Big data and artificial intelligence-based peasant household entrepreneurship financing risk assessment system

Abstract

The invention relates to the technical field of big data analysis technology artificial intelligence application, and discloses a peasant household entrepreneurship financing risk assessment system based on big data and artificial intelligence, and the system comprises a peasant household information collection module, a historical data clustering module, a risk parameter screening module, a trend prediction module, a dynamic correction module, and an assessment scheme generation module. According to the system, target peasant household main body information and entrepreneurship project feature information are collected, historical financing data of the same kind of peasant households are called and subjected to clustering analysis, and key variables are extracted to generate a historical risk parameter set. And forming a risk parameter sequence through optimization screening, predicting a risk rising rate and a risk falling rate, dynamically correcting a prediction result in combination with the feature difference of the entrepreneurship project, and finally generating risk assessment prompt financing operation guidance. According to the method, the problems of insufficient data utilization, large correction deviation and weak decision support of a traditional method are solved, and the accuracy and practicability of peasant household entrepreneurship financing risk assessment are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of big data analysis technology and artificial intelligence application technology, and specifically to a farmer's entrepreneurship financing risk assessment system based on big data and artificial intelligence. Background Art

[0002] Traditional risk assessment methods primarily rely on static financial indicators or manual judgment, resulting in problems such as single-dimensional data, poor timeliness, and high subjectivity. While some existing technologies attempt to incorporate credit scoring models, these fail to fully incorporate the dynamic characteristics of farmer entrepreneurship projects, such as key factors like industry type and changes in business scale. This results in assessments that deviate significantly from actual risk.

[0003] Currently, big data and artificial intelligence technologies offer new solutions for financing risk assessment. For example, cluster analysis can identify risk patterns in historical data, and machine learning models can predict risk trends. However, existing systems still face the following limitations in the context of farmer entrepreneurship: First, they underutilize historical data and fail to differentiate clusters based on the characteristics of similar farmers; second, they lack a dynamic optimization mechanism for risk parameter screening, making it difficult to adapt to changes in farmers' operating environments; and third, the correction process fails to consider the fine-grained differences between entrepreneurial project characteristics and standard characteristics, leading to cumulative bias in prediction results. Furthermore, the assessment plans generated by traditional systems lack operational guidance and are unable to provide specific decision support to financial institutions.

[0004] Therefore, an assessment system is needed that can integrate multidimensional data, dynamically optimize parameters, and accurately correct risk trends to address the accuracy, timeliness, and practicality issues in farmer entrepreneurship financing risk assessment. This invention, through a modular design, optimizes the entire process from data collection to decision-making, providing financial institutions with a scientific and reliable risk management tool. Summary of the Invention

[0005] The purpose of the present invention is to provide a farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence, the system comprising: A farmer information collection module is used to obtain the subject information of the target farmer currently applying for financing, as well as the characteristic information of the target farmer's entrepreneurial project. Based on the target farmer's subject information, the module retrieves the historical financing data of similar farmers within the user's historical time period; A historical data clustering module, configured to cluster historical risk influencing factors within the historical financing data to obtain a plurality of clustered risk feature groups, extract historical key variable information sets and a plurality of historical financing operation sets from the plurality of clustered risk feature groups, and process and generate a plurality of historical risk parameter sets; a risk parameter screening module, wherein the risk parameter screening module is used to optimize and screen the multiple historical risk parameter sets respectively to obtain multiple screened risk parameter groups, and arrange them in chronological order to form multiple historical risk parameter sequences; A trend prediction module, configured to predict financing risk trends based on the multiple historical risk parameter sequences to obtain risk rise and fall rates; a dynamic correction module, the dynamic correction module being used to match the entrepreneurial project characteristic information of the target farmer with the multiple clustered risk characteristic groups, determine a matching risk characteristic group, and correct the risk increase rate and decrease rate based on the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group to obtain a corrected increase rate and a corrected decrease rate; An evaluation scheme generation module is used to make financing risk assessment decisions based on the modified increase rate and the modified decrease rate, generate risk assessment prompts, and provide financing operation guidance.

[0007] Preferably, the target farmer's subject information for the current financing application is obtained, and the characteristic information of the target farmer's entrepreneurial project is collected. Based on the target farmer's subject information, the historical financing data of similar farmers in the user's historical time is retrieved, including: Obtaining identity attribute information and credit record information of target farmers, and collecting industry type and business scale information of the target farmers' entrepreneurial projects as entrepreneurial project feature information; Based on the target farmer's main information, a related search is performed in the historical financing database to obtain historical financing data of similar farmers.

[0008] Preferably, the historical risk influencing factors in the historical financing data are clustered to obtain multiple clustered risk feature groups, and historical key variable information sets and multiple historical financing operation sets under the multiple clustered risk feature groups are extracted to generate multiple historical risk parameter sets, including: Extracting multiple risk influencing factors from the historical financing data, performing feature clustering processing, and obtaining multiple clustered risk feature groups; Collecting the operating stability indicators of farmers in the historical financing data under the multiple clustered risk feature groups to form a historical key variable information set, and extracting the financing application parameter set and financing processing time set submitted by users under the multiple clustered risk feature groups; Classify and generate multiple historical basic parameter sets according to the degree of deviation between the multiple financing application parameter sets and the historical key variable information set; According to the comparison results between the preset time threshold and the multiple financing processing time sets, the multiple historical basic parameter sets are adjusted and calculated to generate multiple historical risk parameter sets.

[0009] Preferably, the plurality of historical risk parameter sets are optimized and screened respectively to obtain a plurality of screened risk parameter groups, which are arranged in chronological order to form a plurality of historical risk parameter sequences, including: Selecting a first benchmark risk parameter in a first historical risk parameter set among the plurality of historical risk parameter sets; Assigning selection probabilities based on the degree of difference between other parameters in the first historical risk parameter set and the first benchmark risk parameter to form a first basic probability distribution, wherein the degree of difference is negatively correlated with the selection probability; Optimizing and screening the first set of historical risk parameters based on the first basic probability distribution to obtain a first screening risk parameter group; Arrange the time identification information of multiple parameters in the first screening risk parameter group in sequence to form the first historical risk parameter sequence; Repeat the optimization screening and time series arrangement operations on the remaining multiple historical risk parameter sets to form multiple historical risk parameter sequences.

