Agricultural product risk control method and system based on combination of production and fusion

Abstract

The invention relates to the field of artificial intelligence, and provides an agricultural product risk control method and system based on production and fusion combination, and the method comprises the steps: carrying out the block chain storage of financial risk assessment data, agricultural product risk assessment data and real-time agricultural data, and obtaining public production and fusion data; utilizing a pre-trained agricultural product risk assessment model to perform risk assessment operation based on yield, market and natural disasters on agricultural product risk assessment data in the public production and fusion data to obtain an agricultural product risk assessment result; utilizing a pre-trained agricultural product risk control model to perform risk control policy prediction operation on the agricultural product risk assessment result and financial risk assessment data in the public production and fusion data to obtain a policy scheme; and according to the insurance policy scheme, constructing an insurance relationship between the target agricultural area and the financial institution. According to the method, the integration and transparency of agricultural data and financial data are improved, and a risk management and control scheme for benefits of an agricultural party and a financial party is constructed.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a risk control method and system for agricultural products based on the integration of industry and finance. Background Art

[0002] Agriculture is a basic industry of the national economy, but its unique production characteristics make it face many risks and challenges, including natural disasters, market fluctuations and production management uncertainties. In recent years, global climate change has intensified, and natural disasters have occurred frequently (such as floods, droughts, typhoons, etc.), which directly threaten the stability of agricultural output. At the same time, the market price of agricultural products is significantly affected by supply and demand, international trade and policy changes, and market risks are further aggravated. For farmers who rely on agricultural income, these risks not only affect the stability of income, but may also lead to a break in the capital chain, thereby affecting their sustainable development.

[0003] As a risk management tool, financial instruments such as agricultural insurance have alleviated agricultural risks to a certain extent, but there are still the following major pain points: existing insurance policies cannot effectively implement a risk-sharing mechanism involving multiple parties, some high-risk farmers are excluded from insurance coverage, and agricultural data (output, market, disasters, etc.) and financial data (credit default rate, historical compensation records, etc.) are not fully integrated, resulting in a disconnect between financial services and the actual needs of agricultural production. Therefore, there is an urgent need for a risk control method that makes data public and transparent, reasonably shares insurance policy risks, and benefits both agricultural product parties and financial service parties. Summary of the invention

[0004] The present invention provides an agricultural product risk control method based on the integration of industry and finance, the main purpose of which is to improve the integration and transparency of agricultural data and financial data, and to build a risk control solution that benefits both agricultural and financial parties.

[0005] To achieve the above-mentioned purpose, the present invention provides a risk control method for agricultural products based on the combination of industry and finance, comprising: Acquire a target agricultural area, and acquire agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data, and agricultural product price fluctuation data; Acquire the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, acquire the production environment information of the target agricultural area using a pre-built IoT sensor cluster, and acquire the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, the production environment information and the satellite remote sensing information as real-time agricultural data; Acquire pre-built financial risk assessment data between financial institutions and the target agricultural region, wherein the financial risk assessment data includes historical claims data and credit default rates; The financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; Using the pre-trained agricultural product risk assessment model, the agricultural product risk assessment data in the public production and finance data is subjected to risk assessment operations based on output, market and natural disasters to obtain agricultural product risk assessment results; Using the pre-trained agricultural product risk control model, the risk control policy prediction operation is performed on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan; According to the insurance policy plan, an insurance relationship is established between the target agricultural area and the financial institution.

[0006] Optionally, after establishing the insurance relationship between the target agricultural area and the financial institution, the method further includes: Using pre-built monitoring services, real-time agricultural data in the public industrial and financial data is used to monitor natural disasters; When a natural disaster is detected in the target agricultural area, real-time agricultural data of the natural disaster is acquired, disaster data is obtained, and a pre-built automatic order replenishment service is started; By utilizing the automatic policy replenishment service, the agricultural product risk control model and the agricultural product risk control model are mobilized to automatically generate insurance policies for the disaster data, obtain additional insurance policies, and use the additional insurance policies to update the insurance relationship.

[0007] Optionally, the financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in a blockchain to obtain public production and financial data, including: Acquire agricultural data of the target agricultural area, and acquire financial data of the financial institution, wherein the agricultural data includes the agricultural product risk assessment data, real-time agricultural data, and pre-constructed agricultural signatures, and the financial data includes the financial risk assessment data and pre-constructed financial signatures; Conducting traceability authentication on the agricultural party signature and the financial party signature; When the traceability certification is passed, the agricultural product risk assessment data and real-time agricultural data in the agricultural data are obtained, and the financial risk assessment data in the financial data are obtained; Send the agricultural product risk assessment data, real-time agricultural data and financial risk assessment data to a pre-built third-party authority for authentication, and receive authentication hash data fed back by the third-party authority, wherein the authentication includes authenticity authentication, integrity authentication and authority authentication; The pre-built public chain is used to process the authentication hash data on the chain to obtain public industrial and financial data.

