Vehicle metering risk detection method, device, equipment and medium

Abstract

The present application relates to the technical field of artificial intelligence, and provides a vehicle odometer risk detection method, device, equipment and medium, which can collect audio-visual data, working condition data and cloud behavior portrait data of a target vehicle, and correspondingly generate wear degradation index, physical working condition characteristics and portrait characteristic quantitative values, realize multi-source data transmission link connection, and solve the data island problem; the wear degradation index, physical working condition characteristics and portrait characteristic quantitative values are input into a pre-trained prediction model as a feature vector to obtain the real confidence mileage of the target vehicle under the current loss state, and the deviation degree of the odometer display mileage relative to the real confidence mileage is calculated to obtain the mileage deviation index, which can quantify the mileage deviation degree based on multi-dimensional data, effectively solve the problem of avoiding cross-validation through a single tampering method, and generate the odometer risk detection result of the target vehicle according to the mileage deviation index, thereby improving the accuracy of vehicle odometer risk detection.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, apparatus, equipment and medium for detecting the risk of vehicle odometer tampering. Background Technology

[0002] Currently, vehicle odometer tampering detection mainly relies on the following methods: (1) Judgment by human experience: The appraiser subjectively infers whether the mileage matches by observing sensory data such as the wear of interior parts (such as steering wheel, gear lever, accelerator pedal), the wear depth of brake discs, and tire production date; (2) Maintenance and repair shop record inquiry: Inquire about the historical records of 4S stores or insurance companies through a third-party platform and determine whether there is a mileage inversion (e.g., the record in 2023 is 80,000 kilometers, but the current instrument panel shows 50,000 kilometers). (3) Simple OBD (On-Board Diagnostics) reading: Use a diagnostic tool to read the mileage data recorded by the instrument system and the engine computer or transmission computer, and perform a simple two-way comparison.

[0003] The above methods still have obvious technical shortcomings: (1) Highly subjective and easily deceived: Manual inspection can be easily circumvented by refurbishing the interior and replacing worn parts; (2) Data silos and breaks: Maintenance records are not mandatory to be connected to the network in real time, and a large number of vehicles will choose to be repaired at non-4S stores after the warranty expires, resulting in a missing data chain; (3) Upgraded electronic tampering methods: Current odometer tamperers can not only modify the dashboard, but also modify the ECU (Electronic Control Unit) at the same time, and even modify the mileage data in the key chip. Therefore, the traditional simple two-way comparison method will become ineffective. (4) Lack of quantitative logic: Existing methods cannot provide an accurate way to quantify the risk of tampering, resulting in a lack of evidence to support disputes. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method, device, equipment and medium for detecting the risk of vehicle odometer tampering, in order to solve the problems of inaccurate detection of vehicle odometer tampering risk, the existence of data silos and difficulty in quantification.

[0005] A method for detecting the risk of odometer tampering in vehicles, the method comprising: In response to the command to detect the risk of odometer tampering of the target vehicle, the audio-visual data, operating condition data and cloud-based behavioral profile data of the target vehicle are collected; The audiovisual data is input into the vehicle wear prediction model to obtain the wear degradation index; Multiple physical operating condition features are generated based on the operating condition data; The cloud-based behavioral profile data is quantized to obtain multiple profile feature quantization values; The wear and degradation index, the multiple physical condition features, and the multiple profile feature quantization values ​​are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in the current wear state. Obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index; The odometer tampering risk detection result for the target vehicle is generated based on the mileage deviation index.

[0006] A vehicle odometer tampering risk detection device, the vehicle odometer tampering risk detection device comprising: The data acquisition unit is used to collect audio-visual data, operating condition data and cloud-based behavioral profile data of the target vehicle in response to the odometer tampering risk detection command. The input unit is used to input the audiovisual data into the vehicle wear prediction model to obtain the wear degradation index; A generation unit is used to generate multiple physical working condition features based on the working condition data; The quantization unit is used to quantize the cloud-based behavioral profile data to obtain multiple profile feature quantization values; The input unit is also used to input the wear and degradation index, the multiple physical condition features, and the multiple profile feature quantization values ​​as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in the current wear state. The calculation unit is used to obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index; The generation unit is also used to generate the odometer tampering risk detection result of the target vehicle based on the mileage deviation index.