[0010] Preferably, the first historical risk parameter set is optimized and screened based on the first basic probability distribution to obtain a first screened risk parameter group, including: Randomly selecting a preset number of risk parameters from the first historical risk parameter set to form a first screening risk parameter group; Allocating selection probabilities based on the degree of difference between the parameters within the first screening risk parameter group and the first benchmark risk parameter to form a first screening probability distribution; Calculating the similarity between the first screening probability distribution and the first basic probability distribution as the first screening fitness; Again randomly selecting a preset number of risk parameters from the first historical risk parameter set to form a second screening risk parameter group, and calculating a second screening fitness; The optimization and screening operation is continued until the convergence condition is reached, and the screening risk parameter group with the highest fitness is output as the first screening risk parameter group.

[0011] Preferably, the financing risk trend forecast is performed based on the multiple historical risk parameter sequences to obtain the risk rise rate and risk fall rate, including: Collect sample financing data of multiple farmers, extract a set of sample risk parameter sequences, and obtain a set of sample rising rates and a set of sample falling rates based on the parameter change characteristics within each sample risk parameter sequence; Taking the sample risk parameter sequence set as input features and the sample increase rate set and sample decrease rate set as output targets, a risk trend prediction model is constructed; Using the risk trend prediction model, risk trend classification prediction is performed on the multiple historical risk parameter sequences to obtain multiple characteristic increase rates and multiple characteristic decrease rates; Analyze the similarity between the entrepreneurial project characteristic information of the target farmer and the multiple clustered risk characteristic groups, and perform weighted calculation on the multiple characteristic increase rates and multiple characteristic decrease rates according to the numerical values of the multiple similarities to obtain the risk increase rate and decrease rate.

[0012] Preferably, the entrepreneurial project characteristic information of the target farmer is matched with the multiple clustered risk characteristic groups to determine a matching risk characteristic group, and the risk increase rate and decrease rate are corrected according to the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group to obtain a corrected increase rate and a corrected decrease rate, including: Selecting the clustered risk feature group with the highest similarity as the matching risk feature group, and obtaining standard feature information of the matching risk feature group; Setting a risk correction coefficient according to the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group; The risk correction coefficient is used to correct the risk increase rate and decrease rate to obtain a corrected increase rate and a corrected decrease rate.

[0013] Preferably, a financing risk assessment decision is made based on the modified rising rate and the modified falling rate, a risk assessment prompt is generated, and financing operation guidance is provided, including: Collect a set of sample correction rising rates and a set of sample correction falling rates, and set sample evaluation prompt content according to the numerical value of each sample correction rising rate and sample correction falling rate to form a set of sample evaluation prompts, wherein each sample evaluation prompt includes a parameter adjustment range, and the numerical values of the sample correction rising rate and the sample correction falling rate are negatively correlated with the parameter adjustment range; Constructing a risk assessment decision model using the sample corrected rise rate set and the sample corrected fall rate set as input variables and the sample evaluation prompt set as output results; The risk assessment decision model is used to evaluate and decide on the revised rise rate and the revised fall rate, and generate a risk assessment prompt.

[0014] Preferably, sample financing data of multiple farmers are collected, a sample risk parameter sequence set is extracted, and a sample increase rate set and a sample decrease rate set are obtained according to the parameter change characteristics within each sample risk parameter sequence, including: Screen the sample data of farmers with complete financing records in the past three years and extract the time series of risk assessment parameters for each sample; Analyze the increase and decrease of the parameters at adjacent time points in the risk parameter time series of each sample, and calculate the risk increase and decrease rates of each sample; The risk parameter time series of all samples are summarized into a sample risk parameter series set, and the risk increase rate and decrease rate of all samples are summarized into a sample increase rate set and a sample decrease rate set respectively.

[0015] Preferably, the risk correction coefficient is set according to the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group, including: Calculate the difference between the entrepreneurial project feature information and the standard feature information in the industry type dimension, and record it as a first difference value; Calculate the difference between the entrepreneurial project characteristic information and the standard characteristic information in the business scale dimension, and record it as a second difference value; Performing a weighted summation on the first difference value and the second difference value to obtain a comprehensive difference value; According to the preset correspondence table between difference values and correction coefficients, the value corresponding to the comprehensive difference value is searched and used as the risk correction coefficient.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The farmer entrepreneurship financing risk assessment system provided by this invention achieves intelligent dynamic optimization of the entire risk assessment process through the collaborative operation of multiple modules. The system first utilizes the farmer information collection module to obtain detailed information and entrepreneurial project characteristics of target farmers, ensuring comprehensive data dimensionality. The historical data clustering module then groups historical financing data of similar farmers into feature groups, extracts key variables, and generates a set of risk parameters, significantly improving the efficiency of historical data utilization. The risk parameter screening module utilizes a probability distribution optimization method to dynamically screen time series parameters, effectively reducing the interference of noise data on prediction results.

[0017] The trend prediction module uses a machine learning model to analyze the changing patterns of risk parameter sequences, accurately predicting the rate of risk increase and decrease, and providing a reliable basis for subsequent corrections. The dynamic correction module calculates correction coefficients to adjust the predicted values by matching the characteristics of entrepreneurial projects with those of clustering criteria, addressing the assessment distortion caused by characteristic bias in traditional methods. Finally, the assessment solution generation module combines the correction results to generate specific risk assessment prompts and operational guidance, helping financial institutions develop differentiated financing strategies and enhance risk management capabilities.

[0018] The system has demonstrated significant advantages in practical applications. By combining cluster analysis with dynamic correction, the system can adapt to the needs of farmers of different industry types and operating scales, and the assessment results are more targeted. Optimized screening of time series prediction technology enhances the model's anti-interference ability, making risk assessment more stable and reliable. In addition, the financing operation guidelines generated by the system are directly linked to the adjustment range of risk parameters, providing financial institutions with feasible decision-making support, lowering the financing threshold for farmers and promoting rural economic vitality. The present invention has outstanding effects in improving assessment accuracy, enhancing practicality, and optimizing decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a working principle diagram of the farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to the present invention; Figure 2 This is the design diagram of the historical data clustering module; Figure 3 This is the design diagram of the trend prediction module; Figure 4 This is the design diagram of the risk correction factor. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] See also Figure 1-Figure 4 The present invention relates to a farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence, and its specific implementation is as follows: The farmer information collection module obtains the main information of the target farmer currently applying for financing, as well as the characteristic information of the target farmer's entrepreneurial project. Based on the main information of the target farmer, it retrieves the historical financing data of similar farmers within the user's historical time.

