Vehicle rental approval method and device and computer readable storage medium

Abstract

The invention discloses a vehicle rental approval method and device and a computer readable storage medium, and relates to the technical field of data processing, and the method comprises the steps: carrying out the analysis through a machine learning algorithm according to the behavior and credit comprehensive data of a customer, and determining a risk analysis result of the customer; based on the risk analysis result, calculating a credit comprehensive score of the customer and generating a risk assessment report; and based on the risk assessment report, a preset score threshold is compared with the credit comprehensive score, and a lease approval result is generated. By integrating multi-dimensional data of customers and performing analysis based on a risk analysis model, the credit risk level of the customers is preliminarily evaluated, the customer risk identification and prevention and control capability is enhanced, the consistency of the approval process is improved by generating a standardized risk assessment report, the risk assessment report is approved through a preset decision rule, and the risk assessment efficiency is improved. And the examination and approval efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a vehicle rental approval method, device, and computer-readable storage medium. Background Art

[0002] The traditional vehicle leasing approval process is mainly reviewed by humans based on experience and judgment. This method is not only inefficient, but also prone to poor consistency in approval results due to human factors. Therefore, the traditional review method is difficult to conduct accurate and rapid approval in a short period of time, which leads to low efficiency in the current vehicle leasing approval process.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a vehicle rental approval method, device and computer-readable storage medium, aiming to solve the technical problem of how to improve the efficiency of vehicle rental approval.

[0005] To achieve the above purpose, the present application proposes a vehicle rental approval method, which includes: Based on the customer's behavior and credit comprehensive data, the risk analysis results of the customer are determined by analyzing through machine learning algorithms; Based on the risk analysis results, calculate the customer's comprehensive credit score and generate a risk assessment report; Based on the risk assessment report, a comparison is made with the comprehensive credit score according to a preset score threshold to generate a lease approval result.

[0006] In one embodiment, before the step of analyzing the customer's behavior and credit comprehensive data through a machine learning algorithm to determine the risk analysis result of the customer, the following steps are included: Sending a request for collecting information to the customer according to the customer's request for leasing a vehicle; If the customer's consent information for requesting information collection is received, the customer's behavioral data and comprehensive credit data are collected to evaluate the customer's rental qualifications.

[0007] In one embodiment, the step of collecting historical customer behavior and credit comprehensive data and corresponding risk results, performing data cleaning and preprocessing operations, and inputting into the risk analysis model for training includes: Checking duplicate values ​​and missing values ​​in the historical customer's behavior and credit comprehensive data, and performing filling, interpolation and / or deletion processing; Standardize the historical customer behavior and credit comprehensive data and unify the format of the data; Constructing training data and verification data for the analysis model based on the processed historical customer behavior and credit comprehensive data and corresponding annotation information; Based on the training data, the risk analysis model is trained by a machine learning algorithm, and the training result of the analysis model is verified based on the verification data.

[0008] In one embodiment, the step of analyzing the customer's behavior and credit comprehensive data through a machine learning algorithm to determine the customer's risk analysis result includes: Clean the collected comprehensive behavior and credit data of the customers, and fill, interpolate and / or delete duplicate values ​​and missing values; Based on the risk analysis model, analyzing the customer's behavior and credit comprehensive data to determine the customer's risk status; According to the risk status, the risk level of the customer's behavior and credit comprehensive data in each risk dimension is calculated to determine the risk analysis result of the customer.

[0009] In one embodiment, the step of calculating the customer's comprehensive credit score and generating a risk assessment report based on the risk analysis result includes: Calculating the comprehensive credit score of the customer according to the weights of the risk dimensions; Fill the risk level of each risk dimension of the customer and the comprehensive credit score into the risk assessment report template to generate the risk assessment report.

[0010] In one embodiment, the step of generating a lease approval result based on the risk assessment report and comparing the risk assessment report with the comprehensive credit score according to a preset score threshold comprises: Comparing the risk level and the comprehensive credit score of each risk dimension of the customer in the risk assessment report with the score threshold in the decision rule; If the comprehensive credit score is less than the score threshold, a rental approval result is generated to reject the rental vehicle request; If the comprehensive credit score is greater than or equal to the score threshold, the risk level of each risk dimension is compared with the corresponding risk level threshold in the decision rule, and for at least one risk assessment report whose risk level exceeds the risk level threshold, a rental approval result is generated to reject the request to rent a vehicle.