[0007] A computer device, the computer device comprising: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the vehicle odometer tampering risk detection method.

[0008] A computer-readable storage medium storing at least one instruction, which is executed by a processor in a computer device to implement the vehicle odometer tampering risk detection method.

[0009] As can be seen from the above technical solutions, this invention can collect audiovisual data, operating condition data, and cloud-based behavioral profile data of the target vehicle, and generate wear and degradation index, multiple physical operating condition features, and multiple profile feature quantification values ​​accordingly, realizing the connection of multi-source data transmission links and solving the data silo problem; the wear and degradation index, multiple physical operating condition features, and multiple profile feature quantification values ​​are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle under the current wear state, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index, which can quantify the degree of mileage deviation based on multi-dimensional data, effectively solving the problem of avoiding cross-validation through a single tampering method; the mileage deviation index generates the odometer tampering risk detection result of the target vehicle, thereby improving the accuracy of vehicle odometer tampering risk detection. Attached Figure Description

[0010] Figure 1 This is a flowchart of a preferred embodiment of the vehicle odometer tampering risk detection method of the present invention; Figure 2 This is a functional block diagram of a preferred embodiment of the vehicle odometer tampering risk detection device of the present invention; Figure 3 This is a schematic diagram of the structure of a computer device that implements a preferred embodiment of the vehicle odometer tampering risk detection method of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0012] like Figure 1 The diagram shown is a flowchart of a preferred embodiment of the vehicle odometer tampering risk detection method of the present invention. The order of the steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0013] The vehicle odometer tampering risk detection method is applied to one or more computer devices. The computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0014] The computer device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), interactive network television (IPTV), smart wearable device, etc.

[0015] The computer equipment may also include network equipment and / or user equipment. The network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0016] The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0017] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0018] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0019] The network in which the computer device is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0020] S10, in response to the command to detect the risk of odometer tampering of the target vehicle, collects the audio-visual data, operating condition data and cloud-based behavioral profile data of the target vehicle.

[0021] In this embodiment, the table adjustment risk detection command can be triggered according to actual detection needs.

[0022] In this embodiment, the collection of audiovisual data, operating condition data, and cloud-based behavioral profile data of the target vehicle includes: The audiovisual data is collected according to preset locations; The operating condition data is collected through the on-board automatic diagnostic system of the target vehicle; The vehicle identification number of the target vehicle is used to retrieve the cloud-based behavioral profile data of the target vehicle.

[0023] For example, high-definition images can be captured at fixed shooting distances and angles at four preset locations: the 3 / 9 o'clock position of the steering wheel, the left side wing of the driver's seat, the rubber surface of the brake pedal, and the edge step of the brake disc. It can also record short dynamic videos of the vehicle chassis and brake discs, simultaneously collect the acoustic characteristics of the engine operation, and quantify and record abnormal noise indicators. All audiovisual data can be in a unified format and stored in a local raw dataset.

[0024] The audiovisual data can be used to collect standardized visual materials of wear and tear on the vehicle's exterior, interior, and chassis, avoiding the problems of inconsistent perspectives and scales in manual observation, and providing standard samples for subsequent wear quantification and scoring.

[0025] For example, a terminal can send a standard diagnostic request command to the target vehicle's CAN-FD (CAN with Flexible Data-Rate) bus via the On-Board Diagnostics (OBD) interface to directly connect to the underlying ECUs (Electronic Control Units) such as the engine, transmission, and battery. This allows for the reading of core, tamper-proof data, such as the engine's total cumulative running time, the cumulative operating time of each gear in the transmission, the vehicle's cumulative fuel consumption, the number of charge / discharge cycles of the power battery, and the mileage displayed on the vehicle's instrument panel, which is then used as the operating condition data.