[0022] The historical data clustering module clusters the historical risk influencing factors in the historical financing data, obtains multiple clustered risk feature groups, extracts historical key variable information sets and multiple historical financing operation sets under the multiple clustered risk feature groups, and processes and generates multiple historical risk parameter sets.

[0023] The risk parameter screening module optimizes and screens multiple historical risk parameter sets respectively, obtains multiple screened risk parameter groups, and arranges them in chronological order to form multiple historical risk parameter sequences.

[0024] The trend prediction module predicts financing risk trends based on multiple historical risk parameter sequences to obtain risk rise and fall rates.

[0025] The dynamic correction module matches the entrepreneurial project characteristic information of the target farmers with multiple clustered risk characteristic groups, determines the matching risk characteristic group, and corrects the risk increase rate and decrease rate according to the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group to obtain the corrected increase rate and corrected decrease rate.

[0026] The assessment plan generation module makes financing risk assessment decisions based on the revised rising rate and revised falling rate, generates risk assessment prompts, and provides financing operation guidance. Example 1:

[0027] This example describes in detail the specific implementation of the farmer information collection module: During system operation, the system first needs to complete the acquisition of the target farmer's principal information. This process involves the collection of identity attribute information covering multiple dimensions. For example, the acquisition of name information must ensure that it is completely consistent with the information on the farmer's ID card to ensure accurate identification. The ID card number is a unique identifier, and the system will perform format verification and uniqueness verification to avoid duplication or errors. The collection of age information not only records the specific value, but also conducts correlation analysis based on the farmer's labor capacity and the characteristics of the entrepreneurial project. Household registration information is refined to the specific township and village, which is of great significance for subsequent analysis of the economic development level and policy support of the farmer's region.

[0028] To collect credit history information, the system connects with multiple credit information platforms. Bank credit reporting systems are a key data source, capturing information such as farmers' overdue payment records, credit card overdrafts, and loan defaults. Furthermore, the system collects farmers' credit records with other financial institutions, such as rural credit cooperatives, as well as transaction credit data on e-commerce platforms, such as defaulted orders and refund rates. This multi-dimensional credit record information comprehensively reflects farmers' credit status and provides a crucial basis for subsequent financing risk assessments.

[0029] To gather characteristic information about target farmer entrepreneurial projects and determine their industry types, detailed understanding of the specific business content of the projects is required. For example, agricultural planting projects require further clarification of the crop types, whether they qualify as cash crops, and the level of sophistication of planting techniques. Agricultural product processing projects require understanding of the product types, processing techniques, and the extent of the industrial chain. Rural e-commerce projects require understanding of the product categories sold, the operational status of the e-commerce platform, and market share. This detailed industry type information helps the system accurately match target farmers with similar farmers in historical financing data.

[0030] The collection of operational scale information also requires the refinement of multiple indicators. Planted area measurements combine satellite remote sensing data with field research to ensure accuracy. Employee statistics include both full-time and part-time employees to reflect the project's workforce. Registered capital information must be verified against industrial and commercial registration data to ensure authenticity. Annual turnover data is collected by referencing farmers' financial statements, bank statements, and other data to comprehensively reflect the project's operational status.

[0031] After obtaining the target farmer's principal information and the characteristics of the entrepreneurial project, the system will enter the retrieval stage of historical financing data. First, the system will use the target farmer's identity attribute information and credit record information as search criteria to conduct a related search in the historical financing database. During the search process, a combination of fuzzy matching and precise matching will be adopted. For example, for household registration information, a precise township-level match will be performed first. If there are few matching results, fuzzy matching will be expanded to the county or city level. For credit record information, a certain credit score threshold will be set, and farmers with credit scores near this threshold will be included in the search scope.

[0032] When searching for similar farmers, the system calculates the similarity between the target farmer and historical farmers based on a preset similarity algorithm. This similarity algorithm comprehensively considers multiple factors, including identity attribute information, credit record information, and entrepreneurial project characteristics. For example, factors such as age and registered residence in identity attribute information are assigned certain weights. Factors such as credit score and number of overdue payments in credit record information are also assigned corresponding weights. Factors such as industry type and business scale in entrepreneurial project characteristics are also assigned weights. Through weighted calculation, the similarity value between each historical farmer and the target farmer is obtained. The system then selects historical farmers with similarity values above the preset threshold and obtains their historical financing data.

[0033] Historical financing data covers multiple aspects. Information on historical financing applications includes information on the financing amount, financing term, and application date; approval results include approval, approval time, and approved amount; and repayment status includes information on repayment time, repayment amount, and whether repayments were made on time. This data is fully retrieved and stored by the system for subsequent cluster analysis and risk assessment.

[0034] To ensure data accuracy and completeness, the system conducts multiple checks on collected and retrieved data. Identity information and credit history are compared with authoritative databases. For information on entrepreneurial project characteristics, farmers are required to provide relevant supporting documentation, such as business licenses, land contracts, and financial statements, which are then reviewed by professionals. Historical financing data is checked for consistency and completeness to ensure there are no missing or erroneous information.

[0035] In terms of data storage, the system will use distributed database technology to store collected and retrieved data on multiple servers to improve data security and availability. At the same time, the data will be encrypted to prevent data leakage.

[0036] The system also incorporates a data update mechanism. Whenever a target farmer's information changes, such as when their credit history is updated or their entrepreneurial project scales up, the system promptly updates the relevant information. For historical financing data, the system also regularly retrieves the latest data from the data source, ensuring the database remains up to date. Example 2:

[0037] This example describes in detail the implementation of the historical data clustering module: When processing historical financing data, the system needs to extract factors that influence financing risk from this massive amount of data. These historical risk factors cover multiple dimensions, including the farmer's own operating conditions, the development trends of the industry in which they operate, and the macroeconomic environment. For example, in terms of farmer's operating conditions, factors such as years of operation, annual profit fluctuations, asset-liability ratio, and fixed asset size are extracted; in terms of industry development trends, factors such as the strength of industry policy support, market demand trends, and the intensity of industry competition are included; and in terms of the macroeconomic environment, factors such as local GDP growth rate, inflation rate, and employment rate are included. The system comprehensively analyzes these factors to ensure that no important risk factors are missed.

