A method and system for generating a user's financial information graph through a financing platform

Abstract

The present invention relates to the field of financial information processing technology, specifically a method and system for generating a user's financial information graph through a financing platform, comprising the following steps: extracting the financing amount, financing time, financing interest rate and repayment period from the user's financing record based on user behavior data, and calling the timestamp to sort the financing behavior records in chronological order. In the present invention, by dynamically extracting the amount, time, interest rate and repayment period from the user's financing data and integrating time series analysis, continuous tracking and in-depth mining of financing behavior are achieved, and the fluctuation patterns of financing amount and interest rate are effectively identified. In combination with the user's repayment behavior and credit characteristics, a feature coupling matrix and a time weight distribution model are generated, which significantly improves the accuracy and comprehensiveness of user behavior prediction. By combining dynamic parameters, time weights and credit characteristics, an intuitive financial information graph can be generated, providing clearer data support and visual expression for financing decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of financial information processing, and in particular to a method and system for generating a user's financial information graph through a financing platform. Background Art

[0002] The field of financial information processing encompasses all methods and systems that use information technology to collect, store, analyze, and display financial data. Its core focus is on providing users with accurate and efficient financial services and support through the integration and computation of massive amounts of financial data. This technical field encompasses data collection techniques, structured and unstructured data processing, data analysis methods, and data visualization techniques, encompassing multiple financial scenarios, including investment management, credit assessment, risk control, and financing decision support. The systematic nature of financial information processing technology lies in its ability to perform multi-dimensional computations and cross-domain integration of various data types, enabling dynamic information generation and presentation based on user needs.

[0003] Among them, the method of generating a user's financial information graph through a financing platform refers to a specific method of using data modeling analysis and visualization technology to generate intuitive graphical information expressions for the user's financial data and financing needs in the financing platform scenario. The subject of this patent mainly covers the process of classifying and extracting features from the financing application data submitted by the user, and generates visual graphics including time series analysis and data distribution analysis by performing data cleaning and correlation analysis on the user's financial information, combined with multi-dimensional feature modeling. At the same time, the method obtains dynamic transaction information on the financing platform through an embedded financial data interface and conducts a comprehensive comparison with the user's characteristic data to realize the graphical generation process. The above method uses data correlation analysis and visual expression methods to systematically process and graphically display user financial data.

[0004] Existing technologies for processing user financing data often remain at the static analysis level, lacking full utilization of the temporal dynamics of data and making it difficult to fully capture the changing trends in user financing behavior. Inadequate correlation analysis between time series and user characteristics limits the accuracy of risk predictions. Regarding data visualization, existing technologies have limited ability to interpret complex data, failing to clearly display user behavior and characteristics. This can lead to a decrease in the matching of financial services and restrict the role of dynamic data in financing decisions. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for generating a user's financial information graph through a financing platform.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for generating a user's financial information graph through a financing platform, comprising the following steps:

[0007] S1: Based on user behavior data, extract the financing amount, financing time, financing interest rate, and repayment period from the user's financing records. Use timestamps to sort the financing behavior records in chronological order, calculate the difference in financing amounts at adjacent time points, integrate interest rate change data to calculate the fluctuation range, and combine the repayment ratio change trend to generate a set of user financing dynamic parameters.

[0008] S2: Based on the user financing dynamic parameter set, analyze the rate of change of the financing amount difference and the interest rate fluctuation range, use the time data in the user's repayment behavior to normalize it, and construct the financing behavior feature vector of the time node through cumulative calculation to generate the user financing cumulative feature vector set;

[0009] S3: Based on the cumulative feature vector set of user financing, extract time series data, combine the score and default probability in the user credit characteristics, analyze the changes in the feature values ​​of multiple time nodes, calculate the feature coupling matrix, classify and process by period, and generate the user financing dynamic coupling feature matrix;

[0010] S4: Based on the user financing dynamic coupling characteristic matrix, analyze the time dependency coefficient, combine the overdue data and repayment time distribution in the user repayment behavior, calculate the time weight distribution, classify the results by time period, and generate a user financing time weight distribution model;

[0011] S5: Based on the user financing time weight distribution model, combined with the user financing dynamic coupling feature matrix, perform time period cumulative weight calculation, analyze the relationship between financing amount and credit score data, construct node distribution and edge weight, and generate a user financial information graph.

[0012] The user financing dynamic parameter set specifically includes the financing amount difference, interest rate changes, and repayment ratio trends. The user financing cumulative feature vector set includes the financing amount change rate, interest rate fluctuation range, and time-normalized data. The user financing dynamic coupling feature matrix specifically includes time series data, credit score, and default probability. The user financing time weight distribution model specifically includes the time dependence coefficient, overdue data, and repayment time distribution. The user financial information graph includes node distribution and edge weights.

[0013] As a further solution of the present invention, the steps for obtaining the user financing dynamic parameter set are specifically as follows:

[0014] S101: Read the financing amount and financing time of the user's financing record, arrange the data by timestamp, calculate the difference sequence of the financing amount based on consecutive time points, analyze the changes in the financing interest rate data, and classify the changes in the financing amount and its associated parameters in combination with the repayment cycle data to generate a financing amount change sequence;

[0015] S102: Combining the financing amount change sequence with the financing interest rate data, normalizing the financing interest rate and repayment ratio parameters within each fluctuation range of the financing behavior, generating a trend feature based on the numerical changes between the two, segmenting the numerical changes of the trend feature according to the repayment cycle and extracting a trend sequence to generate a repayment ratio trend sequence;

[0016] S103: Based on the financing amount change sequence and the repayment ratio trend sequence, the correlation characteristics of the repayment ratio change trend to the financing amount fluctuation are analyzed using the formula:

[0017] ;

[0018] Calculate the dynamic parameters of the repayment ratio change trend and the financing amount fluctuation, and generate a set of user financing dynamic parameters;

[0019] in, A comprehensive indicator representing a set of financing dynamics parameters, represents the financing amount at time i, Represents the financing amount at the i-1th time point, represents the financing rate, Represents the repayment ratio change rate, Represents the total number of financing records.

