Agricultural insurance management system and method based on block chain

Abstract

The invention discloses an agricultural insurance management system and method based on a block chain, and relates to the technical field of insurance management, and the method comprises the steps: collecting crop image data and disaster data, calculating a standardized agricultural loss factor: reducing insurance premium without loss, and returning monitoring; if slight or serious loss occurs, the insurance premium is not adjusted or increased; whole-course block chain evidence storage is achieved, and intelligent claim settlement and premium dynamic adjustment are achieved. According to the invention, the loss factor is accurately calculated by fusing crop images and disaster data, the accuracy of loss assessment is improved, and natural disasters and poor man-made management are distinguished; the insurance premium is dynamically adjusted based on the loss result, and intelligent risk pricing is achieved; and in combination with block chain evidence storage, the process is transparent and credible, and the insurance efficiency and agricultural worker trust are improved.

Description

Technical Field

[0001] This invention relates to the field of insurance management technology, specifically to a blockchain-based agricultural insurance management system and method. Background Technology

[0002] Traditional agricultural insurance suffers from problems such as information asymmetry, data opacity, and low operational efficiency in risk identification, pricing, and claims settlement, which restricts the accuracy and effectiveness of insurance services. In recent years, blockchain technology, with its decentralized, tamper-proof, and traceable characteristics, has provided a new path for the innovative development of agricultural insurance.

[0003] While blockchain technology brings transparency and automation to agricultural insurance, its advantages are turned into risks due to technological bottlenecks in agricultural loss assessment. Existing agricultural loss assessment technologies struggle to distinguish between crop losses caused by natural disasters and those due to human mismanagement. This misjudgment treats human mismanagement as a natural disaster, distorting the essence of insurance companies' compensation for force majeure losses. Crop loss data cannot be deleted once it's recorded on the blockchain, triggering automatic payouts via smart contracts. To avoid erroneous payouts, insurance companies are forced to suspend smart contracts. However, the transparency of blockchain data means that agricultural workers may see loss records but not receive compensation, leading to misunderstandings and a crisis of trust, ultimately hindering the development of new agricultural models. Summary of the Invention

[0004] Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a blockchain-based agricultural insurance management system and method. This solves the problem that agricultural loss assessment technology cannot distinguish between natural disasters and human mismanagement, leading to misjudgments. After the data is uploaded to the blockchain, insurance companies suspend smart contracts to avoid erroneous claims, but the transparency of blockchain causes misunderstandings and a crisis of trust among farmers, ultimately hindering the development of new agriculture.

[0005] To achieve the above objectives, this invention provides the following technical solution: a blockchain-based agricultural insurance management method, comprising the following specific steps: Step 1: Collect crop image data from agricultural workers, including the number of pixels, pixel coordinates, and pixel brightness; simultaneously acquire disaster data, including data from various natural dimensions; Step 2: Perform comprehensive calculations and standardization on the crop image data and disaster data to obtain an agricultural loss factor; analyze crop losses based on the agricultural loss factor; if the analysis indicates no crop loss, lower the agricultural insurance premium level for the agricultural worker and return to Step 1; if the analysis indicates minor or severe crop loss, either maintain or increase the agricultural insurance premium level for the agricultural worker; Step 3: Store Step 1 and Step 2 on the blockchain and terminate the process.

[0006] Furthermore, the specific method for obtaining the agricultural loss factor is as follows: comprehensively calculate the crop image data to obtain the crop damage coefficient, comprehensively calculate the disaster data to obtain the natural disaster coefficient, and comprehensively calculate the crop damage coefficient and the natural disaster coefficient to obtain the agricultural loss factor; ;in, Indicates agricultural loss factor, Indicates the crop damage coefficient. Indicates the coefficient of natural disasters. and It represents a positive real number.

[0007] Furthermore, the specific method for obtaining the crop damage coefficient is as follows: the brightness of the pixels in the crop image data is recorded as the unit crop brightness, the number of pixels of the unit crop brightness is counted to obtain the crop area; then the unit crop brightness is combined with the pixel coordinates for comprehensive calculation to obtain the crop density, the crop area and crop density are combined for comprehensive calculation and standardized processing to obtain the crop damage coefficient. ;in, Indicates the crop damage coefficient. Indicates the area of ​​crops. Indicates crop density, or It represents a positive real number.

