Vehicle mileage value recovery method and device based on decision generation, equipment and storage medium

Abstract

This application discloses a method, apparatus, device, and storage medium for vehicle mileage recovery based on decision generation, relating to the field of vehicle data control technology. The disclosed method for vehicle mileage recovery based on decision generation includes: acquiring target mileage data and vehicle identification information; generating time-series data records based on the target mileage data and the vehicle identification information; performing weight calibration on the time-series data records to obtain a cloud-calibrated mileage value; and upon detecting a mileage data recovery request, performing decision processing based on the cloud-calibrated mileage value to generate a target recovery mileage value, and performing mileage recovery based on the target recovery mileage value. This achieves the technical effect of intelligent decision-making based on cloud-calibrated mileage values ​​to accurately recover vehicle mileage, improving the reliability and accuracy of mileage data recovery.

Description

Technical Field

[0001] This application relates to the field of vehicle data control technology, and in particular to a method, apparatus, device, and storage medium for recovering vehicle mileage values ​​based on decision generation. Background Technology

[0002] As the level of automotive electronics and intelligent connectivity continues to increase, total vehicle mileage is no longer just a simple display data, but a core digital asset related to vehicle residual value assessment, financial risk control, insurance pricing, warranty determination, and the credibility of used car transactions.

[0003] Against this technological backdrop, traditional solutions typically use a single data source to record total mileage, employing a combination instrument as the sole or primary storage unit. When an instrument is replaced, data is manually read from the old instrument and written to the new one, or mileage data is backed up to a fixed controller for direct recovery during replacement. This approach relies on single-point data acquisition and single-point or simple two-point backup, with data replication recovery performed when needed. The entire process lacks comprehensive assessment of the data source's reliability and the ability to identify and verify abnormal data. If the original data itself contains errors, jumps, or the backup data is corrupted, the recovery process will unconditionally write the erroneous value, leading to distorted mileage data.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for recovering vehicle mileage values ​​based on decision generation, aiming to solve the technical problem of ensuring the authenticity, continuity, and reliability of total vehicle mileage data when multiple potential sources of error exist, in the event of replacement of key vehicle components or data anomalies.

[0006] To achieve the above objectives, this application proposes a vehicle mileage value recovery method based on decision generation, the method comprising: Acquire target mileage data and vehicle identification information; Generate time-series data records based on the target mileage data and the vehicle identification information; The time-series data records are weighted and calibrated to obtain cloud-calibrated mileage values; When a mileage data recovery request is detected, a decision is made based on the cloud-calibrated mileage value to generate a target recovery mileage value, and mileage value recovery is performed based on the target recovery mileage value.

[0007] In one embodiment, the step of weighting and calibrating the time-series data records to obtain cloud-calibrated mileage values ​​includes: The time-series data records are parsed to obtain the vehicle driving scenario corresponding to the time-series data records; The instantaneous reliability weight of the time-series data records is evaluated based on the vehicle driving scenario to obtain the target weight value; The mileage data recorded in the time series data is weighted and calibrated according to the target weight value to obtain the cloud-calibrated mileage value.

[0008] In one embodiment, the step of evaluating the instantaneous reliability weight of the time-series data record based on the vehicle driving scenario to obtain the target weight value includes: Identify the scene type based on the vehicle driving scenario; The scenario type is input into a preset mileage data fusion model to evaluate the instantaneous reliability weight of the time-series data record, thereby obtaining the power mileage weight, positioning mileage weight, and chassis mileage weight. The target weight value is determined based on the power mileage weight, the positioning mileage weight, and the chassis mileage weight.

[0009] In one embodiment, the step of generating a target recovery mileage value by making a decision based on the cloud-calibrated mileage value when a mileage data recovery request is detected includes: Upon detecting a mileage data recovery request, retrieve local backup mileage values ​​and historical mileage records from the cloud; The local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are compared and analyzed to obtain the data comparison results; Based on the data comparison results, the corresponding target recovery logic is executed to generate the target recovery mileage value.

[0010] In one embodiment, the step of executing the corresponding target recovery logic based on the data comparison result to generate the target recovery mileage value includes: Obtain multi-source mileage evidence chain data; When the data comparison results show that the local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are consistent, the local backup mileage value will be determined as the target recovery mileage value. If the data comparison result shows an abnormal difference between the local backup mileage value and the cloud-calibrated mileage value, and the cloud-calibrated mileage value is the same as the multi-source mileage evidence chain data, then the cloud-calibrated mileage value is determined as the target recovery mileage value. When the data comparison result indicates that there is an abnormal jump in the cloud-based historical mileage record and the local backup mileage value is an abnormal value of the abnormal jump, the target recovery mileage value is determined through the multi-source mileage evidence chain data.

[0011] In one embodiment, the step of generating time-series data records based on the target mileage data and the vehicle identification information includes: The vehicle identification information is used as a unique identifier to generate a cloud-based time-series database of the vehicle corresponding to the vehicle identification information. The target mileage data is stored in the cloud time-series database according to the collection time sequence to generate time-series data records.

