Artificial intelligence-based method, device, equipment and medium for identifying backdoor risks

Abstract

The application relates to the technical field of artificial intelligence, and discloses a method, device and equipment for identifying a backhouse risk based on artificial intelligence and a medium, which comprises the following steps: obtaining usage information of a to-be-tested vehicle, wherein the usage information comprises positioning information, a driving track and time information; determining stay information of the to-be-tested vehicle based on the usage information; determining address information of a lessee of the to-be-tested vehicle; processing the stay information and the address information by using a Vincent algorithm, and obtaining distance details of the to-be-tested vehicle about time and a target distance by combining vehicle information of the to-be-tested vehicle, wherein the target distance is determined based on distances between stay positions in different time periods and addresses in the address information; and identifying a backhouse risk based on the distance details and the lessee information. The application can be applied to the financial field to improve the risk control efficiency and precision of automobile leasing.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of artificial intelligence technology, and in particular to a method, apparatus, device and medium for identifying the risk of unauthorized transactions based on artificial intelligence. Background Technology

[0002] With the continuous development of the auto finance industry and online car rental business, financial leasing companies have discovered a number of cases of unauthorized ownership.

[0003] The car rental business typically involves three parties: a financial leasing company, a car rental company, and the customer. The financial leasing company provides the funds and purchases the vehicles, owning the vehicles; the car rental company leases vehicles from the financial leasing company in its own name, and can use the leased vehicles to provide short-term rentals, chauffeur services, and other car rental services; the customer purchases car rental services from the car rental company according to their actual needs.

[0004] Car rental companies, for cost reduction purposes, sometimes allow their employees or their relatives to rent cars under their personal names, effectively transferring the vehicles to the rental company for operation, with the rental company covering the rent payments. This is often called "backdoor registration," where the lessee and the user of the leased vehicle are not the same person. When the leased vehicle is a car, it's often called a "backdoor vehicle." Such illegal operations harm the interests of the leasing company and carry potential criminal liability. If a car rental company uses backdoor vehicles for operation, the vehicle may fail to repay rent on time due to operational problems, creating a risk of delinquency for the leasing company. If the car rental company disposes of the vehicle privately, but can only hold the individual lessee accountable, it can lead to asset losses and other risks. Summary of the Invention

[0005] This invention provides an artificial intelligence-based method, device, equipment, and medium for identifying the risk of unauthorized ownership of vehicles and lessees, in order to solve the technical problem of the inability to automatically, quickly, and accurately identify the risk of unauthorized ownership of vehicles and lessees, which leads to asset losses and the inability to recover vehicles in car rental companies.

[0006] To address the aforementioned technical problems, in a first aspect, embodiments of the present invention provide an artificial intelligence-based method for identifying the risk of unauthorized transfer of ownership, comprising: Obtain usage information of the vehicle under test, including location information, driving trajectory, and time information; The dwell information of the vehicle under test is determined based on the usage information; Determine the address information of the lessee of the vehicle under test; The Vincent algorithm is used to process the dwell information and address information, and combined with the vehicle information of the vehicle under test, the distance details of the vehicle under test with respect to time and target distance are obtained. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. Risk identification of unauthorized tenants is conducted based on the aforementioned distance details and tenant information.

[0007] Secondly, another embodiment of the present invention provides an artificial intelligence-based device for identifying the risk of unauthorized transfer of ownership, comprising: The acquisition module is used to acquire usage information of the vehicle under test, including location information, driving trajectory, and time information. The first determining module is used to determine the dwell information of the vehicle under test based on the usage information; The second determining module is used to determine the address information of the lessee of the vehicle under test; The processing module is used to process the dwell information and address information using the Vincent algorithm, and combine the vehicle information of the vehicle under test to obtain the distance details of the vehicle under test with respect to time and target distance. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. The identification module is used to identify the risk of unauthorized relocation based on the distance details and lessee information.

