Online tobacco leaf industry financing method, device, equipment and medium

Abstract

The invention provides an online tobacco industry financing method, device, equipment and medium, and the method comprises the steps: collecting the data of tobacco growers, and carrying out the preprocessing, and obtaining the needed financing data; evaluating the credit rating of the tobacco grower according to the financing data; based on a random forest regression model, carrying out model training by adopting a historical planting data training set of tobacco growers to obtain a predicted income calculation model, and obtaining predicted incomes of the tobacco growers through the predicted income calculation model; combining the credit rating, the predicted income and the credit investigation data based on a quota calculation formula: C = R * L-F; r is the predicted income, L is the loan proportion, and F is the debt; the L is set according to the credit rating, the financing efficiency is improved, and the loan risk of a bank is reduced.

Description

Technical Field

[0001] The present invention relates to the field of online financing technology, and in particular to a method, device, equipment and medium for online tobacco industry financing. Background Art

[0002] The traditional agricultural loan approval process is cumbersome and requires tobacco farmers to provide a large amount of paper materials, such as land contract, historical production certificates, etc. Bank auditors need to spend a lot of time to verify the information, resulting in low efficiency in loan approval. At the same time, due to the lack of effective data support, it is difficult for banks to accurately assess the credit status of tobacco farmers, making it difficult to control loan risks. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method, device, equipment and medium for online tobacco industry financing, improve the efficiency of loan approval, and through automated data acquisition and credit assessment, significantly shorten the loan approval time and improve the efficiency of loan issuance.

[0004] In a first aspect, the present invention provides a method for online tobacco industry financing, comprising:

[0005] Step 1: Collect tobacco farmers’ data and pre-process them to obtain the required financing data;

[0006] Step 2: Evaluate the credit rating of tobacco farmers based on financing data;

[0007] Step 3: Based on the random forest regression model, the historical planting data training set of tobacco farmers is used to perform model training to obtain a predicted income calculation model, and the predicted income of tobacco farmers is obtained through the predicted income calculation model;

[0008] Step 4: Combine the credit rating, predicted income and credit data based on the credit limit calculation formula: C = R * LF; R is the predicted income, L is the loan ratio, and F is the liability; L is set according to the credit rating.

[0009] In a second aspect, the present invention provides a device, comprising:

[0010] The data collection module collects tobacco farmers’ data and pre-processes them to obtain the required financing data;

[0011] The rating evaluation module evaluates the credit rating of tobacco farmers based on financing data;

[0012] The profit prediction module is based on the random forest regression model, uses the tobacco farmers' historical planting data training set to perform model training, obtains the profit prediction calculation model, and obtains the tobacco farmers' predicted profit through the profit prediction calculation model;

[0013] The financing credit module calculates the credit limit based on the credit rating, predicted income and credit data. The calculation formula is: C=R*LF; R is the predicted income, L is the loan ratio, and F is the liability; L is set according to the credit rating.

[0014] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0016] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0017] The first is to improve the efficiency of loan approval. Through automated data acquisition and credit assessment, the loan approval time can be significantly shortened and the efficiency of loan issuance can be improved.

[0018] Second, it reduces the risk of bank loans. Credit assessment based on real and reliable tobacco farmers' planting data can more accurately assess the repayment ability of tobacco farmers and reduce the risk of bank loans.

[0019] The third is to promote the development of agricultural informatization. The application of the present invention can promote the sharing and utilization of tobacco planting data and promote the development of agricultural informatization.

[0020] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention will be further described below in conjunction with embodiments with reference to the accompanying drawings.

[0022] Figure 1 is a flow chart of the method in Embodiment 1 of the present invention;

[0023] Figure 2 It is a schematic diagram of the structure of the device in the second embodiment of the present invention. DETAILED DESCRIPTION

[0024] The technical solution in the embodiment of the present application has the following general idea:

[0025] Step 1: Data preparation

[0026] 1. Data Collection:

[0027] Internal bank system: Obtain tobacco grower data in the internal system through the interface, such as basic customer information: name, ID number, contact information, home address, etc. Account information: account opening time, account balance, transaction flow, etc.

