applicable to the full-cycle management method for new agricultural business entities in this embodiment. Through the aforementioned detailed description of the full-cycle management platform for new agricultural business entities, those skilled in the art can clearly understand the full-cycle management method for new agricultural business entities in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0095] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0096] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A full-cycle management platform for new agricultural operators, characterized by: include: The first agricultural risk prediction module is used to predict the risk of the target agricultural business entity and determine the first risk coefficient of the agricultural entity; A supply chain node parsing module, the supply chain node parsing module is used to input the agricultural subject basic information of the target agricultural business entity into the full-cycle agricultural supply chain to determine the agricultural subject node; The second agricultural risk prediction module is used to predict the risk propagation of nodes at the same level for the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate a second agricultural entity risk coefficient; The third agricultural risk prediction module is used to predict the risk propagation of nodes at different levels of the target agricultural business entity based on the agricultural entity node and the full-cycle agricultural supply chain, and generate a third agricultural entity risk coefficient; An agricultural risk warning module is used to provide risk warnings to the target agricultural business entity based on the first agricultural entity risk coefficient, the second agricultural entity risk coefficient and the third agricultural entity risk coefficient, combined with an agricultural entity risk grading warning table.

2. The platform according to claim 1, characterized in that The first agricultural risk prediction module is used to predict the risk of the target agricultural business entity and determine the first risk coefficient of the agricultural entity, including: Based on the target agricultural business entity, real-time status parameter collection is performed to obtain agricultural entity status data; Based on the target agricultural business entity, deep learning is performed to build a dual channel for agricultural risk prediction, and the dual channel for agricultural risk prediction is embedded into the first module for agricultural risk prediction, wherein the dual channel for agricultural risk prediction includes an agricultural risk depth prediction channel and an agricultural risk breadth prediction channel; Inputting the agricultural subject status data into the agricultural risk depth prediction channel to obtain an agricultural risk depth prediction coefficient; Inputting the agricultural subject status data into the agricultural risk breadth prediction channel to obtain the agricultural risk breadth prediction coefficient; Based on the agricultural risk prediction weight condition, the agricultural risk depth prediction coefficient and the agricultural risk breadth prediction coefficient are weightedly calculated to obtain the first agricultural entity risk coefficient.

3. The platform according to claim 2, characterized in that Based on the target agricultural business entities, deep learning is carried out to build a dual channel for agricultural risk prediction, including: Perform risk record retrieval according to the target agricultural business entity to obtain an agricultural entity status record set, an agricultural risk depth record set, and an agricultural risk breadth record set; The residual neural network is trained using the agricultural subject status record set as input data and the agricultural risk depth record set as output data, and the agricultural risk depth prediction loss coefficient is obtained after each predetermined number of trainings; If the agricultural risk depth prediction loss coefficient is less than the agricultural risk depth prediction loss threshold, the agricultural risk depth prediction channel is generated; Based on the agricultural subject status record set and the agricultural risk breadth record set, supervised learning is performed on the BP neural network to generate the agricultural risk breadth prediction channel; The agricultural risk depth prediction channel and the agricultural risk breadth prediction channel are connected to generate the agricultural risk prediction dual channel.

4. The platform according to claim 1, characterized in that The second agricultural risk prediction module is used to predict the risk propagation of nodes at the same level for the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate a second agricultural entity risk coefficient, including: Based on the agricultural subject node, identify the same-level nodes according to the full-cycle agricultural supply chain to determine multiple agricultural subject nodes at the same level; Perform risk identification based on the multiple agricultural subject nodes at the same level to obtain multiple agricultural node risk identification results; Based on the risk identification results of the multiple agricultural nodes, risk propagation characteristics of the target agricultural business entity are predicted to obtain risk propagation coefficients of multiple nodes at the same level; Determine whether the risk propagation coefficients of the plurality of peer nodes are greater than / equal to a peer node risk propagation threshold, and establish a peer node risk propagation feature distribution greater than / equal to the peer node risk propagation threshold; The concentration value is calculated based on the risk propagation characteristic distribution of the nodes at the same level to obtain the second risk coefficient of the agricultural entity.

