A method for identifying automobile anti-fraud risks and related equipment

Abstract

The embodiment of the present application belongs to the field of big data, and relates to a method for identifying automobile anti-fraud risks, including: pre-processing the acquired vehicle GPS data based on a preset algorithm to determine the target area; searching for the number of target vehicles in the target area, and judging the target area based on the number of vehicles, whether vehicles gather and whether there are preset abnormal places, wherein the abnormal places are places that do not meet the preset regulatory requirements; if vehicles gather and preset abnormal places exist in the target area, then according to the preset abnormal usage behavior habit table, the current abnormal usage behavior habits of the target vehicle are identified, and based on the current abnormal usage behavior habits of the target vehicle, the anti-fraud risk type of the target vehicle is judged. The present application also provides an automobile anti-fraud risk identification device, a computer device and a storage medium. The present application improves the recognition accuracy of anti-fraud risk identification.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to an automobile anti-fraud risk identification method and related equipment. Background Art

[0002] In the auto financing business, whether the main loan applicant's intention to buy a car is genuine and whether the car is used by the applicant is important factors affecting the post-loan asset recovery rate. The intention to buy a car is a personal subjective emotion, which is highly hidden and difficult to measure through data. Therefore, it brings great challenges to the post-loan asset management of auto financing.

[0003] The main forms of fraud faced by auto financing scenarios are: false intention to buy a car, using the name of car loan to cash out; real intention to buy a car, but being exploited by bad intermediaries, overestimating the car price, high loan amount, exceeding repayment ability, etc.; the main borrower's own qualifications are insufficient, borrowing the identity of others to act on his behalf, and later causing disputes over vehicle ownership, repayment responsibility, etc. At present, the market lacks effective monitoring methods and collection technologies for such fraud scenarios. After discovering customer fraud, no collection methods that are differentiated from conventional collection methods are adopted, resulting in a rise in bad debt rates. At the same time, the existing vehicle GPS data is messy and disorderly, and data processing is difficult, so it is difficult to meet monitoring needs. At present, most financial monitoring focuses on the pre-loan application stage, and the monitoring of vehicle behavior habits after the loan is relatively weak, resulting in a low accuracy rate in identifying vehicle anti-fraud risks. Summary of the invention

[0004] The purpose of the embodiment of the present application is to propose a method for identifying vehicle anti-fraud risks and related equipment to solve the problem of low accuracy in identifying vehicle anti-fraud risks.

[0005] In order to solve the above technical problems, the present application embodiment provides a method for identifying automobile anti-fraud risks, which adopts the following technical solutions:

[0006] Preprocess the acquired vehicle GPS data based on a preset algorithm to determine the target area;

[0007] Searching for the number of target vehicles in the target area, and judging whether vehicles gather in the target area and whether there is a preset abnormal place according to the number of vehicles, wherein the abnormal place is a place that does not meet the preset supervision requirements;

[0008] If vehicles gather in the target area and the preset abnormal place exists, the usage behavior habits of the corresponding target vehicles in the target area are monitored according to the preset abnormal usage behavior habits to determine the anti-fraud risk type of the target vehicle.

[0009] In order to solve the above technical problems, the embodiment of the present application also provides an automobile anti-fraud risk identification device, which adopts the following technical solution:

[0010] A preprocessing module, used to preprocess the acquired vehicle GPS data based on a preset algorithm to determine the target area;

[0011] A first judgment module is used to search for the number of target vehicles in the target area, and judge whether there is a gathering of vehicles in the target area and whether there is a preset abnormal place according to the number of vehicles, wherein the abnormal place is a place that does not meet the preset supervision requirements;

[0012] The identification module is used to identify the current abnormal usage behavior habits of the target vehicle according to the preset abnormal usage behavior habit table if vehicles gather in the target area and the preset abnormal place exists, and judge the anti-fraud risk type of the target vehicle based on the current abnormal usage behavior habits of the target vehicle.

[0013] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the automobile anti-fraud risk identification method provided in the above embodiment are implemented.

[0014] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the automobile anti-fraud risk identification method provided in the above embodiment are implemented.

[0015] Compared with the prior art, the embodiment of the present application has the following beneficial effects: the present application pre-processes the acquired vehicle GPS data based on a preset algorithm to determine the target area; searches for the number of target vehicles in the target area, and judges the target area based on the number of vehicles, whether vehicles gather and whether there are preset abnormal places, wherein the abnormal places are places that do not meet the preset regulatory requirements; if vehicles gather and there are preset abnormal places in the target area, the current abnormal use behavior habits of the target vehicle are identified according to the preset abnormal use behavior habit table, and the anti-fraud risk type of the target vehicle is judged based on the current abnormal use behavior habits of the target vehicle. In this way, the vehicle GPS data can be regionalized in combination with the preset algorithm to realize the vehicle retrieval and the retrieval of key suspicious objects in the target area. At the same time, the target vehicle use behavior habits of the target vehicles in the target area are monitored and judged in combination with vehicle gathering, preset abnormal places, and preset abnormal use behavior habits to realize the anti-fraud risk identification of the target vehicle. Then, the main borrower's willingness to buy a car and the use of the vehicle are measured, and the customer is warned whether there is fraudulent behavior, so as to improve the recognition accuracy of anti-fraud risk identification and reduce asset losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A flowchart of an embodiment of the automobile anti-fraud risk identification method according to the present application;

[0018] Figure 2 yes Figure 1 A flowchart of a specific implementation of step S101;

[0019] Figure 3 It is a kind of earth region division map provided by this application;

[0020] Figure 4 is Figure 3 Another earth region division map provided by this application based on the above;

[0021] Figure 5 yes Figure 1 A flowchart of a specific implementation of step S102;

[0022] Figure 6 yes Figure 1 A flowchart of a specific implementation of step S103;

[0023] Figure 7 yes Figure 6 A flowchart of a specific implementation of step S405;