[0038] After extracting multiple risk influencing factors, the system will perform feature clustering on these factors. Feature clustering uses an advanced clustering algorithm that can classify risk influencing factors into different groups based on their similarity. During the clustering process, it is necessary to set appropriate clustering parameters, such as the number of clusters and the similarity calculation method. The similarity calculation will comprehensively consider the numerical differences and attribute characteristics of multiple factors. For numerical factors, the differences are calculated using methods such as Euclidean distance; for categorical factors, an appropriate classification similarity algorithm is used for calculation. By continuously adjusting the clustering parameters, the risk influencing factors within each cluster group have a high degree of similarity, and the differences between different cluster groups are large, thus obtaining multiple clustered risk feature groups.

[0039] After clustering, the system needs to collect historical key variable information sets for each clustered risk feature group. This historical key variable information set primarily consists of farmers' business stability indicators. For agricultural planting farmers, for example, business stability indicators may include the number of consecutive years of planting, the fluctuation range of the yield of major crops, the degree of irrigation facilities, and the ability to cope with natural disasters. For agricultural product processing farmers, business stability indicators may include the sophistication of processing equipment, the stability of raw material supply, and the diversity of product sales channels. The system extracts these indicators one by one from historical financing data to ensure that the data source for each indicator is reliable and the records are accurate.

[0040] The system also extracts the financing application parameter sets and financing processing time sets submitted by users under multiple clustered risk feature groups. The financing application parameter set includes information such as the financing amount, desired financing term, acceptable interest rate range, and repayment method proposed by the farmer when applying for financing; the financing processing time set records the time it takes for each financing application to be submitted and finally approved. This information is crucial for subsequent analysis of financing risk parameters.

[0041] The system categorizes historical financing data based on the degree of deviation between multiple financing application parameter sets and historical key variable information sets, generating multiple historical basic parameter sets. The calculation of the degree of deviation requires considering the difference between each financing application parameter and the corresponding historical key variable. For example, if a farmer's application for financing exceeds the asset size and profitability reflected in their historical key variable information, the degree of deviation between the financing application parameter and the historical key variable information will be significant. The system sets a reasonable deviation threshold for each financing application parameter and divides the historical financing data into different categories based on the degree of deviation, with each category corresponding to a historical basic parameter set.

[0042] After generating a set of historical basic parameters, the system needs to adjust and calculate multiple sets of historical basic parameters based on the comparison results of the preset time threshold and multiple financing processing time sets. The preset time threshold is set based on the average financing processing time in the industry and is appropriately adjusted based on different financing types and scales. The system compares each financing processing time with the preset time threshold. If the financing processing time exceeds the threshold, it indicates that there may be some special circumstances in the approval process of the financing, such as difficulty in reviewing farmers' information or complex risk assessment of the project. For these situations, the system will adjust the parameters in the corresponding historical basic parameter set, such as increasing the weight of risk-related parameters to reflect the additional risks that may exist in the approval process. The adjustment calculation process requires comprehensive consideration of multiple factors to ensure that the adjusted historical risk parameter set can more accurately reflect the financing risk situation.

[0043] Throughout the historical data clustering process, data quality control is crucial. The system rigorously verifies and cleanses extracted data on historical risk factors, operational stability indicators, financing application parameters, and other factors. Missing data is filled using appropriate interpolation methods, and outliers are identified and corrected to ensure data accuracy and completeness. Furthermore, the system regularly evaluates and optimizes clustering results, adjusting clustering parameters and calculation methods based on new historical financing data and evolving business needs, ensuring that the clustered risk feature groups and historical risk parameter sets consistently accurately reflect actual conditions.

[0044] The system also establishes an update mechanism for historical risk parameter sets. When new historical financing data is entered, the system automatically incorporates it into the cluster analysis process, regenerating clustered risk profile groups and historical risk parameter sets to ensure data timeliness and accuracy. This dynamic update approach allows the system to continuously learn and adapt to new risk profiles, improving the accuracy and reliability of financing risk assessments.

[0045] Through the detailed implementation described above, the historical data clustering module can effectively perform cluster analysis on historical financing data, generating a set of historical risk parameters that accurately reflect financing risk characteristics, providing strong support for subsequent risk parameter screening and risk trend forecasting. The entire process strictly adheres to the principles of standardized and scientific data processing, ensuring that every step of the operation accurately reflects the inherent characteristics and risk patterns of historical financing data. Example 3:

[0046] This example describes the specific implementation of the risk parameter screening module: When screening risk parameters, the system first selects the first benchmark risk parameter from the first of multiple historical risk parameter sets. This first set includes multiple financing risk-related parameters extracted from historical financing data, such as the farmer's debt-to-asset ratio, years of operation, and industry risk coefficient. The selection of benchmark risk parameters requires comprehensive consideration of their importance and representativeness for financing risk assessment. Typically, parameters with a high correlation with financing risk in historical data are selected, such as the debt-to-asset ratio. This parameter directly reflects the farmer's debt repayment ability and has a significant impact on financing risk assessment.

[0047] After selecting the first benchmark risk parameter, the system calculates the degree of difference between the other parameters in the first historical risk parameter set and the benchmark risk parameter, and assigns selection probabilities based on the degree of difference, forming the first basic probability distribution. The calculation of the degree of difference takes into account the parameter type and numerical characteristics. For numerical parameters, the difference is measured by calculating the absolute or relative difference between the parameter value and the benchmark parameter value. For categorical parameters, the degree of difference is determined by determining the difference between the parameter category and the benchmark parameter category. The degree of difference is inversely correlated with the probability of selection: the smaller the difference between a parameter and the benchmark risk parameter, the higher the probability of selection during the screening process, and vice versa. For example, if the benchmark risk parameter is a debt-to-asset ratio of 25% and another parameter is a debt-to-asset ratio of 28%, the degree of difference is small, resulting in a higher probability of selection. On the other hand, if a parameter is a debt-to-asset ratio of 45%, the degree of difference is large, resulting in a lower probability of selection.