[0011] In one embodiment, after the step of generating a lease approval result by comparing the risk assessment report with the comprehensive credit score according to a preset score threshold, the following steps are included: Sending detailed information of the lease approval result to the customer; If the rental approval result is approval of the rental vehicle request, real-time monitoring of the vehicle corresponding to the rental approval result based on the Internet of Things technology; If it is detected that the vehicle triggers a risk warning rule, a warning message is sent to the vehicle management personnel so that the vehicle management personnel can perform further risk warning operations.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle rental approval device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle rental approval method described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle rental approval method described above are implemented.

[0014] The present application provides a vehicle leasing approval method, which firstly integrates the multi-dimensional data of the customer and analyzes it based on the risk analysis model to preliminarily assess the customer's credit risk level, thereby enhancing the ability to identify and prevent customer risks. By generating a standardized risk assessment report, the consistency of the approval process is improved. Through preset decision rules, the risk assessment report is automatically approved without manual intervention, thereby improving the efficiency of approval. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 A flowchart of the first embodiment of the vehicle leasing approval method for application is provided; Figure 2 A flow chart of the second embodiment of the vehicle leasing approval method for this application; Figure 3 A flowchart of the third embodiment of the vehicle leasing approval method for this application; Figure 4A flowchart of the fourth embodiment of the vehicle leasing approval method for this application is provided; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the vehicle rental approval method in the embodiment of the present application.

[0018] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0020] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0021] The main solutions of the embodiments of this application are: At present, the traditional vehicle leasing approval process is mainly reviewed by humans based on experience and judgment. This method is not only inefficient, but also prone to poor consistency in approval results due to human factors. Therefore, it is difficult for the traditional review method to conduct accurate and rapid approval in a short period of time, which in turn leads to low processing efficiency in the current vehicle leasing approval process.

[0022] This application integrates the customer's multi-dimensional data and analyzes it based on the risk analysis model to preliminarily assess the customer's credit risk level, thereby enhancing the ability to identify and prevent customer risks. By generating standardized risk assessment reports, the consistency of the approval process is improved. Through preset decision rules, risk assessment reports are automatically approved without human intervention, thereby improving the efficiency of approval.

[0023] It should be noted that the execution subject of this embodiment can be a vehicle rental approval device, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a vehicle rental approval control device capable of realizing the above functions, etc., and this embodiment does not specifically limit this. The following takes the vehicle rental approval device as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0024] Embodiment 1 Based on this, this application proposes a vehicle rental approval method of the first embodiment, please refer to Figure 1 , the vehicle leasing approval method includes: Step S10, analyzing the customer's behavior and credit comprehensive data through a machine learning algorithm to determine the risk analysis result of the customer.

[0025] Utilizing the customer's behavioral data and comprehensive credit data, in-depth analysis is performed through machine learning algorithms to accurately determine the customer's risk analysis results, which helps to identify potential risk points and formulate effective risk management strategies.

[0026] In this embodiment, the behavior and credit comprehensive data are various behavior data generated by customers in the process of using services or products and credit comprehensive data used to evaluate customers' credit status and repayment ability. The behavior data include transaction records, browsing records, purchase habits, interaction frequency and other behavior records. The credit comprehensive data includes customers' credit scores, historical loan records, repayment status, number of overdue payments, guarantee information, etc. The risk analysis results are the evaluation results of customers' potential risks based on the analysis of customer behavior and credit data, including credit scores, fraud risk levels, default probability, etc.

[0027] As an optional implementation method, the customer's behavioral data and comprehensive credit data are collected, the collected data is integrated and cleaned, and the data is analyzed through a model of a machine learning algorithm to determine the customer's risk analysis results.

[0028] Optionally, step S10 includes: Step S11, cleaning the collected comprehensive behavior and credit data of the customer, and filling, interpolating and / or deleting duplicate values ​​and missing values.

[0029] In this embodiment, data cleaning is the process of correcting or deleting erroneous, duplicate or missing information in data through technical means such as filling, interpolation and deletion.

[0030] For example, for missing values ​​in the comprehensive customer behavior and credit data, statistics such as mean, median, mode, etc. are used to fill in the missing values ​​based on the distribution characteristics of the data. For the time series data, interpolation methods are used to estimate missing values, and duplicate values ​​are directly deleted.