[0008] Optionally, the pre-trained agricultural product risk assessment model is used to perform risk assessment operations based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain agricultural product risk assessment results, including: Using the pre-trained agricultural product risk assessment model, feature extraction operations are performed on the agricultural product risk assessment data in the public production and finance data to obtain yield fluctuation characteristics, market fluctuation characteristics, and disaster law characteristics; Obtaining the average yield in recent years in the yield fluctuation characteristics, and performing yield prediction on the yield fluctuation characteristics to obtain a yield prediction result, calculating the difference percentage between the yield prediction result and the average yield in recent years, and calculating the yield risk; Obtaining the average grain price in recent years in the market fluctuation characteristics, and performing price forecasting on the market fluctuation characteristics to obtain a price forecast result, calculating the difference percentage between the price forecast result and the average grain price in recent years, and calculating the market risk; Perform disaster prediction on the disaster regularity characteristics to obtain disaster risk, wherein the disaster risk includes disaster type and disaster probability; The yield risk, market risk and disaster risk are summarized and output to obtain the agricultural product risk assessment result.

[0009] Optionally, obtaining the average output in recent years in the output fluctuation characteristic includes: Obtaining a yield change rate fluctuation characteristic from the yield fluctuation characteristic; Compare the preset change rate threshold with the fluctuation characteristics of the output change rate to obtain a set of high change rate time points, obtain the latest high change rate time point from the set of high change rate time points, and obtain the cutoff time; The current time is obtained, and the average output in the time period from the deadline to the current time is calculated to obtain the average output in recent years.

[0010] Optionally, the pre-trained agricultural product risk control model is used to perform a risk control policy prediction operation on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan, including: Using the pre-trained agricultural product risk control model, the loss prediction is performed on the yield risk, market risk and disaster risk in the agricultural product risk assessment results to obtain the expected loss ratio; Obtaining the planting scale of the target agricultural area, performing weighted calculation on the planting scale and the expected loss ratio to obtain the expected loss amount, and performing weighted calculation on the expected loss amount and the disaster probability in the disaster risk to obtain the pure risk premium; Obtaining a financial management fee, summing the pure risk premium and the financial management fee to obtain a comprehensive premium, using a pre-built risk assessment strategy, and fine-tuning the comprehensive premium according to the financial risk assessment data to obtain a final premium; A policy plan is constructed based on the final premium and the pre-constructed claim threshold.

[0011] Optionally, before using the pre-trained agricultural product risk control model, the method further includes: Obtaining the premium calculation model of the financial institution and obtaining an initialized agricultural product risk control model; Using the premium calculation model to perform transfer learning on the initialized agricultural product risk control model to obtain an updated agricultural product risk control model; Obtain training samples, and use the updated agricultural product risk control model to perform forward network calculations on the training samples to obtain a predicted insurance policy plan; Obtaining a policy adjustment plan from a preset third-party agency for the predicted policy plan; Calculate the loss value between the policy adjustment plan and the predicted policy plan, minimize the loss value, and obtain the network model parameters when the loss value is minimized; According to the network model parameters, the network parameters and compensation thresholds in the updated agricultural product risk control model are adjusted and trained to obtain a trained agricultural product risk control model.

[0012] Optionally, before using the pre-built monitoring service, the method may further include: The monitoring service is used as a trigger condition, and the automatic order filling service is used as the execution logic to construct a smart contract; The smart contract is configured on the public chain.

[0013] Optionally, after the insurance relationship is updated by using the additional insurance policy, the method further includes: Using a pre-built notification contract, the updated insurance relationship is sent to the contact information reserved by the target agricultural area and financial institution.

[0014] To achieve the above objectives, the present invention also provides an agricultural product risk control system based on the integration of industry and finance, comprising: The industrial and financial data combination module is used to obtain the target agricultural area and obtain the agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data and agricultural product price fluctuation data, and obtain the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, use a pre-built Internet of Things sensor cluster to obtain the production environment information of the target agricultural area, and obtain the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, production environment information and satellite remote sensing information as real-time agricultural data, and obtain the financial risk assessment data between the pre-built financial institution and the target agricultural area, wherein the financial risk assessment data includes historical compensation data and credit default rate, and the financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; An agricultural product risk assessment module, which is used to use a pre-trained agricultural product risk assessment model to perform risk assessment operations based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain an agricultural product risk assessment result; The risk-sharing insurance policy generation module is used to use the pre-trained agricultural product risk control model to perform risk control insurance policy prediction operations on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain an insurance policy plan; The risk control module is used to establish an insurance relationship between the target agricultural area and the financial institution according to the insurance policy plan.

[0015] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: A memory storing at least one instruction; The processor executes the instructions stored in the memory to implement the above-mentioned agricultural product risk control method based on the integration of industry and finance.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned agricultural product risk control method based on the integration of industry and finance.

[0017] The present invention solves the problems described in the background technology. The present invention first puts agricultural product risk assessment data and financial risk assessment data on the blockchain, which can effectively ensure the openness, transparency and security of the data. Then, the agricultural product risk assessment data is predicted based on output, market and natural disasters to obtain agricultural product risk assessment results. The agricultural product risk assessment results can be observed by the agricultural product party and the financial party at the same time to ensure that the agricultural product party and the financial party understand the basic information of the risk. The present invention also transfers the learning of the financial party's agricultural product risk control model, and through training, the agricultural product risk control model can be more reasonably and more credible to share risks, so that the insurance policy can effectively achieve risk control. Therefore, the present invention can improve the integration and transparency of agricultural data and financial data, and build a risk control plan that benefits both the agricultural party and the financial party. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of a method for risk control of agricultural products based on the integration of industry and finance provided in one embodiment of the present invention; Figure 2 A functional module diagram of an agricultural product risk control system based on the integration of production and finance provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the agricultural product risk control method based on the integration of industry and finance provided in one embodiment of the present invention.