[0026] The operating condition data is the original physical data of the vehicle hardware operation. This type of data is extremely difficult to tamper with and serves as the core underlying basis for mileage verification, thus avoiding the problem of tampering with the mileage of a single instrument.

[0027] For example, vehicle identification numbers can be uploaded to the cloud to automatically retrieve a full big data profile of the vehicle, such as vehicle usage attributes (e.g., ride-hailing, taxi, private commuter vehicle, cross-city logistics, commercial vehicle), insurance records, repair locations, and operator trajectory data, to determine the vehicle's frequently active areas and cross-regional driving frequency. It can also extract cloud-archived mileage data corresponding to historical time points to form a mileage time-series data chain.

[0028] The cloud-based behavioral profile data can supplement data on vehicle usage attributes, driving environment, and behavioral habits, breaking the limitations of single vehicle hardware data.

[0029] In this embodiment, the collected multidimensional data can also be standardized to solve the problem of inconsistent formats, dimensions, and types of multi-source data, and to eliminate invalid noise, thereby ensuring the accuracy of subsequent feature extraction and model calculation.

[0030] S11, The audiovisual data is input into the vehicle wear prediction model to obtain the wear degradation index.

[0031] In this embodiment, the vehicle wear prediction model can be a convolutional neural network model.

[0032] Specifically, a general pre-trained convolutional neural network model can be obtained, and a large number of samples including wear labels of used car interior and chassis components can be constructed to fine-tune the pre-trained convolutional neural network model and obtain the vehicle wear prediction model.

[0033] Furthermore, standardized audiovisual data such as images of the steering wheel, seat, pedals, and brake discs can be input into the vehicle wear prediction model, and the wear degradation index can be output.

[0034] If the wear degradation index is close to 0, it indicates that the part has clear texture and is close to the condition of a new car; if the wear degradation index is close to 1, it indicates that the surface of the part is worn, carbonized, and bare.

[0035] Through the above embodiments, the degree of wear and tear determined by human intervention can be transformed into a continuous quantitative value within the range of 0-1, realizing the standardization and quantification of audiovisual wear and tear, and exposing wear and tear logic conflicts in refurbished parts.

[0036] S12, generate multiple physical operating condition features based on the operating condition data.

[0037] In this embodiment, generating multiple physical condition features based on the operating condition data includes: The mileage displayed on the instrument panel and the total cumulative engine running time are obtained from the operating condition data, and the average speed of the target vehicle throughout its entire life cycle is obtained by calculating the quotient of the mileage displayed on the instrument panel and the total cumulative engine running time. Obtain the reference speed range of the target vehicle and the congestion level of the location of the target vehicle; The reference speed range is adjusted according to the degree of congestion to obtain the target speed range of the target vehicle; Calculate the degree of deviation of the average speed over the entire life cycle from the target speed range to obtain the speed deviation coefficient; When the average speed over the entire life cycle is less than the lowest speed in the target speed range, a mileage risk marker quantification value is generated to characterize the obvious low mileage. The cumulative operating time of each gear of the transmission, the cumulative fuel consumption of the whole vehicle, the number of charge and discharge cycles of the power battery, and the cumulative total operating time of the engine of the target vehicle are obtained and used as the underlying working condition quantitative index values. The average speed over the entire life cycle, the speed deviation coefficient, the mileage risk marker quantification value, and the underlying operating condition quantification index value are determined as the multiple physical operating condition characteristics.

[0038] For example, the reference speed range can be found in the following table:

[0039] For cities with high congestion, the baseline speed range can be lowered by 15% overall, and a personalized baseline speed range can be generated.

[0040] The mileage risk marker quantification value representing the low explicit mileage can be either a 0 or a 1.