[0020] As a further solution of the present invention, the steps for obtaining the user financing cumulative feature vector set are specifically as follows:

[0021] S201: Based on the user financing dynamic parameter set, analyze the financing amount difference and the rate of change of the interest rate fluctuation range, calculate the change in the financing amount at adjacent time points in the financing behavior record, determine the fluctuation characteristics of the change rate based on the difference between the upper and lower bounds of the interest rate fluctuation range, screen the financing behavior records that meet the conditions, extract the characteristic values, and generate the basic characteristic value of the financing behavior;

[0022] S202: Using the basic characteristic values ​​of the financing behavior, normalize the time dimension parameters in the characteristic values, adjust the distribution interval based on the mean value and standard deviation of the basic characteristic values, and normalize the financing amount difference and the rate of change of the upper and lower bounds of interest rate fluctuations within a unified range to generate a normalized financing behavior characteristic value;

[0023] S203: Based on the normalized financing behavior feature quantity, construct a financing behavior feature vector of the time node using the formula:

[0024] ;

[0025] Through weighted cumulative calculation, the user financing cumulative feature vector set is obtained;

[0026] in, Represents the result of the cumulative feature vector set of user financing, represents the normalized characteristic quantity of financing behavior, is the mean value calculated during the normalization process, is the standard deviation calculated during the normalization process, is the weight coefficient, which is used to adjust the influence of the normalized feature quantity in the cumulative feature vector. is the total number of normalized financing behavior characteristics.

[0027] As a further solution of the present invention, the steps for obtaining the user financing dynamic coupling characteristic matrix are specifically as follows:

[0028] S301: extracting time series data from the user financing cumulative feature vector set, combining the user credit feature score and the change parameters of the default probability, analyzing the trend of the feature value at the time node, and segmenting the feature value based on the change trend and extracting the feature change rate to generate the time series analysis results;

[0029] S302: Calling the time series analysis result data, calculating the coupling degree between the characteristic value at each time point and the user's credit score and default probability, constructing the characteristic distribution relationship between time points based on the change rate of the characteristic value, and measuring the coupling strength between the differentiated features in the time series data based on a standardized method to generate a characteristic coupling analysis result;

[0030] S303: Based on the characteristic coupling analysis results, calculate the characteristic coupling matrix, measure the mutual relationship between the characteristic values ​​through normalization, and use the formula:

[0031] ;

[0032] Classify and process by period to generate the user financing dynamic coupling feature matrix;

[0033] in, represents the coupling degree between feature i and feature j, represents the normalized value of feature i at time point t, represents the normalized value of feature j at time point t, is the total number of time points.

[0034] As a further solution of the present invention, the steps for obtaining the user financing time weight distribution model are specifically as follows:

[0035] S401: Based on the time dependency coefficient in the user financing dynamic coupling feature matrix, by matching the overdue days and repayment time distribution data in the user's repayment behavior, evaluating the behavioral abnormality rate at multiple time nodes, extracting key credit behavior pattern features based on the abnormality rate changes, and generating time dependency analysis results;

[0036] S402: Matching the behavioral pattern features of multiple time nodes in the time dependency analysis results with time periods, cumulatively calculating the credit impact weight within each time period based on the degree of overdue payment, repayment time distribution pattern, and feature weights, and generating a time weight calculation result by combining the behavioral concentration trend and change pattern within the time period;

[0037] S403: Based on the time weight calculation result, the user's credit behavior is classified by time period using the formula:

[0038] ;

[0039] Combining Gaussian weighting and time-dependent features, we analyze the weighted summaries of multiple time periods and classify them by time period to generate a user financing time weight distribution model.

[0040] in, Represents the weight value at time t, which is used to measure the impact of time t on user financing behavior. Represents the weight coefficient of time period classification, reflecting the importance of multiple time periods in user financing behavior. is the central time point of time period i, indicating the key monitoring point within the time period, is the standard deviation of the time period, which indicates the width of the time distribution.

[0041] As a further solution of the present invention, the steps of obtaining the user financial information graph are specifically as follows:

[0042] S501: Calling the user financing time weight distribution model and the user dynamic coupling feature matrix, constructing the weight accumulation feature within the time period through the coupling relationship between the time weight parameter and the feature matrix, and combining the interaction results of the weight accumulation feature to evaluate the dynamic correlation characteristics within the time period and generate the time period cumulative weight analysis results;

[0043] S502: Based on the cumulative weight analysis results for the time period, calculate the change range of the financing amount and credit score within the differentiated time period, extract the correlation characteristics between the amount and the score within the time period, evaluate the dynamic impact of the amount change on the score, determine the key connection points based on the relationship between node characteristics and adjacent node data changes, and generate relationship analysis results;

[0044] S503: Based on the relationship analysis results, construct node distribution and edge weights using the formula:

[0045] ;

[0046] By weighting node features and connection strength, edge weights and node distribution are constructed to generate a user financial information graph;

[0047] in, represents the weight distribution of nodes v and edges e in the graph, is the basic weight of the node, indicating the initial criticality of each node, is the adjustment coefficient, which reflects the sensitivity of the connection strength between nodes. is the characteristic value of node i, which represents the financial attribute value of each node, It is the center point of the adjustment coefficient and represents the benchmark value of the weight balance between nodes.

[0048] A system for generating a user's financial information graph through a financing platform, wherein the system is used to execute the above-mentioned method for generating a user's financial information graph through a financing platform, and the system comprises:

[0049] The financing behavior extraction module extracts the financing amount, financing time, financing interest rate, and repayment period from financing records based on user behavior data. It then sorts the records by timestamp, calculates the difference in financing amounts between adjacent time points, integrates interest rate change data to calculate the fluctuation range, calculates the repayment ratio change trend, and generates a set of financing dynamic parameters.

[0050] The financing feature vector generation module analyzes the rate of change of the financing amount difference and the interest rate fluctuation range based on the financing dynamic parameter set, normalizes the repayment time data, constructs the time node feature values ​​of the financing behavior through cumulative calculation, and generates a financing cumulative feature vector set;

[0051] The feature matrix analysis module extracts time series data from the accumulated financing feature vector set, combines the user credit score and default probability, analyzes the changes in feature values ​​at multiple time nodes, calculates feature coupling relationships, classifies and processes feature coupling data, and generates a financing dynamic coupling feature matrix;

[0052] The time weight modeling module analyzes the time dependency coefficient based on the financing dynamic coupling characteristic matrix, combines the overdue data in the repayment behavior with the repayment time distribution, calculates the time weight distribution, classifies and calculates the time weight values, and generates a financing time weight distribution model;

[0053] The financial information graph generation module is based on the financing time weight distribution model, combined with the financing dynamic coupling feature matrix, calculates the cumulative weight of the time period, analyzes the relationship between the financing amount and the credit score, calculates the node distribution and edge weight value, and generates the user financial information graph.