[0019] Description of figure markings: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides an agricultural product risk control method based on the combination of industry and finance. The execution subject of the agricultural product risk control method based on the combination of industry and finance includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the agricultural product risk control method based on the combination of industry and finance can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1FIG. 1 is a flow chart of an agricultural product risk control method based on industry-finance integration provided by an embodiment of the present invention. In this embodiment, the agricultural product risk control method based on industry-finance integration includes: S1. Acquire a target agricultural area, and acquire agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data, and agricultural product price fluctuation data.

[0024] The target agricultural area may refer to a farm or an agricultural area within an administrative area. In the embodiment of the present invention, the target agricultural area may be represented by "agricultural product side" or "agricultural side".

[0025] Specifically, agricultural product parties or regional agricultural institutions can establish a cooperative relationship with the management platform of the agricultural product risk control system based on the integration of production and finance. The management platform can then obtain historical relevant data of the target agricultural area from regional agricultural institutions, or environmental institutions, and regional governments to obtain agricultural product risk assessment data, wherein the agricultural product risk assessment data includes historical data on natural disasters, regional agricultural product output data, and agricultural product price fluctuation data.

[0026] In the embodiment of the present invention, based on the agricultural product risk assessment data, risk prediction of agricultural products can be performed from three aspects: yield fluctuation, market fluctuation and natural law. In addition, according to the specific actual situation, financial flow data, policy data, technical cost information and other data can also be obtained to process financial risks, policy and legal risks and technical risks.

[0027] Specifically, the embodiments of the present invention are described by taking three risk areas, namely, historical data of natural disasters, regional agricultural product output data, and agricultural product price fluctuation data, as examples.

[0028] S2. Obtain the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, use a pre-built Internet of Things sensor cluster to obtain the production environment information of the target agricultural area, and obtain the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, production environment information and satellite remote sensing information as real-time agricultural data.

[0029] The agricultural big data platform may be a subsystem of the management platform, or may be a data platform constructed by other agricultural-related enterprises and government agencies for obtaining agricultural-related data and information.

[0030] Among them, the Internet of Things sensor cluster can include various sensors for monitoring soil moisture, temperature, rainfall and pests and diseases, which can be used to reflect the current real production situation and environmental changes.

[0031] The satellite remote sensing information can be obtained through meteorological departments or regional government departments for early warning of extreme weather or natural disasters.

[0032] Specifically, in the embodiment of the present invention, the management platform is connected to the agricultural big data platform, the IoT sensor cluster, and the meteorological and government departments through a data interface to obtain data from various aspects. Different from the historical data in S1, the data obtained here are all real-time data, which is convenient for providing data support for agricultural product production reduction caused by sudden accidents, so as to replenish agricultural product insurance policies in a timely manner and enhance risk control capabilities.

[0033] S3. Acquire pre-built financial risk assessment data between the financial institution and the target agricultural area, wherein the financial risk assessment data includes historical compensation data and credit default rate.

[0034] In the embodiment of the present invention, the financial institution may be an agricultural product insurance service provider found by the agricultural product party itself or an insurance service provider in cooperation with the management platform, which is used to provide financial services for agricultural products and improve the risk resistance of agricultural products. The present invention may represent the financial institution according to the "financial party".

[0035] Specifically, in the embodiment of the present invention, historical compensation data and credit default rate can be obtained from the transaction records between the agricultural product party and the financial party, thereby obtaining financial risk assessment data, which is related to the degree of trust of the financial party in the agricultural product party. When there is a guarantee from the management platform, regional government agencies, agricultural cooperatives and other organizations, a smaller weight can be assigned to the financial risk assessment data to reduce additional costs in the subsequent premium calculation process.

[0036] S4. The financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data.

[0037] Among them, the blockchain is an open, transparent, traceable and highly secure data storage method.

[0038] In detail, in an embodiment of the present invention, the financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public production and financial data, including: Acquire agricultural data of the target agricultural area, and acquire financial data of the financial institution, wherein the agricultural data includes the agricultural product risk assessment data, real-time agricultural data, and pre-constructed agricultural signatures, and the financial data includes the financial risk assessment data and pre-constructed financial signatures; Conducting traceability authentication on the agricultural party signature and the financial party signature; When the traceability certification is passed, the agricultural product risk assessment data and real-time agricultural data in the agricultural data are obtained, and the financial risk assessment data in the financial data are obtained; Send the agricultural product risk assessment data, real-time agricultural data and financial risk assessment data to a pre-built third-party authority for authentication, and receive authentication hash data fed back by the third-party authority, wherein the authentication includes authenticity authentication, integrity authentication and authority authentication; The pre-built public chain is used to process the authentication hash data on the chain to obtain public industrial and financial data.