[0008] Furthermore, the specific method for obtaining the crop density is as follows: calculate the distance between any two pixel coordinates in the crop image data to obtain a distance group, sum the distances in the distance group, and then calculate the ratio to obtain the crop density.

[0009] Furthermore, the specific method for obtaining the natural disaster coefficient is as follows: preset thresholds for each natural dimension, calculate the difference between the data value of each natural dimension and the corresponding natural dimension threshold to obtain the outlier value of each natural dimension, and sum the outlier values ​​of each natural dimension to obtain the natural disaster coefficient.

[0010] Furthermore, the specific method for adjusting or increasing the agricultural insurance premium level for this agricultural worker in step two is as follows: an initial adjustment of the premium is made based on the crop loss situation, and then a second adjustment of the premium is made based on the crop loss trend.

[0011] Furthermore, the specific method for initially adjusting the premium based on the extent of crop damage is as follows: if the crop suffers minor damage, the premium will not be adjusted; if the crop suffers severe damage, the premium will be increased by X yuan, unless it is the maximum premium, in which case the increase will stop.

[0012] Furthermore, the specific method for secondary premium adjustment based on crop loss trends is as follows: When the agricultural loss factor exceeds the minor loss threshold, the loss time is recorded. During the loss time, the changing trend of the agricultural loss factor at each moment is analyzed. If the crop suffers minor loss and the analysis shows an increase in the agricultural loss factor, the premium is increased by X yuan, unless it is the maximum premium, in which case the increase stops. If the crop suffers minor loss and the analysis shows a decrease in agricultural loss or an unchanged trend, the premium remains unchanged. If the crop suffers severe loss and the analysis shows an increase in the agricultural loss factor or an unchanged trend, the premium is still increased by X yuan, unless it is the maximum premium, in which case the increase stops. If the crop suffers severe loss and the analysis shows a decrease in the agricultural loss factor, the premium remains unchanged.

[0013] Furthermore, the specific method for analyzing the changing trend of the agricultural loss factor at each moment within the loss time is as follows: The output value of the agricultural loss factor at the next moment is compared with the output value of the agricultural loss factor at the previous moment. If the output value of the agricultural loss factor at the next moment is greater than the output value of the agricultural loss factor at the previous moment, it indicates an increase, and the number of increases is counted. If the output value of the agricultural loss factor at the next moment is less than the output value of the agricultural loss factor at the previous moment, it indicates a decrease, and the number of decreases is counted. The number of increases is compared with the number of decreases. If the number of increases is greater than the number of decreases, it indicates that the agricultural loss factor is increasing. If the number of increases equals the number of decreases, it indicates that the trend of the agricultural loss factor remains unchanged. If the number of increases is greater than the number of decreases, it indicates that the agricultural loss factor is decreasing.

[0014] A blockchain-based agricultural insurance management system includes the following specific modules: a data acquisition module, an agricultural loss assessment module, and a blockchain evidence storage module. The data acquisition module collects crop image data from agricultural workers, including the number of pixels, pixel coordinates, and pixel brightness; it also acquires disaster data, including data from various natural dimensions. The agricultural loss assessment module performs comprehensive calculations and standardization on the crop image data and disaster data to obtain an agricultural loss factor. Based on this factor, it analyzes crop losses. If the analysis indicates no crop loss, the agricultural worker's agricultural insurance premium level is lowered, and the data is returned to the data acquisition module. If the analysis indicates minor or severe crop loss, the agricultural worker's agricultural insurance premium level is either not adjusted or is increased. The blockchain evidence storage module stores the data from the data acquisition module and the agricultural loss assessment module via blockchain, and then the process ends.

[0015] Beneficial effects Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: 1. By comprehensively collecting crop image data and disaster data, and using mathematical models to calculate agricultural loss factors, the degree of crop damage and the impact of natural disasters can be quantified more accurately. This method effectively distinguishes between losses caused by natural disasters and those caused by poor human management, reduces misjudgment problems in traditional loss assessment, and thus ensures that insurance compensation is more in line with actual risks, improving the accuracy and reliability of insurance services.

[0016] 2. Based on the analysis results of agricultural loss factors, the system can automatically adjust the premium level: lower the premium when there is no crop loss, raise the premium when there is a minor or serious loss, and make a secondary adjustment based on the loss trend. This dynamic mechanism not only reflects real-time risk changes, but also encourages agricultural workers to take remedial measures to avoid further losses. At the same time, through standardized processing and trend analysis, the premium adjustment is more fair and reasonable, enhancing the flexibility and adaptability of insurance products.