[0054] Compared with the prior art, the advantages and positive effects of the present invention are:

[0055] This method dynamically extracts the amount, time, interest rate, and repayment period from user financing data and integrates time series analysis to continuously track and deeply analyze financing behavior, effectively identifying fluctuations in financing amounts and interest rates. Combining user repayment behavior with credit characteristics, it generates a feature coupling matrix and a time-weighted distribution model, significantly improving the accuracy and comprehensiveness of user behavior predictions. By combining dynamic parameters, time weights, and credit characteristics, intuitive financial information graphs can be generated, providing clearer data support and visualization for financing decisions. This also enhances data correlation analysis capabilities, optimizing risk identification and personalized service effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0057] Figure 2 A flowchart of the steps for obtaining a user financing dynamic parameter set according to the present invention;

[0058] Figure 3 A flow chart of the steps for obtaining a set of cumulative feature vectors for user financing according to the present invention;

[0059] Figure 4 A flowchart of the steps for obtaining the user financing dynamic coupling characteristic matrix of the present invention;

[0060] Figure 5 A flow chart of the steps for obtaining the user financing time weight distribution model of the present invention;

[0061] Figure 6 This is a flow chart of the steps for obtaining the user financial information graph of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined. Example

[0064] See also Figure 1 The present invention provides a technical solution: a method for generating a user's financial information graph through a financing platform, comprising the following steps:

[0065] S1: Based on user behavior data, extract the financing amount, financing time, financing interest rate, and repayment period from the user's financing records. Use timestamps to sort the financing behavior records in chronological order, calculate the difference in financing amounts at adjacent time points, integrate interest rate change data to calculate the fluctuation range, and combine the repayment ratio change trend to generate a set of user financing dynamic parameters.

[0066] S2: Based on the user financing dynamic parameter set, analyze the rate of change of the financing amount difference and the interest rate fluctuation range, use the time data in the user repayment behavior to normalize it, and construct the financing behavior feature vector of the time node through cumulative calculation to generate the user financing cumulative feature vector set;

[0067] S3: Based on the cumulative feature vector set of user financing, extract time series data, combine the score and default probability in the user credit characteristics, analyze the changes in the feature values ​​of multiple time nodes, calculate the feature coupling matrix, classify and process by period, and generate the user financing dynamic coupling feature matrix;

[0068] S4: Based on the user financing dynamic coupling feature matrix, analyze the time dependency coefficient, combine the overdue data and repayment time distribution in the user repayment behavior, calculate the time weight distribution, classify the results by time period, and generate the user financing time weight distribution model;

[0069] S5: Based on the user financing time weight distribution model, combined with the user financing dynamic coupling feature matrix, the cumulative weight of each period is calculated, the relationship between the financing amount and credit score data is analyzed, the node distribution and edge weight are constructed, and the user financial information graph is generated.

[0070] The user financing dynamic parameter set specifically includes the financing amount difference, interest rate changes, and repayment ratio trends. The user financing cumulative feature vector set includes the financing amount change rate, interest rate fluctuation range, and time-normalized data. The user financing dynamic coupling feature matrix specifically includes time series data, credit score, and default probability. The user financing time weight distribution model specifically includes the time dependence coefficient, overdue data, and repayment time distribution. The user financial information graph includes node distribution and edge weights.

[0071] See also Figure 2 , the specific steps for obtaining the user financing dynamic parameter set are:

[0072] S101: Read the financing amount and financing time of the user's financing record, arrange the data by timestamp, calculate the difference sequence of the financing amount based on consecutive time points, analyze the changes in the financing interest rate data, and classify the changes in the financing amount and its associated parameters in combination with the repayment cycle data to generate a financing amount change sequence;

[0073] Call the timestamp to sort the financing behavior records in chronological order, extract the difference in financing amounts at adjacent time points in the financing behavior, perform structured integration of various parameters based on data characteristics, generate a time series through the difference in financing amounts at consecutive time points, analyze the data range of the financing amount field in the financing record and clean up outliers, remove abnormal data points through upper and lower thresholds, and recalculate the difference in financing amounts at adjacent time points. Based on the cleaned data, establish a continuous financing amount change sequence, call the timestamp field to standardize the financing time, and perform range normalization on the financing interest rate field in the financing behavior based on the actual distribution characteristics. Combine the normalized interest rate data with the difference in financing amount changes to generate a financing amount change sequence. After the financing amount change sequence is generated, call the subsequent steps as parameters.

[0074] S102: Combining the financing amount change sequence with the financing interest rate data, normalizing the financing interest rate and repayment ratio parameters within each fluctuation range of the financing behavior, generating a trend feature based on the numerical changes between the two, and segmenting the numerical changes of the trend feature according to the repayment cycle and extracting the trend sequence to generate a repayment ratio trend sequence;

[0075] Based on the financing amount change sequence and interest rate change data, the financing behavior fluctuation range is integrated and calculated, the time series data of the financing amount change difference field is segmented according to time period slices, and the relative volatility characteristics are analyzed based on the financing interest rate data of each segment. The financing amount change difference in each time slice is matched with the interest rate value to calculate its mean and standard deviation. The standard deviation field of financing fluctuation within the segmented time is calculated as the basis for fluctuation characteristic evaluation. A fluctuation characteristic score is generated for the fluctuation characteristics of each time slice. The time slices that do not meet the set standards are eliminated according to the threshold set by the score. The mean of the fluctuation characteristics of the remaining time slices is extracted as the core parameter of the financing behavior fluctuation range. The changing trend of the repayment ratio field in the data that meets the fluctuation range is tracked and recorded. The trend difference between adjacent repayment ratio data points is calculated to generate a repayment ratio change trend sequence. The combination of the financing behavior fluctuation range and the repayment ratio change trend sequence provides basic parameters for the next step of analysis.

