Multi-source heterogeneous automobile credit data acquisition and processing system and method

Abstract

The embodiment of the invention discloses a multi-source heterogeneous automobile credit data collection and processing system and method, and relates to the technical field of data processing, and the system comprises a multi-source data collection module which is used for collecting a plurality of types of data from a plurality of data sources; the data processing module is used for performing data cleaning and format normalization on the automobile credit data acquired by the multi-source data acquisition module; the data storage module is used for respectively storing the data processed by the data processing module in different servers according to a preset rule; the data analysis module is used for carrying out data statistics and carrying out risk assessment and default prediction by using a data analysis model; and the data report generation module is used for generating a visual report according to the statistical data and the prediction result of the data analysis module. According to the multi-source heterogeneous automobile credit data acquisition and processing system, efficient and multi-source data acquisition and risk assessment can be realized based on mutual cooperation of the modules, and the debit and credit risk can be assessed more accurately.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and in particular to a system and method for collecting and processing multi-source heterogeneous automobile credit data. Background Art

[0002] Compared with other types of credit data (such as credit cards, personal loans, housing loans, etc.), auto credit data has some unique characteristics, which will bring specific challenges and requirements in data acquisition, data processing, data storage, etc. The following is a detailed introduction:

[0003] 1. Dual risk factors:

[0004] Customer credit risk: Similar to traditional credit, auto credit also includes the customer's credit risk, such as the customer's income, credit score, debt ratio, repayment history, etc.

[0005] Vehicle risk: Auto loans also involve vehicle-related risks, such as vehicle valuation, age, model, usage (such as mileage, driving behavior), etc. Factors such as the vehicle's depreciation rate and market demand will also affect the risk of default.

[0006] 2. Vehicle dynamic data:

[0007] Auto loan data usually includes dynamic data of the vehicle, such as GPS location data, driving behavior data (such as sudden acceleration, sudden braking, speeding, etc.), vehicle usage frequency, etc. These data can help evaluate customers' driving habits and vehicle usage, and then predict default risks.

[0008] Other credit data generally do not involve such dynamic data and focus more on static customer financial information and credit history.

[0009] 3. Loan period:

[0010] The term of auto loans is usually short (generally 1-5 years). Compared with housing loans (which may be as long as 20-30 years), auto loans have a shorter repayment period, and customers' repayment behavior and default risk are more time-sensitive. Therefore, data analysis needs to pay more attention to short-term changes in customer behavior and market fluctuations.

[0011] 4. Vehicle residual value:

[0012] As a movable property, the residual value of a car will gradually decrease during the loan period. The change in the residual value of the vehicle will affect the customer's default tendency and the lender's ability to recover.

[0013] In a home loan, the property typically has the potential to appreciate in value, whereas in an auto loan, the vehicle is typically a depreciating asset.

[0014] Existing auto credit assessments usually use traditional credit data for assessment without taking into account the characteristics of auto credit.

[0015] To sum up, how to acquire and process multi-source credit data based on the characteristics of auto credit is an issue that needs to be solved. Summary of the invention

[0016] In view of this, the embodiments of the present disclosure provide a multi-source heterogeneous automobile credit data collection and processing system and method, so as to acquire and process multi-source credit data in combination with the characteristics of automobile credit.

[0017] In a first aspect, the embodiments of the present disclosure provide a multi-source heterogeneous automobile credit data collection and processing system, which adopts the following technical solutions:

[0018] A multi-source data collection module is used to collect multiple categories of data from multiple data sources;

[0019] The data processing module is used to clean and normalize the automobile credit data collected by the multi-source data collection module;

[0020] The data storage module is used to store the data processed by the data processing module in different servers according to preset rules;

[0021] Data analysis module, used for data statistics and risk assessment and default prediction using data analysis models;

[0022] The data report generation module is used to generate visual reports based on the statistical data and predicted results of the data analysis module.