[0017] 3. By using blockchain technology to record data collection and loss assessment processes, an immutable hash record is generated, ensuring that all operations are open and transparent. Insurance companies, governments, and agricultural workers can all verify the data, reducing information asymmetry and disputes. This not only improves the efficiency of the insurance process but also alleviates the trust crisis caused by the suspension of smart contracts, promoting the healthy development of new agricultural insurance.

[0018] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0019] Figure 1 This invention provides a flowchart of a blockchain-based agricultural insurance management method.

[0020] Figure 2 This invention relates to a structural diagram of a blockchain-based agricultural insurance management system. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0023] Example 1: like Figure 1 As shown, this embodiment of the invention provides a blockchain-based agricultural insurance management method, including the following specific steps: Step 1: Using remote sensing satellites or drones, photograph, divide, and record the farmland of each agricultural worker. Agricultural workers refer not only to farmers but also to staff of agricultural enterprises or cooperatives that contract farmland. Obtain farmland images, perform noise reduction processing to remove noise points, and use artificial intelligence technology to identify crops in the farmland images. Specifically, first, train a convolutional neural network using a large number of labeled farmland images. The model automatically learns multi-layered features from basic texture to crop morphology, forming the ability to distinguish different crops. After training, pixel-level analysis can be performed on new images to accurately determine crop types and delineate distribution boundaries, achieving large-scale crop identification. Finally, grayscale conversion is performed to reduce image data volume and simplify calculations, obtaining crop image data, including the number of pixels, pixel coordinates, and pixel brightness, used to reflect the growth status of crops. Disasters near the land are detected by a variety of sensors, such as humidity sensors, anemometers, and low temperature sensors used to detect natural disasters. Disaster data is obtained, including data from various natural dimensions, to reflect the impact of natural disasters. The disaster data is then cleaned to remove redundant values.

[0024] Step Two: The denoised crop image data and the cleaned disaster data are combined and standardized to eliminate dimensional differences and convert values ​​of different orders of magnitude into a unified range, resulting in an agricultural loss factor. Based on this factor, crop losses are analyzed. If no crop loss is found, the agricultural worker's agricultural insurance premium is lowered by X yuan, unless the premium is already at the minimum, in which case the reduction stops. Since no crop loss indicates proactive disaster prevention by the agricultural worker, this helps translate their efforts into tangible economic benefits, encouraging a proactive approach that prioritizes prevention over claims. This helps reduce overall agricultural system risk and lays the foundation for insurance companies to build a healthier and more sustainable insurance pool. The process then returns to Step One. If the analysis indicates minor or severe crop loss, the agricultural worker's agricultural insurance premium is adjusted (either not adjusted or increased), meaning the worker will need to apply for insurance based on the revised premium next time.

[0025] Step 3: Proof of Step 1 and Step 2 is stored on the blockchain. This involves generating a unique hash value through binding and storing it on the blockchain. The immutability of the blockchain ensures transparency and trustworthiness throughout the process, creating authoritative evidence that can be verified and accepted by insurance companies, governments, and agricultural workers. This concludes the process.

[0026] Example 2 differs from Example 1 in that: The specific methods for obtaining agricultural loss factors are as follows: By comprehensively calculating crop image data, a crop damage coefficient is obtained; by comprehensively calculating disaster data, a natural disaster coefficient is obtained; and by comprehensively calculating the crop damage coefficient and the natural disaster coefficient, an agricultural loss factor is obtained. ; in, Indicates agricultural loss factor, This represents the crop damage coefficient, reflecting the degree of crop damage. This represents the natural disaster coefficient, reflecting the degree of impact of natural disasters. and It represents a positive real number to avoid the agricultural loss factor being meaningless when the crop damage coefficient or natural disaster coefficient is zero.