[0048] Based on the initial basic probability distribution, the system begins optimizing and screening the first set of historical risk parameters. Specifically, the system randomly selects a preset number of risk parameters from the first set of historical risk parameters to form the first screened risk parameter group. The setting of this preset number depends on the size of the parameter set and the required accuracy of the risk assessment. It is typically set to cover the key risk characteristics, such as randomly selecting 10 parameters from a set of 20 parameters.

[0049] After forming the first screening risk parameter group, the system calculates the degree of difference between the parameters within that group and the first baseline risk parameter and redistributes the selection probabilities based on the degree of difference, forming the first screening probability distribution. The system then calculates the degree of similarity between the first screening probability distribution and the first baseline probability distribution, using this as the first screening fitness. This similarity is calculated using a probability distribution similarity algorithm, which measures the proximity between two probability distributions.

[0050] The system will again randomly select a preset number of risk parameters from the first set of historical risk parameters to form a second screening risk parameter group. The system will then calculate the second screening fitness using the same method. This random selection and fitness calculation process will be repeated to continuously optimize the screening process.

[0051] During the optimization and screening process, the system sets convergence criteria. The screening process is considered converged when the screening fitness no longer significantly improves or when the preset number of iterations is reached. At this point, the system outputs the screening risk parameter set with the highest fitness as the first screening risk parameter set. This process is similar to searching for the combination of parameters that best matches the underlying probability distribution among numerous possible combinations, ensuring that the selected parameter set best reflects the characteristics of the historical risk parameter set.

[0052] After obtaining the first set of screening risk parameters, the system will sort the parameters within that set according to their time stamps, forming the first historical risk parameter sequence. The time stamps record the time points corresponding to each parameter, such as the financing application date and approval date. By arranging the parameters in chronological order, we can reflect the trend of risk parameters over time.

[0053] After completing the screening and sorting of the first set of historical risk parameters, the system repeats the optimization, screening, and chronological arrangement of the remaining sets. For each set, a baseline risk parameter is selected, the degree of variance and underlying probability distribution are calculated, and then random selection and fitness calculations are performed until convergence results in a selected risk parameter set. Finally, the set is arranged chronologically to form a historical risk parameter sequence.

[0054] Throughout the risk parameter screening process, data processing and calculations must maintain a high degree of accuracy and consistency. The system rigorously verifies each historical risk parameter set to ensure the accuracy of both the parameter values and time stamps. Missing time stamps are supplemented by linking other data records. Abnormal parameter values are verified and corrected.

[0055] At the same time, the system dynamically adjusts parameters such as the number of presets and convergence criteria based on the characteristics of different historical risk parameter sets. For example, for sets with a large number of parameters, the number of presets can be appropriately increased to ensure that the selected parameter groups contain sufficient risk characteristics; for sets with higher data quality, the convergence criteria can be appropriately increased to obtain more accurate screening results.

[0056] In addition, the system establishes a verification mechanism for screening results. The validity and accuracy of the historical risk parameter sequences obtained through screening are verified by comparing them with actual financing risk results. If significant deviations between the screening results and actual conditions are found, the screening process will be reviewed and relevant parameters and algorithms will be adjusted to ensure that the selected risk parameters accurately reflect the changing trends in financing risk. Example 4:

[0057] In the farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence, the specific implementation of the trend prediction module in Example 4 is as follows: To predict financing risk trends, the system needs to collect sample financing data from multiple farmers. Using historical data from a rural financial institution in a specific county as an example, the system selects a sample of farmers with complete financing records over the past three years, for example, selecting 1,000 farmers from various industries, including planting, breeding, and rural e-commerce. This sample data must include information on the entire financing process, from application to repayment, including basic farmer information, entrepreneurial project characteristics, historical risk parameters, and corresponding risk assessment results.

[0058] The system extracts a time series of risk assessment parameters from each sample. For example, for a farmer named Zhang, his risk parameter time series might include a debt-to-asset ratio of 35%, five years of operation, and an industry risk coefficient of 0.6 in January 2022; a debt-to-asset ratio of 38%, five.5 years of operation, and an industry risk coefficient of 0.7 in July 2022 (due to the impact of natural disasters that year); and a debt-to-asset ratio of 36%, six years of operation, and an industry risk coefficient of 0.5 in January 2023. The parameters at each time point correspond to a specific financing application or post-loan management node. The system aggregates the parameter time series of the 1,000 sample households into a set of sample risk parameter sequences, each containing parameter data from at least three time points.

[0059] The system analyzes the changes in each sample's risk parameter time series at adjacent time points and calculates the sample's rate of increase and rate of decrease. For example, Mr. Zhang's debt-to-asset ratio rose from 35% to 38% from January to July 2022, with a rate of increase of (38% - 35%) / 35% (≈ 8.57%). From July 2022 to January 2023, it fell from 38% to 36%, with a rate of decrease of (38% - 36%) / 38% (≈ 5.26%). For each sample, the rate of increase and rate of decrease are calculated for all risk parameters (such as the debt-to-asset ratio and industry risk factor), and the average is taken as the sample's rate of increase and rate of decrease. For example, Mr. Zhang's comprehensive rate of increase is the arithmetic average of the rate of increase of each parameter, and the same applies to the comprehensive rate of decrease. The rate of increase and rate of decrease for the 1,000 sample households are aggregated into a sample rate of increase set (e.g., containing 1,000 values of the rate of increase) and a sample rate of decrease set, respectively.

[0060] The system uses a set of sample risk parameter sequences as input features and a set of sample increase and decrease rates as output targets to construct a risk trend prediction model. The model utilizes recurrent neural networks (RNNs) or long short-term memory networks (LSTMs) in machine learning, as they are well-suited for processing time series data. Taking the LSTM model as an example, the input layer receives risk parameters (such as debt-to-asset ratios and years of operation) at each time point. The hidden layer uses memory cells to capture the changing trends of these parameters over time, and the output layer predicts the corresponding increase and decrease rates. During model training, 800 households are used as a training set and 200 households as a validation set. Hyperparameters such as the number of network layers and neurons are adjusted to minimize the model's prediction error on the validation set.