[0008] Thirdly, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the artificial intelligence-based method for identifying the risk of unauthorized transactions as described in any of the above descriptions.

[0009] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the artificial intelligence-based method for identifying the risk of unauthorized transactions as described above.

[0010] Based on the above embodiments of the present invention, an artificial intelligence-based method, apparatus, device, and medium for identifying the risk of vehicle misappropriation combines the vehicle's location with the latitude and longitude of its address information and identifies vehicles with potential misappropriation risks based on identification rules. Then, further clustering analysis of potential misappropriation vehicles is performed on the lessee based on these vehicles, thereby identifying lessees with misappropriation risks. In summary, the method of this embodiment can fully utilize the existing vehicle location information of financial companies and effectively identify vehicles with misappropriation risks and their corresponding lessees by combining the lessee's address information registered in the contract. This provides investigators with clues about vehicles with misappropriation risks, improving the accuracy and efficiency of risk control for leased vehicles.

[0011] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0012] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0013] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating the artificial intelligence-based method for identifying the risk of unauthorized transfer of ownership in an embodiment of the present invention.

[0015] Figure 2 This is a flowchart illustrating an artificial intelligence-based method for identifying the risk of unauthorized transfer of assets, as described in another embodiment of the present invention.

[0016] Figure 3 This is a structural block diagram of an artificial intelligence-based device for identifying the risk of unauthorized transactions, as described in an embodiment of the present invention.

[0017] Figure 4 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] Figure 5 This is another structural schematic diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0019] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but these are not intended to limit the scope of the invention.

[0020] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the following description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope of this disclosure will be apparent to those skilled in the art.

[0021] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.

[0022] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0023] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention.

[0024] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0025] Specific embodiments of the present disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure and can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the present disclosure. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but are merely representative of the present disclosure and are intended to teach those skilled in the art to use the present disclosure in a variety of substantially any suitable detailed structures.

[0026] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0027] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0028] like Figure 1 As shown, this embodiment of the invention provides a method for identifying the risk of unauthorized transfer of ownership based on artificial intelligence, including: S1: Obtain the usage information of the vehicle under test, including location information, driving trajectory, and time information; S2: Determine the dwell information of the vehicle under test based on the usage information; S3: Determine the address information of the lessee of the vehicle under test; S4: The Vincent algorithm is used to process the dwell information and address information, and combined with the vehicle information of the vehicle under test, the distance details of the vehicle under test with respect to time and target distance are obtained. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. S5: Identify the risk of unauthorized transfer of ownership based on the distance details and lessee information.

[0029] The AI-based method for identifying the risk of unauthorized ownership in this embodiment can be applied to the auto finance industry and online car rental business. Specifically, the method can be deployed in a car rental system to automatically identify the risk of unauthorized ownership of the rented vehicle (i.e., the vehicle under test) based on the platform system. Alternatively, the method can be deployed in a third-party monitoring system; there are no specific limitations. The following section refers to the implementing entity as the system's solution. For example, the system first obtains the usage information of the vehicle under test (i.e., the already rented vehicle), such as the vehicle's real-time location information, driving trajectory, and corresponding time information. This information can be obtained, but is not limited to, simultaneously through the vehicle's GPS device. Next, the system determines the vehicle's dwell information based on the obtained usage information, such as when the vehicle is in motion and when it is parked. Then, it determines the address information of the lessee of the vehicle under test, which is usually obtained and recorded when the rental contract is signed. Therefore, the address information can be obtained by recording and storing contract information. Different types of lessees have different address information. For example, for lessees formed by natural persons, the address information includes the lessee's ID address, residential address, and workplace address, specifically including the address information recorded on the lessee's ID, actual residential address, and workplace address. For lessees formed by legal entities, the address information includes the company's address, etc., and is not unique. After obtaining the above information, the system will use the Vincent algorithm to process the obtained stop information and address information, and combine it with the vehicle information of the vehicle under test to obtain the distance details of the vehicle under test regarding time and target distance. The Vincent algorithm is a set of mathematical formulas in surveying used for high-precision geographic calculations on the surface of an ellipsoid (reference ellipsoid), used to achieve high-precision calculation of parameters such as distance and azimuth between two points under a non-spherical (i.e., ellipsoidal) model. The target distance is determined based on the distance between the stop location at different time periods and the address in the address information. This target distance can reflect the difference between the daily use location of the vehicle under test and the registered location. Then, the system can accurately identify the risk of unauthorized relocation based on the distance details and lessee information, and obtain identification results with high reference value.