[0031] Step S12: Analyze the customer's behavior and credit comprehensive data based on the risk analysis model to determine the customer's risk status.

[0032] In this embodiment, the risk analysis model is a model based on a machine learning algorithm for assessing a customer's risk status, and predicts possible future risk events such as default and fraud of the customer based on the customer's behavior and credit data.

[0033] Optionally, before using the risk analysis model, the risk analysis model is trained through historical data on customer behavior and credit, historical data related to risk analysis is collected, and preprocessing operations such as cleaning, deduplication, and format conversion are performed on the collected historical data. The preprocessed historical data is divided into a training set, a validation set, and a test set. The model is trained using the training set data, and the model is validated using the validation set data to evaluate the performance of the model. Based on the validation results, the model's performance is optimized by adjusting the model's parameters and structure, and the model is tested using the test set data. The model's performance is quantified by calculating indicators such as the model's accuracy, recall, and F1 score.

[0034] Exemplarily, the customer's behavior and credit comprehensive data are input into the risk analysis model, and the risk analysis results are output and displayed in a table form.

[0035] Step S13, according to the risk status, calculate the risk level of the customer's behavior and credit comprehensive data in each risk dimension, and determine the risk analysis result of the customer.

[0036] In this embodiment, the risk dimensions are various factors that affect the risk status of the customer, including repayment ability, credit history, consumption behavior, etc. Each risk dimension reflects the risk characteristics of the customer in a certain aspect. The risk level is to classify the customer into different risk levels according to the risk status of the customer, including low risk, medium risk, high risk, etc.

[0037] For example, based on business needs and data characteristics, determine the risk dimensions that need to be evaluated, calculate the risk score for each risk dimension, and divide customers into different risk levels based on the score. The risk level of each risk dimension is integrated to form an overall risk analysis result for the customer.

[0038] Step S20, based on the risk analysis result, calculate the customer's comprehensive credit score and generate a risk assessment report.

[0039] In this embodiment, the credit score is an indicator for quantitatively assessing the credit status of a customer. It is calculated based on the risk analysis results and the risk level of the customer's behavior in each risk dimension and the credit comprehensive data. The higher the credit score, the better the customer's credit status. The risk assessment report includes each risk item of the customer and the corresponding credit score.

[0040] Optionally, step S20 includes: Step S21, calculating the comprehensive credit score of the customer according to the weights of the risk dimensions.

[0041] In this embodiment, the weight of the risk dimension is the weight assigned according to the degree of influence of different risk dimensions on credit assessment, reflecting the importance of each dimension in credit scoring. The credit score is a value calculated based on the preset scoring criteria and the weight of the risk dimension, which is used to measure the credit status of the customer.

[0042] As an optional implementation method, the weight of each risk dimension is determined according to its importance in credit assessment, the risk level of each risk dimension is converted into a corresponding numerical value, multiplied by the corresponding weight to obtain the weighted risk level, and the weighted risk levels of all risk dimensions are added together to determine the customer's comprehensive credit score.

[0043] Exemplarily, the total credit score of the customer is calculated according to the weight of each risk dimension, and the calculation formula is credit score = Σ(risk level value * risk dimension weight).

[0044] Step S22, filling the risk level of each risk dimension and the comprehensive credit score of the customer into a risk assessment report template to generate the risk assessment report.

[0045] In this embodiment, the risk assessment report template is a pre-designed document format used to organize and record various risk information of customers, including risk dimensions, risk levels, comprehensive credit scores, etc.

[0046] Optionally, a risk assessment report template is designed based on business needs. The risk assessment report template includes the customer's basic information, the risk level of each risk dimension, the comprehensive credit score, etc.

[0047] Exemplarily, the collected customer risk information and credit scores are filled in one by one according to the format and fields of the risk assessment report template to generate a risk assessment report.

[0048] Step S30, based on the risk assessment report, a comparison is performed with the comprehensive credit score according to a preset score threshold to generate a lease approval result.

[0049] In this embodiment, the preset scoring threshold is a score limit set in advance in the leasing approval process to determine whether the customer's credit level meets the leasing conditions. The leasing approval result is a conclusion on whether the customer meets the leasing conditions based on the comparison result of the risk assessment report and the preset scoring threshold.

[0050] Optionally, a scoring threshold is set based on factors such as risk policy, characteristics of the leased vehicle, and market environment.

