Vehicle mortgage data processing method and system, computer and storage medium

Abstract

The invention provides a vehicle mortgage data processing method and system, a computer and a storage medium. The method comprises the following steps: receiving and acquiring office data of a user; carrying out asymmetric encryption on the office data through an RSA algorithm, and carrying out parallel shunting processing on flow audit data, office information data and GPS installation data in the office data by using an asynchronous technology; and if the step flow corresponding to each piece of data is not abnormal, issuing the mortgage to the user based on the fund party. The asynchronous technology is adopted to perform parallel shunting processing on the process auditing data, the handling information data and the GPS installation data, so that the mode of serial operation of the traditional car handling loan business is changed, all links can be simultaneously propelled, and the time of the whole business process is greatly shortened.

Description

Technical Field

[0001] The present invention relates to the field of financial data technology, and in particular to a vehicle mortgage data processing method, system, computer and storage medium. Background Art

[0002] In the traditional vehicle mortgage loan business process, the review, mortgage processing and GPS installation are usually carried out in series.

[0003] The asset side needs to first review the borrower's qualifications, vehicle conditions, etc., and then contact the collateral side to handle mortgage registration after the review is passed, and finally arrange for GPS installation. This sequential operation method results in a long business process and low loan efficiency. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a vehicle mortgage data processing method, system, computer and storage medium, aiming to solve the technical problem of low classification accuracy in the prior art.

[0005] In order to achieve the above-mentioned object, in a first aspect, the present invention provides: a vehicle mortgage data processing method, comprising the following steps: Receive and obtain the user's arrival data, wherein the arrival data includes process review data, arrival information data and GPS installation data; The arrival data is asymmetrically encrypted using the RSA algorithm, and the process review data, arrival information data and GPS installation data in the arrival data are processed in parallel using asynchronous technology; Receive and compare the feedback results of each data in the arrival data to determine whether there is any process abnormality; If there are no abnormalities in the steps corresponding to each data, the mortgage will be issued to the user based on the funding party.

[0006] According to one aspect of the above technical solution, the steps of receiving and comparing the feedback results of each data in the processing data to determine whether a process abnormality occurs specifically include: Verify the user's personal credit data and vehicle information data in the process review data; Receive and compare the verification feedback results of the process audit data. If there is a deviation between the feedback results and the first preset value, it is determined that the process is abnormal and the processing flow of other data in the processing data is terminated.

[0007] According to one aspect of the above technical solution, the steps of receiving and comparing the feedback results of each data in the processing data to determine whether a process abnormality occurs specifically include: Based on the gradient boosting decision tree algorithm, the risk of sample indicators in the arrival information data is predicted; Receive and compare the predicted feedback result of the arrival information data. If the feedback result deviates from the second preset value, it is determined that an abnormality occurs in the process and the processing flow of other data in the arrival data is terminated.

[0008] According to one aspect of the above technical solution, the step of predicting the risk of sample indicators in the processing information data based on the gradient boosting decision tree algorithm specifically includes: A risk prediction model is established based on a gradient boosting decision tree algorithm to perform risk prediction on sample indicators in the processing information data; The calculation expression of the risk prediction model is as follows: ; In the formula, is the output of the model, m is the number of iterations, is the learning rate, is the output of the decision tree after m iterations, is the output of the model at m-1 iterations.

[0009] According to one aspect of the above technical solution, the initial output of the risk prediction model before iteration and the calculation expressions of the negative gradient of the sample during iteration are respectively: ; ; In the formula, is the initial output, is the model prediction label, L is the loss function, n is the number of samples, is the true label of the i-th sample, is the prediction result of the current model, is the partial derivative.

[0010] According to one aspect of the above technical solution, the calculation expression of the loss function is: ; In the formula, is the category weight factor, To introduce the coefficient, The probability that the model predicts that the sample belongs to the negative class, The probability that the predicted sample belongs to the positive class.

[0011] In a second aspect, the present invention provides a vehicle mortgage data processing system, comprising: A data module is used to receive and obtain the user's arrival data, wherein the arrival data includes process review data, arrival information data and GPS installation data; A parallel processing module is used to asymmetrically encrypt the arrival data using an RSA algorithm, and use asynchronous technology to parallelly distribute the process review data, arrival information data, and GPS installation data in the arrival data; The feedback module is used to receive and compare the feedback results of each data in the processing data to determine whether there is any process abnormality; The funding module is used to distribute the mortgage funds to the user based on the funding party if there are no abnormalities in the step processes corresponding to each data.