[0030] Based on the above, the method in this embodiment combines the vehicle's location with the latitude and longitude of the lessee's address information and identifies vehicles with potential for fraudulent ownership based on identification rules. Then, it performs further clustering analysis on lessees based on these potential fraudulent vehicles, thereby identifying lessees with fraudulent ownership risks. In summary, the method in this embodiment can fully utilize the financial company's existing vehicle location information and, combined with the lessee's address information registered in the contract, effectively identify vehicles with fraudulent ownership and their corresponding lessees, providing investigators with clues about vehicles with fraudulent ownership risks and improving the accuracy and efficiency of risk control for leased vehicles.

[0031] In one embodiment, the usage information can be reported by the vehicle's GPS device, including wired and wireless device positioning. The GPS positioning collection module on the vehicle receives and saves the obtained data to the platform server or other designated storage system for the platform system to read and access.

[0032] Furthermore, determining the dwell information of the vehicle under test based on the usage information includes: S201: Determine the speed of the vehicle under test based on the usage information; S202: Perform speed segmentation on the vehicle's speed; S203: Determine the stopping information of the vehicle under test based on the segmented speed value.

[0033] For example, the original GPS-reported location points are too dense and contain a large number of "passing" locations. To determine where a vehicle is "moving," it is necessary to filter out location points that are not meaningful during the journey, and then determine the vehicle's stopping information based on the filtered data. In this embodiment, the vehicle's trajectory is segmented based on speed and time, dividing the continuous trajectory into "driving segments" and "stopping segments" according to time or speed characteristics. Specifically, a speed > 5 km / h can be considered "driving," and a speed < 5 km / h within 30 consecutive minutes can be considered a "stopping" segment. The speed and time values ​​can be flexibly changed. The segmentation results are filtered using these rules to obtain driving and stopping segments. Then, the time and location corresponding to the driving and stopping segments are determined, including latitude and longitude information, thus obtaining the stopping information. In practical applications, an ETL task can be built for the system, allowing the system to utilize Spark Streaming or structured stream processing methods, or Spark SQL methods to calculate the information.

[0034] Furthermore, determining the address information of the lessee of the vehicle under test includes: S301: Synchronize the lease contract information in the storage system to the data warehouse based on the data synchronization algorithm and preset cycle; S302: Retrieve the lease contract information from the ODS (Operational Data Storage Layer) of the data warehouse; S303: The address information of the lessee is obtained by querying the lease contract information using SQL values.

[0035] For example, by connecting to the business database of a financial leasing company through a system interface, and utilizing data synchronization tools, including but not limited to Flink, a scheduled task can be configured to synchronize contract data every other day, such as T+1. This automatically extracts and loads the "lease start contract" data added or changed the previous day from the business database into the ODS layer of the data warehouse. This ensures that the lease start contract data used for analysis is up-to-date and complete without affecting the performance of the business system. In the ODS layer, the system can query and clean the raw contract data using SQL statements, extracting unique vehicle identifiers, such as the vehicle identification number (VIN), and text addresses of the lessee's registered addresses, such as residence, workplace, ID card location, and company location. Next, the system can call a map API to accurately convert these text addresses into corresponding latitude and longitude coordinates. Finally, the processed VIN and address information are stored in a dedicated table, serving as the core comparison benchmark for subsequent risk identification modules.