[0027] The specific methods for obtaining the crop damage coefficient are as follows: Because crop image data is converted to grayscale, the image changes from colorful to black and white. Crops are then identified by the difference in image brightness. The brightness of each pixel in the crop image data is recorded as the unit crop brightness. The number of pixels per unit crop brightness is counted to obtain the crop area. Then, the unit crop brightness is combined with the pixel coordinates to calculate the crop density. The crop area and crop density are combined and standardized to obtain the crop damage coefficient. ; in, This represents the crop damage coefficient, reflecting the degree of crop damage. This indicates the area of ​​crops; the smaller the area of ​​crops, the more severe the damage to the crops. This indicates crop density; the lower the crop density, the sparser the crops, and consequently, the more severe the crop damage. or It represents a positive real number to avoid the crop damage coefficient being meaningless when the crop area and crop density are zero.

[0028] The specific methods for obtaining crop density are as follows: The Euclidean distance formula is used to calculate the distance between any two pixels in the crop image data. The Euclidean distance formula is used to represent the straight-line distance between two pixels. The distances are then summed and the ratios are calculated to obtain the crop density, which is the average spacing between crops.

[0029] The specific methods for obtaining the natural disaster coefficient are as follows: By pre-setting thresholds for each natural dimension, the difference between the data value of each natural dimension and the corresponding threshold is calculated. For example, the difference between the rainfall data value and the rainfall threshold is calculated to obtain the outliers of each natural dimension. The outliers of each natural dimension are then summed to obtain the natural disaster coefficient. In other words, the threshold difference method normalizes multidimensional natural data into a single disaster coefficient. The calculation is simple and efficient, the thresholds are clear and adjustable, and the comprehensive intensity of disasters can be quickly quantified, providing objective, interpretable and easily implementable decision-making basis for insurance actuarial science.

[0030] The specific method for analyzing crop losses based on agricultural loss factors is as follows: Preset thresholds for minor and severe losses are used to classify the level of loss. The agricultural loss factor is compared with the minor and severe loss thresholds. If the agricultural loss factor is less than or equal to the minor loss threshold, it means that the crops have not been lost; if the agricultural loss factor is greater than the minor loss threshold but less than the severe loss threshold, it means that the crops have suffered minor losses; if the agricultural loss factor is greater than or equal to the severe loss threshold, it means that the crops have suffered severe losses.

[0031] The specific methods for adjusting or increasing the agricultural insurance premium level for this agricultural worker are as follows: The initial premium adjustment is based on the extent of crop loss. After a single detection, the system immediately triggers the preset premium adjustment rules based on the loss level to achieve static basic risk pricing. The premium is then adjusted a second time based on the crop loss trend. By continuously monitoring the trend of loss factors on the basis of static basic risk pricing, the premium is dynamically adjusted according to deterioration, stabilization or improvement, using behavior-oriented pricing to incentivize farmers to take the initiative in disaster prevention and mitigation.

[0032] The specific method for initial premium adjustments based on crop losses is as follows: If the crops suffer minor damage, the premium will not be adjusted. If the crops suffer severe damage, the premium will be increased by X yuan, unless it is the maximum premium, in which case the increase will stop.

[0033] The specific method for adjusting premiums a second time based on crop loss trends is as follows: When the agricultural loss factor exceeds the minor loss threshold, the loss time is recorded. During the loss time, the trend of the agricultural loss factor at each moment is analyzed. That is, once the system detects a loss, it will start a monitoring cycle and continuously track and analyze the dynamic trend of the loss factor within this cycle. If the crop is slightly damaged and the analysis shows that the agricultural loss factor is increasing, it indicates that the agricultural loss is increasing and reflects that agricultural workers may not have taken remedial measures for the farmland. As a result, the premium will be increased by X yuan, unless it is the maximum premium, in which case the increase will stop. That is, there is a situation where agricultural workers have not taken effective remedial measures, resulting in the expansion of the loss. Therefore, the increased risk is reflected by increasing the premium. If the crop loss is minor and the analysis shows that the agricultural loss is decreasing or the trend remains unchanged, it means that the agricultural loss has become smaller or the loss remains unchanged. It also reflects that agricultural workers may have taken remedial measures for the farmland. Therefore, the premium is not adjusted, which means that there are cases where agricultural workers have taken effective remedial measures to prevent the loss from expanding further. As an incentive, the premium is kept unchanged and no additional penalty is imposed. If crops suffer severe damage and analysis shows that agricultural loss factors are increasing or the trend remains unchanged, it indicates that agricultural losses have increased or remained unchanged, and reflects that agricultural workers have not taken remedial measures for the farmland. Therefore, the premium will still be increased by X yuan, unless it is the maximum premium, in which case the increase will stop. Even in severe cases, there may be situations where agricultural workers have not intervened effectively, which is extremely risky. Therefore, the system will continue to implement the punitive measures of premium increase until the premium cap is reached. If crops suffer severe damage and the analysis shows a decrease in agricultural loss factors, it indicates that agricultural losses are decreasing and reflects the possibility that agricultural workers may take remedial measures for the farmland. Consequently, the premium will not be adjusted. Even if the initial loss is severe, as long as the trend is positive, the system will suspend further premium increases to incentivize agricultural workers' remedial efforts.