[0076] S103: Based on the financing amount change sequence and the repayment ratio trend sequence, analyze the correlation characteristics of the repayment ratio change trend with the financing amount fluctuation, using the formula:

[0077] ;

[0078] Calculate the dynamic parameters of the repayment ratio change trend and the financing amount fluctuation, and generate a set of user financing dynamic parameters;

[0079] in, A comprehensive indicator representing a set of financing dynamics parameters, represents the financing amount at time i, Represents the financing amount at the i-1th time point, represents the financing rate, Represents the repayment ratio change rate, Represents the total number of financing records.

[0080] formula:

[0081] ;

[0082] The formula is beneficial in that, by comprehensively considering the synergistic relationship between the difference in financing amount changes, the financing interest rate, and the rate of change of the repayment ratio, it can accurately capture the dynamic characteristics of financing behavior and enhance the model's ability to comprehensively describe the fluctuation range and repayment behavior.

[0083] Detailed explanation of the formula and the process of formula calculation and derivation:

[0084] According to the financing records after cleaning, the financing amount change sequence is used as the basic data, and the first The financing amount is , the financing amount at adjacent time points is , the first in the repayment ratio change rate sequence The change in repayment ratio is The financing rate is , first calculate the square of the difference in financing amount at adjacent time points, and get , then divide each square of the difference by , perform normalization calculations, perform summation operations, and the summation range is from arrive , and finally calculate the square root to get the result , assuming the financing amount data is The financing rate is , the repayment ratio change rate is , calculated as follows:

[0085] 1. Calculate the square of the difference in financing amount change:

[0086] ;

[0087] 2. Calculate the standardization of each component:

[0088] ;

[0089] 3. Perform the summation:

[0090] ;

[0091] 4. Calculate the square root to get :

[0092] ;

[0093] The results show that the comprehensive index value of the financing dynamic parameter set is 409.22, which indicates the dynamic fluctuation characteristics of the current financing behavior and can provide a key reference for further optimizing financing behavior.

[0094] See also Figure 3 , the specific steps for obtaining the user financing cumulative feature vector set are:

[0095] S201: Based on the user's financing dynamic parameter set, analyze the rate of change of the financing amount difference and the interest rate fluctuation range, calculate the change in the financing amount at adjacent time points in the financing behavior record, and determine the fluctuation characteristics of the change rate by combining the difference between the upper and lower bounds of the interest rate fluctuation range. Filter the financing behavior records that meet the conditions and extract the characteristic values ​​to generate the basic characteristic value of the financing behavior;

[0096] By calculating the change in the financing amount at adjacent time points in the financing behavior record, extracting the financing amount data at adjacent time points and calculating the difference, using the formula Get the change in the financing amount in each time period, combine it with the fluctuation range of the financing interest rate, filter the difference between the upper and lower limits of the financing interest rate, and use the formula Calculate the amplitude change within the interest rate fluctuation range, determine whether the change in the financing amount fluctuates significantly, and compare the change with the fluctuation threshold. and The screening criteria are determined by the correlation relationship, the records with changes greater than the threshold are extracted and the feature quantities are calculated, the financing behavior records that meet the conditions are extracted through the index timestamp, and the change feature values ​​in the financing behavior are extracted in combination with the results of the change calculation; the basic feature quantities of the financing behavior are generated.

[0097] S202: Using the basic characteristic quantities of financing behavior, normalize the time dimension parameters in the characteristic quantities, adjust the distribution range based on the mean value and standard deviation of the basic characteristic quantities, and normalize the financing amount difference and the rate of change of the upper and lower bounds of interest rate fluctuations within a unified range to generate normalized financing behavior characteristic quantities;

[0098] Extract the financing amount difference and interest rate fluctuation data, and convert the time dimension data The scope is limited to , through the normalization formula Map the values ​​of the time dimension to Within the range, the standardized formulas are used for the difference in financing amount and the fluctuation range of interest rate and Processing, where 、 is the average of the difference in financing amount and interest rate fluctuation range, 、 is the standard deviation. After standardization, all characteristic values ​​are evenly distributed. The normalized financing behavior characteristic quantity is generated by combining the normalized result of the time dimension and the normalized results of the financing amount difference and the interest rate fluctuation range.

[0099] S203: Based on the normalized financing behavior characteristic quantity, construct the financing behavior characteristic vector of the time node using the formula:

[0100] ;

[0101] Through weighted cumulative calculation, the user financing cumulative feature vector set is obtained;

[0102] in, Represents the result of the cumulative feature vector set of user financing, represents the normalized characteristic quantity of financing behavior, is the mean value calculated during the normalization process, is the standard deviation calculated during the normalization process, is the weight coefficient, which is used to adjust the influence of the normalized feature quantity in the cumulative feature vector. is the total number of normalized financing behavior characteristics.

[0103] formula:

[0104] ;

[0105] The benefit of the formula is that by adding the weight coefficient Adjust the influence of different characteristic quantities and combine the normalized financing behavior characteristic quantities ,Calculating the cumulative feature vector can more flexibly adapt to the differences between multi-feature data and eliminate the dimensional differences between features.

[0106] Detailed explanation of the formula and the process of formula calculation and derivation:

[0107] represents the cumulative feature vector set of user financing, represents the normalized financing behavior characteristic quantity, is the mean of the characteristic quantity, through the formula calculate, is the standard deviation of the characteristic quantity, through the formula calculate, is the weight coefficient, which is determined by analyzing the contribution of each characteristic quantity to the overall behavior. is the total number of features, and the calculation steps of the cumulative feature vector are:

[0108] For the normalized financing behavior characteristic , first calculate its mean by the formula and standard deviation ;

[0109] Combined weight coefficient , after the feature quantity is standardized, it is calculated cumulatively by weight;

[0110] By cumulative formula Calculate the final financing cumulative feature vector.

[0111] Example calculation:

[0112] Assume that the characteristic quantity of financing behavior is , mean , standard deviation , the weight coefficient is , the calculation process is:

[0113] , , ;

[0114] 2. Cumulative calculation is:

[0115] ;

[0116] The results show that the cumulative characteristic vector value of the financing behavior characteristic quantity is , which reflects the comprehensive performance of all normalized feature quantities after weighted cumulative calculation, and is used to further analyze the dynamic trend of financing behavior.