[0036] In one embodiment, the method further includes: S6: Read the stopping information of the vehicle under test, and determine the stopping time and stopping location of the vehicle under test as a list of positioning points; S7: Read the address information of the lessee and determine the address list of the lessee; S8: By performing an inner join between the location point list, the address list, and the vehicle equipment number of the vehicle under test through the target processing engine, a detailed list of the real-time location and address information of the vehicle under test is obtained.

[0037] In this embodiment, taking an individual as the lessee and Spark as the target processing engine, the system loads two types of data from Hive in the data warehouse: one is a "Location Point RDD" (Resilient Distributed Dataset) composed of the vehicle's GPS location points and stop points, containing the vehicle identification number (VIN), latitude and longitude, and the time period involved in the location point, such as a certain month or week; the other is a "Three-Address RDD" composed of the lessee's three addresses (latitude and longitude), containing the VIN, residential / work / ID card address coordinates. Subsequently, the system uses the VIN as the association key and performs an inner join operation through SparkSQL to concatenate each location point or stop point of the same vehicle with the three addresses of the lessee corresponding to that vehicle into the same record, thereby generating a "Detailed RDD" containing all such matching relationships. Each row in this detailed table completely records the coordinates of a certain location point of a certain vehicle under test and the coordinates of the three addresses of the lessee of that vehicle, laying the data foundation for subsequent processing.

[0038] Furthermore, the processing of the dwell information and address information using the Vincent algorithm includes: S401: Based on the grouping operator in the target processing engine, the detailed RDD is grouped using the vehicle equipment number as the grouping key, and the data in different groups correspond to different vehicles under test; S402: Calculate the distance between addresses in the dwell position and address information by using the Vincent algorithm for each set of data.

[0039] For example, continuing from the above example, the system uses the obtained PDD detail table as a unit, and uses the Spark grouping operator to group the data in the table. For all vehicle location points in each group, the system uses the high-precision Vincenty formula to calculate the distance between each location and the three addresses of the lessee: residence, workplace, and ID card registration address.

[0040] Furthermore, by combining the vehicle information of the vehicle under test, a detailed distance information of the vehicle under test regarding time and target distance is obtained, including: S403: Determine the minimum distance and the corresponding time among the distances between the addresses in the stated stopping position and address information; S404: Combine the vehicle information, minimum distance, and corresponding time of the vehicle under test to obtain the distance details of the vehicle under test with respect to time and target distance.

[0041] Specifically, continuing from the previous embodiment, the system uses the "vehicle equipment number" as the grouping key and utilizes Spark's grouping operator to aggregate all records belonging to the same vehicle in the "details RDD" into the same group. For each group of data, the algorithm traverses all the vehicle's location points, including GPS points during travel and calculated stop points, and uses the high-precision Vincenty formula to calculate the spherical distance from each location point to the lessee's three addresses, including residence, workplace, and ID card registration address. For a single location point, the system takes the minimum distance value from that point to the three addresses as the representative distance for that point. After calculating the representative distances for all location points of a vehicle, the system further takes the minimum value as the "most recent activity distance" (i.e., the target distance) for the vehicle within the entire statistical period, which can be a month or a week. This minimum value and its corresponding location point information are retained. Finally, the system combines the vehicle identification number (VIN), GPS equipment number (optional), the most recent distance value, and the statistical period (e.g., a certain month) to save the result table to disk, obtaining the distance details.

[0042] like Figure 2 As shown, the risk identification of unauthorized tenants based on the distance details and tenant information includes: S601: Filter out the target distances in the distance details that exceed the preset distance threshold, and identify the vehicles to be tested corresponding to the target distances as risk vehicles; S602: Based on the rental contract information corresponding to the risk vehicle, make an inner connection between the vehicle information of the risk vehicle and the corresponding lessee to generate a correspondence table containing vehicle information, lessee, and the time when the vehicle under test is identified as a risk vehicle. S603: Query, identify, and statistically process the corresponding relationship table to obtain the target risk vehicles that have been identified as risk vehicles for n consecutive months, and the lessees corresponding to the target risk vehicles; S604: The lessee whose number of the target risk vehicles under their name exceeds the threshold for the number of risk vehicles is identified as a lessee with a hidden account risk.