[0051] Optionally, a mapping relationship between risk items in the risk assessment report and decision rules is established, and a decision matrix is ​​designed to map the score of each risk item with the corresponding decision rule. The decision matrix is ​​a two-dimensional table, in which a row represents a risk item, a column represents different score ranges, and each cell contains the decision rule corresponding to the score range.

[0052] For example, for each risk item, a different score range is set. For the risk item of credit history, a score range of 1-10 is set, where 10 points represent the lowest risk and 1 point represents the highest risk. According to the score range, the following decision rules are set: a score of 9-10 points represents a good credit record and no additional review is required; a score of 6-8 points represents an average credit record and further examination of the cause and frequency of overdue payments is required; a score of 3-5 points represents a poor credit record and a detailed review is required and additional guarantees or deposits may be required; a score of 1-2 points represents an extremely poor credit record and the rental application is directly rejected.

[0053] As an optional implementation, a decision matrix is ​​used to make a comprehensive judgment based on the evaluation results of multiple risk items. The evaluation results of each risk item are weighted and summed according to the importance of the risk item to obtain a comprehensive score. The comprehensive score is compared with a preset score threshold to determine whether to approve the lease application. Based on the matching results of the rules and data, if the comprehensive score reaches or exceeds the score threshold, the lease application is approved; otherwise, the application is rejected.

[0054] Optionally, step S30 includes: Step S31, comparing the risk level of each risk dimension and the comprehensive credit score of the customer in the risk assessment report with the score threshold in the decision rule.

[0055] Step S32: if the comprehensive credit score is less than the score threshold, a rental approval result is generated to reject the vehicle rental request.

[0056] Step S33, if the comprehensive credit score is greater than or equal to the score threshold, the risk level of each risk dimension is compared with the corresponding risk level threshold in the decision rule, and for at least one risk assessment report whose risk level exceeds the risk level threshold, a rental approval result is generated to reject the rental vehicle request.

[0057] Optionally, if the comprehensive credit score is greater than or equal to the score threshold, and the risk level of each risk dimension does not exceed the risk level threshold, the rental approval result is generated to approve the rental vehicle request.

[0058] The present embodiment provides a vehicle rental approval method. The present embodiment firstly integrates the multi-dimensional data of the customer and performs analysis based on the risk analysis model to preliminarily evaluate the customer's credit risk level, thereby enhancing the ability to identify and prevent customer risks. By generating a standardized risk assessment report, the consistency of the approval process is improved. Through preset decision rules, the risk assessment report is automatically approved without manual intervention, thereby improving the efficiency of approval.

[0059] Based on Example 1, Example 2 of this application proposes a vehicle rental approval method, referring to Figure 2 , before step S10, including: Step S40: sending a request for collecting information to the customer according to the customer's request for renting a vehicle.

[0060] Before providing rental vehicle services to customers, we legally collect the necessary information to assess the customer's rental qualifications and clearly inform the customer of the information required and the purpose of the information by sending a request to collect information.

[0061] In this embodiment, the rental vehicle request is a request from a customer to rent a certain vehicle. The collection information request is a request issued to the customer to request the customer to provide necessary information for rental qualification assessment.

[0062] As an optional implementation, upon receiving a request from a customer to rent a vehicle, a request message for collecting information is sent to the customer.

[0063] As another optional implementation, upon receiving a vehicle rental request from a customer, a form for collecting information is sent to the customer, requiring the customer to upload relevant documents.

[0064] For example, after receiving a request from a customer to rent a vehicle, the information is sent to the customer via SMS, email, or in-APP message, clearly informing the customer of the type of information to be collected, its purpose, and measures to protect the customer's privacy.

[0065] Step S50: If the customer's consent information for requesting information collection is received, the customer's behavior data and credit comprehensive data are collected to evaluate the customer's rental qualifications.

[0066] As an optional implementation method, after receiving the customer's consent information for information collection request, the information collection process is initiated to obtain the user's behavioral data and comprehensive credit data through a third-party data provider.

[0067] For example, customer data is queried from a variety of third-party data sources to collect information such as the customer's personal credit, legal information, Internet usage behavior, mobile phone usage status, etc., which can be used to evaluate the customer's economic status, credit status, and payment ability.