[0041] The cumulative operating time of each gear of the transmission, the cumulative fuel consumption of the whole vehicle, the number of charge and discharge cycles of the power battery, and the cumulative total operating time of the engine can be standardized and quantified to eliminate the influence of different dimensions.

[0042] Through the above embodiments, the physical and logical relationship between engine running time and mileage can be utilized, combined with vehicle usage scenarios and regional characteristics, to construct dynamic speed thresholds and identify mileage anomalies from the perspective of operating conditions.

[0043] S13, quantify the cloud-based behavioral profile data to obtain multiple profile feature quantization values.

[0044] In this embodiment, the quantization of the cloud-based behavioral profile data to obtain multiple profile feature quantization values ​​includes: Vehicle usage attributes are obtained from the cloud-based behavioral profile data, and these vehicle usage attributes are quantified into vehicle usage attribute quantization label values. The target vehicle's permanent residence and intercity driving frequency are obtained from the cloud-based behavioral profile data, and a mileage matching score is calculated based on the permanent residence and intercity driving frequency. The regional congestion correction coefficient and the historical mileage time sequence conflict quantification value are obtained from the cloud-based behavioral profile data. The vehicle usage attribute quantification label value, the mileage matching score, the regional congestion correction coefficient, and the historical mileage time sequence conflict quantification value are determined as the multiple profile feature quantification values.

[0045] For example: the vehicle usage attribute quantitative label value for ride-hailing vehicles is 0, the vehicle usage attribute quantitative label value for private cars is 1, and the vehicle usage attribute quantitative label value for commercial vehicles is 2; the mileage matching score is calculated based on specific business logic.

[0046] Through the above embodiments, the rationality of mileage can be verified from the dimensions of vehicle usage behavior and usage scenarios, and the hidden odometer tampering behavior of electronic data tampering but behavioral logic contradictions can be assisted in identifying such behavior.

[0047] S14, the wear and degradation index, the multiple physical condition features, and the multiple profile feature quantization values ​​are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in the current wear state.

[0048] In this embodiment, the prediction model can be an XGBoost (extreme gradient boosting) regression model or an MLP (multilayer perceptron) model trained in the cloud.

[0049] Specifically, the prediction model is based on an extreme gradient boosting regression model and is obtained by supervised training in the cloud based on a training set constructed with the multiple feature vectors as data dimensions; each sample in the training set is labeled with a true confidence mileage.

[0050] For example, the prediction model is based on an extreme gradient boosting regression model. It employs an integrated architecture of multiple decision trees stacked sequentially, with defined hyperparameters such as maximum base tree depth, total number of iteration trees, learning rate, and minimum number of samples per leaf. Each tree contains feature binning branches and independent branches for missing values, and a prediction value interval truncation mapping layer is configured at the output. During training, a mean squared error loss function can be used, combined with L1 and L2 regularization constraints and tree pruning strategies. Training and validation subsets are divided at a fixed ratio, and early stopping convergence conditions are set. Simultaneously, outlier filtering, standardization, and feature binning preprocessing are uniformly performed on the input features. Internally, the model splits decision tree nodes according to the feature gain criterion, and defines core hyperparameters such as maximum base tree depth, number of iteration trees, and learning rate. During cloud training, a distributed computing mechanism with data sharding and synchronous gradient updates can also be used.

[0051] In this embodiment, the wear and degradation index, the multiple physical condition features, and the multiple profile feature quantization values ​​can be aligned and standardized to obtain multiple feature vectors.

[0052] S15, obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index.

[0053] In this embodiment, the difference between the mileage displayed on the dashboard and the true confidence mileage can be calculated, and the absolute value of the quotient of the difference and the mileage displayed on the dashboard can be calculated to obtain the mileage deviation index.

[0054] In this embodiment, the method further includes: When the prediction model has not been trained, obtain the feature coefficient matrix; A weighted value is calculated based on the feature coefficient matrix and the plurality of feature vectors to obtain a first value; The difference between the mileage displayed on the dashboard and the first value is calculated to obtain the second value; The absolute value of the quotient of the second value and the mileage displayed on the dashboard is calculated to obtain the mileage deviation index.