[0043] For example, the system can execute an SQL query on the obtained distance details and filter the distances by the condition that the distance value is greater than m (m = 1000 meters or other distance values, which are not unique) to obtain the target distance value. Based on this, the corresponding vehicles to be tested are identified, thus identifying risky vehicles. Next, based on the identified potential risky vehicles with hidden ownership, the system further identifies lessees suspected of systematic hidden ownership operations. In specific implementation, the system first performs an inner join between each risky vehicle and a vehicle rental contract table containing lessee information through the vehicle identification number (VIN). It then filters out the lessee name and corresponding statistical time information for each risky vehicle, i.e., the aforementioned monthly and weekly information, and generates an intermediate result table. Next, the system performs an aggregate query on the table, grouping by lessee name, and counts the number of vehicles marked as risky vehicles each month or week within a consecutive month or week (e.g., the last three months or four weeks). The system then uses the SQL HAVING clause to filter out target lessees whose number of risky vehicles is consistently no less than a specified number (e.g., 5, 7, etc.) across multiple consecutive months or weeks. Finally, the target lessee is determined to be a "risky lessee with a hidden account." This determination result can be recorded in a designated data table for the risk control department to conduct focused investigations and on-site inspections.

[0044] like Figure 3 As shown, another embodiment of the present invention also provides an artificial intelligence-based device for identifying the risk of unauthorized transfer of accounts, comprising: Module 1 is used to obtain usage information of the vehicle under test, including location information, driving trajectory, and time information. The first determining module 2 is used to determine the dwell information of the vehicle under test based on the usage information; The second determining module 3 is used to determine the address information of the lessee of the vehicle under test; Processing module 4 is used to process the dwell information and address information using the Vincent algorithm, and combine the vehicle information of the vehicle under test to obtain the distance details of the vehicle under test with respect to time and target distance. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. The identification module 5 is used to identify the risk of unauthorized relocation based on the distance details and lessee information.

[0045] In some embodiments, determining the dwell information of the vehicle under test based on the usage information includes: The speed of the vehicle under test is determined based on the usage information. The speed of the vehicle is divided into speed segments; The stopping information of the vehicle under test is determined based on the segmented speed values.

[0046] In some embodiments, determining the address information of the lessee of the vehicle under test includes: Based on data synchronization algorithms and preset cycles, the lease contract information in the storage system is synchronized to the data warehouse; Retrieve the lease contract information from the ODS of the data warehouse; The address information of the lessee can be obtained by querying the lease contract information using SQL values.

[0047] In some embodiments, the apparatus further includes: The third determining module is used to read the stopping information of the vehicle under test and determine the stopping time and stopping location of the vehicle under test as a list of positioning points; The fourth determination module is used to read the address information of the lessee and determine the address list of the lessee; The connection module is used to perform an inner join between the location point list, the address list, and the vehicle equipment number of the vehicle under test through the target processing engine to obtain a detailed list of the real-time location and address information of the vehicle under test. The target processing engine includes Spark.

[0048] In some embodiments, processing the dwell information and address information using the Vincent algorithm includes: Based on the grouping operator in the target processing engine, the detailed list is grouped using the vehicle equipment number as the grouping key, and the data in different groups correspond to different vehicles under test; The Vincent algorithm is used to calculate the distance between addresses in the dwell position and address information for each set of data.