[0039] Among them, the agricultural party signature and the financial party signature refer to the products of data calculation by the agricultural party and the financial party through their respective keys, which are used to ensure that the source of the data can be traced and cannot be tampered with.

[0040] Specifically, in the embodiment of the present invention, the management platform will perform communication authentication through a preset channel or decrypt the signature through the keys pre-stored in the management platform by both the agricultural product party and the financial party, thereby ensuring that the signature is correct.

[0041] The third-party authoritative organization may be a third-party organization agreed upon by the agricultural product party, the financial party and the management platform, or an agricultural association or government department in the target agricultural area as a third-party authoritative organization.

[0042] Specifically, in the embodiment of the present invention, the third-party authority is used to authenticate the authenticity (verify whether the data matches the actual situation) and integrity (ensure that the data has not been tampered with or lost) of the data, and mark the digital certificate of the authority authentication. When the authentication is passed, the third-party authority generates a fixed-length hash value as the unique identifier of the data, performs asymmetric encryption (such as RSA algorithm) on the data content, and generates encrypted authentication hash data.

[0043] Among them, the public chain is a blockchain suitable for scenarios that require high transparency.

[0044] Specifically, in the embodiment of the present invention, Ethereum is used as a public chain to publicly store the authentication hash data. In addition, it can also be stored through a consortium chain, such as Hyperledger Fabric. Compared with Ethereum, the Hyperledger Fabric has a limited public scope, but it is also very suitable for collaboration between agricultural products, financial parties and government agencies.

[0045] S5. Using the pre-trained agricultural product risk assessment model, perform risk assessment operations based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain agricultural product risk assessment results.

[0046] The agricultural product risk assessment model is a prediction model based on a neural network. The model structure is relatively simple and is a common regression prediction neural network, but the structure is repetitive and is used to perform yield risk assessment, market risk assessment and natural disaster assessment. Compared with the natural disaster assessment, the yield risk assessment and market risk assessment have added an untrained network for calculating the difference percentage.

[0047] In detail, in the embodiment of the present invention, the pre-trained agricultural product risk assessment model is used to perform a risk assessment operation based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain the agricultural product risk assessment results, including: Using the pre-trained agricultural product risk assessment model, feature extraction operations are performed on the agricultural product risk assessment data in the public production and finance data to obtain yield fluctuation characteristics, market fluctuation characteristics, and disaster law characteristics; Obtaining the average yield in recent years in the yield fluctuation characteristics, and performing yield prediction on the yield fluctuation characteristics to obtain a yield prediction result, calculating the difference percentage between the yield prediction result and the average yield in recent years, and calculating the yield risk; Obtaining the average grain price in recent years in the market fluctuation characteristics, and performing price forecasting on the market fluctuation characteristics to obtain a price forecast result, calculating the difference percentage between the price forecast result and the average grain price in recent years, and calculating the market risk; Perform disaster prediction on the disaster regularity characteristics to obtain disaster risk, wherein the disaster risk includes disaster type and disaster probability; The yield risk, market risk and disaster risk are summarized and output to obtain the agricultural product risk assessment result.

[0048] Specifically, in the embodiment of the present invention, the feature extraction operation of obtaining the characteristics of production fluctuation, market fluctuation and disaster law is realized by the convolution layer, pooling layer and fully connected structure in the neural network. Then, the characteristics of production fluctuation, market fluctuation and disaster law are predicted according to the regression parameters learned in the training process to obtain the production prediction results, price prediction results and disaster risks.

[0049] Then, based on the untrained calculation difference percentage network, according to the average yield and average grain price in recent years, the risk of yield forecast results and price forecast results is calculated to obtain yield risk and market risk.

[0050] Then summarize the outputs to get the agricultural product risk assessment results: Disaster risk: The main climate risk in a certain area is drought, with a probability of 25%.

[0051] Market risk: The average annual price fluctuation of a certain agricultural product in the past five years was 20%, and it is expected that the fluctuation will increase to 30% in the future due to the imbalance between supply and demand; Yield risk: Due to substandard seed quality in a certain area, the crop germination rate dropped by 10%, and the yield is expected to decrease by 15%-20%.

[0052] In addition, in an embodiment of the present invention, the agricultural product risk assessment model can be trained by a cross entropy loss algorithm and a gradient descent algorithm, which will not be elaborated here.

[0053] In detail, in the embodiment of the present invention, the obtaining of the average yield in recent years in the yield fluctuation characteristics includes: Obtaining a yield change rate fluctuation characteristic from the yield fluctuation characteristic; Compare the preset change rate threshold with the fluctuation characteristics of the output change rate to obtain a set of high change rate time points, obtain the latest high change rate time point from the set of high change rate time points, and obtain the cutoff time; The current time is obtained, and the average output in the time period from the deadline to the current time is calculated to obtain the average output in recent years.