[0012] According to one aspect of the above technical solution, the feedback module is specifically used for: Verify the user's personal credit data and vehicle information data in the process review data; Receive and compare the verification feedback results of the process audit data. If there is a deviation between the feedback results and the first preset value, it is determined that the process is abnormal and the processing flow of other data in the processing data is terminated.

[0013] According to one aspect of the above technical solution, the feedback module is specifically used for: Based on the gradient boosting decision tree algorithm, the risk of sample indicators in the arrival information data is predicted; Receive and compare the predicted feedback result of the arrival information data. If the feedback result deviates from the second preset value, it is determined that an abnormality occurs in the process and the processing flow of other data in the arrival data is terminated.

[0014] According to one aspect of the above technical solution, the feedback module is further used for: A risk prediction model is established based on a gradient boosting decision tree algorithm to predict the risk of sample indicators in the processing information data; The calculation expression of the risk prediction model is as follows: ; In the formula, is the output of the model, m is the number of iterations, is the learning rate, is the output of the decision tree after m iterations, is the output of the model at m-1 iterations.

[0015] In a third aspect, the present invention further provides a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the vehicle mortgage data processing method as described in the above technical solution when executing the computer program.

[0016] In a fourth aspect, the present invention further provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the vehicle mortgage data processing method as described in the above technical solution is implemented.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: by adopting asynchronous technology to parallelly divert and process the process review data, the mortgage information data and the GPS installation data, the serial operation mode of the traditional car mortgage loan business is changed, and each link can be promoted simultaneously, which greatly shortens the time of the entire business process, and uses the RSA algorithm to asymmetric encrypt the mortgage data, which provides a strong security guarantee for data transmission and storage, and ensures the confidentiality and integrity of the business data; the gradient boosting decision tree algorithm is combined to predict the risk of sample indicators in the mortgage information data, and at the same time, the personal credit data and vehicle information data of the user in the process review data are checked, and the risk of the car mortgage loan business is comprehensively evaluated from multiple dimensions, which can accurately identify the repayment ability of the borrower and the risk status of the mortgaged vehicle, discover potential risk factors, and provide a more reliable basis for business decision-making; in the risk assessment process, once it is found that the risk prediction result deviates from the preset value, the system can promptly determine that the process is abnormal and take corresponding measures, such as suspending the business process, re-examining the data, etc., and timely intervention can be made before the risk event occurs, reducing the risk of loan default and ensuring the safety of the funds of the funder. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of a vehicle mortgage data processing method in the first embodiment of the present invention; Figure 2 It is a structural block diagram of a vehicle mortgage data processing system in a second embodiment of the present invention; Figure 3 is a schematic diagram of the hardware structure of a computer in a third embodiment of the present invention; The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0019] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] Embodiment 1 See also Figure 1 , which is a flow chart of a vehicle mortgage data processing method in a first embodiment of the present invention. As shown in the figure, the method includes the following steps: Step S100, receiving and obtaining the user's mortgage data, wherein the mortgage data includes process review data, mortgage information data and GPS installation data. Specifically, the process review data includes the borrower's basic information, credit record data, income and asset data and vehicle data, and the vehicle data includes vehicle driving license, vehicle purchase invoice, vehicle registration certificate, etc. These data are used to verify the ownership of the vehicle, the purchase price and time of the vehicle, whether the vehicle is mortgaged, etc.; the mortgage information data includes mortgage registration information, mortgage contract data and mortgage progress data, etc.; the GPS installation data includes GPS device information, press and hold information and device status data.

[0023] Step S200, asymmetrically encrypt the mortgage data using the RSA algorithm, and use asynchronous technology to parallelly divert the process review data, mortgage information data and GPS installation data in the mortgage data. The RSA algorithm is an asymmetric encryption algorithm that uses a pair of keys, namely a public key and a private key. The public key is public and used to encrypt data; the private key is confidential and used to decrypt data. In the vehicle mortgage business, the business system will generate a pair of public and private keys, and distribute the public key to the sender of the data (such as the borrower, the mortgage party and the funding party). The sender uses the public key to encrypt the mortgage data and transmits it to the business system, and the business system then uses the private key to decrypt it.