[0049] In some embodiments, obtaining distance details of the vehicle under test regarding time and target distance by combining the vehicle information of the vehicle under test includes: Determine the minimum distance and the corresponding time between the distances between the stated location and the address in the address information; By combining the vehicle information, minimum distance, and corresponding time of the vehicle under test, a distance detail of the vehicle under test with respect to time and target distance is obtained.

[0050] In some embodiments, the identification of backdoor registration risk based on the distance details and lessee information includes: Target distances exceeding a preset distance threshold are filtered out from the distance details, and the vehicles to be tested corresponding to the target distances are identified as risk vehicles. Based on the rental contract information corresponding to the risk vehicle, the vehicle information of the risk vehicle is internally joined with the corresponding lessee to generate a correspondence table containing vehicle information, lessee, and the time when the vehicle under test is identified as a risk vehicle. The corresponding relationship table is queried, identified, and statistically processed to obtain the target risk vehicles that have been identified as risk vehicles for n consecutive months, and the lessees of the corresponding target risk vehicles. Lessees whose number of target risk vehicles exceeds the risk vehicle number threshold are identified as lessees with hidden ownership risks.

[0051] An embodiment of the present invention also provides a computer device, which can be a client, such as a third-party monitoring device, and its internal structure diagram can be as follows. Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When executed by the processor, the computer program implements the functions or steps of an artificial intelligence-based method for identifying fraudulent transactions.

[0052] like Figure 5 As shown, another embodiment of the present invention also provides a computer device, such as a server for a car rental company, the computer device comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the steps of the AI-based method for identifying the risk of unauthorized transactions as described above: Obtain usage information of the vehicle under test, including location information, driving trajectory, and time information; The dwell information of the vehicle under test is determined based on the usage information; Determine the address information of the lessee of the vehicle under test; The Vincent algorithm is used to process the dwell information and address information, and combined with the vehicle information of the vehicle under test, the distance details of the vehicle under test with respect to time and target distance are obtained. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. Risk identification of unauthorized tenants is conducted based on the aforementioned distance details and tenant information.

[0053] Furthermore, one embodiment of the present invention also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the artificial intelligence-based method for identifying the risk of unauthorized transactions as described above: Obtain usage information of the vehicle under test, including location information, driving trajectory, and time information; The dwell information of the vehicle under test is determined based on the usage information; Determine the address information of the lessee of the vehicle under test; The Vincent algorithm is used to process the dwell information and address information, and combined with the vehicle information of the vehicle under test, the distance details of the vehicle under test with respect to time and target distance are obtained. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. Risk identification of unauthorized tenants is conducted based on the aforementioned distance details and tenant information.

[0054] It should be understood that the various solutions in this embodiment have the same technical effects as those in the above method embodiments, and will not be repeated here.

[0055] Furthermore, embodiments of the present invention also provide a computer program product, which is tangibly stored on a computer-readable medium and includes computer-readable instructions that, when executed, cause at least one processor to perform steps such as the artificial intelligence-based method for identifying the risk of unauthorized transactions described in the embodiments above.

[0056] It should be noted that the computer storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access storage medium (RAM), a read-only storage medium (ROM), an erasable programmable read-only storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only storage medium (CD-ROM), an optical storage medium, a magnetic storage medium, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program configured for use by or in connection with an instruction execution system, system, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, antenna, optical fiber, RF, etc., or any suitable combination thereof.

[0057] Furthermore, those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0058] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been authorized (with the knowledge and consent) by the relevant parties or has been fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0061] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.

Claims

1. An artificial intelligence-based method for identifying a risk of a backdoor, characterized by, include: Obtain usage information of the vehicle under test, including location information, driving trajectory, and time information; The dwell information of the vehicle under test is determined based on the usage information; Determine the address information of the lessee of the vehicle under test; The Vincent algorithm is used to process the dwell information and address information, and combined with the vehicle information of the vehicle under test, the distance details of the vehicle under test with respect to time and target distance are obtained. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. Risk identification of unauthorized tenants is conducted based on the aforementioned distance details and tenant information.