[0054] Specifically, in an embodiment of the present invention, the yield fluctuation characteristics include the fluctuation information of the agricultural product yield, and the advanced characteristics can be further calculated to obtain the yield change rate fluctuation characteristics. In an embodiment of the present invention, the change rate threshold is set to 15%. When the change rate threshold is exceeded, a set of high change rate time points is obtained, such as [23 years, 20 years, 16 years...]. It is then found that the most recent high change rate time point is 23 years, so 23 years is used as the cutoff time to the current time 24 years, and the average yield of the two years is used as the average yield in recent years. If the set of high change rate time points is [20 years, 16 years...], the average yield of the five years from 20 years to 24 years is used as the average yield in recent years.

[0055] Furthermore, the calculation process of the average grain price in recent years is the same as the above method.

[0056] S6. Using the pre-trained agricultural product risk control model, perform risk control policy prediction operations on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan.

[0057] Among them, the agricultural product risk control model is a policy calculation model based on a neural network, which is used to identify agricultural product risk assessment results and generate an insurance policy that shares the risks between the agricultural product party and the financial party.

[0058] In detail, in the embodiment of the present invention, the pre-trained agricultural product risk control model is used to perform a risk control policy prediction operation on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan, including: Using the pre-trained agricultural product risk control model, the loss prediction is performed on the yield risk, market risk and disaster risk in the agricultural product risk assessment results to obtain the expected loss ratio; Obtaining the planting scale of the target agricultural area, performing weighted calculation on the planting scale and the expected loss ratio to obtain the expected loss amount, and performing weighted calculation on the expected loss amount and the disaster probability in the disaster risk to obtain the pure risk premium; Obtaining a financial management fee, summing the pure risk premium and the financial management fee to obtain a comprehensive premium, using a pre-built risk assessment strategy, and fine-tuning the comprehensive premium according to the financial risk assessment data to obtain a final premium; A policy plan is constructed based on the final premium and the pre-constructed claim threshold.

[0059] It should be known that the scientific nature of insurance pricing is the basis for judging whether risk sharing is reasonable. Financial companies usually calculate the following key indicators based on the risk prediction results of agricultural products, combined with their own data and models: risk probability, expected loss ratio, and compensation threshold. The premium is then calculated as pure risk premium = risk probability × expected loss amount. In addition, the insurance company will add management expenses, profits and reinsurance costs to form the final premium. The compensation model is an important factor in measuring whether the risk is evenly shared. Reasonable compensation should match the risk prediction results. For example, if the predicted probability of drought is 20%, the compensation conditions should clearly stipulate the drought indicators that trigger compensation (such as rainfall below a certain value).

[0060] However, the insurance pricing process is relatively hidden for agricultural product parties, and many pricing model parameters do not distribute the risks of agricultural product parties and financial parties to an appropriate proportion.

[0061] In detail, in the embodiment of the present invention, before using the pre-trained agricultural product risk control model, the method further includes: Obtaining the premium calculation model of the financial institution and obtaining an initialized agricultural product risk control model; Using the premium calculation model to perform transfer learning on the initialized agricultural product risk control model to obtain an updated agricultural product risk control model; Obtain training samples, and use the updated agricultural product risk control model to perform forward network calculations on the training samples to obtain a predicted insurance policy plan; Obtaining a policy adjustment plan from a preset third-party agency for the predicted policy plan; Calculate the loss value between the policy adjustment plan and the predicted policy plan, minimize the loss value, and obtain the network model parameters when the loss value is minimized; According to the network model parameters, the network parameters and compensation thresholds in the updated agricultural product risk control model are adjusted and trained to obtain a trained agricultural product risk control model.

[0062] Specifically, in order to further guarantee the rights and interests of both the agricultural product party and the financial party, in the embodiment of the present invention, the network parameters in the premium calculation model of the financial party are transferred to the agricultural product risk control model through transfer learning, and then the agricultural product risk control model is saved in the management platform, thereby making the model data more open and transparent.

[0063] The training samples are a set of actual insurance policy compensation data.

[0064] Specifically, the present invention performs forward network calculation on the training samples through the updated agricultural product risk control model to obtain a predicted insurance policy plan, and then performs a tripartite evaluation on the rationality of the policy risk sharing through preset three-party institutions, such as the agricultural product party (or the entrusted management platform), the financial party and the government, so as to sort out a more appropriate insurance policy adjustment plan, and uses the insurance policy adjustment plan as a label in the training process of the agricultural product risk control model to readjust the network model parameters and fixed parameter indicators such as the compensation threshold in the agricultural product risk control model, so that the trained agricultural product risk control model can well balance the risks of the agricultural product party and the financial party, and obtain an insurance policy plan acceptable to both parties.

[0065] S7. Establishing an insurance relationship between the target agricultural area and the financial institution based on the insurance policy plan.

[0066] Specifically, in the embodiment of the present invention, the management platform will send the insurance policy plan to the agricultural product party and the financial party. After confirmation by both parties, the insurance relationship between the agricultural product party and the financial party can be publicly saved.

[0067] According to the insurance relationship, the agricultural product party has enhanced its ability to resist risks, whether it is natural disasters (such as droughts and floods) or market risks (such as price fluctuations). Through data evaluation and risk sharing mechanisms, the agricultural product party's business stability is enhanced and the upper limit of losses is clearer. Due to the transparency of risks, financial institutions can more accurately evaluate the credit of agricultural product parties, reduce the risk of default, and thus provide more favorable insurance terms. With the transparency and enhanced protection of the risk control mechanism, agricultural product parties can focus more on production itself instead of worrying about possible losses.