[0068] This embodiment provides a vehicle rental approval method. This embodiment first sends an information collection request to the customer, clearly informing the customer what information is needed and the purpose of the information, thereby avoiding legal risks. Through clear requests, the customer can be guided to provide necessary information, thereby avoiding missing or repeated information collection and improving the efficiency of information collection. By collecting the customer's behavioral data and comprehensive credit data, the customer's rental qualifications can be more comprehensively evaluated.

[0069] Based on the first embodiment, the third embodiment of the present application proposes a vehicle rental approval method, referring to Figure 3 , before step S10, including: Step S60, collect historical customer behavior and credit comprehensive data and corresponding risk results, perform data cleaning and preprocessing operations, and input them into the risk analysis model for training.

[0070] Collect historical customer behavior and comprehensive credit data as well as the corresponding risk results, and perform data cleaning and preprocessing operations to ensure the accuracy of the data input into the model, so that the risk analysis model can better learn the relationship between customer behavior and credit risk during the training process, thereby more accurately evaluating the leasing qualifications of new customers in subsequent practical applications.

[0071] In this embodiment, the risk result is based on the historical customer behavior and credit comprehensive data, and the customer risk level or risk score is obtained according to the historical data records. Data cleaning refers to checking the historical customer behavior and credit comprehensive data, correcting errors, deleting duplicate data, processing missing values, etc. to ensure the accuracy of the data.

[0072] Optionally, step S60 includes: Step S61, checking the repeated values ​​and missing values ​​in the historical customer's behavior and credit comprehensive data, and performing filling, interpolation and / or deletion processing.

[0073] As an optional implementation method, traverse the historical customer behavior and credit comprehensive data, find missing values ​​and duplicate values, use interpolation methods to estimate missing values ​​in time series data, use statistical values ​​such as mean, median, mode, etc. to fill missing values, and directly delete duplicate values.

[0074] Exemplarily, check the data records one by one, identify and delete identical records, and for missing numeric data, estimate and fill the missing values ​​based on the mean or median of the field in other records. For missing categorical data, find the most common value of the field to fill the missing values. If the proportion of missing values ​​is too high, affecting the integrity and reliability of the data, choose to delete these fields or records containing missing values. For missing values ​​in time series data, use linear interpolation methods to estimate and fill the missing values.

[0075] Step S62, standardizing the historical customer behavior and credit comprehensive data to unify the format of the data.

[0076] Exemplarily, a statistical method is used to unify the dimensions of the data. For numerical data, the data is standardized by calculating the mean and standard deviation of each field, then subtracting the mean from each value and dividing it by the standard deviation.

[0077] Step S63, constructing training data and verification data for the analysis model based on the processed historical customer behavior and credit comprehensive data, as well as the corresponding annotation information.

[0078] Optionally, in the historical customer behavior and credit comprehensive data, a risk result field is added for each customer, and the corresponding risk result is filled in for annotation.

[0079] Exemplarily, a random sampling method is used to randomly select a certain proportion of records from the annotated historical customer behavior and credit comprehensive data as training data, and the remaining records are used as verification data.

[0080] Step S64: Based on the training data, train the risk analysis model through a machine learning algorithm, and verify the training result of the analysis model based on the verification data.

[0081] In this embodiment, the machine learning algorithm is an algorithm used to train the model, including logistic regression, decision tree, random forest, support vector machine, etc.

[0082] Exemplarily, a machine learning algorithm is selected based on the problem type and data characteristics, the model is trained using training data, and the algorithm parameters are adjusted to optimize model performance, the model performance is evaluated using validation data, and the model parameters are adjusted based on the validation results, and the training and validation process is repeated for iterative optimization.

[0083] Step S70, monitoring the performance indicators of the risk analysis model and evaluating the performance of the model.

[0084] In this embodiment, the performance indicators are various quantitative indicators for measuring the performance of the model, including accuracy, recall rate, F1 score, etc., which reflect the ability of the model in identifying positive and negative classes, as well as the stability of the model.

[0085] As an optional implementation method, a monitoring cycle is set to regularly calculate and monitor the performance indicators of the model, and the changing trends of the performance indicators are displayed through visualization tools. A benchmark performance level is set as a reference standard for the model performance, and the monitored performance indicators are compared with the benchmark performance to generate a performance evaluation report.

[0086] Step S80, adjusting the parameters and structure of the model according to the evaluation results, so that the model can accurately analyze the risk status of the customer.