2. The method for identifying the risk of unauthorized transfer of assets based on artificial intelligence according to claim 1, characterized in that, Determining the dwell information of the vehicle under test based on the usage information includes: The speed of the vehicle under test is determined based on the usage information. The speed of the vehicle is divided into speed segments; The stopping information of the vehicle under test is determined based on the segmented speed values.

3. The method for identifying the risk of unauthorized transfer of assets based on artificial intelligence according to claim 1, characterized in that, The process of determining the address information of the lessee of the vehicle under test includes: Based on data synchronization algorithms and preset cycles, the lease contract information in the storage system is synchronized to the data warehouse; Retrieve the lease contract information from the ODS of the data warehouse; The address information of the lessee can be obtained by querying the lease contract information using SQL values.

4. The method for identifying the risk of unauthorized transfer of assets based on artificial intelligence according to claim 1, characterized in that, The method further includes: Read the stopping information of the vehicle under test, and determine the stopping time and stopping location of the vehicle under test as a list of positioning points; Read the address information of the lessee to determine the list of lessee addresses; The target processing engine performs an inner join on the location point list, address list, and vehicle equipment number of the vehicle under test to obtain a detailed list of real-time location and address information for the vehicle under test.

5. The artificial intelligence-based method for identifying the risk of unauthorized transfer of assets according to claim 4, characterized in that, The processing of the dwell information and address information using the Vincent algorithm includes: Based on the grouping operator in the target processing engine, the detailed list is grouped using the vehicle equipment number as the grouping key, and the data in different groups correspond to different vehicles under test; The Vincent algorithm is used to calculate the distance between addresses in the dwell position and address information for each set of data.

6. The artificial intelligence-based method for identifying the risk of unauthorized transfer of assets according to claim 5, characterized in that, By combining the vehicle information of the vehicle under test, a detailed distance breakdown of the vehicle under test with respect to time and target distance is obtained, including: Determine the minimum distance and the corresponding time between the distances between the stated location and the address in the address information; By combining the vehicle information, minimum distance, and corresponding time of the vehicle under test, a distance detail of the vehicle under test with respect to time and target distance is obtained.

7. The artificial intelligence-based method for identifying the risk of unauthorized transfer of assets according to claim 3, characterized in that, The process of identifying the risk of unauthorized relocation based on the distance details and lessee information includes: Target distances exceeding a preset distance threshold are filtered out from the distance details, and the vehicles to be tested corresponding to the target distances are identified as risk vehicles. Based on the rental contract information corresponding to the risk vehicle, the vehicle information of the risk vehicle is internally joined with the corresponding lessee to generate a correspondence table containing vehicle information, lessee, and the time when the vehicle under test is identified as a risk vehicle. The corresponding relationship table is queried, identified, and statistically processed to obtain the target risk vehicles that have been identified as risk vehicles for n consecutive months, and the lessees of the corresponding target risk vehicles. Lessees whose number of target risk vehicles exceeds the risk vehicle number threshold are identified as lessees with hidden ownership risks.

8. A device for identifying the risk of unauthorized transfer of ownership based on artificial intelligence, characterized in that, include: The acquisition module is used to acquire usage information of the vehicle under test, including location information, driving trajectory, and time information. The first determining module is used to determine the dwell information of the vehicle under test based on the usage information; The second determining module is used to determine the address information of the lessee of the vehicle under test; The processing module is used to process the dwell information and address information using the Vincent algorithm, and combine the vehicle information of the vehicle under test to obtain the distance details of the vehicle under test with respect to time and target distance. The target distance is determined based on the distance between the dwell position and the address in the address information at different time periods. The identification module is used to identify the risk of unauthorized relocation based on the distance details and lessee information.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the artificial intelligence-based method for identifying the risk of unauthorized transfer of assets as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the artificial intelligence-based method for identifying the risk of unauthorized transfer of assets as described in any one of claims 1 to 7.

Images