[0024] Figure 8 is a flow chart of another embodiment of the automobile anti-fraud risk identification method according to the present application;

[0025] Fig. 9 It is a structural schematic diagram of an embodiment of an automobile anti-fraud risk identification device according to the present application;

[0026] Fig.10 yes Fig. 9 A schematic structural diagram of a specific implementation of the preprocessing module shown;

[0027] Fig.11 yes Fig. 9 A structural schematic diagram of a specific implementation of the first judgment module shown;

[0028] Fig.12 yes Fig. 9 A schematic structural diagram of a specific implementation of the identification module shown;

[0029] Fig.13 yes Fig.12 A schematic structural diagram of a specific implementation of the second determination unit is shown;

[0030] Fig.14 is a structural schematic diagram of another embodiment of the automobile anti-fraud risk identification device according to the present application;

[0031] Fig.15 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0033] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0035] refer to Figure 1 , shows a flow chart of an embodiment of the automobile anti-fraud risk identification method according to the present application. The automobile anti-fraud risk identification method comprises the following steps:

[0036] Step S101 , preprocessing the acquired vehicle GPS data based on a preset algorithm to determine a target area.

[0037] Among them, the above-mentioned preset algorithm can be a Geohash algorithm, which is an address encoding method that can encode the longitude and latitude data of a two-dimensional space into a character string. The above-mentioned vehicle GPS data can be a set of two-dimensional vector groups composed of longitude and latitude, which are used to locate the position of the vehicle. The above-mentioned target area can be obtained according to the area where the GPS data of each vehicle is distributed in the preprocessing result. The above-mentioned target area is an area that needs to be monitored for anti-fraud risks. The vehicle GPS data can be stored in a database of a big data system, or stored in a database of a data analysis system. Both the big data system and the data analysis system can be data systems provided by an authoritative organization.

[0038] Specifically, the vehicle GPS data itself is disorganized, so it is necessary to effectively process the vehicle GPS data, and to divide the area based on the preprocessing results of each vehicle GPS data, so as to determine the above target area.

[0039] Optional, such as Figure 2 As shown, step S101 includes:

[0040] Step S201, obtaining multiple vehicle GPS data, each vehicle GPS data is a set of longitude and latitude data.

[0041] In the embodiment of the present application, the main borrower's vehicle in the auto financing scenario is generally equipped with wireless or wired GPS according to the loan amount and customer credit status. The vehicle GPS data can be returned to the background in real time and saved in the background database. Each vehicle corresponds to a GPS data, which is of great significance to the vehicle's behavior habits. Therefore, multiple vehicle GPS data can be obtained from the background in real time.

[0042] Step S202, using a preset algorithm and a preset encoding method to encode each set of longitude and latitude data into a corresponding character string.

[0043] In the embodiment of the present application, the above preset encoding method is: according to the longitude range of 180 degrees east longitude to 180 degrees west longitude, the latitude range is 90 degrees south latitude to 90 degrees north latitude, the west longitude is set to negative, the south latitude is set to negative, so the longitude range on the earth is [-180, 180], and the latitude range is [-90, 90]. If the prime meridian and the equator are used as boundaries, the earth can be divided into 4 parts. If the latitude range [-90°, 0°) is represented by binary 0, (0°, 90°] is represented by binary 1, and the longitude range [-180°, 0°) is represented by binary 0, (0°, 180°] is represented by binary 1, then the earth can be divided into the following parts: Figure 3 The four parts are shown.

[0044] Of course, if we further subdivide it in the same way, Figure 3 The Earth is divided into four parts based on Figure 4 The portion shown.

[0045] After a series of divisions by the preset algorithm, the earth is finally divided into a rectangular area of ​​more than four parts.

[0046] Specifically, after the encoding method is determined, the preset algorithm can be used to convert each vehicle's GPS data into a corresponding character string according to the preset encoding method. At the same time, each character string can also represent the location of each vehicle.

[0047] Step S203, performing region segmentation processing on each character string to obtain a region segmentation processing result.

[0048] In the embodiment of the present application, after obtaining the character string corresponding to each vehicle's GPS data, the vehicle's position on the earth can be determined based on these character strings, and finally the region is divided according to the position distribution of each vehicle to obtain the distribution area of ​​each vehicle's position. When the positions of multiple vehicles are the same, these vehicles are distributed in the same area.

[0049] Step S204: determining a target area according to the area segmentation processing result and a preset risk tolerance level.

[0050] In an embodiment of the present application, the above-mentioned preset risk tolerance level can be set artificially, and the preset risk tolerance level can reflect the identification accuracy of anti-fraud risk. For example, if the preset risk tolerance level is low, it means that the identification accuracy of anti-fraud risk is high. If the preset risk tolerance level is high, it means that the identification accuracy of anti-fraud risk is low.

[0051] Specifically, after obtaining the distribution area of ​​each vehicle GPS in the earth, the final target area can be determined in combination with the preset risk tolerance. For example, the preset risk tolerance is set to 3 levels, each level corresponds to a different area, such as the first level corresponds to 1 / 3 of the area, the second level corresponds to 2 / 3 of the area, and the third level corresponds to the entire area. At this time, if the vehicle GPS data of 100 vehicles are processed and divided into regions, 90 vehicles are distributed in the same area or a very close area, and the other 10 vehicles are distributed in a farther area, then the three levels can divide the distribution area of ​​the 100 vehicles into 1 / 3, 2 / 3, and 3 / 3 of the area. If the preset risk tolerance selected at this time is 2 levels, then 2 / 3 of the area of ​​the entire area where the GPS data of 100 vehicles are distributed can be selected as the target area, and the area with dense vehicle distribution is the center. Of course, the target area can be reduced or expanded in time according to the selected preset risk tolerance.

[0052] In the embodiment of the present application, a preset algorithm can be used to encode complex vehicle GPS data into a simple string in a preset encoding method, and the vehicle position can be segmented into regions according to the corresponding string, and the corresponding target region can be determined according to the preset risk tolerance, so that the target region can be determined simply and intuitively.