[0055] Through the above embodiments, nonlinear weighted fusion of three types of multimodal data—image, working condition, and behavior—can be achieved to quantify the degree of mileage deviation and form a multidimensional coupled verification, making it impossible for a single tampering method to circumvent cross-verification.

[0056] S16, Generate the odometer tampering risk detection result of the target vehicle based on the mileage deviation index.

[0057] In this embodiment, generating the odometer tampering risk detection result of the target vehicle based on the mileage deviation index includes: When the mileage deviation index is less than or equal to the low-risk threshold, the odometer tampering risk detection result is determined to be low-risk; or When the mileage deviation index is greater than the low-risk threshold and less than or equal to the high-risk threshold, the odometer tampering risk detection result is determined to be medium risk; or When the mileage deviation index is greater than the high-risk threshold, the odometer tampering risk detection result is determined to be high-risk.

[0058] The low-risk threshold and the high-risk threshold can be optimal values ​​selected based on a large number of experiments.

[0059] In this embodiment, after generating the odometer tampering risk detection result of the target vehicle based on the mileage deviation index, the method further includes: When the table adjustment risk detection result is high risk, detect whether there is a logical anomaly between each feature vector; Using feature vectors with logical anomalies as anchor points in the evidence chain, a reliable metric report of vehicle mileage is generated based on the odometer tampering risk detection results and the multiple feature vectors.

[0060] For example, when the vehicle wear and degradation index is quantitatively matched with the reasonable vehicle condition mileage of 0-10000km, and the OBD engine cumulative running time and total fuel consumption are converted into reasonable working condition mileage of 112000-125000km, then the degree of component wear is seriously contradictory to the underlying vehicle operating condition data, which can be used to determine that there is a logical anomaly between the vehicle wear and degradation index and the physical working condition characteristics.

[0061] For example, the vehicle mileage reliability measurement report may include, but is not limited to, the following core content: Risk assessment result for metric tampering: High risk; Key features: The dashboard displays a mileage of 52,000 km, and the quantified true confidence mileage is [112,000 km, 125,000 km].

[0062] Anchor point of the chain of evidence: specific conflicting items (such as "the difference between the fuel consumption logic mileage and the instrument value reaches 60,000 kilometers" and "steering wheel wear matches working conditions of more than 100,000 kilometers").

[0063] The vehicle mileage reliability measurement report can be a standardized visualization report that integrates image evidence, data deviation charts, and profile conflict explanations.

[0064] The vehicle mileage credible measurement report can be sent to the mobile detection terminal through an encrypted channel and is equipped with an anti-tampering mechanism.

[0065] The vehicle mileage reliability measurement report may also include the confidence level of the odometer tampering risk detection results to further improve interpretability.

[0066] The standardized visualization report can also be displayed on a designated terminal for relevant personnel to view directly.

[0067] Furthermore, the full data from the current detection can be archived to a cloud database to serve as new samples for regular optimization of the prediction model and vehicle wear prediction model, thereby continuously improving the model's recognition accuracy and generalization ability.

[0068] Through the above embodiments, a formal report with a complete chain of evidence and quantitative conclusions can be output, making the data traceable and the results verifiable, and providing reference value for transaction disputes and appraisals.

[0069] As can be seen from the above technical solutions, this invention can collect audiovisual data, operating condition data, and cloud-based behavioral profile data of the target vehicle, and generate wear and degradation index, multiple physical operating condition features, and multiple profile feature quantification values ​​accordingly, realizing the connection of multi-source data transmission links and solving the data silo problem; the wear and degradation index, multiple physical operating condition features, and multiple profile feature quantification values ​​are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle under the current wear state, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index, which can quantify the degree of mileage deviation based on multi-dimensional data, effectively solving the problem of avoiding cross-validation through a single tampering method; the mileage deviation index generates the odometer tampering risk detection result of the target vehicle, thereby improving the accuracy of vehicle odometer tampering risk detection.

