WO2021042905A1

WO2021042905A1 - Vehicle information processing method and apparatus, and computer device and storage medium

Info

Publication number: WO2021042905A1
Application number: PCT/CN2020/104806
Authority: WO
Inventors: 施奕明; 虎晨光; 杨镭; 张超亚; 付晓
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2019-09-03
Filing date: 2020-07-27
Publication date: 2021-03-11
Also published as: CN110751567A

Abstract

A vehicle information processing method, relating to the field of big data, comprising: receiving vehicle information sent by a terminal, the vehicle information carrying a user identifier (202); extracting a driving route and an accident position corresponding to the user identifier from a database (204); extracting a geographic position corresponding to a monitoring position stored in a third-party public credit platform from the driving route, the monitoring position being a position where the accident rate is higher than a preset value determined according to an accident image photographed by a traffic signal probe (206); determining whether the accident position is overlapped with the geographic position or not, and if yes, obtaining a user claim settlement record corresponding to the user identifier (208); and inputting the user claim settlement record into a driving risk model to obtain a vehicle guaranteed value corresponding to the vehicle information, and returning the vehicle guaranteed value to the terminal (210).

Description

Vehicle information processing method, device, computer equipment and storage medium

Cross-references to related applications

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on September 3, 2019, the application number is 201910827757.0, and the application title is "Vehicle Information Processing Methods, Devices, Computer Equipment, and Storage Media", the entire contents of which are incorporated by reference Incorporated in this application.

Technical field

This application relates to the field of big data technology, in particular to a vehicle information processing method, device, computer equipment and storage medium.

Background technique

When the server recommends product information, it usually obtains the guaranteed value of the vehicle by analyzing the user's vehicle information, and then further recommends product information based on the obtained guaranteed value.

However, the inventor realizes that only analyzing vehicle information is easily affected by external factors, making the obtained guaranteed value calculation error or low accuracy rate, resulting in a low success rate of product information recommendation, and triggering the server to respond to invalid information. Reduced server computing speed and processing performance.

Summary of the invention

According to various embodiments disclosed in the present application, a vehicle information processing method, device, computer device, and storage medium are provided.

A vehicle information processing method, including:

Receiving vehicle information sent by the terminal, where the vehicle information carries a user identifier;

Extracting the driving route and accident location corresponding to the user identifier from the database;

Extracting a geographic location corresponding to a monitoring location stored in a third-party public trust platform from the driving route, where the monitoring location is a location where the accident rate determined according to the accident image taken by the traffic signal probe is higher than a preset value;

Determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier; and

The user's claim settlement record is input into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and the guaranteed value of the vehicle is returned to the terminal.

A vehicle information processing device, including:

The instruction receiving module is used to receive vehicle information sent by the terminal, where the vehicle information carries a user ID;

The driving record acquisition module is used to extract the driving route and the accident location corresponding to the user identifier from the database;

The geographic location acquisition module is used to extract the geographic location corresponding to the monitored location stored in the third-party public trust platform from the driving route, where the monitored location is determined based on the accident image taken by the traffic signal probe and the accident rate is higher than The position of the preset value;

A claim settlement record acquisition module, configured to determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier; and

The guaranteed value generating module inputs the user claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and returns the guaranteed value of the vehicle to the terminal.

A computer device, including a memory and one or more processors, the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the one or more processors execute The following steps:

One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:

The vehicle information processing method, device, computer equipment and storage medium. The server extracts the vehicle information from the driving route and accident location, and then compares the accident location with the monitored location on the driving route. When the accident location overlaps with the monitored location, pass Analyze the user's claim records to generate the guaranteed value of the vehicle, not only screen the user's accident location to avoid inaccurate user claim records due to external causes, but also use the driving risk model to horizontally summarize the screened user's driving behavior. It also summarizes the user's driving behavior vertically to increase the accuracy of the guaranteed value of the vehicle, so as to increase the success rate of product recommendation, avoid the server from responding to invalid information, and improve the server's computing speed and processing performance.

The details of one or more embodiments of the present application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the description, drawings and claims.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative work, other drawings can be obtained from these drawings.

Fig. 1 is an application scenario diagram of a vehicle information processing method according to one or more embodiments.

Fig. 2 is a schematic flowchart of a vehicle information processing method according to one or more embodiments.

Fig. 3 is a schematic flowchart of a method for generating a driving risk model according to one or more embodiments.

Fig. 4 is a schematic flowchart of the steps of generating a driving risk model according to another or more embodiments.

FIG. 5 is a schematic flowchart of the steps of generating the estimated driving risk value according to another or more embodiments.

Fig. 6 is a structural block diagram of a vehicle information processing device according to one or more embodiments.

Figure 7 is a block diagram of a computer device according to one or more embodiments.

detailed description

In order to make the technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

The vehicle information processing method provided in this application can be applied to the application environment as shown in FIG. 1. The terminal 102 communicates with the server 104 through a network, and the server 104 communicates with the third-party public trust platform 106 through another network. The terminal 102 sends the vehicle information carrying the user identification to the server 104. The server 104 receives the vehicle information, and extracts the driving route and the accident location corresponding to the user identification from the database; the server 104 extracts the driving route from the third-party public trust platform The geographic location corresponding to the monitored location stored in 106. The monitored location is a location where the accident rate determined based on the accident image taken by the traffic signal probe is higher than the preset value; the server 104 determines whether the accident location overlaps with the geographic location, and if so, the server 104 obtains the user claim settlement record corresponding to the user identification; the server 104 inputs the user claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and returns the guaranteed value of the vehicle to the terminal 102. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, and portable smart devices. Both the server 104 and the third-party public trust platform 106 can use independent servers or a server cluster composed of multiple servers. to fulfill.