[0068] The financial sector has reduced business risks. Through data sharing and risk sharing, the risks of default or compensation for loans and insurance have been greatly reduced. The business scale has been expanded, and there is a strong demand for financial products involved in agricultural risk control (such as loans, insurance, futures, etc.), which will bring a broader market space for financial institutions. In addition, although historical data is reliable, it cannot reflect the current environment and production status in real time, especially when facing sudden risks (such as extreme weather), it may lag behind the actual situation.

[0069] In detail, in the embodiment of the present invention, after establishing the insurance relationship between the target agricultural area and the financial institution, the method further includes: Using pre-built monitoring services, real-time agricultural data in the public industrial and financial data is used to monitor natural disasters; When a natural disaster is detected in the target agricultural area, real-time agricultural data of the natural disaster is acquired, disaster data is obtained, and a pre-built automatic order replenishment service is started; By utilizing the automatic policy replenishment service, the agricultural product risk control model and the agricultural product risk control model are mobilized to automatically generate insurance policies for the disaster data, obtain additional insurance policies, and use the additional insurance policies to update the insurance relationship.

[0070] In detail, in the embodiment of the present invention, before using the pre-built monitoring service, the method may further include: The monitoring service is used as a trigger condition, and the automatic order filling service is used as the execution logic to construct a smart contract; The smart contract is configured on the public chain.

[0071] Among them, the smart contract is an automated program on the blockchain that is used to define and execute business logic without human intervention.

[0072] The present invention can realize faster replenishment of insurance policies in emergencies to disperse risks by configuring monitoring services and automatic policy replenishment services, further improving the risk resistance of agricultural products and increasing the number of insurance policies and premiums of financial parties.

[0073] Specifically, in the embodiments of the present invention, the automatic order replenishment service can enable the agricultural product party to adjust the insurance decision according to the real-time data. For example, if the drought risk is detected to be high, drought insurance can be added in time. The financial party uses real-time data to optimize the insurance premium rate. For example, if the crop is growing well and the risk is low, the premium can also be appropriately reduced.

[0074] In detail, in the embodiment of the present invention, after the insurance relationship is updated by using the additional insurance policy, the method further includes: Using a pre-built notification contract, the updated insurance relationship is sent to the contact information reserved by the target agricultural area and financial institution.

[0075] Among them, the notification contract is also a smart contract in the blockchain, which is used to convey the notification content.

[0076] In the embodiment of the present invention, when the insurance relationship is updated, the updated insurance policy can be communicated. When the insurance policy compensation can be automatically transferred to the agricultural product account through other smart contracts after the disaster occurs, the remittance information can also be conveyed. In addition, after the first insurance policy plan is automatically generated, it can also be communicated.

[0077] The present invention solves the problems described in the background technology. The present invention first puts agricultural product risk assessment data and financial risk assessment data on the blockchain, which can effectively ensure the openness, transparency and security of the data. Then, the agricultural product risk assessment data is predicted based on output, market and natural disasters to obtain agricultural product risk assessment results. The agricultural product risk assessment results can be observed by the agricultural product party and the financial party at the same time to ensure that the agricultural product party and the financial party understand the basic information of the risk. The present invention also transfers the learning of the financial party's agricultural product risk control model, and through training, the agricultural product risk control model can be more reasonably and more credible to share risks, so that the insurance policy can effectively achieve risk control. Therefore, the present invention can improve the integration and transparency of agricultural data and financial data, and build a risk control plan that benefits both the agricultural party and the financial party.

[0078] like Figure 2 The figure shows a functional module diagram of an agricultural product risk control system based on the integration of industry and finance provided by one embodiment of the present invention.

[0079] The agricultural product risk control system 100 based on the combination of industry and finance described in the present invention can be installed in an electronic device. According to the functions implemented, the agricultural product risk control system 100 based on the combination of industry and finance can include an industrial and financial data combination module 101, an agricultural product risk assessment module 102, a risk sharing and insurance policy generation module 103 and a risk control module 104. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0080] The industrial and financial data combination module 101 is used to obtain a target agricultural area, and obtain agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data and agricultural product price fluctuation data, and obtain the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, use a pre-built Internet of Things sensor cluster to obtain production environment information of the target agricultural area, and obtain satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, production environment information and satellite remote sensing information as real-time agricultural data, and obtain financial risk assessment data between pre-built financial institutions and the target agricultural area, wherein the financial risk assessment data includes historical compensation data and credit default rate, and the financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; The agricultural product risk assessment module 102 is used to use the pre-trained agricultural product risk assessment model to perform risk assessment operations based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain agricultural product risk assessment results; The risk sharing and insurance policy generation module 103 is used to use the pre-trained agricultural product risk control model to perform risk control insurance policy prediction operations on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain an insurance policy plan; The risk control module 104 is used to establish an insurance relationship between the target agricultural area and the financial institution according to the insurance policy plan.