[0070] like Figure 2 The diagram shown is a functional block diagram of a preferred embodiment of the vehicle odometer tampering risk detection device of the present invention. The vehicle odometer tampering risk detection device 11 includes a data acquisition unit 110, an input unit 111, a generation unit 112, a quantization unit 113, and a calculation unit 114. The module / unit referred to in this invention is a series of computer program segments that can be executed by a processor and perform a fixed function, and are stored in memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0071] The acquisition unit 110 is used to collect the audio-visual data, operating condition data and cloud behavior profile data of the target vehicle in response to the odometer tampering risk detection command of the target vehicle. The input unit 111 is used to input the audiovisual data into the vehicle wear prediction model to obtain the wear degradation index; The generation unit 112 is used to generate multiple physical working condition features based on the working condition data; The quantization unit 113 is used to quantize the cloud-based behavioral profile data to obtain multiple profile feature quantization values; The input unit 111 is also used to input the wear and degradation index, the multiple physical condition features, and the multiple profile feature quantization values ​​as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in the current wear state. The calculation unit 114 is used to obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index. The generation unit 112 is also used to generate the odometer tampering risk detection result of the target vehicle based on the mileage deviation index.

[0072] As can be seen from the above technical solutions, this invention can collect audiovisual data, operating condition data, and cloud-based behavioral profile data of the target vehicle, and generate wear and degradation index, multiple physical operating condition features, and multiple profile feature quantification values ​​accordingly, realizing the connection of multi-source data transmission links and solving the data silo problem; the wear and degradation index, multiple physical operating condition features, and multiple profile feature quantification values ​​are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle under the current wear state, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index, which can quantify the degree of mileage deviation based on multi-dimensional data, effectively solving the problem of avoiding cross-validation through a single tampering method; the mileage deviation index generates the odometer tampering risk detection result of the target vehicle, thereby improving the accuracy of vehicle odometer tampering risk detection.

[0073] like Figure 3 The diagram shown is a schematic diagram of the computer device for implementing the vehicle odometer tampering risk detection method of the present invention.

[0074] The computer device 1 may include a memory 12, a processor 13, and a bus (the arrow in the figure represents the bus), and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a vehicle odometer tampering risk detection program.

[0075] Those skilled in the art will understand that the schematic diagram is merely an example of computer device 1 and does not constitute a limitation on computer device 1. Computer device 1 can be either a bus topology or a star topology. Computer device 1 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, computer device 1 may also include input / output devices, network access devices, etc.

[0076] It should be noted that the computer device 1 described is merely an example. Other existing or future electronic products that are adaptable to this invention should also be included within the scope of protection of this invention and are incorporated herein by reference.

[0077] The memory 12 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the computer device 1, such as a portable hard drive of the computer device 1. In other embodiments, the memory 12 can be an external storage device of the computer device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device 1. Furthermore, the memory 12 can include both internal and external storage units of the computer device 1. The memory 12 can be used not only to store application software and various types of data installed on the computer device 1, such as the code of a vehicle odometer tampering risk detection program, but also to temporarily store data that has been output or will be output.

[0078] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control unit of the computer device 1, connecting various components of the computer device 1 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing a vehicle odometer tampering risk detection program) and calls data stored in the memory 12 to perform various functions of the computer device 1 and process data.

[0079] The processor 13 executes the operating system of the computer device 1 and various installed application programs. The processor 13 executes these application programs to implement the steps in the various vehicle odometer tampering risk detection method embodiments described above, for example... Figure 1 The steps are shown.

[0080] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into an acquisition unit 110, an input unit 111, a generation unit 112, a quantization unit 113, and a calculation unit 114.

[0081] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the vehicle odometer tampering risk detection method described in the various embodiments of this invention.