[0053] Step S102, searching the number of target vehicles in the target area, and judging the target area according to the number of vehicles, whether vehicles gather and whether there is a preset abnormal place.

[0054] In this embodiment, the target vehicle is a vehicle in the target area. There may be multiple target vehicles in the target area. The number of vehicles is the number of vehicles distributed in the target area. Among them, the abnormal place is a place that does not meet the preset regulatory requirements, such as a car resale store and a car mortgage store, and of course, it can also include a car repair shop. The preset abnormal place only represents the customized abnormality in this description, and does not refer to the real abnormality in practice.

[0055] Optional, such as Figure 5 As shown, step S102 includes:

[0056] Step S300, searching for the number of target vehicles in the target area.

[0057] Step S301, determining whether the number of vehicles meets the preset number of gathered vehicles in the target area.

[0058] Step S302: If the number of vehicles meets the preset number of gathered vehicles, it is determined that vehicles gather in the target area.

[0059] Step S303: If the number of vehicles does not meet the preset number of gathered vehicles, it is determined that no vehicles are gathered in the target area.

[0060] In the embodiment of the present application, the preset number of gathering vehicles can be manually set, and the preset number of gathering vehicles is used to determine whether the number of vehicles is gathered. The preset number of gathering vehicles can be set according to actual needs.

[0061] Specifically, when the number of vehicles in the target area is greater than or equal to the preset number of gathered vehicles, it means that the vehicle data meets the preset number of gathered vehicles, that is, vehicle gathering occurs in the target area; otherwise, it means that the number of vehicles does not meet the preset number of gathered vehicles, that is, no vehicle gathering occurs in the target area.

[0062] The above-mentioned step of judging whether there are preset abnormal places in the target area based on the number of vehicles may be: each landmark marked within the target area may be detected, and whether there are preset abnormal places may be judged based on the nature of the landmark. It should be noted that in addition to marking the vehicle position, the positions of various buildings, roads, stores, etc. are also marked within the target area. Therefore, if you want to detect whether there are preset abnormal places in the target area, you can determine it based on the names in the landmarks. For example, if AA car store, BB car mortgage store, etc. are marked in the target area, you can judge that there are preset abnormal places such as AA car store, BB car mortgage store, etc. in the target area. Of course, you can determine whether there are corresponding preset abnormal places based on the layout information of buildings, roads, and stores corresponding to the actual location of the target area in the authoritative system.

[0063] In an embodiment of the present application, it is possible to quickly determine whether vehicle gathering occurs in the target area by presetting the number of gathered vehicles, so as to determine whether there is automobile anti-fraud risk in the target area, thereby further improving the recognition accuracy of automobile anti-fraud risk identification.

[0064] Step S103, if vehicles gather in the target area and there are preset abnormal places, the current abnormal usage behavior habits of the target vehicles are identified according to the preset abnormal usage behavior habit table, and based on the current abnormal usage behavior habits of the target vehicles, the anti-fraud risk type of the target vehicles is determined.

[0065] In this embodiment, the above-mentioned preset abnormal usage behavior habit can be a preset abnormal usage behavior habit standard for judging the vehicle usage behavior habit. The number of preset abnormal usage behavior habits in the preset abnormal usage behavior habit table is at least one. The preset abnormal usage behavior habit table includes at least one or more of the following abnormal usage behaviors:

[0066] The vehicle's GPS signal disappears for a preset period of time;

[0067] The vehicle GPS signal stays in a preset abnormal area for more than a preset time. The preset abnormal area can be a non-working area, a non-residence area, and a non-domiciliary area.

[0068] The GPS signals of vehicles in the same area are aggregated;

[0069] After the loan is released, the vehicle GPS signal stays at the first GPS signal reporting point for more than the preset time;

[0070] The vehicle stays in a preset abnormal location for longer than the preset time;

[0071] Within the same registered residence area, the car loan application is processed at the same online store within the preset time, and the brand and type of the vehicle purchased are similar.

[0072] It should be noted that exceeding the preset time can be judged as long-term, and within the preset time can be judged as short-term.

[0073] Optional, such as Figure 6 As shown, step 103 includes:

[0074] Step S401, obtaining historical GPS data of the target vehicle.

[0075] In the embodiment of the present application, the above historical GPS data is the historical GPS data corresponding to the target vehicle in the target area. The historical GPS data may include user information, parking points, driving tracks, driving time and other information. When there are multiple target vehicles, the corresponding historical GPS data is also multiple, and one target vehicle corresponds to one historical GPS data.

[0076] Specifically, after determining that vehicles gather in the target area and there are preset abnormal places, it can be considered that there may be anti-fraud risk behaviors in the target area. However, whether there is anti-fraud risk behavior or not needs to be determined by judging the usage behavior habits of each vehicle in the target area, so it is necessary to obtain the historical GPS data of the target vehicle.

[0077] Step S402, analyzing historical GPS data to obtain the usage behavior habits of the target vehicle.

[0078] In an embodiment of the present application, specifically, after analyzing the historical GPS data of each target vehicle, the corresponding user information, historical parking point information, historical trajectory information, and corresponding historical time information can be obtained, and then the usage behavior habits of the target vehicle can be obtained based on this information.

[0079] Step S403, determining whether the usage behavior habit of the target vehicle conforms to one or more of the preset abnormal usage behavior habits.

[0080] In the embodiment of the present application, after the usage behavior habits of the target vehicle are obtained, they can be compared with the preset abnormal usage behavior habits, so as to determine whether the usage behavior habits of the target vehicle are abnormal. If the usage behavior habits of the target vehicle match one or more of the preset abnormal usage behavior habits, it means that the usage behavior habits of the target vehicle are abnormal.

[0081] Step S404: If yes, then the duration of the target vehicle being in the preset abnormal usage behavior habit and the number of types that meet the preset abnormal usage behavior habit are obtained.