[0117] See also Figure 4 ,The specific steps for obtaining the user financing dynamic coupling feature matrix are:

[0118] S301: Extract time series data from the accumulated feature vector set of user financing, combine the user credit feature score and the change parameters of the default probability, analyze the trend of the feature value at the time node, and segment the difference of the feature value based on the change trend and extract the feature change rate to generate the time series analysis results;

[0119] Extract timestamp information from each financing behavior record in the user financing cumulative feature vector set, sort each record in chronological order, extract the amount change, interest rate fluctuation and repayment period change of financing behavior in the time series as time series features, combine the user credit score and default probability, calculate the credit risk index in each record, and map each eigenvalue in the time series to the normalized interval of the credit risk dimension. The normalized interval is calculated by calculating the minimum and maximum values ​​of each eigenvalue as the boundary. The mapping formula is: ,in represents the original eigenvalue, It represents the normalized value. By calculating the change rate of the characteristics of each node in the time series and the normalized credit characteristic value, these normalized characteristic values ​​are constructed into a time series analysis matrix. Each row in the matrix corresponds to a time node, and each column is the characteristic value change rate or the normalized credit characteristic value. Based on the matrix data, the trend characteristics of the time series are calculated and the characteristic change rate is extracted. The change rate is combined with the credit characteristic value to generate the time series analysis results.

[0120] S302: Calling the time series analysis result data, calculating the coupling degree between the characteristic value at each time point and the user's credit score and default probability, constructing the characteristic distribution relationship between time points based on the change rate of the characteristic value, and measuring the coupling strength between the differentiated features in the time series data based on a standardized method to generate the characteristic coupling analysis results;

[0121] Apply standardization to measure the correlation between each feature and the user's credit score and default probability. Through the data of each column in the time series analysis result matrix, the change rate of each feature value is normalized one by one. The normalization method is to calculate the mean and standard deviation of each column of data and use the formula Each eigenvalue is standardized, where is the current value, is the mean of the column, is the standard deviation of the column. The standardized eigenvalues ​​are evenly distributed within the range of zero mean and unit standard deviation. The coupling relationship between the eigenvalues ​​is calculated through the normalized eigenvalue data matrix. The coupling degree is calculated by the Pearson correlation coefficient of the eigenvalue changes. The correlation coefficient formula is: ,in and Time Upper feature and The standardized value of and Characterized by and The coupling matrix between the eigenvalues ​​is calculated by the above formula, and the normalized correlation data between the eigenvalues ​​and the credit score and default probability are combined to further generate the characteristic coupling analysis results.

[0122] S303: Based on the characteristic coupling analysis results, calculate the characteristic coupling matrix, measure the relationship between the characteristic values ​​through normalization, and use the formula:

[0123] ;

[0124] Classify and process by period to generate the user financing dynamic coupling feature matrix;

[0125] in, represents the coupling degree between feature i and feature j, represents the normalized value of feature i at time point t, represents the normalized value of feature j at time point t, is the total number of time points.

[0126] formula:

[0127] ;

[0128] The benefit of the formula is that, by calculating the weighted inner product between the normalized time series eigenvalues, it can accurately reflect the mutual coupling relationship of each eigenvalue in the entire time series, thereby improving the accuracy of dynamic characteristic matrix analysis.

[0129] Detailed explanation of the formula and the process of formula calculation and derivation:

[0130] Let the eigenvalue For time Point Features The normalized value, eigenvalue For time Point Features The normalized value of is calculated as follows:

[0131] 1. Calculate features and features In time The product at the point is given by , summing this product over all time points, we get ;

[0132] 2. Calculate features separately and features The sum of squares at all time points is given by and ;

[0133] 3. Take the square root of the sum of squares and calculate and ;

[0134] 4. Substitute the above two calculation results into the formula to obtain the coupling degree ;

[0135] 5. By bringing in data and , respectively calculate:

[0136] ;

[0137] ;

[0138] ;

[0139] , ;

[0140] ;

[0141] 6. Calculated .

[0142] This result shows that the characteristics and features The coupling degree in the time series is high, indicating that the changes in the time series between the two are strongly correlated. This coupling degree can be further used to generate the user financing dynamic coupling feature matrix, and the matrix result can be obtained after period classification processing.

[0143] See also Figure 5 ,The specific steps for obtaining the user financing time weight distribution model are:

[0144] S401: Based on the time dependency coefficient in the user financing dynamic coupling feature matrix, by matching the overdue days and repayment time distribution data in the user's repayment behavior, evaluate the behavioral anomaly rate at multiple time nodes, extract key credit behavior pattern features based on the changes in the anomaly rate, and generate time dependency analysis results;

[0145] First, the time dependency coefficient is extracted, and the characteristics of each time node in the matrix are matched with the corresponding user repayment overdue record. The delay time days and payment amount data in the overdue record are extracted. For the delay days data, it is mapped to a proportional value through normalization. The normalization formula is: ,in Indicates delayed days data, and Represent the minimum and maximum values ​​of the data respectively, and calculate the proportional delay days; secondly, perform segmented statistics on the repayment time distribution data, divide all time nodes into fixed time intervals, accumulate the total repayment amount within the time interval, calculate the repayment ratio of each time period, and judge the abnormal behavior of the time node by the ratio; then, compare the normalized delay days data with the repayment time distribution data, and calculate the abnormality score of each time period in combination with the fluctuation value of the abnormal ratio. The scoring formula is ,in Indicates the proportion of delayed days at time point t, represents the proportion of repayment amount at time point t, is the total number of time nodes; through the above steps, the abnormal rate distribution of each time node is obtained, and the time dependence analysis results are generated.

[0146] S402: Match the behavioral pattern characteristics of multiple time nodes in the time dependency analysis results with the time periods. Calculate the credit impact weight for each time period based on the degree of overdue payment, the repayment time distribution pattern, and the characteristic weight. Combined with the behavioral concentration trend and change pattern within the time period, generate a time weight calculation result.