In one of the embodiments, as shown in FIG. 2, a vehicle information processing method is provided. Taking the method applied to the server in FIG. 1 as an example for description, the method includes the following steps:

Step 202: Receive vehicle information sent by a terminal, where the vehicle information carries a user identifier.

In this embodiment, the server receives the vehicle information sent by the terminal. The vehicle information carries the user identification. Vehicle information is used to indicate the status of the user's vehicle, which can include vehicle identification and corresponding user identification, as well as vehicle identification, type identification, energy identification, and user identification.

Step 204: Extract the driving route and the accident location corresponding to the user identifier from the database.

In this embodiment, the server extracts the driving route and the accident location corresponding to the user identifier from the database. The database can be set on the server or on another server that is in communication connection with the server. In this embodiment, the database is set on the server. The database stores the driving route of each user and the location of the accident. The driving route is a route generated based on the user's historical driving behavior. The accident location is the geographic location where the user has the accident. The database updates the driving route and accident location of each user in real time according to the claims or insurance records of each user.

Step 206: Extract the geographic location corresponding to the monitored location stored in the third-party public trust platform from the driving route, where the monitored location is determined based on the accident image taken by the traffic signal probe and the accident rate is higher than a preset value position.

In this embodiment, the server extracts the geographic location corresponding to the monitored location stored in the third-party public trust platform from the driving route. The monitoring location is the location where the accident rate is higher than the preset value determined according to the accident image taken by the traffic signal probe, and the preset value is determined according to factors such as road surface and weather. The traffic signal probe uploads the captured road images to the third-party public trust platform. The third-party public trust platform checks the road images, screens out the accident images, and determines the accident rate based on the accident images. The third-party public trust platform sets the accident rate higher than expected. The setting position is set as the monitoring position. The server can compare the address of the monitored location stored in the third-party public trust platform with the address of the driving route one by one to determine the geographic location corresponding to the monitored location on the driving route; the server can also compare the longitude and latitude of the monitored location and the longitude and latitude of the driving route To determine and extract the geographic location on the driving route.

Step 208: Determine whether the accident location overlaps the geographic location, and if so, obtain a user claim settlement record corresponding to the user identifier.

In this embodiment, the server determines whether the accident location overlaps with the geographic location, and if so, the server obtains the user claim settlement record corresponding to the user identification. By comparing the location of the accident with the geographic location, the server can investigate the user's driving behavior and reduce the impact of other non-objective factors on the claims record.

In this embodiment, the user's claims record may include various types of claims data such as the number of violations, the number of claims, the amount of claims, the number of insurance exposures, etc. of the user within a predetermined historical period. The user's claim record may also include the user's driving years and vehicle service life. And other data information. For example, the user's claim record may be "In 2016, the number of violations of the user whose user ID is '00001' is 1, the number of claims is 0, the amount of claims is 0 yuan, and the number of insurances is 1"; user's claim record It can be a user with a user ID of '00001' and driving experience for 2 years. In 2016, the number of violations is 1, the number of claims is 0, the amount of claims is 0 yuan, and the number of insurances is 1"; the user's claim record is OK It is a user whose user ID is '00001', has a driving experience of 2 years, a vehicle service life of 3 years, the number of violations in 2016 is 1, the number of claims is 0, the amount of claims is 0 yuan, and the number of accidents is 1; In 2017, the number of violations was 0, the number of claims was 0, the amount of claims was 0 yuan, and the number of accidents was 1". The server may obtain the user's claim settlement record from the server's claim settlement record database according to the user identification, or may obtain the user's user claim settlement record from other servers via the network.

Step 210: Input the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and return the guaranteed value of the vehicle to the terminal.

In this embodiment, the driving risk model is obtained by analyzing the sample claims records of the sample persons, and it is the number of violations, the number of claims, the amount of claims, the number of insurance exposures and the sample guarantees that have occurred for people with different classification labels. The value is analyzed and constructed, which can be a sample claim record, a relationship model corresponding to the guaranteed value and the classification label, or a function and guarantee calculated based on the number of violations, the number of claims, the amount of claims, and the number of risks in the sample claims record Correspondence model of value and classification label.

In this embodiment, the server may input the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and return the guaranteed value of the vehicle to the terminal. The guaranteed value of the vehicle is used to characterize the value corresponding to the vehicle information. It can correspond to money, such as the premium or the amount of insurance for the vehicle, or it can correspond to the item. The server inputs the user's claim records into the driving risk model, and can first obtain the user's classification label through the driving risk model, and then obtain the vehicle guarantee value of the vehicle information through the functional relationship in the driving risk model; the server can also first obtain the user's information through the driving risk model The classification label, and then obtain the user's estimated driving risk value within the estimated time according to the classification label, and obtain the vehicle guarantee value of the vehicle information according to the estimated driving risk value. After the server sends the guaranteed value of the vehicle to the terminal, it can also push information to the terminal according to the guaranteed value of the vehicle, or receive response information to the recommended information corresponding to the guaranteed value of the vehicle, and send it to the terminal.

In the above vehicle information processing method, the vehicle information is extracted from the driving route and the accident location, and then the accident location is compared with the monitoring location on the driving route. When the accident location overlaps the monitoring location, the user's claim settlement record is analyzed to generate The guaranteed value of the vehicle not only screens the user’s accident location to avoid inaccurate user claims records due to external causes, but also uses the driving risk model to summarize the screened user’s driving behavior horizontally and vertically. , Increase the accuracy of the guaranteed value of the vehicle, so as to improve the success rate of product recommendation, avoid the server from responding to invalid information, and improve the server's computing speed and processing performance.

In another embodiment, as shown in FIG. 3, the method for generating a driving risk model includes the following steps:

Step 302: Obtain the classification label of the sample personnel, the driving years, the sample claim settlement record within the preset period, and the sample guaranteed value.