[0082] In the embodiment of the present application, the above-mentioned duration is the length of time that the target vehicle is in a certain abnormal usage behavior habit.

[0083] Specifically, after determining that the target vehicle's usage behavior habits are abnormal, the duration of the target vehicle's abnormal usage behavior habits and the number of types of abnormal usage behavior habits that are simultaneously in place can be determined. For example, the target vehicle's usage behavior habits are that after the vehicle GPS signal disappears for more than a preset time, the vehicle GPS signal stays in a preset abnormal area for more than a preset time. Then it can be determined that the duration is long-term, and the number of types of preset abnormal usage behavior habits that the target vehicle meets is two.

[0084] Step S405, determining the anti-fraud risk type of the target vehicle according to the duration and the number of types.

[0085] In an embodiment of the present application, the historical GPS data of the target vehicle can be effectively combined to obtain the usage behavior habits of the target vehicle, and then determine whether the usage behavior habits of the target vehicle are abnormal, and further determine the anti-fraud risk type of the target vehicle, thereby improving the recognition accuracy of anti-fraud risk identification.

[0086] Optional, such as Figure 7 As shown, step S405 includes:

[0087] Step S501, determining whether the duration meets the preset time;

[0088] Step S502, if satisfied, determining the type category content of the type category corresponding to the type category number of the preset abnormal usage behavior habit;

[0089] Step S503, determining the anti-fraud risk type of the target vehicle based on the category content.

[0090] In the embodiment of the present application, the above-mentioned preset time is used to determine whether the duration is a long-term or short-term time condition. If the duration meets the preset time, it means that the duration is long-term. If the duration does not meet the preset time, it means that the duration is short-term.

[0091] Specifically, when it is determined that the target vehicle has been in use for a long period of time and satisfies one or more of the preset abnormal usage behavior habits, the anti-fraud risk type of the target vehicle can be determined based on the specific type and content of the preset abnormal usage behavior habits.

[0092] For example, if the target vehicle stays in a preset abnormal place for a long time and then the vehicle GPS signal disappears for a long time, there is a high probability that the target vehicle has been sold, and it is necessary to contact the main lender corresponding to the target vehicle by phone to confirm the anti-fraud behavior and preserve the evidence.

[0093] Another example: the target vehicle appears first, and after the loan is issued, the vehicle's GPS signal stays at the first GPS signal reporting point for a long time. Later, monitoring shows that within the same household registration area, a car loan application is processed in the same online store within a short period of time, and the brand and type of the purchased vehicles are similar. Then it is highly likely that the same person controls or packages multiple different main borrowers, and works with vehicle sales stores to concentrate on cashing out and defrauding loans.

[0094] In the embodiment of the present application, the anti-fraud risk type of the target vehicle can be further determined by the duration of the target vehicle being in abnormal usage behavior habits.

[0095] In the embodiment of the present application, the present application pre-processes the acquired vehicle GPS data based on a preset algorithm to determine the target area; search the number of target vehicles in the target area, and judge the target area based on the number of vehicles, whether vehicles gather and whether there are preset abnormal places, wherein the abnormal places are places that do not meet the preset regulatory requirements; if vehicles gather and preset abnormal places exist in the target area, the current abnormal use behavior habits of the target vehicle are identified according to the preset abnormal use behavior habit table, and the anti-fraud risk type of the target vehicle is judged based on the current abnormal use behavior habits of the target vehicle. In this way, the vehicle GPS data can be regionalized in combination with the preset algorithm to realize the vehicle retrieval and the retrieval of key suspicious objects in the target area. At the same time, the target vehicle use behavior habits of the target vehicle in the target area are monitored and judged in combination with vehicle gathering, preset abnormal places, and preset abnormal use behavior habits to realize the anti-fraud risk identification of the target vehicle. Then measure the main lender's willingness to buy a car and the use of the vehicle, and warn the customer whether there is fraudulent behavior, so as to improve the recognition accuracy of anti-fraud risk identification and reduce asset losses.

[0096] In some optional implementations of this embodiment, such as Figure 8 As shown, after step 103, the electronic device may further perform the following steps:

[0097] Step S601, determining whether the target user corresponding to the target vehicle with abnormal usage behavior habits is a user in arrears.

[0098] Step S602: If the target user is a user in arrears, the target user is determined to be a fraudulent user, and differentiated loss recovery measures are taken for the fraudulent user.

[0099] In the embodiment of the present application, after determining that the target vehicle has anti-fraud risk behavior, the corresponding fraudulent customer can be determined based on the relationship between the target vehicle and the owner. For confirmed fraudulent customers, the conventional method of first calling and then collecting on-site may miss the opportunity to collect, so differentiated collection and loss recovery measures must be taken: The specific loss recovery measures are as follows:

[0100] For confirmed fraud users, if the preset repayment period has not been exceeded and there is sufficient evidence to confirm the fraud, the contract will be terminated early according to the preset contract and the customer will be required to repay the outstanding balance in advance;

[0101] For confirmed fraud users, if the preset repayment period has been exceeded and they are in the regular collection sequence, the fraud users will be removed from the collection sequence and put into the fraud loss recovery queue, and on-site collection or asset preservation will be carried out;

[0102] For confirmed fraudulent users, we urge them to repay the full amount through preferential measures such as exemptions and reductions to avoid losing contact with customers after they repay the due amount.

[0103] This application monitors abnormal customer vehicle usage behavior and adopts differentiated loss recovery measures. It strengthens collection methods in accordance with the steps of early detection, early intervention, and strong collection to reduce asset losses.

[0104] This application involves the field of macroeconomics. The automobile anti-fraud risk identification method is an important indicator for macroeconomic research and analysis. It can determine whether a customer's automobile loan has an anti-fraud risk by analyzing the automobile usage behavior habits, so as to facilitate the management of the customer's automobile loan situation, evaluate the customer's willingness to buy a car, willingness to repay, and repayment ability, and reduce asset losses.