[0061] Once the model is built, the system uses it to categorize and predict risk trends for multiple historical risk parameter sequences. For example, for a historical risk parameter sequence that includes a 40% debt-to-asset ratio and three years of operation in January 2023, a 42% debt-to-asset ratio and three.5 years of operation in July 2023, and a 45% debt-to-asset ratio and four years of operation in January 2024, the model predicts a characteristic increase rate of 10% and a characteristic decrease rate of 3%, reflecting an upward trend in risk for this type of household.

[0062] At the same time, the system analyzes the similarity between the target farmer's entrepreneurial project characteristics and multiple clustered risk feature groups. For example, for target farmer Li (engaged in fruit farming), his entrepreneurial project characteristics are "cash crop farming" industry type and "planting area of 50 mu, annual turnover of 800,000 yuan." The system matches these characteristics with risk feature groups derived from historical clustering (such as "cash crop farming - small scale" and "grain farming - large scale") and calculates the similarity between each feature group. The similarity is calculated based on the matching degree of the industry type (e.g., a perfect match between "cash crop farming" and the industry type of a feature group is assigned a score of 1, while a partial match is assigned a score of 0.5) and the difference in business scale (e.g., the score is calculated by the difference between the normalized planting area and turnover and the standard value of the feature group). This ultimately yields a comprehensive similarity score for each feature group. Assume that Li's similarity with the "cash crop farming - medium scale" feature group is the highest, at 0.85, while his similarity with the other feature groups is 0.6, 0.4, and so on.

[0063] Based on the numerical values of multiple similarities, the system performs a weighted calculation on the model's predicted multiple feature increase and decrease rates. The weighted formula is: Risk Increase Rate = Σ(Feature Increase Rate × Similarity of Corresponding Feature Groups) / ΣSimilarity. The same applies to the Risk Decrease Rate. For example, if the model predicts feature increase rates of 8%, 10%, and 12% for Mr. Li's three feature groups, and similarities of 0.85, 0.1, and 0.05, respectively, then the Risk Increase Rate = (8% × 0.85 + 10% × 0.1 + 12% × 0.05) / (0.85 + 0.1 + 0.05) = (6.8% + 1% + 0.6%) / 1 = 8.4%. The Risk Decrease Rate is calculated using the same logic.

[0064] Throughout the implementation process, sample data screening and preprocessing are crucial. The system eliminates samples with incomplete financing records (e.g., missing post-loan management data) and corrects or flags abnormal parameter values (e.g., debt-to-asset ratios exceeding 100% without reasonable explanation). For samples with insufficient time series length (e.g., containing only a single time point), interpolation is used to supplement intermediate node data to ensure consistent model input.

[0065] Furthermore, the model's update mechanism must be continuously operational. When more than 500 new sample data accounts are added, the system retrains the LSTM model, adjusting parameter weights to adapt to the new risk trend characteristics. For example, if the risk parameter trends in the rural e-commerce industry in the new data differ from previous ones, the model will be retrained to capture these changes and avoid prediction bias. Example 5:

[0066] In the farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence, the specific implementation methods of the dynamic correction module and the assessment scheme generation module in Example 5 are as follows: During the implementation of the dynamic correction module, the system matches the target farmer's entrepreneurial project characteristics with multiple clustered risk profile groups to determine the matching risk profile group. For example, the target farmer, Mr. Wang, has an entrepreneurial project called "agricultural product processing enterprise with an annual output of 100 tons." His industry type is agricultural product processing, and his business scale is reflected in a plant area of 1,000 square meters, 20 employees, and an annual turnover of 5 million yuan. The system then compares this characteristic information with multiple risk profile groups formed by clustering historical data, such as "agricultural product processing - small enterprise," "agricultural product processing - medium-sized enterprise," and "planting - large-scale."

[0067] During the matching process, the system calculates the degree of similarity between the entrepreneurial project's characteristic information and each clustered risk feature group. For industry type, a category matching approach is used. If the target farmer's industry type exactly matches a particular feature group, the industry dimension score is 1; if it belongs to a related industry (such as agricultural product processing and agricultural product cultivation), the score is 0.5. For business scale, the specific values of the target farmer (such as factory area and turnover) are compared with the standard feature information of the feature group. For example, the standard feature information for the "Agricultural Product Processing - Small Enterprise" feature group is factory area of 500-1500 square meters, number of employees of 10-30, and annual turnover of 3-8 million yuan. Mr. Wang's factory area of 1000 square meters falls within this range, so it receives a score of 1; the number of employees of 20 also falls within this range, so it receives a score of 1; and the annual turnover of 5 million yuan also falls within this range, so it receives a score of 1. Based on the scores of industry type and business scale, the system calculated that Wang's similarity with the "agricultural product processing-small enterprise" feature group is (1+1+1) / 3×1 (industry weight) = 1. The similarity with other feature groups is lower than this value. Therefore, this feature group is selected as the matching risk feature group, and its standard feature information is obtained, namely the range of factory area, number of employees, annual turnover and the corresponding standard values of risk parameters.

[0068] The system needs to adjust the risk rise and fall rates based on the difference between the entrepreneurial project's characteristic information and the standard characteristic information of the matching risk characteristic group. For example, although Mr. Wang's business scale value is within the standard range, the system further calculates the difference between his specific value and the median of the standard range. For the "Agricultural Product Processing - Small Enterprise" characteristic group, the median of the standard range for factory area is 1,000 square meters, and Mr. Wang's factory area is exactly at the median, so the first difference value is 0. The median of the standard range for number of employees is 20, and Mr. Wang also has 20 employees, so the second difference value is 0. The median of the standard range for annual turnover is 5.5 million yuan, and Mr. Wang's annual turnover is 5 million yuan, so the difference from the median is 500,000 yuan. After normalization (for example, dividing the difference value by the interval span), the second difference value is -0.2 (assuming the interval span is 5 million yuan, (500-550) / 500 = -0.1. The specific calculation is adjusted according to the actual data range). The first difference value (industry dimension) and the second difference value (operating scale dimension) are weighted and summed according to the preset weights (such as industry dimension weight 0.4, operating scale weight 0.6), and the resulting comprehensive difference value is 0×0.4+(-0.2)×0.6=-0.12.