[0024] Asynchronous technology allows the system to start processing other tasks while processing one task without waiting for the task to complete. In the vehicle mortgage business, process review data, mortgage information data and GPS installation data can be processed simultaneously, rather than in the traditional serial way. For example, when reviewing the borrower's credit record, the vehicle mortgage registration and GPS device installation can be processed at the same time. In this step, the spring open source framework annotation @Async is used to cut the data into independent sub-functions to ensure that the data flow can proceed normally.

[0025] Step S300, receiving and comparing the feedback results of each data in the arrival data to determine whether there is a process abnormality. The data includes the verification of information in the process review data, the information comparison and risk assessment of the arrival information data, and the installation progress of the GPS device.

[0026] Preferably, in this embodiment, the step of receiving and comparing the feedback results of each data in the processing data to determine whether a process abnormality occurs specifically includes: Step S310: Check the user's personal credit data and vehicle data in the process review data, including the completeness, accuracy and risk assessment of the information.

[0027] Step S320, receiving and comparing the verification feedback results of the process audit data, if the feedback results deviate from the first preset value, the process is judged to be abnormal, and the processing flow of other data in the processing data is terminated. The first preset value is a series of standards and thresholds set according to business experience, risk preferences and relevant regulations. For example, the minimum requirement for credit score, the reasonable range of vehicle value, the upper limit of the number of overdue payments, etc.

[0028] Step S330, predicting the risk of sample indicators in the arrival information data based on the gradient boosting decision tree algorithm. Gradient boosting decision tree (GBDT) is an iterative decision tree ensemble learning algorithm that iteratively trains a series of decision trees, and each new decision tree tries to fit the residual of the previous round of model, gradually improving the prediction performance of the model.

[0029] Key sample indicators related to risks are selected from the mortgage information data, such as mortgage registration time, mortgage contract terms, mortgage progress, etc., to reflect the various characteristics and potential risk factors in the mortgage process.

[0030] Step S340, receiving and comparing the predicted feedback result of the said settlement information data, if the feedback result deviates from the second preset value, then the process is judged to be abnormal, and the processing flow of other data in the settlement data is terminated. The second preset value is a risk threshold set according to the risk tolerance and risk management objectives of the business. For example, the upper limit of the risk score, the critical value of the risk level, etc.

[0031] Furthermore, the step of predicting the risk of sample indicators in the processing information data based on the gradient boosting decision tree algorithm specifically includes: A risk prediction model is established based on a gradient boosting decision tree algorithm to predict the risk of sample indicators in the processing information data; The calculation expression of the risk prediction model is as follows: ; In the formula, is the output of the model, m is the number of iterations, is the learning rate, is the output of the decision tree after m iterations, is the output of the model at m-1 iterations.

[0032] Preferably, in this embodiment, the initial output of the risk prediction model before iteration and the calculation expressions of the negative gradient of the sample during the iteration are respectively: ; ; In the formula, is the initial output, is the model prediction label, L is the loss function, n is the number of samples, is the true label of the i-th sample, is the prediction result of the current model, is the partial derivative.

[0033] For ease of understanding, the processing steps of the risk prediction model are as follows: First, the initial output of the model needs to be determined based on the above formula, and a model prediction label is found to minimize the loss function of all samples; then iterative training is performed, and the negative gradient is calculated through the above formula. The negative gradient indicates the direction in which the loss function decreases fastest. The model reduces the loss by fitting the negative gradient; then the features and negative gradient of the current sample are used as training data to train a new decision tree. The training process of the decision tree is to find the best split point and features, divide the samples into different nodes, make the samples in each node as similar as possible, and then control the contribution of each decision tree to the model update according to the learning rate.

[0034] Preferably, in this embodiment, the calculation expression of the above loss function is: ; In the formula, is the category weight factor, To introduce the coefficient, The probability that the model predicts that the sample belongs to the negative class, The probability that the predicted sample belongs to the positive class.

[0035] Specifically, refers to the true label of the sample, Indicates that the sample belongs to the positive class, Indicates that the sample belongs to the negative class; The above category weight factors , the value range is between [0-1], its role is to coordinate the imbalance of the positive and negative sample ratios, by adjusting The value of can make the model pay more attention to the category with fewer samples. For example, in the prediction of vehicle mortgage default, if the number of default samples (positive class) is much smaller than the number of normal repayment samples (negative class), Set it larger, such as =0.7, so when calculating the loss, the loss weight of the default sample will be relatively increased, prompting the model to better learn the characteristics of the default sample.