[0082] If the modules / units integrated in the computer device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0083] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0084] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0085] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0086] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 3 The bus is represented by only one straight line, but this does not mean that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0087] Although not shown, the computer device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 13 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0088] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the computer device 1 and other computer devices.

[0089] Optionally, the computer device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the computer device 1 and to display a visual user interface.

[0090] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0091] It will be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the computer device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0092] Combination Figure 1 The memory 12 in the computer device 1 stores multiple instructions to implement a method for detecting the risk of odometer tampering in vehicles, and the processor 13 can execute the multiple instructions to achieve the following: In response to the command to detect the risk of odometer tampering of the target vehicle, the audio-visual data, operating condition data and cloud-based behavioral profile data of the target vehicle are collected; The audiovisual data is input into the vehicle wear prediction model to obtain the wear degradation index; Multiple physical operating condition features are generated based on the operating condition data; The cloud-based behavioral profile data is quantized to obtain multiple profile feature quantization values; The wear and degradation index, the multiple physical condition features, and the multiple profile feature quantization values ​​are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in the current wear state. Obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index; The odometer tampering risk detection result for the target vehicle is generated based on the mileage deviation index.

[0093] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 1 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0094] It should be noted that all the data involved in this case was legally obtained.

[0095] If any AI models, software tools, or components not belonging to this company appear in the embodiments of this invention, they are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this invention has been obtained by an entity authorized (with the knowledge and consent) or fully authorized by all parties 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.

[0096] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0097] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0098] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0100] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0101] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0102] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this invention can also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for detecting the risk of odometer tampering in vehicles, characterized in that, The method for detecting the risk of vehicle odometer tampering includes: In response to the command to detect the risk of odometer tampering of the target vehicle, the audio-visual data, operating condition data and cloud-based behavioral profile data of the target vehicle are collected; The audiovisual data is input into the vehicle wear prediction model to obtain the wear degradation index; Multiple physical operating condition features are generated based on the operating condition data; The cloud-based behavioral profile data is quantized to obtain multiple profile feature quantization values; The wear and degradation index, the multiple physical condition features, and the quantified values ​​of the multiple profile features are input as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in its current wear state. The prediction model is based on an extreme gradient boosting regression model and is obtained through supervised training in the cloud using a training set constructed with the multiple feature vectors as data dimensions. Each sample in the training set is labeled with its true confidence mileage. Obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index; The odometer tampering risk detection result of the target vehicle is generated based on the mileage deviation index; The step of generating multiple physical operating condition features based on the operating condition data includes: obtaining the mileage displayed on the dashboard and the total cumulative engine running time from the operating condition data, and calculating the quotient of the mileage displayed on the dashboard and the total cumulative engine running time to obtain the average speed of the target vehicle throughout its entire life cycle; obtaining the reference speed range of the target vehicle and the congestion level of the target vehicle's location; adjusting the reference speed range according to the congestion level to obtain the target speed range of the target vehicle; and calculating the average speed of the entire life cycle relative to the target speed range. The degree of deviation is used to obtain the speed deviation coefficient; when the average speed over the entire life cycle is less than the lowest speed in the target speed range, a mileage risk marker quantification value is generated to characterize the obvious low mileage; the cumulative working time of each gear of the transmission, the cumulative fuel consumption of the whole vehicle, the number of charge and discharge cycles of the power battery, and the cumulative total running time of the engine of the target vehicle are obtained and used as the underlying working condition quantification index value; the average speed over the entire life cycle, the speed deviation coefficient, the mileage risk marker quantification value, and the underlying working condition quantification index value are determined as the multiple physical working condition characteristics.

2. The vehicle odometer tampering risk detection method as described in claim 1, characterized in that, The collection of audiovisual data, operating condition data, and cloud-based behavioral profile data of the target vehicle includes: The audiovisual data is collected according to preset locations; The operating condition data is collected through the on-board automatic diagnostic system of the target vehicle; The vehicle identification number of the target vehicle is used to retrieve the cloud-based behavioral profile data of the target vehicle.