[0069] The system presets a table that corresponds to difference values and correction coefficients. For example, when the comprehensive difference value is between -0.15 and -0.1, the risk correction coefficient is 0.95; when it is between -0.1 and 0, the correction coefficient is 1. Based on Wang's comprehensive difference value of -0.12, the risk correction coefficient is determined to be 0.95. Assuming that the trend prediction module determines the risk increase rate to be 10% and the risk decrease rate to be 5%, the risk correction coefficient is used to make the correction calculation: the corrected increase rate = 10% × 0.95 = 9.5%, and the corrected decrease rate = 5% × 0.95 = 4.75%. In other words, by adjusting the differences between the entrepreneurial project characteristics and the standard characteristics, the expected increase in risk is reduced.

[0070] In the assessment plan generation module, the system first collects a set of sample revised upward and downward rates. Taking a historical sample of 1,000 households as an example, each sample receives a corresponding revised upward and downward rate after dynamic correction. For example, Sample A has a revised upward rate of 8% and a revised downward rate of 6%, while Sample B has a revised upward rate of 12% and a revised downward rate of 3%. The system sets sample assessment prompts based on the values of each sample's revised upward and downward rates, forming a set of sample assessment prompts. For example, when the revised upward rate is ≤5% and the revised downward rate is ≥8%, the assessment prompt is "Low risk, recommending full approval of the financing application." When the revised upward rate is between 5% and 10% and the revised downward rate is between 3% and 8%, the prompt is "Medium risk, recommending adjustment of the financing amount and shortening of the term." When the revised upward rate is greater than 10%, the prompt is "High risk, recommending rejection of financing or requiring collateral." Each sample evaluation prompt includes the parameter adjustment range, and the values of the revised rising rate and the revised falling rate are negatively correlated with the parameter adjustment range, that is, the higher the revised rising rate, the greater the recommended financing amount adjustment range (such as reducing the financing amount).

[0071] The system uses a set of sample revised increase and decrease rates as input variables and a set of sample assessment prompts as output to construct a risk assessment decision model. The model can employ classification algorithms such as support vector machines (SVMs) or random forests to learn the mapping between revision rates and assessment prompts using training sample data. For example, a random forest model uses revised increase and decrease rates as feature inputs and outputs the assessment prompt category (e.g., "low risk," "medium risk," or "high risk"). By constructing multiple decision trees for ensemble learning, classification accuracy is improved.

[0072] Using a risk assessment decision model, the system evaluates and determines the target farmer's revised upward and downward rates, generating risk assessment prompts. For example, Wang's revised upward and downward rates of 9.5% and 4.75% were classified as "medium risk" by the model, generating the following risk assessment prompt: "This farmer's entrepreneurial project presents medium financing risk. We recommend adjusting the requested financing amount from 2 million yuan to 1.5 million yuan, and requiring fixed asset collateral." The model also provides specific financing operational guidance, such as recommending quarterly interest payments and principal repayments at maturity to reduce post-loan management risks. Post-loan inspections are also recommended to be conducted quarterly to closely monitor the farmer's operating conditions.

[0073] During implementation, the completeness and accuracy of sample data directly impact the effectiveness of the model. The system regularly updates the sample library to incorporate new financing cases, ensuring the model adapts to market conditions and policy changes. For example, if policy support for the agricultural product processing industry increases, the distribution of correction rates for newly added samples may shift. The system then retrains the model with updated sample data, adjusting the thresholds and content of assessment prompts.

[0074] Furthermore, the variance calculation and correction coefficient tables in the dynamic correction module are adjusted based on industry developments. For example, if the average operating scale of the agricultural product processing industry increases in a given year, the standard characteristic information for "small enterprises" might be adjusted to a factory area of 800-1800 square meters. The system will then simultaneously update the standard characteristic information and variance calculation method to ensure that the correction process is consistent with current industry realities.

[0075] Through the above implementation methods, the dynamic correction module and the evaluation plan generation module realize the quantitative processing of the entire process from feature matching, difference correction to risk decision-making. Combined with historical sample data and real-time feature analysis, they provide scientific risk assessment prompts and operational guidance for farmers' entrepreneurial financing, which not only guarantees the risk control needs of financial institutions, but also provides farmers with targeted financing suggestions, thereby improving the accuracy and efficiency of rural financial services.

[0076] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0077] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence, characterized by: The system comprises: A farmer information collection module is used to obtain the subject information of the target farmer currently applying for financing, as well as the characteristic information of the target farmer's entrepreneurial project. Based on the target farmer's subject information, the module retrieves the historical financing data of similar farmers within the user's historical time period; A historical data clustering module, configured to cluster historical risk influencing factors within the historical financing data to obtain a plurality of clustered risk feature groups, extract historical key variable information sets and a plurality of historical financing operation sets from the plurality of clustered risk feature groups, and process and generate a plurality of historical risk parameter sets; a risk parameter screening module, wherein the risk parameter screening module is used to optimize and screen the multiple historical risk parameter sets respectively to obtain multiple screened risk parameter groups, and arrange them in chronological order to form multiple historical risk parameter sequences; A trend prediction module, configured to predict financing risk trends based on the multiple historical risk parameter sequences to obtain risk rise and fall rates; a dynamic correction module, the dynamic correction module being used to match the entrepreneurial project characteristic information of the target farmer with the multiple clustered risk characteristic groups, determine a matching risk characteristic group, and correct the risk increase rate and decrease rate based on the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group to obtain a corrected increase rate and a corrected decrease rate; An evaluation scheme generation module is used to make financing risk assessment decisions based on the modified increase rate and the modified decrease rate, generate risk assessment prompts, and provide financing operation guidance.

2. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 1 is characterized in that: Obtain the target farmer's subject information for the current financing application, as well as the entrepreneurial project feature information of the target farmer. Based on the target farmer's subject information, retrieve the user's historical financing data for similar farmers within the historical period, including: Obtaining identity attribute information and credit record information of target farmers, and collecting industry type and business scale information of the target farmers' entrepreneurial projects as entrepreneurial project feature information; Based on the target farmer's main information, a related search is performed in the historical financing database to obtain historical financing data of similar farmers.

3. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 1 is characterized in that: Clustering the historical risk influencing factors in the historical financing data to obtain multiple clustered risk feature groups, extracting historical key variable information sets and multiple historical financing operation sets under the multiple clustered risk feature groups, and processing to generate multiple historical risk parameter sets, including: Extracting multiple risk influencing factors from the historical financing data, performing feature clustering processing, and obtaining multiple clustered risk feature groups; Collecting the operating stability indicators of farmers in the historical financing data under the multiple clustered risk feature groups to form a historical key variable information set, and extracting the financing application parameter set and financing processing time set submitted by users under the multiple clustered risk feature groups; Classify and generate multiple historical basic parameter sets according to the degree of deviation between the multiple financing application parameter sets and the historical key variable information set; According to the comparison results between the preset time threshold and the multiple financing processing time sets, the multiple historical basic parameter sets are adjusted and calculated to generate multiple historical risk parameter sets.

4. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 1 is characterized in that: Optimize and screen the multiple historical risk parameter sets respectively to obtain multiple screened risk parameter groups, and arrange them in chronological order to form multiple historical risk parameter sequences, including: Selecting a first benchmark risk parameter in a first historical risk parameter set among the plurality of historical risk parameter sets; Assigning selection probabilities based on the degree of difference between other parameters in the first historical risk parameter set and the first benchmark risk parameter to form a first basic probability distribution, wherein the degree of difference is negatively correlated with the selection probability; Optimizing and screening the first set of historical risk parameters based on the first basic probability distribution to obtain a first screening risk parameter group; Arrange the time identification information of multiple parameters in the first screening risk parameter group in sequence to form the first historical risk parameter sequence; Repeat the optimization screening and time series arrangement operations on the remaining multiple historical risk parameter sets to form multiple historical risk parameter sequences.

5. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 4 is characterized in that: Based on the first basic probability distribution, the first historical risk parameter set is optimized and screened to obtain a first screened risk parameter group, including: Randomly selecting a preset number of risk parameters from the first historical risk parameter set to form a first screening risk parameter group; Allocating selection probabilities based on the degree of difference between the parameters within the first screening risk parameter group and the first benchmark risk parameter to form a first screening probability distribution; Calculating the similarity between the first screening probability distribution and the first basic probability distribution as the first screening fitness; Again randomly selecting a preset number of risk parameters from the first historical risk parameter set to form a second screening risk parameter group, and calculating a second screening fitness; The optimization and screening operation is continued until the convergence condition is reached, and the screening risk parameter group with the highest fitness is output as the first screening risk parameter group.

6. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 1 is characterized in that: Financing risk trend forecasting is performed based on the multiple historical risk parameter sequences to obtain risk rise and fall rates, including: Collect sample financing data of multiple farmers, extract a set of sample risk parameter sequences, and obtain a set of sample rising rates and a set of sample falling rates based on the parameter change characteristics within each sample risk parameter sequence; Taking the sample risk parameter sequence set as input features and the sample increase rate set and sample decrease rate set as output targets, a risk trend prediction model is constructed; Using the risk trend prediction model, risk trend classification prediction is performed on the multiple historical risk parameter sequences to obtain multiple characteristic increase rates and multiple characteristic decrease rates; Analyze the similarity between the entrepreneurial project characteristic information of the target farmer and the multiple clustered risk characteristic groups, and perform weighted calculation on the multiple characteristic increase rates and multiple characteristic decrease rates according to the numerical values of the multiple similarities to obtain the risk increase rate and decrease rate.

7. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 6 is characterized in that: Matching the entrepreneurial project characteristic information of the target farmer with the multiple clustered risk characteristic groups to determine a matching risk characteristic group, and correcting the risk increase rate and decrease rate based on the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group to obtain a corrected increase rate and a corrected decrease rate, including: Selecting the clustered risk feature group with the highest similarity as the matching risk feature group, and obtaining standard feature information of the matching risk feature group; Setting a risk correction coefficient according to the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group; The risk correction coefficient is used to correct the risk increase rate and decrease rate to obtain a corrected increase rate and a corrected decrease rate.

8. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 1 is characterized in that: Based on the modified increase rate and the modified decrease rate, a financing risk assessment decision is made, risk assessment prompts are generated, and financing operation guidance is provided, including: Collect a set of sample correction rising rates and a set of sample correction falling rates, and set sample evaluation prompt content according to the numerical value of each sample correction rising rate and sample correction falling rate to form a set of sample evaluation prompts, wherein each sample evaluation prompt includes a parameter adjustment range, and the numerical values of the sample correction rising rate and the sample correction falling rate are negatively correlated with the parameter adjustment range; Constructing a risk assessment decision model using the sample corrected rise rate set and the sample corrected fall rate set as input variables and the sample evaluation prompt set as output results; The risk assessment decision model is used to evaluate and decide on the revised rise rate and the revised fall rate, and generate a risk assessment prompt.

9. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 6 is characterized in that: Collect sample financing data of multiple farmers, extract the sample risk parameter series set, and obtain the sample increase rate set and sample decrease rate set based on the parameter change characteristics within each sample risk parameter series, including: Screen the sample data of farmers with complete financing records in the past three years and extract the time series of risk assessment parameters for each sample; Analyze the increase and decrease of the parameters at adjacent time points in the risk parameter time series of each sample, and calculate the risk increase and decrease rates of each sample; The risk parameter time series of all samples are summarized into a sample risk parameter series set, and the risk increase rate and decrease rate of all samples are summarized into a sample increase rate set and a sample decrease rate set respectively.

10. The farmer entrepreneurship financing risk assessment system based on big data and artificial intelligence according to claim 7 is characterized in that: The risk correction coefficient is set according to the difference between the entrepreneurial project characteristic information and the standard characteristic information of the matching risk characteristic group, including: Calculate the difference between the entrepreneurial project feature information and the standard feature information in the industry type dimension, and record it as a first difference value; Calculate the difference between the entrepreneurial project characteristic information and the standard characteristic information in the business scale dimension, and record it as a second difference value; Performing a weighted summation on the first difference value and the second difference value to obtain a comprehensive difference value; According to the preset correspondence table between difference values and correction coefficients, the value corresponding to the comprehensive difference value is searched and used as the risk correction coefficient.

Images