[0028] Historical loan information: loan type, loan amount, loan term, repayment record, etc.

[0029] Credit reporting agencies: Obtain tobacco farmers’ credit reports provided by credit reporting agencies through interfaces. Such as personal credit records: credit card usage, loan repayments, overdue records, etc. Credit scores: Sesame Credit, Tencent Credit, etc. Tobacco companies: Obtain tobacco farmers’ data stored in tobacco companies through interfaces. Such as tobacco farmers’ basic information: name, ID number, contact information, planting address, etc. Tobacco field information: tobacco field area, soil type, irrigation conditions, etc. Tobacco leaf planting information: tobacco leaf varieties, planting time, fertilization, pest and disease control, etc. Historical production information: tobacco leaf production, grade, purchase price, etc. in the past few years.

[0030] 2. Data preprocessing:

[0031] The collected data is cleaned, converted, and feature engineered to meet the model training requirements.

[0032] Data cleaning: handle missing values, outliers, duplicate values, etc. For example, use the mean to fill missing numerical features, and use the mode to fill missing categorical features. Data that exceeds the mean ±3 times the standard deviation is considered an outlier and removed.

[0033] Data conversion: converting non-numeric data into numeric data, such as using one-hot encoding to process categorical features. Feature engineering: performing operations such as feature scaling, feature combination, and feature selection. For example, using standardization methods to scale numeric features, combining historical yields and planted areas into per-unit area yield features.

[0034] Step 2: Credit Assessment:

[0035] Based on the tobacco farmers' personal information, production and operation information, financial information, and historical loan information, a credit scoring model is constructed to assess the farmers' credit rating.

[0036] Feature selection: Select features related to credit risk, such as age, income, debt ratio, number of overdue payments, etc.

[0037] Model training: Use the logistic regression algorithm to train the credit scoring model based on historical data.

[0038] Credit scoring: Use the trained model to score each tobacco farmer and obtain their credit score.

[0039] Step 3: Train the prediction revenue calculation model:

[0040] 1. Model selection: Use the RandomForestRegressor class in the sklearn.ensemble module.

[0041] 2. Hyperparameter adjustment: Use grid search, random search and other methods to find the best hyperparameter combination, for example:

[0042] n_estimators: The number of decision trees in the forest, range: 50-200.

[0043] max_depth: The maximum depth of the decision tree, which limits the model complexity and prevents overfitting. Range: 10-50.

[0044] min_samples_split: The minimum number of samples required for node splitting to prevent overfitting, range: 2-10.

[0045] min_samples_leaf: The minimum number of samples required for a leaf node to prevent overfitting, range: 1-5.

[0046] max_features: The maximum number of features considered at each split, which increases randomness and improves generalization ability. Range: 0.5-1.0.

[0047] Model training: Use the tobacco farmers’ planting data training set (tobacco field area, tobacco leaf variety, planting time, etc.) provided by the tobacco company to train the random forest regression model.

[0048] 3. Model Evaluation

[0049] Use the trained model to predict the test set data. And use the following indicators to evaluate the prediction accuracy and generalization ability of the model:

[0050] Mean square error (MSE): Formula: MSE = sum((y_true-y_pred)**2) / len(y_true)

[0051] The smaller the value, the better, indicating that the error between the predicted value and the true value is smaller.

[0052] Root mean square error (RMSE): Formula: RMSE = sqrt(MSE) The smaller the better, it more intuitively reflects the size of the prediction error.

[0053] Mean absolute error (MAE): Formula: MAE = sum(abs(y_true-y_pred)) / len(y_true). The smaller the better, and it is insensitive to outliers.

[0054] R2 Score: Formula: R 2 =1-(sum((y_true-y_pred)**2) / sum((y_true-mean(y_true))**2)) The closer it is to 1, the better, indicating that the model explains a higher proportion of the variance of the target variable.