In this embodiment, the server obtains the classification label of the sample personnel, the driving years, the sample claim settlement record within the preset period, and the sample guaranteed value. The classification label can be set by the system or the user, and can be set according to the occupation or other information of the sample personnel. For example, the classification label can be classified according to the level of knowledge, professional characteristics, job position, workplace status, and salary thickness. "Collar, white-collar, pink-collar, gold-collar", the classification label can also be the occupation of the sample personnel. The driving years can be the number of years the sample person actually drives, or the number of years the sample person has a driver's license. The sample claims record can include the number of violations, the number of claims, the amount of claims, and the number of insurance exposures of the sample personnel in multiple insurance periods. The insurance period can be calculated on a monthly or quarterly or yearly basis. The sample guarantee value is used to characterize the value of the sample car information.

Step 304: Summarize the sample claim settlement records according to the classification label and the driving years, and construct a distribution diagram of the relationship between the historical driving risk value of the sample and the number of the sample.

In this embodiment, the server summarizes the sample claim settlement records according to the classification label and driving years, and constructs a distribution map of the relationship between the historical driving risk value of the sample and the number of the sample. The server can extract the corresponding sample claims records according to the classification tags, and extract the corresponding sample historical driving risk values from the sample claims records, and then count the number of samples and driving years corresponding to the historical driving risk values of each sample, and then calculate the number of samples , The driving years and the historical driving risk value of the sample are drawn into a relationship distribution diagram in a three-dimensional coordinate system, where the x-axis can refer to the sample number, the y-axis can refer to the historical driving risk value of the sample, and the z-axis can refer to the driving years. The server can also draw a relationship distribution map in a four-dimensional coordinate system, where the x-axis can refer to the number of samples, the y-axis can refer to the historical driving risk value of the sample, the z-axis can refer to the driving years, and the w-axis can refer to the classification label.

Step 306: Construct a mapping relationship corresponding to the sample claim record, the sample guarantee value, the driving years and the classification label according to the relationship distribution map, to obtain a driving risk model.

In this embodiment, the server may construct a mapping relationship corresponding to the sample claims record, the sample guarantee value, the driving years and the classification label according to the relationship distribution map, to obtain a driving risk model. The server can obtain the threshold of the proportion of claims records, and obtain the sample historical driving risk range corresponding to the classification labels and driving years from the relationship distribution diagram according to the threshold of the proportion of claims records, and then construct the classification labels, driving years, sample guaranteed value and sample historical driving The mapping relationship corresponding to the risk range obtains the driving risk model. The threshold for the proportion of claims settlement records is the maximum proportion of all the sample persons whose historical driving risk value is within the range of the historical driving risk of the sample in the total number of persons in the sample, and generally ranges from 70% to 95%.

In the above-mentioned vehicle information processing method, the classification label, driving years and the corresponding mapping relationship between the sample historical driving risk range and the sample driving behavior are obtained through the classification label of the sample person, the driving age and the sample claim record in the preset period. Make a horizontal comparison with the user's driving behavior to increase the accuracy of the vehicle guarantee value.

In one of the embodiments, the sample claim records are summarized according to the classification labels and the driving years to construct a distribution map of the relationship between the historical driving risk value of the sample and the number of people in the sample, including the following steps: The sample claim settlement records are classified; the sample historical driving risk values of the sample persons are sequentially extracted from the classified sample claims records according to the driving years; the number of sample persons corresponding to the sample historical driving risk values is counted; according to The relationship between the number of the sample and the historical driving risk value of the sample is drawn with respect to the relationship distribution diagram for the driving years.

In this embodiment, the server classifies sample claim settlement records according to each classification label, and classifies sample claim settlement records of sample persons belonging to the same classification label into one category. The server extracts the sample historical driving risk value of each sample person from the classified sample claim settlement record based on the classification label, specifically, extracting the sample historical driving risk value of each sample person in turn according to the driving years. The server counts the sample number corresponding to the historical driving risk value of each sample, and the sample number corresponds to the classification label and driving years. The server can draw a relationship distribution map for driving years in a two-dimensional coordinate system according to the sample number and the sample historical driving risk value, where the x-axis can refer to the sample historical driving risk value, and the y-axis can refer to the sample number. Each relationship distribution map corresponds to a driving age and a classification label. Under the same classification label, the server generates a relationship distribution map for each driving year.

In the above-mentioned vehicle information processing method, a distribution diagram of the relationship between the historical driving risk value of the sample and the number of the sample is generated according to the classification label, driving years, and sample claim records, which simply and clearly reflects the probability of the sample person's risk under each classification label, which is convenient for follow-up and quick Summarize the risk range of the sample historical driving.

In one of the embodiments, as shown in FIG. 4, the mapping relationship between the sample claims record, the sample guaranteed value, the driving years and the classification label is constructed according to the relationship distribution map to obtain the driving risk model, which has the following steps:

Step 402: Calculate the average value and standard deviation of each of the relationship distribution graphs.

In this embodiment, when the relationship distribution diagram is a relationship diagram in a two-dimensional coordinate system, and the x-axis refers to the number of samples, and the y-axis refers to the historical driving risk value of the sample, the server can calculate the sample history in each relationship distribution diagram. The average value and standard deviation of the driving risk value. When the relationship distribution diagram is a relationship diagram in a three-dimensional coordinate system, and the x-axis refers to the sample number, the y-axis refers to the historical driving risk value of the sample, and the z-axis refers to the driving years, the server can calculate the relationship distribution based on the driving years The average value and standard deviation corresponding to the historical driving risk value of the sample in the figure.

Step 404: Obtain a sample historical driving risk range corresponding to the relationship distribution map according to the average value and the standard deviation.