[0105] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0106] It should be understood that, although the steps in the flowchart of the accompanying drawings 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 otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0107] Further references Fig. 9 , as a response to the above Figure 1 The present application provides an embodiment of a vehicle anti-fraud risk identification device, and the vehicle anti-fraud risk identification device 700 embodiment is similar to Figure 1 Corresponding to the method embodiment shown, the automobile anti-fraud risk identification device 700 can be specifically applied to various electronic devices.

[0108] like Fig. 9 As shown, the automobile anti-fraud risk identification device 700 of this embodiment includes: a pre-processing module 701, a first judgment module 702 and an identification module 703. Among them:

[0109] The preprocessing module 701 is used to preprocess the acquired vehicle GPS data based on a preset algorithm to determine the target area.

[0110] Among them, the above-mentioned Geohash algorithm is an address encoding method that can encode the longitude and latitude data of a two-dimensional space into a character string. The above-mentioned vehicle GPS data can be a set of two-dimensional vector groups composed of longitude and latitude, which are used to locate the position of the vehicle. The above-mentioned target area can be obtained according to the area where the GPS data of each vehicle is distributed in the preprocessing result. The above-mentioned target area is the area that needs to be monitored for anti-fraud risks. The vehicle GPS data can be stored in the database of the big data system, or stored in the database of the data analysis system. Both the big data system and the data analysis system can be data systems provided by authoritative organizations.

[0111] Specifically, the vehicle GPS data itself is disorganized, so it is necessary to effectively process the vehicle GPS data, and to divide the area based on the preprocessing results of each vehicle GPS data, so as to determine the above target area.

[0112] Optional, such as Fig.10 As shown, the pre-processing module 701 includes:

[0113] The first acquisition unit 7011 is used to acquire multiple vehicle GPS data, each vehicle GPS data is a set of longitude and latitude data.

[0114] In the embodiment of the present application, the main borrower's vehicle in the auto financing scenario is generally equipped with wireless or wired GPS according to the loan amount and customer credit status. The vehicle GPS data can be returned to the background in real time and saved in the background database. Each vehicle corresponds to a GPS data, which is of great significance to the vehicle's behavior habits. Therefore, multiple vehicle GPS data can be obtained from the background in real time.

[0115] The encoding unit 7012 is used to encode each set of longitude and latitude data into a corresponding character string using a preset algorithm and a preset encoding method.

[0116] In the embodiment of the present application, the above preset encoding method is: according to the longitude range of 180 degrees east longitude to 180 degrees west longitude, the latitude range is 90 degrees south latitude to 90 degrees north latitude, the west longitude is set to negative, the south latitude is set to negative, so the longitude range on the earth is [-180, 180], and the latitude range is [-90, 90]. If the prime meridian and the equator are used as boundaries, the earth can be divided into 4 parts. If the latitude range [-90°, 0°) is represented by binary 0, (0°, 90°] is represented by binary 1, and the longitude range [-180°, 0°) is represented by binary 0, (0°, 180°] is represented by binary 1, then the earth can be divided into the following parts: Figure 3 The four parts are shown.

[0117] Of course, if we further subdivide it in the same way, Figure 3 The Earth is divided into four parts based on Figure 4 The portion shown.

[0118] After a series of divisions by the preset algorithm, the earth is finally divided into more than four rectangular areas.

[0119] Specifically, after the encoding method is determined, the preset algorithm can be used to convert each vehicle's GPS data into a corresponding character string according to the preset encoding method. At the same time, each character string can also represent the location of each vehicle.

[0120] The segmentation processing unit 7013 is used to perform region segmentation processing according to each character string to obtain a region segmentation processing result.

[0121] In the embodiment of the present application, after obtaining the character string corresponding to each vehicle's GPS data, the vehicle's position on the earth can be determined based on these character strings, and finally the region is divided according to the position distribution of each vehicle to obtain the distribution area of ​​each vehicle's position. When the positions of multiple vehicles are the same, these vehicles are distributed in the same area.

[0122] The first determining unit 7014 is used to determine the target area according to the area segmentation processing result and the preset risk tolerance level.

[0123] In an embodiment of the present application, the above-mentioned preset risk tolerance level can be set artificially, and the preset risk tolerance level can reflect the identification accuracy of anti-fraud risk. For example, if the preset risk tolerance level is low, it means that the identification accuracy of anti-fraud risk is high. If the preset risk tolerance level is high, it means that the identification accuracy of anti-fraud risk is low.

[0124] Specifically, after obtaining the distribution area of ​​each vehicle GPS in the earth, the final target area can be determined in combination with the preset risk tolerance. For example, the preset risk tolerance is set to 3 levels, each level corresponds to a different area, such as the first level corresponds to 1 / 3 of the area, the second level corresponds to 2 / 3 of the area, and the third level corresponds to the entire area. At this time, if the vehicle GPS data of 100 vehicles are processed and divided into regions, 90 vehicles are distributed in the same area or a very close area, and the other 10 vehicles are distributed in a farther area, then the three levels can divide the distribution area of ​​the 100 vehicles into 1 / 3, 2 / 3, and 3 / 3 of the area. If the preset risk tolerance selected at this time is 2 levels, then 2 / 3 of the area of ​​the entire area where the GPS data of 100 vehicles are distributed can be selected as the target area, and the area with dense vehicle distribution is the center. Of course, the target area can be reduced or expanded in time according to the selected preset risk tolerance.

[0125] The first judgment module 702 is used to search for the number of target vehicles in the target area, and judge whether there is a gathering of vehicles in the target area and whether there is a preset abnormal place according to the number of vehicles, wherein the abnormal place is a place that does not meet the preset supervision requirements.