[0023] As an optional implementation, the multi-source data acquisition module includes:

[0024] An insurance data collection unit, used to access the insurance data source to collect insurance claim data of the original vehicle of the designated person;

[0025] A maintenance record collection unit, used to access the maintenance record data source to collect the maintenance record of the original vehicle of the designated person;

[0026] A vehicle data collection unit, used to access the vehicle data data source to collect the original vehicle data of a designated person;

[0027] The credit data collection unit is used to access the credit data source to collect the credit data of the designated person.

[0028] As an optional implementation, the data processing module includes:

[0029] Noise removal unit, which removes outliers in the data through smoothing and outlier detection;

[0030] An error data identification unit, which identifies error data and missing data based on preset rules;

[0031] Error data processing unit, business rules correct erroneous data or delete missing data;

[0032] Data conversion unit converts the processed data into a unified format.

[0033] As an optional implementation, the data storage module includes:

[0034] Data desensitization unit, used to desensitize some fields in personal data;

[0035] The distributed storage unit is used to store the processed data according to the categories when the multi-source data acquisition module collects the data.

[0036] As an optional implementation, the data analysis module includes:

[0037] The data statistics unit reads the data of each category of the designated person from the distributed storage unit and forms the data into input data;

[0038] The data analysis unit uses the risk assessment model and the default prediction model to perform data analysis based on the input data.

[0039] As an optional implementation, the data analysis unit includes:

[0040] A risk assessment module is used to obtain risk assessment data by performing data analysis based on input data using a risk assessment model;

[0041] The default prediction module is used to use the default prediction model to perform data analysis based on input data to obtain a default prediction.

[0042] As an optional implementation, as an optional implementation, the data report generation module includes:

[0043] A report data acquisition unit reads all data of a designated person in a distributed storage unit;

[0044] A report data processing unit, which classifies all data according to categories and obtains a highlight value that satisfies a highlight condition in each category of data;

[0045] The data report generation unit generates a report for each category based on the data of each category and highlights prominent values.

[0046] As an optional implementation, the multi-source data acquisition module further includes:

[0047] The traffic violation data collection unit is used to access the traffic violation data source to collect the traffic violation data of the original vehicle of the designated person.

[0048] In a second aspect, the embodiment of the present disclosure further provides a multi-source heterogeneous automobile credit data collection and processing method, based on the above-mentioned multi-source heterogeneous automobile credit data collection and processing system, comprising:

[0049] Using the multi-source data collection module to collect multiple categories of data from multiple data sources;

[0050] Using the data processing module to clean and normalize the automobile credit data collected by the multi-source data collection module;

[0051] Using the data storage module to store the data processed by the data processing module in different servers according to preset rules;

[0052] Utilize the data analysis module to collect data and use the data analysis model to perform risk assessment and default prediction;

[0053] The data report generation module is used to generate a visual report based on the statistical data and predicted results of the data analysis module.

[0054] As an optional implementation, using the multi-source data collection module to collect multiple categories of data from multiple data sources includes:

[0055] Using the insurance data collection unit to access the insurance data source to collect the insurance claim data of the original vehicle of the designated person;

[0056] Using the maintenance record collection unit to access the maintenance record data source to collect the maintenance record of the original vehicle of the designated person;

[0057] Using the vehicle data collection unit to access the vehicle data data source to collect the original vehicle data of the designated person;

[0058] The credit data collection unit is used to access the credit data source to collect the credit data of the designated person.

[0059] In summary, the technical effects of the multi-source heterogeneous automobile credit data collection and processing system provided by the present disclosure are:

[0060] The multi-source heterogeneous automobile credit data collection and processing system provided by the present disclosure can realize efficient, multi-source data collection and risk assessment based on the mutual cooperation of various modules, which helps to more accurately assess the lending risk. Specifically, it has the following benefits:

[0061] 1. The multi-source data collection module can obtain data from multiple different data sources (such as bank statements, credit reports, social media, sales records, etc.), covering various aspects of the borrower's information. This not only reduces the labor of manual data collection, but also ensures the comprehensiveness and diversity of the data, which helps to more accurately assess lending risks.

[0062] 2. The data processing module is responsible for cleaning and formatting the collected raw data, eliminating invalid, erroneous or duplicate information, and ensuring the quality of data input into the analysis model. High-quality data is an important prerequisite for ensuring the accuracy of analysis results.