In this embodiment, the server may use the 3σ criterion to determine the sample historical driving risk range based on the calculated average value and standard deviation of the sample historical driving risk value. The 3σ principle is: the probability of a value distribution in (μ-σ, μ+σ) is 0.6827; the probability of a value distribution in (μ-2σ, μ+2σ) is 0.9545; the value distribution is in (μ-3σ, μ+ The probability in 3σ) is 0.9973, where μ is the mean and σ is the standard deviation. The sample historical driving risk range can be (μ-3σ,μ+3σ), (μ-2σ,μ+2σ) or (μ-σ,μ+σ).

Step 406: Establish a mapping relationship between the sample historical driving risk range and the driving years and the classification label.

In this embodiment, the server establishes the mapping relationship between the sample historical driving risk range, the driving age and the classification label. The server can establish a mapping relationship between classification label-driving years-sample historical driving risk range. The server can obtain the mapped classification label through the driving years and driving risk value, and the mapped historical driving risk range of the sample can be obtained through the classification labels and driving years.

Step 408: Train the established mapping relationship and the sample guarantee value to construct a driving risk model.

In this embodiment, the server trains the established mapping relationship and the sample guarantee value to construct a driving risk model. The server can extract the sample historical driving risk range corresponding to the classification label and driving years from the mapping relationship, find the corresponding relationship between the historical driving risk range of each sample and the classification label and driving years, and find out the historical driving risk range of each sample The corresponding relationship between the guaranteed value of the sample is used to construct a driving risk model through the corresponding relationship. The corresponding relationship between the sample historical driving risk range and the classification label and driving years can be a one-to-one correspondence between the sample historical driving risk range and the classification label and driving years, or it can be a summary of the sample historical driving risk range, and then according to The summarized content, the corresponding relationship between the summarized content and the classification label and driving years is obtained. The server can input the user's historical driving risk value into the driving risk model, so that the driving risk model can determine the classification label through the corresponding relationship, and then output the guaranteed value of the vehicle.

In another embodiment, as shown in FIG. 5, inputting the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information includes the following steps:

Step 502: Extract the user's historical driving risk value from the user's claim settlement record.

In this embodiment, the server may extract the user's historical driving risk value from the user's claim settlement record.

The user’s historical driving risk value can be the number of violations, the number of claims, the amount of claims, and the number of accidents of the user in a predetermined historical period, or a value summarized based on the number of violations, the number of claims, the amount of claims, and the number of accidents of the user in the predetermined historical period. , This value can increase with the increase of the number of violations, the number of claims, the amount of claims, and the number of accidents. It can be obtained by superimposing the data of each driving claim or converting through a specific formula. For example, the user's claim record may be "a user whose user ID is '00001' and has been driving for 2 years. In 2016, the number of violations was 1, the number of claims was 0, the amount of claims was 0 yuan, and the number of insurances was 1" The historical driving risk value extracted by the server can be "the number of violations is 1, the number of claims is 0, the amount of claims is 0 yuan, and the number of risks is 1", or "the historical driving risk value is 2".

Step 504: Analyze the historical driving risk value of the user to obtain a classification label of the user.

In this embodiment, the server may analyze the user's historical driving risk value through the driving risk model, thereby obtaining and outputting the user's classification label through the driving risk model.

Step 506: Obtain a sample historical driving risk range according to the classification label of the user.

In this embodiment, the server obtains the sample historical driving risk range according to the user's classification label.

Specifically, the server may obtain the user's sample historical driving risk range for each driving year according to the user's classification label, and the server may also select the corresponding sample historical driving risk range according to the driving year in the user's claim settlement record. For example, if the user's driving years is M years, the server can obtain the sample historical driving risk ranges for the Mth year and the M+1th year according to the classification label and driving years.

Step 508: Obtain the user's estimated driving risk value of the user according to the user's historical driving risk value and the sample historical driving risk range.

In this embodiment, the server may obtain the user's estimated driving risk value of the user according to the user's historical driving risk value and the sample historical driving risk range. For example, if the user’s driving years is M years, the server can compare and analyze the sample historical driving risk range of the M-th year with the user’s historical driving risk value to obtain the user’s historical driving risk value and the maximum value and/or the sample’s historical driving risk range. The functional relationship between the minimum values. Further, the server can obtain the user's estimated driving risk value of the corresponding user according to the sample historical driving risk range of the M+1 year according to the functional relationship.

In this embodiment, the estimated driving risk value may be the number of violations, the number of claims, the amount of claims, and the number of insurance risks that the user estimates that occur within the estimated time, or it may be based on the user's estimated number of violations within the estimated time. The value generated by the number of times, the number of claims, the amount of claims, and the number of accidents. This value can increase with the increase of the number of violations, the number of claims, the amount of claims, and the number of accidents. It can be the superimposition of the data of each driving claim or conversion through a specific formula Obtained, and the influence coefficient of the number of violations, the number of claims, the amount of claims, and the number of insurance exposures from small to large can be the number of violations>the number of claims≥the amount of claims>the number of insurances.

Step 510: Obtain the vehicle guarantee value of the vehicle information according to the estimated driving risk value of the user.

In this embodiment, the server may obtain the vehicle guarantee value corresponding to the vehicle information according to the user's estimated driving risk value and vehicle information, and may also obtain the vehicle guarantee value corresponding to the vehicle information according to the user's estimated driving risk value.

In the above vehicle information processing method, the user's estimated driving risk value is obtained through the user's historical driving risk value and the sample historical driving risk range, so that the final estimated driving risk value is closer to the user's actual driving risk value, and the guaranteed value of the vehicle is increased Accuracy.

In one of the embodiments, after judging whether the accident location and the geographic location overlap, the method further includes the following steps: when the judgment is no, extract the number of user claims from the user claims record; obtain a preset claim threshold; When the number of user settlements is not greater than the preset claim settlement threshold, inputting the user's claim settlement record into the driving risk model is executed to obtain the guaranteed value of the vehicle corresponding to the vehicle information.