[0036] The above-mentioned introduced coefficients are used to adjust the model's attention to samples with different confidence levels. >0, for samples with higher prediction confidence, the penalty of the loss function will be relatively reduced; and for samples with lower prediction confidence, the penalty of the loss function will be relatively increased. For example, if =2, when the model has a high probability (such as =0.9) predicts that a business will default, the loss is relatively small; but if the model predicts that a business will default at a lower rate (such as = 0.2) predicts that a business will default, but in fact the business actually defaults ( ), the loss will be larger, causing the model to pay more attention to samples with inaccurate predictions.

[0037] Step S400: If there are no abnormalities in the steps corresponding to the data, the funder will issue the mortgage to the user. After the previous review and comparison, it is confirmed that there are no abnormalities in each link of the mortgage data, and the funder will issue the mortgage to the user according to the established process and agreement.

[0038] In summary, the vehicle mortgage data processing method in the above embodiment of the present invention adopts asynchronous technology to parallelly divert and process the process review data, the mortgage information data and the GPS installation data, thereby changing the serial operation mode of the traditional car mortgage loan business. Each link can be promoted simultaneously, which greatly shortens the time of the entire business process. The RSA algorithm is used to asymmetric encrypt the mortgage data, which provides a strong security guarantee for data transmission and storage, and ensures the confidentiality and integrity of the business data. The gradient boosting decision tree algorithm is combined to predict the risk of sample indicators in the mortgage information data, and the personal credit data and vehicle information data of the user in the process review data are checked. The risk of the car mortgage loan business is comprehensively evaluated from multiple dimensions, which can accurately identify the repayment ability of the borrower and the risk status of the mortgaged vehicle, discover potential risk factors, and provide a more reliable basis for business decision-making. In the risk assessment process, once it is found that the risk prediction result deviates from the preset value, the system can promptly determine that the process is abnormal and take corresponding measures, such as suspending the business process, re-examining the data, etc., and timely intervention can be made before the risk event occurs, reducing the risk of loan default and ensuring the safety of the funds of the funding party.

[0039] Embodiment 2 The second embodiment of the present application also provides a vehicle mortgage data processing system, which is used to implement the embodiments and preferred implementations, and will not be repeated hereafter. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware for a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and contemplated.

[0040] like Figure 2 As shown, the system includes: a data module 100, a parallel processing module 200, a feedback module 300, and a funding module 400.

[0041] The data module 100 is used to receive and obtain the user's arrival data, wherein the arrival data includes process review data, arrival information data and GPS installation data; The parallel processing module 200 is used to asymmetrically encrypt the arrival data by using the RSA algorithm, and to perform parallel shunt processing on the process review data, arrival information data and GPS installation data in the arrival data by using asynchronous technology; The feedback module 300 is used to receive and compare the feedback results of each data in the processing data to determine whether there is a process abnormality; The funding module 400 is used to distribute the mortgage funds to the user based on the funding party if there are no abnormalities in the step processes corresponding to each data.

[0042] Preferably, in this embodiment, the feedback module 300 is specifically used for: Verify the user's personal credit data and vehicle information data in the process review data; Receive and compare the verification feedback results of the process audit data. If there is a deviation between the feedback results and the first preset value, it is determined that the process is abnormal and the processing flow of other data in the processing data is terminated.

[0043] Preferably, in this embodiment, the feedback module 300 is specifically used for: Based on the gradient boosting decision tree algorithm, the risk of sample indicators in the arrival information data is predicted; Receive and compare the predicted feedback result of the arrival information data. If the feedback result deviates from the second preset value, it is determined that an abnormality occurs in the process and the processing flow of other data in the arrival data is terminated.

[0044] Preferably, in this embodiment, the feedback module 300 is further used for: A risk prediction model is established based on a gradient boosting decision tree algorithm to predict the risk of sample indicators in the processing information data; The calculation expression of the risk prediction model is as follows: ; In the formula, is the output of the model, m is the number of iterations, is the learning rate, is the output of the decision tree after m iterations, is the output of the model at m-1 iterations.

[0045] It should be noted that each module can be a functional module or a program module, and can be implemented by software or hardware. For modules implemented by hardware, each module can be located in the same processor; or each module can be located in different processors in any combination.

[0046] Embodiment 3 A third embodiment of the present application provides a computer, which may include a processor 81 and a memory 82 storing computer program commands.