[0063] 3. Different data storage strategies can take corresponding measures according to the sensitivity of the data, such as different types of server storage, encrypted storage, etc., which not only meet business needs, but also ensure data security and comply with relevant laws and regulations, and protect personal privacy and corporate information security.

[0064] 4. The data analysis module can reveal the key factors of credit risk by conducting in-depth analysis of the cleaned data, establish a prediction model by learning from historical data, and conduct data analysis. The complex analysis results can then be displayed in a visual manner through the data report generation module, providing decision support for loan approval, helping companies to effectively manage credit risks and reduce default losses.

[0065] In summary, the system can not only improve work efficiency, data quality and security, but also facilitate business decision-making and promote the development of the auto credit industry.

[0066] 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 in accordance with 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 following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0068] Figure 1 A schematic diagram of the structure of a multi-source heterogeneous automobile credit data collection and processing system provided by an embodiment of the present disclosure;

[0069] Figure 2 A flowchart of a multi-source heterogeneous automobile credit data collection and processing method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0070] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0071] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0072] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0073] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0074] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0075] Reference Figure 1 The first aspect of the present invention provides a multi-source heterogeneous automobile credit data collection and processing system, comprising:

[0076] A multi-source data collection module is used to collect multiple categories of data from multiple data sources;

[0077] The data processing module is used to clean and normalize the automobile credit data collected by the multi-source data collection module;

[0078] The data storage module is used to store the data processed by the data processing module in different servers according to preset rules;

[0079] Data analysis module, used for data statistics and risk assessment and default prediction using data analysis models;

[0080] The data report generation module is used to generate visual reports based on the statistical data and predicted results of the data analysis module.

[0081] The multi-source heterogeneous automobile credit data collection and processing system provided by the present disclosure can realize efficient, multi-source data collection and risk assessment based on the mutual cooperation of various modules, which helps to more accurately assess the lending risk. Specifically, it has the following benefits:

[0082] 1. Improve data collection efficiency: The multi-source data collection module can obtain data from multiple different data sources (such as bank statements, credit reports, social media, sales records, etc.), covering various aspects of the borrower's information. This not only reduces the labor of manual data collection, but also ensures the comprehensiveness and diversity of the data, which helps to more accurately assess lending risks.

[0083] 2. Enhance data quality: The data processing module is responsible for cleaning and formatting the collected raw data, eliminating invalid, erroneous or duplicate information, and ensuring the quality of data input into the analysis model. High-quality data is an important prerequisite for ensuring the accuracy of analysis results.

[0084] 3. Ensure data security and compliance: Different data storage strategies can take corresponding measures according to the sensitivity of the data, such as different types of server storage, encrypted storage, etc., which not only meet business needs, but also ensure data security and comply with relevant laws and regulations, and protect personal privacy and corporate information security.

[0085] 4. Improve decision-making support capabilities: The data analysis module can reveal the key factors of credit risk by conducting in-depth analysis of the cleaned data, establish a prediction model by learning from historical data, and conduct data analysis. The complex analysis results are then presented in a visual manner through the data report generation module, providing decision support for loan approval, helping companies to effectively manage credit risks and reduce default losses.

[0086] In summary, the system can not only improve work efficiency, data quality and security, but also facilitate business decision-making and promote the development of the auto credit industry.

[0087] As an optional implementation, the multi-source data acquisition module includes:

[0088] The insurance data collection unit is used to access the insurance data source to collect the insurance claim data of the original vehicle of the designated person; the claim data generally includes the insurance type, casualties, vehicle maintenance status, etc.

[0089] The maintenance record collection unit is used to access the maintenance record data source to collect the maintenance record of the original vehicle of the designated person.

[0090] The vehicle data collection unit is used to access the vehicle data data source to collect the original vehicle data of the designated person, including the purchase time, whether it is a new or used car, the usage time, etc.

[0091] The credit data collection unit is used to access the credit data source to collect the credit data of the designated person.