[0081] In detail, each module in the agricultural product risk control system 100 based on the combination of industry and finance described in the embodiment of the present invention is used in the same manner as described above. Figure 1 The technical means are the same as the agricultural product risk control method based on the integration of industry and finance described in, and can produce the same technical effects, so I will not go into details here.

[0082] like Figure 3 As shown, it is a schematic diagram of the structure of an electronic device for implementing a method for risk control of agricultural products based on the integration of industry and finance provided by an embodiment of the present invention.

[0083] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an agricultural product risk control method program based on the integration of industry and finance.

[0084] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the agricultural product risk control method program based on the combination of industry and finance, but also can be used to temporarily store data that has been output or is to be output.

[0085] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory 11 (such as the agricultural product risk control method program based on the combination of industry and finance, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0086] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0087] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0088] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0089] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0090] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0091] The agricultural product risk control method program based on the combination of industry and finance stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Acquire a target agricultural area, and acquire agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data, and agricultural product price fluctuation data; Acquire the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, acquire the production environment information of the target agricultural area using a pre-built IoT sensor cluster, and acquire the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, the production environment information and the satellite remote sensing information as real-time agricultural data; Acquire pre-built financial risk assessment data between financial institutions and the target agricultural region, wherein the financial risk assessment data includes historical claims data and credit default rates; The financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; Using the pre-trained agricultural product risk assessment model, the agricultural product risk assessment data in the public production and finance data is subjected to risk assessment operations based on output, market and natural disasters to obtain agricultural product risk assessment results; Using the pre-trained agricultural product risk control model, the risk control policy prediction operation is performed on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan; According to the insurance policy plan, an insurance relationship is established between the target agricultural area and the financial institution.

[0092] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0093] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0094] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement: Acquire a target agricultural area, and acquire agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data, and agricultural product price fluctuation data; Acquire the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, acquire the production environment information of the target agricultural area using a pre-built IoT sensor cluster, and acquire the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, the production environment information and the satellite remote sensing information as real-time agricultural data; Acquire pre-built financial risk assessment data between financial institutions and the target agricultural region, wherein the financial risk assessment data includes historical claims data and credit default rates; The financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; Using the pre-trained agricultural product risk assessment model, the agricultural product risk assessment data in the public production and finance data is subjected to risk assessment operations based on output, market and natural disasters to obtain agricultural product risk assessment results; Using the pre-trained agricultural product risk control model, the risk control policy prediction operation is performed on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan; According to the insurance policy plan, an insurance relationship is established between the target agricultural area and the financial institution.

[0095] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0096] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0098] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A risk control method for agricultural products based on the integration of industry and finance, characterized in that: The method comprises: Acquire a target agricultural area, and acquire agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data, and agricultural product price fluctuation data; Acquire the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, acquire the production environment information of the target agricultural area using a pre-built IoT sensor cluster, and acquire the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, the production environment information and the satellite remote sensing information as real-time agricultural data; Acquire pre-built financial risk assessment data between financial institutions and the target agricultural area, wherein the financial risk assessment data includes historical claims data and credit default rates; The financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; Using the pre-trained agricultural product risk assessment model, the agricultural product risk assessment data in the public production and finance data is subjected to risk assessment operations based on output, market and natural disasters to obtain agricultural product risk assessment results; Using the pre-trained agricultural product risk control model, the risk control policy prediction operation is performed on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan; According to the insurance policy plan, an insurance relationship is established between the target agricultural area and the financial institution.

2. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 1, characterized in that: After establishing the insurance relationship between the target agricultural area and the financial institution, the method further includes: Using pre-built monitoring services, real-time agricultural data in the public industrial and financial data is used to monitor natural disasters; When a natural disaster is detected in the target agricultural area, real-time agricultural data of the natural disaster is acquired, disaster data is obtained, and a pre-built automatic order replenishment service is started; By utilizing the automatic policy replenishment service, the agricultural product risk control model and the agricultural product risk control model are mobilized to automatically generate insurance policies for the disaster data, obtain additional insurance policies, and use the additional insurance policies to update the insurance relationship.

3. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 2 is characterized in that: The financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public financial and production data, including: Acquire agricultural data of the target agricultural area, and acquire financial data of the financial institution, wherein the agricultural data includes the agricultural product risk assessment data, real-time agricultural data, and pre-constructed agricultural signatures, and the financial data includes the financial risk assessment data and pre-constructed financial signatures; Conducting traceability authentication on the agricultural party signature and the financial party signature; When the traceability certification is passed, the agricultural product risk assessment data and real-time agricultural data in the agricultural data are obtained, and the financial risk assessment data in the financial data are obtained; Sending the agricultural product risk assessment data, real-time agricultural data and financial risk assessment data to a pre-built third-party authority for authentication, and receiving authentication hash data fed back by the third-party authority, wherein the authentication includes authenticity authentication, integrity authentication and authority authentication; The pre-built public chain is used to process the authentication hash data on the chain to obtain public industrial and financial data.

4. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 3 is characterized in that: The agricultural product risk assessment model used in the pre-training is used to perform risk assessment operations based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain agricultural product risk assessment results, including: Using the pre-trained agricultural product risk assessment model, feature extraction operations are performed on the agricultural product risk assessment data in the public production and finance data to obtain yield fluctuation characteristics, market fluctuation characteristics, and disaster law characteristics; Obtaining the average yield in recent years in the yield fluctuation characteristics, and performing yield prediction on the yield fluctuation characteristics to obtain a yield prediction result, calculating the difference percentage between the yield prediction result and the average yield in recent years, and calculating the yield risk; Obtaining the average grain price in recent years in the market fluctuation characteristics, and performing price forecasting on the market fluctuation characteristics to obtain price forecasting results, calculating the difference percentage between the price forecasting results and the average grain price in recent years, and calculating market risk; Perform disaster prediction on the disaster regularity characteristics to obtain disaster risk, wherein the disaster risk includes disaster type and disaster probability; The yield risk, market risk and disaster risk are summarized and output to obtain the agricultural product risk assessment result.

5. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 4 is characterized in that: The obtaining of the average output in recent years in the output fluctuation characteristics includes: Obtaining a yield change rate fluctuation characteristic from the yield fluctuation characteristic; Compare the preset change rate threshold with the fluctuation characteristics of the output change rate to obtain a set of high change rate time points, obtain the latest high change rate time point from the set of high change rate time points, and obtain the cutoff time; The current time is obtained, and the average output in the time period from the deadline to the current time is calculated to obtain the average output in recent years.

6. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 5 is characterized in that: The pre-trained agricultural product risk control model is used to perform risk control policy prediction operations on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain a policy plan, including: Using the pre-trained agricultural product risk control model, the loss prediction is performed on the yield risk, market risk and disaster risk in the agricultural product risk assessment results to obtain the expected loss ratio; Obtaining the planting scale of the target agricultural area, performing weighted calculation on the planting scale and the expected loss ratio to obtain the expected loss amount, and performing weighted calculation on the expected loss amount and the disaster probability in the disaster risk to obtain the pure risk premium; Obtaining a financial management fee, summing the pure risk premium and the financial management fee to obtain a comprehensive premium, using a pre-built risk assessment strategy, and fine-tuning the comprehensive premium according to the financial risk assessment data to obtain a final premium; An insurance policy plan is constructed based on the final premium and the pre-constructed claim threshold.

7. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 6, characterized in that: Before using the pre-trained agricultural product risk control model, the method further includes: Obtaining the premium calculation model of the financial institution and obtaining an initialized agricultural product risk control model; Using the premium calculation model to perform transfer learning on the initialized agricultural product risk control model to obtain an updated agricultural product risk control model; Obtain training samples, and use the updated agricultural product risk control model to perform forward network calculations on the training samples to obtain a predicted insurance policy plan; Obtaining a policy adjustment plan from a preset third-party agency for the predicted policy plan; Calculate the loss value between the policy adjustment plan and the predicted policy plan, minimize the loss value, and obtain the network model parameters when the loss value is minimized; According to the network model parameters, the network parameters and compensation thresholds in the updated agricultural product risk control model are adjusted and trained to obtain a trained agricultural product risk control model.

8. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 7 is characterized in that: Before using the pre-built monitoring service, the method may further include: The monitoring service is used as a trigger condition, and the automatic order filling service is used as the execution logic to construct a smart contract; The smart contract is configured on the public chain.

9. The agricultural product risk control method based on the combination of industry and finance as claimed in claim 8, characterized in that: After the insurance relationship is updated by using the additional insurance policy, the method further includes: Using a pre-built notification contract, the updated insurance relationship is sent to the contact information reserved by the target agricultural area and financial institution.

10. An agricultural product risk control system based on the integration of industry and finance, characterized in that: The system comprises: The industrial and financial data combination module is used to obtain the target agricultural area and obtain the agricultural product risk assessment data of the target agricultural area within a preset historical time period, wherein the agricultural product risk assessment data includes historical data of natural disasters, regional agricultural product output data and agricultural product price fluctuation data, and obtain the real-time price information of agricultural products in the target agricultural area from a pre-built agricultural big data platform, use a pre-built Internet of Things sensor cluster to obtain the production environment information of the target agricultural area, and obtain the satellite remote sensing information of the target agricultural area, and use the real-time price information of agricultural products, production environment information and satellite remote sensing information as real-time agricultural data, and obtain the financial risk assessment data between the pre-built financial institution and the target agricultural area, wherein the financial risk assessment data includes historical compensation data and credit default rate, and the financial risk assessment data, agricultural product risk assessment data and real-time agricultural data are stored in blockchain to obtain public industrial and financial data; An agricultural product risk assessment module, which is used to use a pre-trained agricultural product risk assessment model to perform risk assessment operations based on output, market and natural disasters on the agricultural product risk assessment data in the public production and finance data to obtain an agricultural product risk assessment result; The risk-sharing insurance policy generation module is used to use the pre-trained agricultural product risk control model to perform risk control insurance policy prediction operations on the agricultural product risk assessment results and the financial risk assessment data in the public industrial and financial data to obtain an insurance policy plan; The risk control module is used to establish an insurance relationship between the target agricultural area and the financial institution according to the insurance policy plan.

Images