5. The platform according to claim 4, characterized in that Based on the risk identification results of the multiple agricultural nodes, the risk propagation characteristics of the target agricultural business entity are predicted to obtain multiple risk propagation coefficients of the same-level nodes, including: Traversing the plurality of agricultural node risk identification results, and extracting a first agricultural node risk identification result; According to the risk identification result of the first agricultural node, the risk spread probability of the target agricultural business entity is predicted to determine the first risk spread probability coefficient; According to the first agricultural node risk identification result, the risk spread impact prediction is performed on the target agricultural business entity to obtain a first risk propagation impact coefficient; The first risk propagation probability coefficient and the first risk propagation influence coefficient are weightedly calculated based on the peer node risk propagation weight condition to obtain a first peer node risk propagation coefficient, and the first peer node risk propagation coefficient is added to the multiple peer node risk propagation coefficients.

6. The platform according to claim 1, characterized in that The third agricultural risk prediction module is used to perform heterogeneous node risk propagation prediction on the target agricultural business entity based on the agricultural entity node and according to the full-cycle agricultural supply chain, and generate a third agricultural entity risk coefficient, including: According to the full-cycle agricultural supply chain, the agricultural subject node is identified at a different level, and a plurality of agricultural subject nodes at different levels are determined; Based on the multiple heterogeneous agricultural subject nodes, an association analysis is performed on the target agricultural business entity to determine a set of associated heterogeneous agricultural nodes; Perform risk propagation prediction on the target agricultural business entity according to the associated heterogeneous agricultural node set to obtain multiple heterogeneous node risk propagation coefficients; Determine whether the plurality of heterogeneous node risk propagation coefficients are greater than / equal to a heterogeneous node risk propagation threshold, and establish a heterogeneous node risk propagation feature distribution greater than / equal to the heterogeneous node risk propagation threshold; The third coefficient of risk of the agricultural entity is obtained by calculating the concentration value based on the risk propagation characteristic distribution of the heterogeneous nodes.

7. The platform according to claim 6, characterized in that The risk propagation of the target agricultural business entity is predicted according to the associated heterogeneous agricultural node set, and a plurality of heterogeneous node risk propagation coefficients are obtained, including: Traversing the associated heterogeneous agricultural node set, extracting a first associated heterogeneous agricultural node; Perform risk prediction based on the first associated heterogeneous agricultural node to obtain a first heterogeneous node risk prediction result; Perform risk impact analysis on the target agricultural business entity according to the first heterogeneous node risk prediction result to obtain a first risk impact probability coefficient and a first risk impact coefficient; The first risk spread probability coefficient and the first risk spread influence coefficient are weightedly calculated according to the heterogeneous node risk propagation weight condition to generate a first heterogeneous node risk propagation coefficient, and the first heterogeneous node risk propagation coefficient is added to the multiple heterogeneous node risk propagation coefficients.

8. The full-cycle management method for new agricultural operators is characterized by: The method is implemented by a full-cycle management platform for new agricultural business entities according to any one of claims 1 to 7, wherein the full-cycle management method for new agricultural business entities includes: Conduct risk forecasting for target agricultural business entities and determine the first risk coefficient for agricultural entities; Input the agricultural subject basic information of the target agricultural business entity into the full-cycle agricultural supply chain to determine the agricultural subject node; Based on the agricultural subject node, the risk propagation prediction of the target agricultural business subject at the same level is performed according to the full-cycle agricultural supply chain to generate a second coefficient of agricultural subject risk; Based on the agricultural subject node, the risk propagation prediction of the target agricultural business subject is carried out according to the full-cycle agricultural supply chain to generate the third coefficient of agricultural subject risk; Based on the first agricultural entity risk coefficient, the second agricultural entity risk coefficient and the third agricultural entity risk coefficient, combined with the agricultural entity risk grading warning table, a risk warning is issued to the target agricultural business entity.

Images