[0126] In this embodiment, the target vehicle is a vehicle in the target area. There may be multiple target vehicles in the target area. The number of vehicles is the number of vehicles distributed in the target area. Among them, the abnormal place is a place that does not meet the preset regulatory requirements, such as a car resale store and a car mortgage store, and of course, it can also include a car repair shop. The preset abnormal place only represents the customized abnormality in this description, and does not refer to the real abnormality in practice.

[0127] Optional, such as Fig.11 As shown, the first judgment module 702 includes:

[0128] The search unit 7020 is used to search for the number of target vehicles in the target area.

[0129] The second judgment unit 7021 is used to judge whether the number of vehicles meets the preset number of gathered vehicles in the target area.

[0130] The third determination unit 7022 is used to determine that vehicles gather in the target area if the number of vehicles meets a preset number of gathered vehicles.

[0131] The fourth determination unit 7023 is used to determine that no vehicle gathering occurs in the target area if the number of vehicles does not meet a preset number of gathered vehicles.

[0132] In the embodiment of the present application, the preset number of gathering vehicles can be manually set, and the preset number of gathering vehicles is used to determine whether the number of vehicles is gathered. The preset number of gathering vehicles can be set according to actual needs.

[0133] Specifically, when the number of vehicles in the target area is greater than or equal to the preset number of gathered vehicles, it means that the vehicle data meets the preset number of gathered vehicles, that is, vehicle gathering occurs in the target area; otherwise, it means that the number of vehicles does not meet the preset number of gathered vehicles, that is, no vehicle gathering occurs in the target area.

[0134] The above-mentioned step of judging whether there are preset abnormal places in the target area based on the number of vehicles may be: each landmark marked within the target area may be detected, and whether there are preset abnormal places may be judged based on the nature of the landmark. It should be noted that in addition to marking the vehicle position, the positions of various buildings, roads, stores, etc. are also marked within the target area. Therefore, if you want to detect whether there are preset abnormal places in the target area, you can determine it based on the names in the landmarks. For example, if AA car store, BB car mortgage store, etc. are marked in the target area, you can judge that there are preset abnormal places such as AA car store, BB car mortgage store, etc. in the target area. Of course, you can determine whether there are corresponding preset abnormal places based on the layout information of buildings, roads, and stores corresponding to the actual location of the target area in the authoritative system.

[0135] The identification module 703 is used to identify the current abnormal usage behavior habits of the target vehicle according to the preset abnormal usage behavior habit table if vehicles gather in the target area and there are preset abnormal places, and judge the anti-fraud risk type of the target vehicle based on the current abnormal usage behavior habits of the target vehicle.

[0136] In this embodiment, the above-mentioned preset abnormal usage behavior habit can be a preset abnormal usage behavior habit standard for judging the vehicle usage behavior habit. The number of preset abnormal usage behavior habits in the preset abnormal usage behavior habit table is at least one. The preset abnormal usage behavior habit table includes at least one or more of the following abnormal usage behaviors:

[0137] The vehicle's GPS signal disappears for a preset period of time;

[0138] The vehicle GPS signal stays in a preset abnormal area for more than a preset time. The preset abnormal area can be a non-working area, a non-residence area, and a non-domiciliary area.

[0139] The GPS signals of vehicles in the same area are aggregated;

[0140] After the loan is released, the vehicle GPS signal stays at the first GPS signal reporting point for more than the preset time;

[0141] The vehicle stays in a preset abnormal location for longer than the preset time;

[0142] In the same registered residence area, apply for a car loan at the same online store within the preset time, and the brand and type of the vehicle purchased must be similar.

[0143] Optional, such as Fig.12 As shown, the identification module 703 includes:

[0144] The second acquisition unit 7031 is used to acquire historical GPS data of the target vehicle.

[0145] In the embodiment of the present application, the above historical GPS data is the historical GPS data corresponding to the target vehicle in the target area. The historical GPS data may include user information, parking points, driving tracks, driving time and other information. When there are multiple target vehicles, the corresponding historical GPS data is also multiple, and one target vehicle corresponds to one historical GPS data.

[0146] Specifically, after determining that vehicles gather in the target area and there are preset abnormal places, it can be considered that there may be anti-fraud risk behaviors in the target area. However, whether there is anti-fraud risk behavior or not needs to be determined by judging the usage behavior habits of each vehicle in the target area, so it is necessary to obtain the historical GPS data of the target vehicle.

[0147] The analysis unit 7032 is used to analyze the historical GPS data to obtain the usage behavior habits of the target vehicle.

[0148] In an embodiment of the present application, specifically, after analyzing the historical GPS data of each target vehicle, the corresponding user information, historical parking point information, historical trajectory information, and corresponding historical time information can be obtained, and then the usage behavior habits of the target vehicle can be obtained based on this information.

[0149] The first judgment unit 7033 is used to judge whether the usage behavior habits of the target vehicle conform to one or more preset abnormal usage behavior habits.

[0150] In the embodiment of the present application, after the usage behavior habits of the target vehicle are obtained, they can be compared with the preset abnormal usage behavior habits, so as to determine whether the usage behavior habits of the target vehicle are abnormal. If the usage behavior habits of the target vehicle match one or more of the preset abnormal usage behavior habits, it means that the usage behavior habits of the target vehicle are abnormal.

[0151] The third acquisition unit 7034 is used to acquire the duration of the target vehicle being in a preset abnormal usage behavior habit and the number of types that meet the preset abnormal usage behavior habit if it meets the requirements.

[0152] In the embodiment of the present application, the above-mentioned duration is the length of time that the target vehicle is in a certain abnormal usage behavior habit.

[0153] Specifically, after determining that the target vehicle's usage behavior habits are abnormal, the duration of the target vehicle's abnormal usage behavior habits and the number of types of abnormal usage behavior habits that are in place at the same time can be determined. For example, the target vehicle's usage behavior habits are that after the vehicle GPS signal disappears for more than a preset time, the vehicle GPS signal stays in a preset abnormal area for more than a preset time. The preset abnormal area can be a three-non-zone, which is a non-workplace, non-residence, and non-household registration place. Then it can be determined that the duration is long-term, and the number of types of preset abnormal usage behavior habits that the target vehicle meets is two.