[0147] First, the abnormal rate data of each time point in the time dependency analysis results are segmented and the abnormal rates of all time points in the time period are summed to obtain the initial time period weight value; secondly, the abnormal rate within the time period is standardized to calculate the normalized abnormal rate distribution. The normalization formula is: ,in is the abnormal rate weight value of time period i, For time period The abnormal rate weight value, is the total number of time periods; then, based on the central tendency of the behavior within the time period, the mean and standard deviation of the behavior distribution are calculated, and the discreteness of the distribution is determined. For time periods with significant central tendency, the corresponding weight parameters are increased, and the weight formula is adjusted as follows: ,in is the central tendency adjustment coefficient, is the central tendency score of time period i, specifically the ratio of the distribution mean to the standard deviation; the adjusted weight value is renormalized, and the normalized weight distribution is mapped to each time period to generate the time weight calculation result.

[0148] S403: Based on the time weight calculation result, the user's credit behavior is classified by time period using the formula:

[0149] ;

[0150] Combining Gaussian weighting and time-dependent features, we analyze the weighted summaries of multiple time periods and classify them by time period to generate a user financing time weight distribution model.

[0151] in, Represents the weight value at time t, which is used to measure the impact of time t on user financing behavior. Represents the weight coefficient of time period classification, reflecting the importance of multiple time periods in user financing behavior. is the central time point of time period i, indicating the key monitoring point within the time period, is the standard deviation of the time period, which indicates the width of the time distribution.

[0152] formula:

[0153] ;

[0154] The benefit of the formula is that it accurately quantifies the impact of time t by combining the time period classification weight coefficient and time dependency characteristics, and introduces Gaussian distribution parameters to adjust the relationship between time points and time periods, thereby improving the flexibility and accuracy of time weight distribution.

[0155] Detailed explanation of the formula and the process of formula calculation and derivation:

[0156] Represents the weight value of time t, representing the dynamic impact weight of time t on user financing behavior, It represents the classification weight coefficient of the i-th time period. Its value is calculated by the abnormal rate distribution of the time period and adjusted according to the distribution concentration. is the center point of the i-th time period. Its value is the average of the start and end time of the time period, indicating the center time point of the time period. The standard deviation of the time period is the standard deviation of the behavior distribution within the time period, which indicates the distribution width of the time period. It is a specific time node, extracted from the actual time-dependent data;

[0157] 1. Get data: Assume the time period is , , corresponding to the center point , ;

[0158] 2. Bring into calculation:

[0159] ;

[0160] = ;

[0161] 3. Calculate step by step:

[0162] = ;

[0163] = ;

[0164] = ;

[0165] = ;

[0166] ≈0.1100;

[0167] The results show that at time point 3, the weight value is 0.1100, indicating that the impact of time point 3 on financing behavior is relatively moderate. After combining the results with the time period anomaly rate and time dependence characteristics, a user financing time weight distribution model can be further generated.

[0168] See also Figure 6 ,The specific steps for obtaining the user financial information graph are:

[0169] S501: Call the user financing time weight distribution model and the user dynamic coupling feature matrix, construct the weight accumulation feature within the time period through the coupling relationship between the time weight parameter and the feature matrix, and combine the interaction results of the weight accumulation feature to evaluate the dynamic correlation characteristics within the time period and generate the time period cumulative weight analysis results;

[0170] First, the time weight value in the user financing time weight distribution model is extracted and grouped by time period. The dynamic coupling eigenvalue of each node in the financing dynamic coupling feature matrix is ​​called, and the weight and eigenvalue in the same time period are interactively calculated. The time weight is used to weight the dynamic features in the calculation process. The specific calculation is to express the dynamic coupling eigenvalue in matrix form as , the time weight is expressed as ,in represents the coupling value of the jth node in the i-th time period, Represents the weight value of the i-th time period, and combines the two into a cumulative feature weight value matrix , the formula is , through matrix multiplication, we get the cumulative feature weight value matrix, where each element in the matrix Represents the cumulative eigenvalue of node j in time period i, and then normalizes each node value in the cumulative eigenvalue weight matrix node by node. The normalization formula is ,Through the normalization operation, the time period cumulative weight matrix is ​​obtained, and the elements in the matrix represent the standardized cumulative feature weight values ​​between time periods and nodes, and the time period cumulative weight analysis results are generated.

[0171] S502: Based on the cumulative weight analysis results of each period, calculate the change in the financing amount and credit score within the differentiated time period, extract the correlation characteristics between the amount and the score within the period, evaluate the dynamic impact of the amount change on the score, determine the key connection points based on the relationship between node characteristics and adjacent node data changes, and generate relationship analysis results;

[0172] First, extract the normalized weight value of the time period in the cumulative weight analysis result of the time period , combined with the period amount changes in the financing amount record and time-period score changes in user credit score data By calculating the change range of the amount and the score, we can evaluate the correlation between the two and calculate the ratio of the amount change and the score change within the period. The formula is: ,in Represents the characteristic value of the relationship between the change in financing amount and the change in score in the i-th time period, and further calculates the mean characteristic in all time periods , calculate the global mean eigenvalue, combined with and The difference value of The time periods with deviation values ​​higher than the set threshold are selected as key time periods, and the trend of amount and score changes within the key time periods is extracted. The trend change rate of each time period is calculated, and the key data connection points are determined by weighted fitting of the trend data of amount and score to generate relationship analysis results.

[0173] S503: Combine the relationship analysis results to construct node distribution and edge weights using the formula:

[0174] ;

[0175] By weighting node features and connection strength, edge weights and node distribution are constructed to generate a user financial information graph;

[0176] in, represents the weight distribution of nodes v and edges e in the graph, is the basic weight of the node, indicating the initial criticality of each node, is the adjustment coefficient, which reflects the sensitivity of the connection strength between nodes. is the characteristic value of node i, which represents the financial attribute value of each node, It is the center point of the adjustment coefficient and represents the benchmark value of the weight balance between nodes.

[0177] formula:

[0178] ;

[0179] The benefit of the formula is that it quantifies the connection strength between nodes by combining the basic weight, adjustment coefficient and node characteristic value of the node, comprehensively considers the dynamic characteristics and adjustment effect of the node, and improves the ability to describe the user's financial information in detail.