Specifically, when the server determines that it is no, the server may extract the number of user settlements from the user's claim settlement record. The server obtains the preset claim settlement threshold, and compares and judges the number of user settlements with the preset claim settlement threshold. When the number of user settlements is not greater than the preset claim settlement threshold, the server may input the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information. When the number of user claims is greater than the preset claim threshold, the server may generate a high-risk indicator, and input the user's claim record into the driving risk model to obtain the initial vehicle guarantee value corresponding to the vehicle information. In this embodiment, the server also adjusts the initial vehicle guarantee value according to the high-risk indicator.

In the above-mentioned vehicle information processing method, the user claim records are screened twice according to the number of user claims, not only extracts the user claim records, but also identifies the user claim records of high-risk vehicles and generates the corresponding vehicle guaranteed value, ensuring that under different circumstances The vehicle guarantees the accuracy of the value in order to improve the success rate of product recommendation.

It should be understood that although the various steps in the flowcharts of FIGS. 2-5 are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in Figures 2-5 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. These sub-steps or stages The execution order of is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

In one of the embodiments, as shown in FIG. 6, a vehicle information processing device is provided, including: an instruction receiving module 602, a driving record acquisition module 604, a geographic location acquisition module 606, a claims record acquisition module 608, and guaranteed value generation Module 610, where:

The instruction receiving module 602 is configured to receive vehicle information sent by the terminal, and the vehicle information carries a user identifier.

The driving record acquisition module 604 is configured to extract the driving route and the accident location corresponding to the user identifier from the database.

The geographic location acquisition module 606 is configured to extract the geographic location corresponding to the monitored location stored in the third-party public trust platform from the driving route, where the monitored location is determined based on the accident image taken by the traffic signal probe with a high accident rate In the position of the preset value.

The claim settlement record obtaining module 608 is configured to determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier.

The guaranteed value generating module 610 inputs the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and returns the guaranteed value of the vehicle to the terminal.

In one of the embodiments, the guaranteed value generation module 610 includes a sample information acquisition unit, a distribution map construction unit, and a risk model construction unit, where:

The sample information acquisition unit is used to acquire the classification labels, driving years of the sample personnel, and sample claim settlement records within a preset period and sample guaranteed value.

The distribution map construction unit is used to summarize the sample claim settlement records according to the classification label and the driving years, and construct a distribution map of the relationship between the historical driving risk value of the sample and the number of the sample.

The model construction unit is configured to construct the mapping relationship between the sample claim record, the sample guarantee value, the driving years and the classification label according to the relationship distribution map, to obtain a driving risk model.

In one of the embodiments, the guaranteed value generation module 610 includes a record classification unit, a risk value extraction unit, a sample population statistics unit, and a relationship distribution map drawing unit, wherein:

The record classification unit is used to classify the sample claim settlement record according to each classification label.

The risk value extraction unit is configured to sequentially extract the sample historical driving risk values of the sample persons from the sample claim settlement records after classification according to the driving years.

The sample population statistical unit is used to count the sample population corresponding to the historical driving risk value of the sample.

The relationship distribution diagram drawing unit is configured to draw a relationship distribution diagram for the driving years according to the sample number of people and the sample historical driving risk value.

In one of the embodiments, the guaranteed value generation module 610 includes a distribution map calculation unit, a driving risk range extraction unit, a mapping relationship establishment unit, and a risk model construction unit, wherein:

The distribution diagram calculation unit is used to calculate the average value and standard deviation of each of the relationship distribution diagrams.

The driving risk range extraction unit is configured to obtain the sample historical driving risk range corresponding to the relationship distribution map according to the average value and the standard deviation.

The mapping relationship establishment unit is used to establish the historical driving risk range of the sample, the mapping relationship corresponding to the driving years and the classification label.

The risk model construction unit is used to train the established mapping relationship and the sample guarantee value to construct a driving risk model.

In one of the embodiments, the guaranteed value generating module 610 includes a user driving risk value extraction unit, a user driving risk value analysis unit, a sample historical driving risk range acquisition unit, a user estimated driving risk value generating unit, and a guaranteed value generating unit, where :

The user driving risk value extraction unit is used to extract the user's historical driving risk value from the user's claim settlement record.

The user driving risk value analysis unit is used to analyze the historical driving risk value of the user to obtain the classification label of the user.

The sample historical driving risk range acquisition unit is configured to obtain the sample historical driving risk range according to the classification label of the user.

The user's estimated driving risk value generating unit is configured to obtain the user's estimated driving risk value of the user according to the user's historical driving risk value and the sample historical driving risk range.

The guaranteed value generating unit is configured to obtain the vehicle guaranteed value of the vehicle information according to the estimated driving risk value of the user.

In one of the embodiments, the claim settlement record acquisition module includes a claim settlement frequency extraction unit, a claim settlement threshold acquisition unit, and an execution unit, wherein:

The number of claims settlement unit is configured to extract the number of user settlements from the user's claim settlement record when the determination is no;

A claim settlement threshold obtaining unit, configured to obtain a preset claim settlement threshold;

The execution unit is configured to execute input of the user's claim settlement record into the driving risk model to obtain the vehicle guarantee value corresponding to the vehicle information when the number of user settlements is not greater than the preset claim settlement threshold.

For the specific limitation of the vehicle information processing device, please refer to the above limitation of the vehicle information processing method, which will not be repeated here. Each module in the above-mentioned vehicle information processing device may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

In one of the embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 7. The computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile or volatile storage medium and internal memory. The non-volatile or volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer equipment is used to store vehicle information processing data, such as sample claims records, premium generation rules, and so on. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instruction is executed by the processor to realize a vehicle information processing method.