[0092] In this embodiment, the designated person is generally a customer who needs a loan. By collecting the original vehicle data, previous vehicle accident data, and vehicle maintenance records, multiple aspects can complement each other to determine the customer's driving habits, vehicle usage habits, etc., which helps to combine credit assessment to assess risks.

[0093] As an optional implementation, the multi-source data acquisition module further includes:

[0094] The traffic violation data collection unit is used to access the traffic violation data source to collect the traffic violation data of the original vehicle of the designated person. Generally speaking, the traffic violation data is not open to the public and can only be applied to the public security traffic police with the authorization of the party concerned.

[0095] As an optional implementation, the data processing module includes:

[0096] Noise removal unit, which removes outliers in the data through smoothing and outlier detection;

[0097] Specifically, smoothing is to remove noise in the data through techniques such as moving average and median filtering. For example, sudden acceleration and braking in driving behavior data can be identified and outliers removed through smoothing algorithms.

[0098] Outlier detection is to detect and remove outliers using statistical methods (such as Z-score, IQR) or machine learning methods (such as IsolationForest).

[0099] The error data identification unit identifies error data and missing data based on preset rules; generally speaking, error data refers to incorrect data that is entered incorrectly or incorrectly due to human or system reasons. For example, the mileage data of a vehicle may be recorded incorrectly due to a sensor failure.

[0100] Identifying erroneous data based on preset rules means correcting obviously erroneous data based on business rules. For example, a vehicle’s fuel consumption cannot be negative, and mileage should not change suddenly and drastically.

[0101] Missing data refers to the absence of certain fields or values ​​in a data record. There are different ways to handle missing data, depending on the proportion and type of missing data.

[0102] Error data processing unit, business rules correct erroneous data or delete missing data;

[0103] Business rules correct erroneous data by cross-validating with other data sources to identify and correct errors in the data. Data validation is usually used to verify whether records in a single data source are consistent with other related data sources or meet certain external standards. For example:

[0104] Compare the vehicle's GPS location data with the road speed limit data to verify whether the vehicle is speeding and correct errors in the record.

[0105] By comparing the vehicle's fuel consumption data with the engine operating data, it is possible to verify whether the fuel consumption is reasonable.

[0106] The specific steps include:

[0107] 1. Determine the data fields that need to be verified: Determine which data fields need to be verified through external data sources, such as the vehicle's speed, location, fuel consumption, etc.

[0108] 2. Obtain external data sources: Obtain other data sources for verification, such as road speed limit data, GPS location data, etc.

[0109] 3. Cross-validation: Compare the original data with external data sources to identify inconsistent records.

[0110] 4. Correct erroneous data: Correct the identified erroneous data based on the external data source.

[0111] Data conversion unit converts the processed data into a unified format.

[0112] As an optional implementation, the data storage module includes:

[0113] The data desensitization unit is used to desensitize some fields in personal data; the data desensitization unit can ensure that user information can be effectively protected when the data is attacked, such as desensitizing the middle few digits of the ID number, desensitizing the middle characters of the name, etc.

[0114] The distributed storage unit is used to store the processed data according to the categories collected by the multi-source data collection module. When distributed storage is used, different categories are stored on different servers, and all data is stored according to different categories, such as insurance data, credit data, personal information, etc. However, in data categories other than personal information, personal information is deleted. The classified stored information is matched by a unique code. Even if the data on a server is stolen, the stolen information cannot be matched to a specific person, effectively ensuring information security issues.

[0115] As an optional implementation, the data analysis module includes:

[0116] The data statistics unit reads the data of each category of the designated person from the distributed storage unit and forms the data into input data;

[0117] The data analysis unit uses the risk assessment model and the default prediction model to perform data analysis based on the input data.

[0118] Specifically, the data analysis unit includes:

[0119] A risk assessment module is used to obtain risk assessment data by performing data analysis based on input data using a risk assessment model;

[0120] The default prediction module is used to use the default prediction model to perform data analysis based on input data to obtain a default prediction.

[0121] Specifically, the main task of the risk assessment module is to calculate the credit risk level of the loan applicant based on the input data. The specific steps are as follows:

[0122] 1. Data reading: Read multi-category data sets of designated persons from distributed storage units, such as personal credit records, bank statements, vehicle information, income certificates, etc.