[0055] Step 4: Model integration

[0056] Combined with credit assessment, predicted income and credit data, the credit limit is calculated based on the formula: C = R * LF

[0057] 1. Predict the return R. R = f (tobacco field area, tobacco leaf variety, planting time, etc.) where f is the model trained in step 3.

[0058] 2. Loan ratio L. L = g(credit score). Function g determines the loan ratio based on the credit score, for example: g(score) = 0.80 (credit score>750). g(score) = 0.50 (credit score<600). The credit score is obtained in step 3, and function g is based on expert rules.

[0059] 3. F is the debt, which comes from the credit data obtained in step 1.

[0060] Step 5: Model deployment and application

[0061] 1. API interface development: Encapsulate the model in step 4 into a RESTful API interface. When tobacco farmers sign on the tobacco company interface, HTTPS requests are automatically called to transmit farmer data and call the model for prediction.

[0062] 2. Front-end interface development: After the model prediction is completed, the predicted amount is returned through this page and the user is redirected to the bank's mobile banking to process the loan.

[0063] Embodiment 1

[0064] like Figure 1 As shown, this embodiment provides a method for online tobacco industry financing, including:

[0065] Step 1: Collect tobacco farmers’ data: Obtain corresponding tobacco farmers’ data and historical loan information from the bank system; obtain corresponding credit data from the credit system; and obtain tobacco farmers’ tobacco field information, tobacco leaf planting information, and historical yield information; clean, convert, and feature engineer the collected data so that the data meets the model training requirements and obtains the required financing data;

[0066] Step 2: Evaluate the credit rating of tobacco farmers based on financing data;

[0067] Step 3: Based on the random forest regression model, the historical planting data training set of tobacco farmers was used for model training. The mean square error, root mean square error, mean absolute error, and the proportion of variance explained by the model to the total variance R were used to calculate the mean square error, root mean square error, mean absolute error, and mean absolute error. 2 When the corresponding set value is reached, the training is stopped to obtain a predicted income calculation model, and then the predicted income of the current tobacco farmers is obtained through the predicted income calculation model;

[0068] Step 4: Combine the credit rating, predicted income and credit data based on the credit limit calculation formula: C = R * LF; R is the predicted income, L is the loan ratio, and F is the liability; L is set according to the credit rating.

[0069] Based on the same inventive concept, the present application also provides a device corresponding to the method in Example 1, see Example 2 for details.

[0070] Embodiment 2

[0071] like Figure 2 As shown, in this embodiment, a device for online tobacco industry financing is provided, including:

[0072] The data collection module collects the data of tobacco farmers: obtains the corresponding tobacco farmer data and historical loan information from the bank system; obtains the corresponding credit data from the credit system; and obtains the tobacco farmer's tobacco field information, tobacco leaf planting information and historical yield information; cleans, converts and features the collected data to make the data meet the model training requirements and obtain the required financing data;

[0073] The rating evaluation module evaluates the credit rating of tobacco farmers based on financing data;

[0074] The forecasting module is based on the random forest regression model. The model is trained using the historical planting data training set of tobacco farmers. The mean square error, root mean square error, mean absolute error, and the proportion of variance explained by the model to the total variance R 2 When the corresponding set value is reached, the training is stopped to obtain a predicted income calculation model, and then the predicted income of the current tobacco farmers is obtained through the predicted income calculation model;

[0075] The financing credit module calculates the credit limit based on the credit rating, predicted income and credit data. The calculation formula is: C=R*LF; R is the predicted income, L is the loan ratio, and F is the liability; L is set according to the credit rating.

[0076] Since the device introduced in the second embodiment of the present invention is a device used to implement the method of the first embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the device based on the method introduced in the first embodiment of the present invention, so it is not described here in detail. All devices used in the method of the first embodiment of the present invention belong to the scope of protection of the present invention.

[0077] Based on the same inventive concept, the present application provides an electronic device embodiment corresponding to the first embodiment, see the third embodiment for details.