Those skilled in the art can understand that the structure shown in FIG. 7 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

A computer device includes a memory and one or more processors, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the one or more processors perform the following steps: Vehicle information, the vehicle information carries the user identification; the driving route and the accident location corresponding to the user identification are extracted from the database; the geographic location corresponding to the monitoring position stored in the third-party public trust platform is extracted from the driving route Location, the monitoring location is the location where the accident rate is higher than the preset value determined based on the accident image taken by the traffic signal probe; it is determined whether the accident location overlaps with the geographic location, and if so, the corresponding user identification is obtained The user claim settlement record; and input the user claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and return the guaranteed value of the vehicle to the terminal.

In one of the embodiments, when the processor executes the steps of the method for generating a driving risk model when the computer readable instructions are executed, it is also used to: obtain the classification label of the sample person, driving years, sample claim settlement records and samples within a preset period Guaranteed value; summarizing the sample claim records according to the classification label and the driving years, constructing a distribution diagram of the relationship between the historical driving risk value of the sample and the number of the sample; and constructing the sample claim records according to the relationship distribution diagram, The guarantee value of the sample, the mapping relationship between the driving years and the classification label are used to obtain a driving risk model.

In one of the embodiments, when the processor executes the computer-readable instructions, the step of summarizing the sample claim records according to the classification label and the driving years, and constructing the relationship distribution map between the sample historical driving risk value and the sample number It is also used to: classify the sample claim settlement records according to each classification label; extract the sample historical driving risk values of the sample persons in sequence according to the driving years from the sample claim settlement records after classification; The sample population corresponding to the sample historical driving risk value; and drawing a relationship distribution diagram for the driving years according to the sample population and the sample historical driving risk value.

In one of the embodiments, when the processor executes the computer-readable instructions, it implements the construction of the sample claim record, the sample guaranteed value, the mapping relationship between the driving years and the classification label according to the relationship distribution graph, to obtain During the steps of the driving risk model, it is also used to: calculate the average value and standard deviation of each of the relationship distribution diagrams; obtain the sample historical driving risk range corresponding to the relationship distribution diagram according to the average value and the standard deviation; Establishing the sample historical driving risk range, the mapping relationship corresponding to the driving years and the classification label; and training the established mapping relationship and the sample guaranteed value to construct a driving risk model.

In one of the embodiments, when the processor executes the computer-readable instruction to realize the step of inputting the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, it is also used to: from the user Extract the user’s historical driving risk value from the claims record; analyze the user’s historical driving risk value to obtain the user’s classification label; obtain the sample historical driving risk range according to the user’s classification label; according to the user history The driving risk value and the sample historical driving risk range obtain the user's estimated driving risk value of the user; and the vehicle guarantee value of the vehicle information is obtained according to the user's estimated driving risk value.

In one of the embodiments, after the processor executes the step of determining whether the accident location overlaps the geographic location when the computer readable instruction is executed, the processor is further configured to: when the determination is no, extract from the user claims record The number of user claims; obtaining a preset claim threshold; and when the number of user claims is not greater than the preset claim threshold, execute inputting the user claim record into the driving risk model to obtain the vehicle guarantee value corresponding to the vehicle information .

One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps: receiving vehicle information sent by the terminal, so The vehicle information carries the user identification; the driving route and the accident location corresponding to the user identification are extracted from the database; the geographic location corresponding to the monitoring position stored in the third-party public trust platform is extracted from the driving route, the The monitoring location is the location where the accident occurrence rate is higher than the preset value determined according to the accident image taken by the traffic signal probe; it is determined whether the accident location overlaps the geographic location, and if so, the user claim settlement record corresponding to the user identification is obtained And input the user's claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and return the guaranteed value of the vehicle to the terminal.

Wherein, the computer-readable storage medium may be non-volatile or volatile.

In one of the embodiments, when the computer-readable instructions are executed by the processor to implement the steps of the method for generating a driving risk model, they are also used to: obtain the classification label of the sample person, the driving years, the sample claim settlement record and the sample within the preset period Guaranteed value; summarizing the sample claim settlement records according to the classification label and the driving years, constructing the relationship distribution diagram between the sample historical driving risk value and the sample population; and constructing the sample claim settlement records according to the relationship distribution diagram, The guarantee value of the sample, the mapping relationship between the driving years and the classification label are used to obtain a driving risk model.

In one of the embodiments, when the computer-readable instructions are executed by the processor, the sample claims records can be summarized according to the classification label and the driving years, and the relationship distribution map between the sample historical driving risk value and the sample population is constructed. The step is also used to: classify the sample claim settlement records according to each classification label; extract the sample historical driving risk values of the sample persons in sequence according to the driving years from the sample claim settlement records after classification; The sample population corresponding to the sample historical driving risk value; and drawing a relationship distribution diagram for the driving years according to the sample population and the sample historical driving risk value.

In one of the embodiments, when the computer-readable instructions are executed by the processor, the mapping relationship between the sample claims record, the sample guaranteed value, the driving years and the classification label is constructed according to the relationship distribution map, The step of obtaining the driving risk model is also used to: calculate the average value and standard deviation of each of the relationship distribution diagrams; obtain the sample historical driving risk range corresponding to the relationship distribution diagram according to the average value and the standard deviation; Establishing the sample historical driving risk range, the mapping relationship corresponding to the driving years and the classification label; and training the established mapping relationship and the sample guaranteed value to construct a driving risk model.

In one of the embodiments, when the computer-readable instruction is executed by the processor, the step of inputting the user's claim record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information is also used to: Extract the user’s historical driving risk value from the claims record; analyze the user’s historical driving risk value to obtain the user’s classification label; obtain the sample historical driving risk range according to the user’s classification label; according to the user history The driving risk value and the sample historical driving risk range obtain the user's estimated driving risk value of the user; and the vehicle guarantee value of the vehicle information is obtained according to the user's estimated driving risk value.