[0123] 2. Feature extraction and preprocessing: Extract features from the read data and convert it into a format that the model can process. For example, convert text data into numerical vectors, fill or delete missing values, etc.

[0124] 3. Model application: Input the preprocessed data into the risk assessment model to calculate the credit risk score or grade.

[0125] 4. Result output: Save the risk assessment results output by the model to the designated data storage unit or directly provide them to the business system for use.

[0126] Risk assessment models are usually trained using machine learning methods. The specific steps are as follows:

[0127] 1. Data preparation: Collect historical loan application data, including the applicant’s basic information, credit record, financial status, etc., and mark each applicant’s risk level (such as high risk, medium risk, low risk).

[0128] 2. Feature engineering: preprocess the data, including data cleaning, feature selection, feature conversion and other steps to ensure the quality of the data and the effectiveness of the model.

[0129] 3. Model selection: Choose an appropriate machine learning model, such as logistic regression, decision tree, random forest, support vector machine, gradient boosted tree (GBDT), etc.

[0130] 4. Model training: Use historical data sets to train the selected model and optimize model parameters to improve prediction accuracy.

[0131] 5. Model evaluation: Evaluate the performance of the model through cross-validation, confusion matrix, AUC-ROC curve and other methods to ensure the generalization ability of the model on new data.

[0132] 6. Model tuning: Adjust model parameters or try different model combinations based on the evaluation results to further improve model performance.

[0133] 7. Model deployment: Deploy the trained model to the production environment for actual loan application risk assessment.

[0134] The main task of the default prediction module is to predict the future default probability of the loan applicant based on the input data. The specific steps are as follows:

[0135] 1. Data reading: Read multi-category data sets of designated persons from distributed storage units, such as personal credit records, bank statements, vehicle information, income certificates, etc.

[0136] 2. Feature extraction and preprocessing: Extract features from the read data and convert it into a format that the model can process. For example, calculate the number of overdue days in the repayment history, income stability, etc.

[0137] 3. Model application: Input the preprocessed data into the default prediction model to calculate the probability of default.

[0138] 4. Result output: Save the default probability results output by the model to the specified data storage unit or directly provide them to the business system for use.

[0139] The default prediction model is usually also trained using machine learning methods. The specific method is the same as above and will not be elaborated in detail.

[0140] As an optional implementation, the data report generation module includes:

[0141] A report data acquisition unit reads all data of a designated person in a distributed storage unit;

[0142] A report data processing unit, which classifies all data according to categories and obtains a highlight value that satisfies a highlight condition in each category of data;

[0143] The data report generation unit generates a report for each category based on the data of each category and highlights the prominent values. The report can be displayed in the form of a line chart, a histogram, etc.

[0144] On the other hand, refer to Figure 2 The present invention provides a multi-source heterogeneous automobile credit data collection and processing method, based on the multi-source heterogeneous automobile credit data collection and processing system as described above, comprising:

[0145] Step S1, using the multi-source data collection module to collect multiple categories of data from multiple data sources respectively;

[0146] Step S2, using the data processing module to clean and normalize the automobile credit data collected by the multi-source data collection module;

[0147] Step S3, using the data storage module to store the data processed by the data processing module in different servers according to preset rules;

[0148] Step S4, using the data analysis module to collect data and use the data analysis model to perform risk assessment and default prediction;

[0149] Step S5, using the data report generation module to generate a visual report based on the statistical data and predicted results of the data analysis module.

[0150] As an optional implementation, using the multi-source data collection module to collect multiple categories of data from multiple data sources includes:

[0151] Using the insurance data collection unit to access the insurance data source to collect the insurance claim data of the original vehicle of the designated person;

[0152] Using the maintenance record collection unit to access the maintenance record data source to collect the maintenance record of the original vehicle of the designated person;

[0153] Using the vehicle data collection unit to access the vehicle data data source to collect the original vehicle data of the designated person;

[0154] The credit data collection unit is used to access the credit data source to collect the credit data of the designated person.