[0078] Embodiment 3

[0079] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any implementation method in the first embodiment can be implemented.

[0080] Since the electronic device introduced in this embodiment is a device used to implement the method in the first embodiment of the present application, based on the method introduced in the first embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements the device used by the method in the embodiment of the present application, it belongs to the scope of protection of the present application.

[0081] Based on the same inventive concept, the present application provides a storage medium corresponding to the first embodiment, see the fourth embodiment for details.

[0082] Embodiment 4

[0083] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any implementation method in the first embodiment can be implemented.

[0084] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] Although the specific implementation modes of the present invention are described above, those skilled in the art should understand that the specific implementation modes described are only illustrative and are not intended to limit the scope of the present invention. Equivalent modifications and changes made by those skilled in the art in accordance with the spirit of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for online tobacco industry financing, characterized in that: include: Step 1: Collect tobacco farmers’ data and pre-process them to obtain the required financing data; Step 2: Evaluate the credit rating of tobacco farmers based on financing data; Step 3: Based on the random forest regression model, the historical planting data training set of tobacco farmers is used to perform model training to obtain a predicted income calculation model, and the predicted income of tobacco farmers is obtained through the predicted income calculation model; Step 4: Combine the credit rating, predicted income and credit data based on the credit limit calculation formula: C = R * LF; R is the predicted income, L is the loan ratio, and F is the liability; L is set according to the credit rating.

2. The method for online tobacco industry financing according to claim 1, characterized in that: The step 1 is specifically as follows: Collect tobacco farmers’ data: obtain corresponding tobacco farmers’ data and historical loan information from the bank system; obtain corresponding credit data from the credit reporting system; and obtain tobacco farmers’ tobacco field information, tobacco leaf planting information, and historical yield information; clean, convert, and feature engineer the collected data so that the data meets the model training requirements and obtains the required financing data.

3. The method for online tobacco industry financing according to claim 1, characterized in that: The step 3 is specifically as follows: based on the random forest regression model, the model is trained using the historical planting data training set of tobacco farmers, and the mean square error, root mean square error, mean absolute error and the proportion of variance explained by the model to the total variance R are used to calculate the model training data. 2 When the corresponding set value is reached, the training is stopped to obtain a predicted income calculation model, and then the predicted income of the current tobacco farmers is obtained through the predicted income calculation model.

4. An online tobacco industry financing device, characterized in that: include: The data collection module collects tobacco farmers’ data and pre-processes them to obtain the required financing data; The rating evaluation module evaluates the credit rating of tobacco farmers based on financing data; The profit prediction module is based on the random forest regression model, uses the tobacco farmers' historical planting data training set to perform model training, obtains the profit prediction calculation model, and obtains the tobacco farmers' predicted profit through the profit prediction calculation model; The financing credit module calculates the credit limit based on the credit rating, predicted income and credit data. The calculation formula is: C=R*LF; R is the predicted income, L is the loan ratio, and F is the liability; L is set according to the credit rating.

5. The device for online tobacco industry financing according to claim 4, characterized in that: The data collection module is specifically: Collect tobacco farmers’ data: obtain corresponding tobacco farmers’ data and historical loan information from the bank system; obtain corresponding credit data from the credit reporting system; and obtain tobacco farmers’ tobacco field information, tobacco leaf planting information, and historical yield information; clean, convert, and feature engineer the collected data so that the data meets the model training requirements and obtains the required financing data.

6. The device for online tobacco industry financing according to claim 1, characterized in that: The prediction revenue module is specifically as follows: based on the random forest regression model, the model is trained using the historical planting data training set of tobacco farmers, and the mean square error, root mean square error, mean absolute error and the proportion of variance explained by the model to the total variance R are used to calculate the predicted revenue. 2 When the corresponding set value is reached, the training is stopped to obtain a predicted income calculation model, and then the predicted income of the current tobacco farmers is obtained through the predicted income calculation model.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images