In one of the embodiments, when the computer-readable instruction is executed by the processor, after the step of judging whether the accident location and the geographic location overlap, it is further used to: when the judgment is no, from the user claims record Extract the number of user claims; obtain a preset claim threshold; and when the number of user claims is not greater than the preset claim threshold, execute inputting the user's claim record into the driving risk model to obtain a vehicle guarantee corresponding to the vehicle information value.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage. In the medium, when the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered as the range described in this specification.

The above-mentioned embodiments only express several implementation manners of the present application, and their description is relatively specific and detailed, but they should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims

A vehicle information processing method, including:

Receiving vehicle information sent by the terminal, where the vehicle information carries a user identifier;

Extracting the driving route and accident location corresponding to the user identifier from the database;

Extracting a geographic location corresponding to a monitoring location stored in a third-party public trust platform from the driving route, where the monitoring location is a location where the accident rate determined according to the accident image taken by the traffic signal probe is higher than a preset value;

Determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier; and

The user's claim settlement record is input into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and the guaranteed value of the vehicle is returned to the terminal.
The method according to claim 1, wherein the method for generating the driving risk model comprises:

Obtain the classification label, driving years of the sample, the sample claim record within the preset period, and the sample guaranteed value;

Summarize the sample claims records according to the classification label and the driving years, and construct a distribution diagram of the relationship between the historical driving risk value of the sample and the number of people in the sample; and

According to the relationship distribution map, a mapping relationship corresponding to the sample claim record, the sample guarantee value, the driving years and the classification label is constructed to obtain a driving risk model.
3. The method according to claim 2, wherein the summarizing the sample claim records according to the classification label and the driving years, and constructing a distribution map of the relationship between the historical driving risk value of the sample and the number of the sample includes:

Classify the sample claims record according to each classification label;

Extracting the sample historical driving risk values of the sample persons in sequence from the sample claim settlement records after classification according to the driving years;

Count the number of sample persons corresponding to the historical driving risk value of the sample; and

Drawing a relationship distribution map for the driving years according to the sample number and the sample historical driving risk value.
2. The method according to claim 2, wherein the construction of the sample claim record, the sample guaranteed value, the mapping relationship between the driving years and the classification label according to the relationship distribution map, to obtain a driving risk model ,include:

Calculate the average value and standard deviation of each of the relationship distribution diagrams;

Obtaining, according to the average value and the standard deviation, a sample historical driving risk range corresponding to the relationship distribution map;

Establishing the sample historical driving risk range and the mapping relationship corresponding to the driving years and the classification label; and

Training the established mapping relationship and the sample guarantee value to construct a driving risk model.
The method according to claim 1, wherein said inputting said user's claim settlement record into a driving risk model to obtain a guaranteed value of a vehicle corresponding to said vehicle information comprises:

Extracting the user's historical driving risk value from the user's claim settlement record;

Analyzing the historical driving risk value of the user to obtain the classification label of the user;

Obtaining a sample historical driving risk range according to the classification label of the user;

Obtain the user's estimated driving risk value of the user according to the user's historical driving risk value and the sample historical driving risk range; and

Obtain the vehicle guarantee value of the vehicle information according to the estimated driving risk value of the user.
The method according to claim 1, wherein after determining whether the accident location and the geographic location overlap, the method further comprises:

When the judgment is no, extract the number of user claims settlement from the user claims settlement record;

Obtain a preset claim threshold; and

When the number of times the user claims settlement is not greater than the preset claim settlement threshold, execute inputting the user claims settlement record into the driving risk model to obtain the vehicle guarantee value corresponding to the vehicle information.
A vehicle information processing device, including:

The instruction receiving module is used to receive vehicle information sent by the terminal, where the vehicle information carries a user ID;

The driving record acquisition module is used to extract the driving route and the accident location corresponding to the user identifier from the database;

The geographic location acquisition module is used to extract the geographic location corresponding to the monitored location stored in the third-party public trust platform from the driving route, where the monitored location is determined based on the accident image taken by the traffic signal probe and the accident rate is higher than The position of the preset value;

A claim settlement record acquisition module, configured to determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier; and

The guaranteed value generating module inputs the user claim settlement record into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and returns the guaranteed value of the vehicle to the terminal.
8. The device according to claim 7, wherein the guaranteed value generating module comprises:

The sample information acquisition unit is used to acquire the classification label, driving years, sample claim settlement records within the preset period, and sample guaranteed value of the sample personnel;

A distribution map construction unit for summarizing the sample claim records according to the classification label and the driving years, and constructing a distribution map of the relationship between the historical driving risk value of the sample and the number of the sample; and

The risk model construction unit is configured to construct the mapping relationship between the sample claim record, the sample guarantee value, the driving years and the classification label according to the relationship distribution map, to obtain a driving risk model.
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more processors The processor performs the following steps:

Receiving vehicle information sent by the terminal, where the vehicle information carries a user identifier;

Extracting the driving route and accident location corresponding to the user identifier from the database;

Extracting the geographic location corresponding to the monitored location stored in the third-party public trust platform from the driving route, where the monitored location is a location where the accident rate determined according to the accident image taken by the traffic signal probe is higher than a preset value;

Determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier; and

The user's claim settlement record is input into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and the guaranteed value of the vehicle is returned to the terminal.
The computer device according to claim 9, wherein the method for generating the driving risk model implemented when the processor executes the computer-readable instruction comprises:

Obtain the classification label, driving years of the sample, the sample claim record within the preset period, and the sample guaranteed value;

Summarize the sample claims records according to the classification label and the driving years, and construct a distribution diagram of the relationship between the historical driving risk value of the sample and the number of people in the sample; and