[0154] The second determination unit 7035 is used to determine the anti-fraud risk type of the target vehicle according to the duration and the number of types.

[0155] Optional, such as Fig.13 As shown, the second determining unit 7035 includes:

[0156] The judging subunit 70351 is used to judge whether the duration meets the preset time.

[0157] The first determining subunit 70352 is used to determine the type category content of the type category corresponding to the number of type categories of the preset abnormal usage behavior habits if the condition is satisfied.

[0158] The second determination subunit 70353 is used to determine the anti-fraud risk type of the target vehicle based on the category content.

[0159] In the embodiment of the present application, the above-mentioned preset time is used to determine whether the duration is a long-term or short-term time condition. If the duration meets the preset time, it means that the duration is long-term. If the duration does not meet the preset time, it means that the duration is short-term.

[0160] Specifically, when it is determined that the target vehicle has been in use for a long period of time and satisfies one or more of the preset abnormal usage behavior habits, the anti-fraud risk type of the target vehicle can be determined based on the specific type and content of the preset abnormal usage behavior habits.

[0161] For example, if the target vehicle stays in a preset abnormal place for a long time and then the vehicle GPS signal disappears for a long time, there is a high probability that the target vehicle has been sold, and it is necessary to contact the main lender corresponding to the target vehicle by phone to confirm the anti-fraud behavior and preserve the evidence.

[0162] Another example: the target vehicle appears first, and after the loan is issued, the vehicle's GPS signal stays at the first GPS signal reporting point for a long time. Later, monitoring shows that within the same household registration area, a car loan application is processed in the same online store within a short period of time, and the brand and type of the purchased vehicles are similar. Then it is highly likely that the same person controls or packages multiple different main borrowers, and works with vehicle sales stores to concentrate on cashing out and defrauding loans.

[0163] This application pre-processes the acquired vehicle GPS data based on a preset algorithm to determine the target area; search the number of target vehicles in the target area, and judge the target area based on the number of vehicles, whether vehicles gather and whether there are preset abnormal places, where abnormal places are places that do not meet the preset regulatory requirements; if vehicles gather and preset abnormal places exist in the target area, the current abnormal use behavior habits of the target vehicle are identified according to the preset abnormal use behavior habit table, and the anti-fraud risk type of the target vehicle is judged based on the current abnormal use behavior habits of the target vehicle. In this way, the vehicle GPS data can be regionalized in combination with the preset algorithm to realize the retrieval of vehicles and key suspicious objects in the target area. At the same time, the target vehicle use behavior habits of the target vehicles in the target area are monitored and judged in combination with vehicle gathering, preset abnormal places, and preset abnormal use behavior habits to realize the anti-fraud risk identification of the target vehicle. Then measure the main lender's willingness to buy a car and the use of the vehicle, and warn the customer whether there is fraudulent behavior, so as to improve the recognition accuracy of anti-fraud risk identification and reduce asset losses.

[0164] In some optional implementations of this embodiment, such as Fig.14 As shown, after the identification module 703, the automobile anti-fraud risk identification device 700 further includes:

[0165] The second judgment module 704 is used to judge whether the target user corresponding to the target vehicle with abnormal usage behavior habits is a user in arrears;

[0166] The taking module 705 is used to determine that the target user is a fraudulent user if the target user is a user in arrears, and take differentiated loss recovery measures for the fraudulent user.

[0167] In the embodiment of the present application, after determining that the target vehicle has anti-fraud risk behavior, the corresponding fraudulent customer can be determined based on the relationship between the target vehicle and the owner. For confirmed fraudulent customers, the conventional method of first calling and then collecting on-site may miss the opportunity to collect, so differentiated collection and loss recovery measures must be taken: The specific loss recovery measures are as follows:

[0168] For confirmed fraudulent users, if the preset repayment period has not been exceeded and there is sufficient evidence to confirm the fraud, the cooperative relationship will be terminated in advance according to the preset contract and the customer will be required to repay the outstanding balance in advance;

[0169] For confirmed fraud users, if the preset repayment period has been exceeded and they are in the regular collection sequence, the fraud users will be removed from the collection sequence and put into the fraud loss recovery queue, and on-site collection or asset preservation will be carried out;

[0170] For confirmed fraudulent users, we urge them to repay the full amount through preferential measures such as exemptions and reductions to avoid losing contact with customers after they repay the due amount.

[0171] This application monitors abnormal customer vehicle usage behavior and adopts differentiated loss recovery measures. It strengthens collection methods in accordance with the steps of early detection, early intervention, and strong collection to reduce asset losses.

[0172] To solve the above technical problems, the present application also provides a computer device. Fig.15 , Fig.15 This is a basic structural block diagram of the computer device in this embodiment.

[0173] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0174] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0175] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk equipped on the computer device 8, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the automobile anti-fraud risk identification method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0176] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer-readable instructions stored in the memory 81 or process data, such as running computer-readable instructions of the automobile anti-fraud risk identification method.

[0177] The network interface 83 may include a wireless network interface or a wired network interface, and the network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0178] The electronic device provided in the embodiment of the present application can implement each process implemented by the automobile anti-fraud risk identification method in the above method embodiment, and can achieve the same beneficial effect. To avoid repetition, it will not be repeated here.

[0179] The present application also provides another implementation, that is, a computer-readable storage medium is provided, the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor, so that at least one processor executes the steps of the above-mentioned automobile anti-fraud risk identification method. And the same technical effect can be achieved, and it will not be repeated here to avoid repetition.

[0180] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the various embodiment methods of the present application.