[0087] As an optional implementation, the parameters of the model are fine-tuned according to the performance evaluation report, the structure of the model is adjusted after the parameters are adjusted, the adjusted model is retrained and verified, the adjusted model is redeployed to the actual business scenario, its performance indicators continue to be monitored, and iterative optimization is performed based on the evaluation results.

[0088] This embodiment provides a vehicle rental approval method. This embodiment first enhances the integrity and accuracy of the data by removing duplicate values ​​and filling missing values, thereby improving the training efficiency of the machine learning model. Regularly monitoring the performance indicators of the model can timely discover fluctuations or declines in model performance, ensure the stability of the model in practical applications, more accurately analyze the customer's risk status, and further improve the efficiency of risk analysis.

[0089] Based on the first embodiment, the fourth embodiment of the present application proposes a vehicle rental approval method, referring to Figure 4 , after step S30, comprising: Step S90: Send the detailed information of the rental approval result to the customer.

[0090] For example, the leasing approval result is sent to the customer via communication methods such as email, text message, and APP push.

[0091] Step S100: If the rental approval result is approval of the vehicle rental request, the vehicle corresponding to the rental approval result is monitored in real time based on the Internet of Things technology.

[0092] In this embodiment, the Internet of Things technology is a huge network formed by combining information sensing devices with the Internet, which connects things to each other, exchanges information and communicates, so as to achieve intelligent identification, positioning, tracking, monitoring and management of vehicles. The information sensing devices include radio frequency identification, infrared sensors, global positioning systems, laser scanners and other devices.

[0093] As an optional implementation method, after the customer is approved to rent a vehicle, the location, speed, driving status and other information of the vehicle are collected in real time through the Internet of Things devices installed on the vehicle.

[0094] Step S110, if it is detected that the vehicle triggers the risk warning rule, the warning information is sent to the vehicle management personnel so that the vehicle management personnel can perform further risk warning operations.

[0095] In this embodiment, the risk warning rules are pre-set rules or conditions for identifying potential risks. When the vehicle status or behavior monitored by the Internet of Things meets these rules, the warning mechanism will be triggered.

[0096] Optionally, vehicle state thresholds and abnormal behavior rules are set, including vehicle speed thresholds, driving state abnormal behavior rules, etc.

[0097] For example, when it is detected that a vehicle triggers an event such as speeding, abnormal parking, deviation from a predetermined route, etc., an early warning message containing the specific location of the vehicle and the type of triggering rule is generated and sent to the vehicle management end so that the vehicle management personnel can respond immediately.

[0098] Optionally, based on the type of warning information triggered by the vehicle, historical processing measures for this type of event are sent to the vehicle management personnel so that the vehicle management personnel can make a quick decision.

[0099] This embodiment provides a vehicle rental approval method. This embodiment first sends the approval result to the customer in real time to ensure that the customer can know the result of the rental approval in time, uses the Internet of Things technology to monitor the vehicles that have been approved for rental in real time to ensure the safety of the vehicles, and when it is detected that the vehicle triggers the risk warning rule, the vehicle management personnel are quickly notified so that timely and effective measures can be taken to reduce the possibility of accidents or mitigate the impact of accidents.

[0100] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the vehicle leasing approval method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0101] The present application provides a vehicle rental approval device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle rental approval method in the above-mentioned embodiment 1.

[0102] Reference below Figure 5, which shows a schematic diagram of the structure of a vehicle rental approval device suitable for implementing the embodiment of the present application. The vehicle rental approval device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The vehicle rental approval device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0103] like Figure 5 As shown, the vehicle rental approval device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle rental approval device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle rental approval device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle rental approval device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0104] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0105] The vehicle rental approval device provided by the present application adopts the vehicle rental approval method in the above embodiment, which can solve the technical problem of how to improve the efficiency of vehicle rental approval. Compared with the prior art, the beneficial effects of the vehicle rental approval device provided by the present application are the same as the beneficial effects of the vehicle rental approval method provided by the above embodiment, and the other technical features in the vehicle rental approval device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0106] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0108] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle rental approval method in the above-mentioned embodiment.

[0109] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0110] The computer-readable storage medium may be included in the vehicle rental approval device; or may exist independently without being assembled into the vehicle rental approval device.

[0111] The computer-readable storage medium carries one or more programs, and when the one or more programs are executed by the vehicle rental approval device, the vehicle rental approval device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0112] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0114] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle rental approval method, and can solve the technical problem of how to improve the efficiency of vehicle rental approval. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the vehicle rental approval method provided in the above-mentioned embodiment, and will not be repeated here.