[0155] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0156] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0157] In the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0158] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0159] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0160] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0161] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0162] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A multi-source heterogeneous automobile credit data collection and processing system, characterized in that: include: A multi-source data collection module is used to collect multiple categories of data from multiple data sources; The data processing module is used to clean and normalize the automobile credit data collected by the multi-source data collection module; The data storage module is used to store the data processed by the data processing module in different servers according to preset rules; Data analysis module, used for data statistics and risk assessment and default prediction using data analysis models; The data report generation module is used to generate visual reports based on the statistical data and predicted results of the data analysis module.

2. The multi-source heterogeneous automobile credit data collection and processing system according to claim 1 is characterized in that: The multi-source data acquisition module includes: An insurance data collection unit, used to access the insurance data source to collect insurance claim data of the original vehicle of the designated person; A maintenance record collection unit, used to access the maintenance record data source to collect the maintenance record of the original vehicle of the designated person; A vehicle data collection unit, used to access the vehicle data data source to collect the original vehicle data of a designated person; The credit data collection unit is used to access the credit data source to collect the credit data of the designated person.

3. The multi-source heterogeneous automobile credit data collection and processing system according to claim 2 is characterized in that: The data processing module includes: Noise removal unit, which removes outliers in the data through smoothing and outlier detection; An error data identification unit, which identifies error data and missing data based on preset rules; Error data processing unit, business rules correct erroneous data or delete missing data; Data conversion unit converts the processed data into a unified format.

4. The multi-source heterogeneous automobile credit data collection and processing system according to claim 3 is characterized in that: The data storage module includes: Data desensitization unit, used to desensitize some fields in personal data; The distributed storage unit is used to store the processed data according to the categories when the multi-source data acquisition module collects the data.

5. The multi-source heterogeneous automobile credit data collection and processing system according to claim 4 is characterized in that: Data analysis modules include: The data statistics unit reads the data of each category of the designated person from the distributed storage unit and forms the data into input data; The data analysis unit uses the risk assessment model and the default prediction model to perform data analysis based on the input data.

6. The multi-source heterogeneous automobile credit data collection and processing system according to claim 5 is characterized in that: The data analysis unit includes: A risk assessment module is used to obtain risk assessment data by performing data analysis based on input data using a risk assessment model; The default prediction module is used to use the default prediction model to perform data analysis based on input data to obtain a default prediction.

7. The multi-source heterogeneous automobile credit data collection and processing system according to claim 5 is characterized in that: The data report generation module includes: A report data acquisition unit reads all data of a designated person in a distributed storage unit; A report data processing unit, which classifies all data according to categories and obtains a highlight value that satisfies a highlight condition in each category of data; The data report generation unit generates a report for each category based on the data of each category and highlights prominent values.

8. The multi-source heterogeneous automobile credit data collection and processing system according to claim 5 is characterized in that: The multi-source data acquisition module also includes: The traffic violation data collection unit is used to access the traffic violation data source to collect the traffic violation data of the original vehicle of the designated person.

9. A multi-source heterogeneous automobile credit data collection and processing method, based on the multi-source heterogeneous automobile credit data collection and processing system as claimed in claim 1, characterized in that: include: Using the multi-source data collection module to collect multiple categories of data from multiple data sources; Using the data processing module to clean and normalize the automobile credit data collected by the multi-source data collection module; Using the data storage module to store the data processed by the data processing module in different servers according to preset rules; Utilize the data analysis module to collect data and use the data analysis model to perform risk assessment and default prediction; The data report generation module is used to generate a visual report based on the statistical data and predicted results of the data analysis module.

10. The multi-source heterogeneous automobile credit data collection and processing method according to claim 9 is characterized in that: Using the multi-source data acquisition module to respectively collect multiple categories of data from multiple data sources includes: Using the insurance data collection unit to access the insurance data source to collect the insurance claim data of the original vehicle of the designated person; Using the maintenance record collection unit to access the maintenance record data source to collect the maintenance record of the original vehicle of the designated person; Using the vehicle data collection unit to access the vehicle data data source to collect the original vehicle data of the designated person; The credit data collection unit is used to access the credit data source to collect the credit data of the designated person.

Images