According to the relationship distribution map, a mapping relationship corresponding to the sample claim record, the sample guarantee value, the driving years and the classification label is constructed to obtain a driving risk model.
10. The computer device according to claim 10, wherein the processor implements the summary of the sample claims record according to the classification label and the driving years when the processor executes the computer readable instruction to construct a sample The distribution diagram of the relationship between the historical driving risk value and the sample population, including:

Classify the sample claims record according to each classification label;

Extracting the sample historical driving risk values of the sample persons in sequence from the sample claim settlement records after classification according to the driving years;

Count the number of sample persons corresponding to the historical driving risk value of the sample; and

Drawing a relationship distribution map for the driving years according to the sample number and the sample historical driving risk value.
The computer device according to claim 10, wherein the construction of the sample claims record, the sample guaranteed value, the sample claim record, the sample guarantee value, and the The mapping relationship between driving years and the classification label to obtain a driving risk model includes:

Calculate the average value and standard deviation of each of the relationship distribution diagrams;

Obtaining, according to the average value and the standard deviation, a sample historical driving risk range corresponding to the relationship distribution map;

Establishing the sample historical driving risk range and the mapping relationship corresponding to the driving years and the classification label; and

Training the established mapping relationship and the sample guarantee value to construct a driving risk model.
The computer device according to claim 9, wherein the input of the user claim record into the driving risk model, which is implemented when the processor executes the computer-readable instruction, obtains a vehicle guarantee corresponding to the vehicle information Value, including:

Extracting the user's historical driving risk value from the user's claim settlement record;

Analyzing the historical driving risk value of the user to obtain the classification label of the user;

Obtaining a sample historical driving risk range according to the classification label of the user;

Obtain the user's estimated driving risk value of the user according to the user's historical driving risk value and the sample historical driving risk range; and

Obtain the vehicle guarantee value of the vehicle information according to the estimated driving risk value of the user.
The computer device according to claim 9, wherein after said determining whether the location of the accident and the geographic location are overlapped by the processor when the processor executes the computer-readable instructions, the method further comprises:

When the judgment is no, extract the number of user claims settlement from the user claims settlement record;

Obtain a preset claim threshold; and

When the number of times the user claims settlement is not greater than the preset claim settlement threshold, execute inputting the user claims settlement record into the driving risk model to obtain the vehicle guarantee value corresponding to the vehicle information.
One or more computer-readable storage media storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, cause the one or more processors to perform the following steps:

Receiving vehicle information sent by the terminal, where the vehicle information carries a user identifier;

Extracting the driving route and accident location corresponding to the user identifier from the database;

Extracting a geographic location corresponding to a monitoring location stored in a third-party public trust platform from the driving route, where the monitoring location is a location where the accident rate determined according to the accident image taken by the traffic signal probe is higher than a preset value;

Determine whether the accident location overlaps the geographic location, and if so, obtain the user claim settlement record corresponding to the user identifier; and

The user's claim settlement record is input into the driving risk model to obtain the guaranteed value of the vehicle corresponding to the vehicle information, and the guaranteed value of the vehicle is returned to the terminal.
15. The storage medium according to claim 15, wherein the method for generating the driving risk model implemented when the computer-readable instructions are executed by the processor comprises:

Obtain the classification label, driving years of the sample, the sample claim record within the preset period, and the sample guaranteed value;

Summarize the sample claims records according to the classification label and the driving years, and construct a distribution diagram of the relationship between the historical driving risk value of the sample and the number of people in the sample; and

According to the relationship distribution map, a mapping relationship corresponding to the sample claim record, the sample guarantee value, the driving years and the classification label is constructed to obtain a driving risk model.
The storage medium according to claim 16, wherein the sample claims record is summarized according to the classification label and the driving years, which is implemented when the computer-readable instruction is executed by the processor, and constructs The distribution diagram of the relationship between the sample historical driving risk value and the sample population, including:

Classify the sample claims record according to each classification label;

Extracting the sample historical driving risk values of the sample persons in sequence from the sample claim settlement records after classification according to the driving years;

Count the number of sample persons corresponding to the historical driving risk value of the sample; and

Drawing a relationship distribution map for the driving years according to the sample number and the sample historical driving risk value.
The storage medium according to claim 16, wherein the construction of the sample claim record, the sample guaranteed value, and the sample claim record according to the relationship distribution diagram, which is implemented when the computer-readable instruction is executed by the processor The mapping relationship between the driving years and the classification labels is used to obtain a driving risk model, including:

Calculate the average value and standard deviation of each of the relationship distribution diagrams;

Obtaining, according to the average value and the standard deviation, a sample historical driving risk range corresponding to the relationship distribution map;

Establishing the sample historical driving risk range and the mapping relationship corresponding to the driving years and the classification label; and

Training the established mapping relationship and the sample guarantee value to construct a driving risk model.
The storage medium according to claim 15, wherein the input of the user claims record into the driving risk model is implemented when the computer-readable instructions are executed by the processor to obtain the vehicle corresponding to the vehicle information Guaranteed value, including:

Extracting the user's historical driving risk value from the user's claim settlement record;

Analyzing the historical driving risk value of the user to obtain the classification label of the user;

Obtaining a sample historical driving risk range according to the classification label of the user;

Obtain the user's estimated driving risk value of the user according to the user's historical driving risk value and the sample historical driving risk range; and

Obtain the vehicle guarantee value of the vehicle information according to the estimated driving risk value of the user.
The storage medium according to claim 15, wherein after the determining whether the accident location and the geographic location are overlapped when the computer-readable instructions are executed by the processor, the method further comprises:

When the judgment is no, extract the number of user claims settlement from the user claims settlement record;

Obtain a preset claim threshold; and

When the number of times the user claims settlement is not greater than the preset claim settlement threshold, execute inputting the user claims settlement record into the driving risk model to obtain the vehicle guarantee value corresponding to the vehicle information.