[0180] Detailed explanation of the formula and the process of formula calculation and derivation:

[0181] Assume the number of nodes is 5 and the node eigenvalues ​​are 、 、 、 、 , the adjustment coefficients are 、 、 、 、 The basic weights are 、 、 、 、 , the center point adjustment value is 、 、 、 、 .

[0182] Substitute into the formula step by step to calculate:

[0183] For node 1:

[0184] ;

[0185] For node 2:

[0186] ;

[0187] For node 3:

[0188] ;

[0189] For Node 4:

[0190] ;

[0191] For Node 5:

[0192] ;

[0193] Final calculation results:

[0194] ;

[0195] The results show that the comprehensive weight distribution of nodes and edges is 1.028, indicating that the overall connection strength of the current nodes and edges is relatively balanced, and the distribution between nodes is consistent with the changes in basic weights, adjustment coefficients and eigenvalues. This value can be further used to draw the specific weight distribution of nodes and edges in the user financial information graph.

[0196] A system for generating a user's financial information graph through a financing platform, the system for generating a user's financial information graph through a financing platform is used to execute the above-mentioned method for generating a user's financial information graph through a financing platform, and the system includes:

[0197] The financing behavior extraction module extracts the financing amount, financing time, financing interest rate, and repayment period from financing records based on user behavior data. It then sorts the records by timestamp, calculates the difference in financing amounts between adjacent time points, integrates interest rate change data to calculate the fluctuation range, calculates the repayment ratio change trend, and generates a set of financing dynamic parameters.

[0198] The financing feature vector generation module analyzes the rate of change between the financing amount difference and the interest rate fluctuation range based on the financing dynamic parameter set, normalizes the repayment time data, and constructs the time node feature values ​​of the financing behavior through cumulative calculation to generate a set of financing cumulative feature vectors.

[0199] The feature matrix analysis module extracts time series data from the accumulated financing feature vector set, combines the user's credit score with the probability of default, analyzes the changes in feature values ​​at multiple time nodes, calculates the feature coupling relationship, classifies and processes the feature coupling data, and generates a financing dynamic coupling feature matrix;

[0200] The time weight modeling module analyzes the time dependency coefficient based on the financing dynamic coupling characteristic matrix, combines the overdue data in the repayment behavior with the repayment time distribution, calculates the time weight distribution, classifies the calculated time weight values, and generates a financing time weight distribution model;

[0201] The financial information graph generation module is based on the financing time weight distribution model, combined with the financing dynamic coupling feature matrix, calculates the cumulative weight of the time period, analyzes the relationship between the financing amount and the credit score, calculates the node distribution and edge weight value, and generates the user financial information graph.

[0202] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for generating a user's financial information graph through a financing platform, characterized in that: The following steps are involved: S1: Based on user behavior data, extract the financing amount, financing time, financing interest rate, and repayment period from the user's financing records. Use timestamps to sort the financing behavior records in chronological order, calculate the difference in financing amounts at adjacent time points, integrate interest rate change data to calculate the fluctuation range, and combine the repayment ratio change trend to generate a set of user financing dynamic parameters. S2: Based on the user financing dynamic parameter set, analyze the rate of change of the financing amount difference and the interest rate fluctuation range, use the time data in the user's repayment behavior to normalize it, and construct the financing behavior feature vector of the time node through cumulative calculation to generate the user financing cumulative feature vector set; S3: Based on the cumulative feature vector set of user financing, extract time series data, combine the score and default probability in the user credit characteristics, analyze the changes in the feature values ​​of multiple time nodes, calculate the feature coupling matrix, classify and process by period, and generate the user financing dynamic coupling feature matrix; S4: Based on the user financing dynamic coupling characteristic matrix, analyze the time dependency coefficient, combine the overdue data and repayment time distribution in the user repayment behavior, calculate the time weight distribution, classify the results by time period, and generate a user financing time weight distribution model; S5: Based on the user financing time weight distribution model, combined with the user financing dynamic coupling feature matrix, perform time period cumulative weight calculation, analyze the relationship between financing amount and credit score data, construct node distribution and edge weight, and generate a user financial information graph; The steps for obtaining the user financial information graph are specifically as follows: S501: Calling the user financing time weight distribution model and the user dynamic coupling feature matrix, constructing the weight accumulation feature within the time period through the coupling relationship between the time weight parameter and the feature matrix, and combining the interaction results of the weight accumulation feature to evaluate the dynamic correlation characteristics within the time period and generate the time period cumulative weight analysis results; S502: Based on the cumulative weight analysis results for the time period, calculate the change range of the financing amount and credit score within the differentiated time period, extract the correlation characteristics between the amount and the score within the time period, evaluate the dynamic impact of the amount change on the score, determine the key connection points based on the relationship between node characteristics and adjacent node data changes, and generate relationship analysis results; S503: Based on the relationship analysis results, construct node distribution and edge weights using the formula: ； By weighting node features and connection strength, edge weights and node distribution are constructed to generate a user financial information graph; in, represents the weight distribution of nodes v and edges e in the graph, is the basic weight of the node, indicating the initial criticality of each node, is the adjustment coefficient, which reflects the sensitivity of the connection strength between nodes. is the characteristic value of node i, which represents the financial attribute value of each node, It is the center point of the adjustment coefficient and represents the benchmark value of the weight balance between nodes.

2. The method for generating a user's financial information graph through a financing platform according to claim 1, characterized in that: The user financing dynamic parameter set specifically includes the financing amount difference, interest rate changes, and repayment ratio trends. The user financing cumulative feature vector set includes the financing amount change rate, interest rate fluctuation range, and time-normalized data. The user financing dynamic coupling feature matrix specifically includes time series data, credit score, and default probability. The user financing time weight distribution model specifically includes the time dependence coefficient, overdue data, and repayment time distribution. The user financial information graph includes node distribution and edge weights.