3. The vehicle odometer tampering risk detection method as described in claim 1, characterized in that, The quantification of the cloud-based behavioral profile data yields multiple profile feature quantization values, including: Vehicle usage attributes are obtained from the cloud-based behavioral profile data, and these vehicle usage attributes are quantified into vehicle usage attribute quantization label values. The target vehicle's permanent residence and intercity driving frequency are obtained from the cloud-based behavioral profile data, and a mileage matching score is calculated based on the permanent residence and intercity driving frequency. The regional congestion correction coefficient and the historical mileage time sequence conflict quantification value are obtained from the cloud-based behavioral profile data. The vehicle usage attribute quantification label value, the mileage matching score, the regional congestion correction coefficient, and the historical mileage time sequence conflict quantification value are determined as the multiple profile feature quantification values.

4. The vehicle odometer tampering risk detection method as described in claim 1, characterized in that, The method further includes: When the prediction model has not been trained, obtain the feature coefficient matrix; A weighted value is calculated based on the feature coefficient matrix and the plurality of feature vectors to obtain a first value; The difference between the mileage displayed on the dashboard and the first value is calculated to obtain the second value; The absolute value of the quotient of the second value and the mileage displayed on the dashboard is calculated to obtain the mileage deviation index.

5. The vehicle odometer tampering risk detection method as described in claim 1, characterized in that, The process of generating the odometer tampering risk detection result for the target vehicle based on the mileage deviation index includes: When the mileage deviation index is less than or equal to the low-risk threshold, the odometer tampering risk detection result is determined to be low-risk; or When the mileage deviation index is greater than the low-risk threshold and less than or equal to the high-risk threshold, the odometer tampering risk detection result is determined to be medium risk; or When the mileage deviation index is greater than the high-risk threshold, the odometer tampering risk detection result is determined to be high-risk.

6. The vehicle odometer tampering risk detection method as described in claim 5, characterized in that, After generating the odometer tampering risk detection result for the target vehicle based on the mileage deviation index, the method further includes: When the table adjustment risk detection result is high risk, detect whether there is a logical anomaly between each feature vector; Using feature vectors with logical anomalies as anchor points in the evidence chain, a reliable metric report of vehicle mileage is generated based on the odometer tampering risk detection results and the multiple feature vectors.

7. A vehicle odometer tampering risk detection device, characterized in that, For performing the vehicle odometer tampering risk detection method as described in any one of claims 1 to 6, the vehicle odometer tampering risk detection device comprises: The data acquisition unit is used to collect audio-visual data, operating condition data and cloud-based behavioral profile data of the target vehicle in response to the odometer tampering risk detection command. The input unit is used to input the audiovisual data into the vehicle wear prediction model to obtain the wear degradation index; A generation unit is used to generate multiple physical working condition features based on the working condition data; The quantization unit is used to quantize the cloud-based behavioral profile data to obtain multiple profile feature quantization values; The input unit is further configured to input the wear and degradation index, the multiple physical condition features, and the multiple profile feature quantification values ​​as multiple feature vectors into a pre-trained prediction model to obtain the true confidence mileage of the target vehicle in its current wear state; wherein, the prediction model is based on an extreme gradient boosting regression model and is obtained through supervised training in the cloud based on a training set constructed with the multiple feature vectors as data dimensions; each sample in the training set is labeled with a true confidence mileage; The calculation unit is used to obtain the mileage displayed on the dashboard of the target vehicle, and calculate the degree of deviation of the mileage displayed on the dashboard from the true confidence mileage to obtain the mileage deviation index; The generation unit is also used to generate the odometer tampering risk detection result of the target vehicle based on the mileage deviation index.

8. A computer device, characterized in that, The computer device includes: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the vehicle odometer tampering risk detection method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which is executed by a processor in a computer device to implement the vehicle odometer tampering risk detection method as described in any one of claims 1 to 6.

Images