[0181] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for identifying automobile anti-fraud risks, characterized in that: The steps include: Preprocess the acquired vehicle GPS data based on a preset algorithm to determine the target area; Searching for the number of target vehicles in the target area, and judging whether vehicles gather in the target area and whether there are preset abnormal places according to the number of vehicles, wherein the abnormal places are places that do not meet the preset supervision requirements; If vehicles gather in the target area and the preset abnormal place exists, the current abnormal usage behavior habits of the target vehicles are identified according to the preset abnormal usage behavior habit table, and the anti-fraud risk type of the target vehicles is determined based on the current abnormal usage behavior habits of the target vehicles; The step of preprocessing the acquired vehicle GPS data based on a preset algorithm to determine the target area specifically includes: Acquire multiple vehicle GPS data, each of which is a set of longitude and latitude data; Using the preset algorithm and the preset encoding method, each set of longitude and latitude data is encoded into a corresponding character string; Performing a region segmentation process on each of the character strings to obtain a region segmentation process result; The target area is determined according to the area segmentation processing result and a preset risk tolerance level, wherein the preset risk tolerance level reflects the recognition accuracy of anti-fraud risk.

2. The automobile anti-fraud risk identification method according to claim 1 is characterized in that: After the step of identifying the current abnormal usage behavior habits of the target vehicle according to the preset abnormal usage behavior habit table if vehicles gather in the target area and the preset abnormal place exists, and judging the anti-fraud risk type of the target vehicle based on the current abnormal usage behavior habits of the target vehicle, the method further includes: Determine whether the target user corresponding to the target vehicle with abnormal usage behavior habits is a user in arrears; If the target user is a user who owes money, the target user is judged to be a fraud user, and differentiated loss recovery measures are taken for the fraud user; The loss recovery measures include at least one or more of the following measures: For confirmed fraud users, if the preset repayment period has not been exceeded and there is sufficient evidence to confirm the fraud, the cooperation relationship will be terminated in advance according to the preset contract, and the customer will be required to repay the outstanding debt in advance; For confirmed fraud users, if the preset repayment period has been exceeded and they are in the regular collection sequence, the fraud users will be removed from the collection sequence and put into the fraud loss recovery queue, and on-site collection or asset preservation will be carried out; For confirmed fraudulent users, we will urge them to repay the full amount through preferential measures such as reduction or exemption.

3. The automobile anti-fraud risk identification method according to claim 1 is characterized in that: The number of preset abnormal usage behavior habits in the preset abnormal usage behavior habit table is at least one; if a vehicle gathering occurs in the target area and the preset abnormal place exists, the steps of identifying the current abnormal usage behavior habit of the target vehicle according to the preset abnormal usage behavior habit table, and judging the anti-fraud risk type of the target vehicle based on the current abnormal usage behavior habit of the target vehicle specifically include: Obtaining historical GPS data of the target vehicle; Analyze the historical GPS data to obtain the usage behavior habits of the target vehicle; Determine whether the usage behavior habit of the target vehicle conforms to one or more of the preset abnormal usage behavior habit table; If yes, then obtaining the duration of the target vehicle being in the preset abnormal usage behavior habit and the number of types that meet the preset abnormal usage behavior habit; The anti-fraud risk type of the target vehicle is determined according to the duration and the number of types.

4. The automobile anti-fraud risk identification method according to claim 3 is characterized in that: The step of determining the anti-fraud risk type of the target vehicle according to the duration and the number of types includes: Determining whether the duration meets a preset time; If satisfied, then determining the type category content corresponding to the number of types of the preset abnormal usage behavior habits; An anti-fraud risk type of the target vehicle is determined based on the category content.

5. The automobile anti-fraud risk identification method according to claim 4 is characterized in that: The preset abnormal usage behavior habit table includes at least one or more of the following abnormal usage behaviors: The vehicle's GPS signal disappears for a preset period of time; The vehicle's GPS signal stays in the preset abnormal area for longer than the preset time; The GPS signals of vehicles in the same area are aggregated; After the loan is released, the vehicle GPS signal stays at the first GPS signal reporting point for more than the preset time; The vehicle stays in a preset abnormal location for longer than the preset time; Within the same registered residence area, the car loan application is processed at the same online store within the preset time, and the brand and type of the vehicle purchased are similar.

6. The automobile anti-fraud risk identification method according to claim 1 is characterized in that: The step of judging whether vehicles gather in the target area according to the number of vehicles comprises: Determining whether the number of vehicles meets a preset number of gathered vehicles in the target area; If the number of vehicles meets the preset number of gathered vehicles, it is determined that vehicles are gathered in the target area; If the number of vehicles does not meet the preset number of gathered vehicles, it is determined that no vehicle gathering occurs in the target area.

7. An automobile anti-fraud risk identification device, characterized in that: include: A preprocessing module, used to preprocess the acquired vehicle GPS data based on a preset algorithm to determine the target area; A first judgment module is used to search for the number of target vehicles in the target area, and judge whether there is a gathering of vehicles in the target area and whether there is a preset abnormal place according to the number of vehicles, wherein the abnormal place is a place that does not meet the preset supervision requirements; An identification module, for identifying the current abnormal usage behavior habits of the target vehicle according to a preset abnormal usage behavior habit table if a vehicle gathering occurs in the target area and the preset abnormal place exists, and judging the anti-fraud risk type of the target vehicle based on the current abnormal usage behavior habits of the target vehicle; The preprocessing module comprises: A first acquisition unit is used to acquire multiple vehicle GPS data, each vehicle GPS data is a set of longitude and latitude data; The encoding unit is used to encode each set of longitude and latitude data into a corresponding character string using a preset algorithm and a preset encoding method; A segmentation processing unit, used for performing region segmentation processing according to each character string to obtain a region segmentation processing result; The first determination unit is used to determine the target area according to the area segmentation processing result and the preset risk tolerance level, wherein the preset risk tolerance level reflects the recognition accuracy of anti-fraud risk.

8. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the automobile anti-fraud risk identification method as described in any one of claims 1 to 6 when executing the computer-readable instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the automobile anti-fraud risk identification method according to any one of claims 1 to 6.

Images