[0115] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle leasing approval method, characterized in that: The method includes: Based on the customer's behavior and credit comprehensive data, the risk analysis results of the customer are determined by analyzing through machine learning algorithms; Based on the risk analysis results, calculate the customer's comprehensive credit score and generate a risk assessment report; Based on the risk assessment report, a comparison is made with the comprehensive credit score according to a preset score threshold to generate a lease approval result.

2. The vehicle rental approval method according to claim 1, characterized in that: Before the step of analyzing the customer's behavior and credit comprehensive data through a machine learning algorithm to determine the risk analysis result of the customer, the step includes: Sending a request for collecting information to the customer according to the customer's request for leasing a vehicle; If the customer's consent information for requesting information collection is received, the customer's behavioral data and comprehensive credit data are collected to evaluate the customer's rental qualifications.

3. The vehicle rental approval method according to claim 1, characterized in that: Before the step of analyzing the customer's behavior and credit comprehensive data through a machine learning algorithm to determine the risk analysis result of the customer, the step includes: Collect historical customer behavior and credit comprehensive data and corresponding risk results for data cleaning and preprocessing, and input them into the risk analysis model for training; Monitoring the performance indicators of the risk analysis model and evaluating the performance of the model; The parameters and structure of the model are adjusted according to the results of the evaluation so that the model can accurately analyze the risk status of the customer.

4. The vehicle rental approval method according to claim 3, characterized in that: The steps of collecting historical customer behavior and credit comprehensive data and corresponding risk results, performing data cleaning and preprocessing operations, and inputting into the risk analysis model for training include: Checking duplicate values ​​and missing values ​​in the historical customer's behavior and credit comprehensive data, and performing filling, interpolation and / or deletion processing; Standardize the historical customer behavior and credit comprehensive data and unify the format of the data; Constructing training data and verification data for the analysis model based on the processed historical customer behavior and credit comprehensive data and corresponding annotation information; Based on the training data, the risk analysis model is trained by a machine learning algorithm, and the training result of the analysis model is verified based on the verification data.

5. The vehicle rental approval method according to claim 1, characterized in that: The step of analyzing the customer's behavior and credit comprehensive data through a machine learning algorithm to determine the customer's risk analysis result includes: Clean the collected comprehensive behavior and credit data of the customers, and fill, interpolate and / or delete duplicate values ​​and missing values; Based on the risk analysis model, analyzing the customer's behavior and credit comprehensive data to determine the customer's risk status; According to the risk status, the risk level of the customer's behavior and credit comprehensive data in each risk dimension is calculated to determine the risk analysis result of the customer.

6. The vehicle rental approval method according to claim 1, characterized in that: The step of calculating the customer's comprehensive credit score and generating a risk assessment report based on the risk analysis result includes: Calculating the comprehensive credit score of the customer according to the weights of the risk dimensions; Fill the risk level of each risk dimension of the customer and the comprehensive credit score into the risk assessment report template to generate the risk assessment report.

7. The vehicle rental approval method according to claim 1, characterized in that: The step of generating a lease approval result based on the risk assessment report and comparing the risk assessment report with the comprehensive credit score according to a preset score threshold comprises: Comparing the risk level and the comprehensive credit score of each risk dimension of the customer in the risk assessment report with the score threshold in the decision rule; If the comprehensive credit score is less than the score threshold, a rental approval result is generated to reject the rental vehicle request; If the comprehensive credit score is greater than or equal to the score threshold, the risk level of each risk dimension is compared with the corresponding risk level threshold in the decision rule, and for at least one risk assessment report whose risk level exceeds the risk level threshold, a rental approval result is generated to reject the request to rent a vehicle.

8. The vehicle rental approval method according to claim 1, characterized in that: After the step of generating a lease approval result by comparing the risk assessment report with the comprehensive credit score according to a preset score threshold, the method further comprises: Sending detailed information of the lease approval result to the customer; If the rental approval result is approval of the rental vehicle request, real-time monitoring of the vehicle corresponding to the rental approval result based on the Internet of Things technology; If it is detected that the vehicle triggers a risk warning rule, a warning message is sent to the vehicle management personnel so that the vehicle management personnel can perform further risk warning operations.

9. A vehicle rental approval device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle rental approval method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle rental approval method according to any one of claims 1 to 8 are implemented.

Images