[0047] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0048] Among them, the memory 82 may include a large-capacity memory for data or commands. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0049] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program commands executed by the processor 81 .

[0050] The processor 81 implements any one of the vehicle mortgage data processing methods in the above-mentioned embodiments by reading and executing the computer program commands stored in the memory 82 .

[0051] In some embodiments, the computer may further include a communication interface 83 and a bus 80. Figure 3 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0052] The communication interface 83 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication interface 83 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0053] The bus 80 includes hardware, software or both, and couples the components of the computer to each other. The bus 80 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0054] Embodiment 4 The fourth embodiment of the present application provides a readable storage medium having computer program commands stored thereon; when the computer program commands are executed by a processor, any one of the vehicle mortgage data processing methods in the above embodiments is implemented.

[0055] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0056] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A vehicle mortgage data processing method, characterized in that: The following steps are involved: Receive and obtain the user's arrival data, wherein the arrival data includes process review data, arrival information data and GPS installation data; The arrival data is asymmetrically encrypted using the RSA algorithm, and the process review data, arrival information data and GPS installation data in the arrival data are processed in parallel using asynchronous technology; Receive and compare the feedback results of each data in the arrival data to determine whether there is any process abnormality; If there are no abnormalities in the steps corresponding to each data, the mortgage will be issued to the user based on the funding party.

2. The vehicle mortgage data processing method according to claim 1, characterized in that: The steps of receiving and comparing the feedback results of each data in the arrival data to determine whether there is any process abnormality include: Verify the user's personal credit data and vehicle information data in the process review data; Receive and compare the verification feedback results of the process audit data. If there is a deviation between the feedback results and the first preset value, it is determined that the process is abnormal and the processing flow of other data in the processing data is terminated.

3. The vehicle mortgage data processing method according to claim 1, characterized in that: The steps of receiving and comparing the feedback results of each data in the arrival data to determine whether there is any process abnormality include: Based on the gradient boosting decision tree algorithm, the risk of sample indicators in the arrival information data is predicted; Receive and compare the predicted feedback result of the arrival information data. If the feedback result deviates from the second preset value, it is determined that an abnormality occurs in the process and the processing flow of other data in the arrival data is terminated.

4. The vehicle mortgage data processing method according to claim 3, characterized in that: The steps of predicting the risk of sample indicators in the arrival information data based on the gradient boosting decision tree algorithm specifically include: A risk prediction model is established based on a gradient boosting decision tree algorithm to perform risk prediction on sample indicators in the processing information data; The calculation expression of the risk prediction model is as follows: ； In the formula, is the output of the model, m is the number of iterations, is the learning rate, is the output of the decision tree after m iterations, is the output of the model at m-1 iterations.

5. The vehicle mortgage data processing method according to claim 4, characterized in that: The initial output of the risk prediction model before iteration and the calculation expressions of the negative gradient of the sample during iteration are respectively: ； ； In the formula, is the initial output, is the model prediction label, L is the loss function, n is the number of samples, is the true label of the i-th sample, is the prediction result of the current model, is the partial derivative.

6. The vehicle mortgage data processing method according to claim 5, characterized in that: The calculation expression of the loss function is: ； In the formula, is the category weight factor, To introduce the coefficient, The probability that the model predicts that the sample belongs to the negative class, The probability that the predicted sample belongs to the positive class.

7. A vehicle mortgage data processing system, characterized in that: include: A data module is used to receive and obtain the user's arrival data, wherein the arrival data includes process review data, arrival information data and GPS installation data; A parallel processing module is used to asymmetrically encrypt the arrival data using an RSA algorithm, and use asynchronous technology to parallelly distribute the process review data, arrival information data, and GPS installation data in the arrival data; The feedback module is used to receive and compare the feedback results of each data in the processing data to determine whether there is any process abnormality; The funding module is used to distribute the mortgage funds to the user based on the funding party if there are no abnormalities in the step processes corresponding to each data.

8. The vehicle mortgage data processing system according to claim 7, characterized in that: The feedback module is specifically used for: Verify the user's personal credit data and vehicle information data in the process review data; Receive and compare the verification feedback results of the process audit data. If there is a deviation between the feedback results and the first preset value, it is determined that the process is abnormal and the processing flow of other data in the processing data is terminated.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the vehicle mortgage data processing method as described in any one of claims 1-6 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a vehicle mortgage data processing method as described in any one of claims 1 to 6 is implemented.

Images