3. The method for generating a user's financial information graph through a financing platform according to claim 2, characterized in that: The steps for obtaining the user financing dynamic parameter set are specifically as follows: S101: Read the financing amount and financing time of the user's financing record, arrange the data by timestamp, calculate the difference sequence of the financing amount based on consecutive time points, analyze the changes in the financing interest rate data, and classify the changes in the financing amount and its associated parameters in combination with the repayment cycle data to generate a financing amount change sequence; S102: Combining the financing amount change sequence with the financing interest rate data, normalizing the financing interest rate and repayment ratio parameters within each fluctuation range of the financing behavior, generating a trend feature based on the numerical changes between the two, segmenting the numerical changes of the trend feature according to the repayment cycle and extracting a trend sequence to generate a repayment ratio trend sequence; S103: Based on the financing amount change sequence and the repayment ratio trend sequence, the correlation characteristics of the repayment ratio change trend to the financing amount fluctuation are analyzed using the formula: ； Calculate the dynamic parameters of the repayment ratio change trend and the financing amount fluctuation, and generate a set of user financing dynamic parameters; in, A comprehensive indicator representing a set of financing dynamics parameters, represents the financing amount at time i, Represents the financing amount at the i-1th time point, represents the financing rate, Represents the repayment ratio change rate, Represents the total number of financing records.

4. The method for generating a user's financial information graph through a financing platform according to claim 3, characterized in that: The steps for obtaining the user financing cumulative feature vector set are specifically as follows: S201: Based on the user financing dynamic parameter set, analyze the financing amount difference and the rate of change of the interest rate fluctuation range, calculate the change in the financing amount at adjacent time points in the financing behavior record, determine the fluctuation characteristics of the change rate based on the difference between the upper and lower bounds of the interest rate fluctuation range, screen the financing behavior records that meet the conditions, extract the characteristic values, and generate the basic characteristic value of the financing behavior; S202: Using the basic characteristic values ​​of the financing behavior, normalize the time dimension parameters in the characteristic values, adjust the distribution interval based on the mean value and standard deviation of the basic characteristic values, and normalize the financing amount difference and the rate of change of the upper and lower bounds of interest rate fluctuations within a unified range to generate a normalized financing behavior characteristic value; S203: Based on the normalized financing behavior feature quantity, construct a financing behavior feature vector of the time node using the formula: ； Through weighted cumulative calculation, the user financing cumulative feature vector set is obtained; in, Represents the result of the cumulative feature vector set of user financing, represents the normalized characteristic quantity of financing behavior, is the mean value calculated during the normalization process, is the standard deviation calculated during the normalization process, is the weight coefficient, which is used to adjust the influence of the normalized feature quantity in the cumulative feature vector. is the total number of normalized financing behavior characteristics.

5. The method for generating a user's financial information graph through a financing platform according to claim 4, characterized in that: The steps for obtaining the user financing dynamic coupling feature matrix are specifically as follows: S301: extracting time series data from the user financing cumulative feature vector set, combining the user credit feature score and the change parameters of the default probability, analyzing the trend of the feature value at the time node, and segmenting the feature value based on the change trend and extracting the feature change rate to generate the time series analysis results; S302: Calling the time series analysis result data, calculating the coupling degree between the characteristic value at each time point and the user's credit score and default probability, constructing the characteristic distribution relationship between time points based on the change rate of the characteristic value, and measuring the coupling strength between the differentiated features in the time series data based on a standardized method to generate a characteristic coupling analysis result; S303: Based on the characteristic coupling analysis results, calculate the characteristic coupling matrix, measure the mutual relationship between the characteristic values ​​through normalization, and use the formula: ； Classify and process by period to generate the user financing dynamic coupling feature matrix; in, represents the coupling degree between feature i and feature j, represents the normalized value of feature i at time point t, represents the normalized value of feature j at time point t, is the total number of time points.

6. The method for generating a user's financial information graph through a financing platform according to claim 5, characterized in that: The steps for obtaining the user financing time weight distribution model are specifically as follows: S401: Based on the time dependency coefficient in the user financing dynamic coupling feature matrix, by matching the overdue days and repayment time distribution data in the user's repayment behavior, evaluating the behavioral abnormality rate at multiple time nodes, extracting key credit behavior pattern features based on the abnormality rate changes, and generating time dependency analysis results; S402: Matching the behavioral pattern features of multiple time nodes in the time dependency analysis results with time periods, cumulatively calculating the credit impact weight within each time period based on the degree of overdue payment, repayment time distribution pattern, and feature weights, and generating a time weight calculation result by combining the behavioral concentration trend and change pattern within the time period; S403: Based on the time weight calculation result, the user's credit behavior is classified by time period using the formula: ； Combining Gaussian weighting and time-dependent features, we analyze the weighted summaries of multiple time periods and classify them by time period to generate a user financing time weight distribution model. in, Represents the weight value at time t, which is used to measure the impact of time t on user financing behavior. Represents the weight coefficient of time period classification, reflecting the importance of multiple time periods in user financing behavior. is the central time point of time period i, indicating the key monitoring point within the time period, is the standard deviation of the time period, which indicates the width of the time distribution.

7. A system for generating a user's financial information graph through a financing platform, characterized in that: The method for generating a user's financial information graph through a financing platform according to any one of claims 1 to 6, wherein the system comprises: The financing behavior extraction module extracts the financing amount, financing time, financing interest rate, and repayment period from financing records based on user behavior data. It sorts the records by timestamp, calculates the difference in financing amounts at adjacent time points, integrates interest rate change data to calculate the fluctuation range, calculates the repayment ratio change trend, and generates a set of financing dynamic parameters. The financing feature vector generation module analyzes the rate of change of the financing amount difference and the interest rate fluctuation range based on the financing dynamic parameter set, normalizes the repayment time data, constructs the time node feature values ​​of the financing behavior through cumulative calculation, and generates a financing cumulative feature vector set; The feature matrix analysis module extracts time series data from the accumulated financing feature vector set, combines the user credit score and default probability, analyzes the changes in feature values ​​at multiple time nodes, calculates feature coupling relationships, classifies and processes feature coupling data, and generates a financing dynamic coupling feature matrix; The time weight modeling module analyzes the time dependency coefficient based on the financing dynamic coupling characteristic matrix, combines the overdue data in the repayment behavior with the repayment time distribution, calculates the time weight distribution, classifies and calculates the time weight values, and generates a financing time weight distribution model; The financial information graph generation module is based on the financing time weight distribution model, combined with the financing dynamic coupling feature matrix, calculates the cumulative weight of the time period, analyzes the relationship between the financing amount and the credit score, calculates the node distribution and edge weight value, and generates the user financial information graph.

Images