[0034] The specific method for analyzing the changing trend of agricultural loss factors at each moment within the loss period is as follows: The output value of the agricultural loss factor at the next moment is compared with the output value of the agricultural loss factor at the previous moment. If the output value of the agricultural loss factor at the next moment is greater than the output value of the agricultural loss factor at the previous moment, it indicates an increase. The number of increases is counted to reflect the overall increasing trend and thus quantify the degree of deterioration of the loss. If the output value of the agricultural loss factor at the next moment is less than the output value of the agricultural loss factor at the previous moment, it indicates a decrease. The number of decreases is counted to reflect the overall decreasing trend and thus quantify the degree of improvement of the loss. Compare the number of increases with the number of decreases. If the number of increases is greater than the number of decreases, it indicates that the agricultural loss factor is increasing. If the number of increases is equal to the number of decreases, it indicates that the trend of the agricultural loss factor remains unchanged. If the number of increases is greater than the number of decreases, it indicates that the agricultural loss factor is decreasing.

[0035] Example 3: like Figure 2 As shown: A blockchain-based agricultural insurance management system includes the following specific modules: Data acquisition module: used to collect crop image data from agricultural workers, including the number of pixels, pixel coordinates, and pixel brightness; it also acquires disaster data, including data from various natural dimensions. The agricultural loss assessment module is used to comprehensively calculate and standardize crop image data and disaster data to obtain agricultural loss factors. Based on the agricultural loss factors, the module analyzes crop losses. If the analysis shows that there is no crop loss, the agricultural worker's agricultural insurance premium level is lowered and the data is returned to the data collection module. If the analysis shows that the crop has suffered minor or severe losses, the agricultural worker's agricultural insurance premium level is either not adjusted or is adjusted upward. Blockchain Evidence Storage Module: Used to store evidence between the data collection module and the agricultural loss assessment module via blockchain, and then terminate the process. The above modules construct a closed loop through data-driven, intelligent decision-making and blockchain-based evidence storage, creating a new paradigm for precise and efficient agricultural insurance, fundamentally solving information asymmetry and trust crises, and reshaping the industry's mutual trust mechanism.

[0036] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A blockchain-based agricultural insurance management method, characterized in that: The specific steps include the following: Step 1: Collect crop image data from agricultural workers, including the number of pixels, pixel coordinates, and pixel brightness; at the same time, acquire disaster data, including data from various natural dimensions. Step 2: Combine crop image data with disaster data for comprehensive calculation and standardization to obtain agricultural loss factors. Analyze crop losses based on agricultural loss factors. If the analysis shows no crop loss, lower the agricultural insurance premium level for this agricultural worker and return to Step 1. If the analysis shows minor or severe crop loss, either adjust or raise the agricultural insurance premium level for this agricultural worker. Step 3: Verify the results of Step 1 and Step 2 using blockchain, and then the process ends.

2. The agricultural insurance management method based on blockchain according to claim 1, characterized in that: The specific methods for obtaining the agricultural loss factors are as follows: By comprehensively calculating crop image data, a crop damage coefficient is obtained; by comprehensively calculating disaster data, a natural disaster coefficient is obtained; and by comprehensively calculating the crop damage coefficient and the natural disaster coefficient, an agricultural loss factor is obtained. ； in, Indicates agricultural loss factor, Indicates the crop damage coefficient. Indicates the coefficient of natural disasters. and It represents a positive real number.

3. The agricultural insurance management method based on blockchain according to claim 2, characterized in that: The specific method for obtaining the crop damage coefficient is as follows: The brightness of pixels in crop image data is recorded as the unit crop brightness. The number of pixels per unit crop brightness is counted to obtain the crop area. Then, the unit crop brightness is combined with the pixel coordinates to calculate the crop density. The crop area and crop density are combined and standardized to obtain the crop damage coefficient. ； in, Indicates the crop damage coefficient. Indicates the area of ​​crops. Indicates crop density, or It represents a positive real number.

4. The agricultural insurance management method based on blockchain according to claim 3, characterized in that: The specific method for obtaining the crop density is as follows: The distance between any two pixels in the crop image data is calculated sequentially to obtain a distance group. The distances in each distance group are summed and then the ratio is calculated to obtain the crop density.

5. The agricultural insurance management method based on blockchain according to claim 2, characterized in that: The specific method for obtaining the natural disaster coefficient is as follows: Preset thresholds for each natural dimension, calculate the difference between the data value of each natural dimension and the corresponding natural dimension threshold to obtain the outlier value of each natural dimension, and sum the outlier values ​​of each natural dimension to obtain the natural disaster coefficient.

6. The agricultural insurance management method based on blockchain according to claim 1, characterized in that: The specific method for adjusting or increasing the agricultural insurance premium level for this agricultural worker in step two is as follows: The premium is initially adjusted based on the extent of crop damage, and then adjusted a second time based on the trend of crop damage.

7. The agricultural insurance management method based on blockchain according to claim 6, characterized in that: The specific method for initial premium adjustments based on crop losses is as follows: If the crops suffer minor damage, the premium will not be adjusted; if the crops suffer severe damage, the premium will be increased by X yuan, unless it is the maximum premium, in which case the increase will stop.

8. The agricultural insurance management method based on blockchain according to claim 6, characterized in that: The specific method for making a secondary adjustment to the premium based on the trend of crop losses is as follows: When the agricultural loss factor exceeds the minor loss threshold, the loss time is recorded. During the loss time, the trend of the agricultural loss factor at each moment is analyzed. If the crop suffers minor loss and the analysis shows an increase in the agricultural loss factor, the premium is increased by X yuan, unless it reaches the maximum premium, in which case the increase stops. If the crop suffers minor loss and the analysis shows a decrease in agricultural loss or no change in the trend, the premium remains unchanged. If the crop suffers severe loss and the analysis shows an increase in the agricultural loss factor or no change in the trend, the premium is still increased by X yuan, unless it reaches the maximum premium, in which case the increase stops. If the crop suffers severe loss and the analysis shows a decrease in the agricultural loss factor, the premium remains unchanged.

9. The agricultural insurance management method based on blockchain according to claim 8, characterized in that: The specific method for analyzing the changing trend of agricultural loss factors at each moment within the loss period is as follows: The output value of the agricultural loss factor at the next moment is compared with the output value of the agricultural loss factor at the previous moment. If the output value of the agricultural loss factor at the next moment is greater than the output value of the agricultural loss factor at the previous moment, it indicates an increase, and the number of increases is counted. If the output value of the agricultural loss factor at the next moment is less than the output value of the agricultural loss factor at the previous moment, it indicates a decrease, and the number of decreases is counted. The number of increases is compared with the number of decreases. If the number of increases is greater than the number of decreases, it indicates that the agricultural loss factor is increasing. If the number of increases is equal to the number of decreases, it indicates that the trend of the agricultural loss factor is unchanged. If the number of increases is greater than the number of decreases, it indicates that the agricultural loss factor is decreasing.

10. A blockchain-based agricultural insurance management system, used to implement the blockchain-based agricultural insurance management method according to any one of claims 1-9, characterized in that, The blockchain-based agricultural insurance management system includes: a data acquisition module, an agricultural loss assessment module, and a blockchain evidence storage module. The data acquisition module is used to collect crop image data from agricultural workers, including the number of pixels, pixel coordinates, and pixel brightness; it also acquires disaster data, including data from various natural dimensions. The agricultural loss assessment module is used to comprehensively calculate and standardize crop image data and disaster data to obtain agricultural loss factors. Based on the agricultural loss factors, the module analyzes crop losses. If the analysis shows that there is no crop loss, the agricultural worker's agricultural insurance premium level is lowered and the data is returned to the data acquisition module. If the analysis shows that there is minor or severe crop loss, the agricultural worker's agricultural insurance premium level is either not adjusted or is increased. The blockchain evidence storage module is used to store the data collection module and the agricultural loss assessment module together via blockchain and then terminate the process.

Images