[0012] In one embodiment, the step of acquiring target mileage data includes: Acquire the driving trajectory integral, wheel speed signal, and target energy consumption and target operating time of the motor controller or engine; The driving range data is determined based on the target energy consumption and the target working time; The positioning mileage data is calculated based on the integration of the driving trajectory. Calculate chassis mileage data based on the wheel speed signals; The target mileage data is determined based on the power mileage data, the positioning mileage data, and the chassis mileage data.

[0013] In addition, to achieve the above objectives, this application also proposes a vehicle mileage value recovery device based on decision generation, the vehicle mileage value recovery device based on decision generation includes: a data acquisition module, used to acquire target mileage data and vehicle identification information; A record generation module is used to generate time-series data records based on the target mileage data and the vehicle identification information; The weight calibration module is used to perform weight calibration on the time-series data records to obtain cloud calibration mileage values; The mileage recovery module is used to make a decision based on the cloud-calibrated mileage value when a mileage data recovery request is detected, generate a target recovery mileage value, and perform mileage recovery based on the target recovery mileage value.

[0014] In addition, to achieve the above objectives, this application also proposes a vehicle mileage recovery device based on decision generation, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle mileage recovery method based on decision generation as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the vehicle mileage value recovery method based on decision generation as described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the decision-based vehicle mileage value recovery method described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: This technology addresses the challenges of existing vehicle mileage recovery technologies. It employs a method that acquires target mileage data and vehicle identification information, generates time-series data records based on these data, performs weight calibration on these records to obtain cloud-calibrated mileage values, and, upon detecting a mileage data recovery request, performs decision-making based on the cloud-calibrated mileage value to generate a target recovery mileage value. Finally, it restores the vehicle mileage according to this target recovery mileage value. This approach solves the problems of mileage data reliability risks due to single-point data reliance, lack of intelligent decision-making capabilities in the event of data conflicts, and mechanical recovery logic that easily recovers erroneous mileage data. Compared to existing technologies, this technology achieves intelligent decision-making for vehicle mileage recovery based on cloud-calibrated mileage values. It effectively identifies and avoids erroneous backup data, ensuring the restored mileage value is as close as possible to the vehicle's actual mileage, thus improving the authenticity, reliability, and accuracy of vehicle mileage recovery. Furthermore, it provides cloud-based decision-making backing for the restored mileage value, enhancing the accuracy of the mileage recovery results. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the vehicle mileage value recovery method based on decision generation in this application. Figure 2 This is a schematic diagram of the system architecture and data flow provided in Embodiment 1 of the vehicle mileage value recovery method based on decision generation in this application; Figure 3 This is a schematic diagram of the cloud data fusion and calibration model provided in Embodiment 1 of the vehicle mileage value recovery method based on decision generation in this application; Figure 4 This is a flowchart illustrating Embodiment 2 of the vehicle mileage value recovery method based on decision generation in this application; Figure 5 A simplified flowchart illustrating the vehicle mileage value recovery method based on decision generation provided in Embodiment 2 of this application; Figure 6 This is a schematic diagram of the module structure of the vehicle mileage value recovery device based on decision generation according to an embodiment of this application; Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the vehicle mileage value recovery method based on decision generation in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of this application embodiment is: to acquire target mileage data and vehicle identification information; to generate time-series data records based on the target mileage data and the vehicle identification information; to perform weight calibration on the time-series data records to obtain cloud-calibrated mileage values; and to perform decision processing based on the cloud-calibrated mileage values ​​when a mileage data recovery request is detected, to generate a target recovery mileage value, and to recover the mileage value based on the target recovery mileage value.

[0025] In this embodiment, for ease of description, the following description will focus on identifying the vehicle mileage value recovery device generated based on decision-making.

[0026] To address the challenges of ensuring the authenticity, continuity, and reliability of vehicle mileage data in situations involving replacement of critical vehicle components or data anomalies, this application provides a solution. This solution involves acquiring target mileage data and vehicle identification information, generating time-series data records based on these data, performing weighted calibration on these records to obtain cloud-calibrated mileage values, and upon detecting a mileage data recovery request, performing decision processing based on the cloud-calibrated mileage values ​​to generate a target recovery mileage value. Finally, the vehicle mileage is recovered according to this target recovery mileage value. This approach solves the problems of mileage data reliability risks due to single-point data reliance in existing vehicle mileage recovery technologies, as well as the lack of intelligent decision-making capabilities in the event of data conflicts and the tendency to recover erroneous mileage data due to mechanical recovery logic. Compared to existing technologies, this solution achieves intelligent decision-making for vehicle mileage recovery based on cloud-calibrated mileage values. It effectively identifies and avoids erroneous backup data, ensuring the recovered mileage value is as close as possible to the vehicle's actual mileage, thus improving the authenticity, reliability, and accuracy of vehicle mileage recovery. Furthermore, it provides cloud-based decision-making backing for the recovered mileage value, enhancing the accuracy of the mileage recovery results.

[0027] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a vehicle mileage value recovery device based on decision generation. The following description uses a vehicle mileage value recovery device based on decision generation as an example to illustrate this embodiment and the subsequent embodiments.

[0028] Based on this, embodiments of this application provide a method for restoring vehicle mileage values ​​based on decision generation, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle mileage value recovery method based on decision generation in this application.

[0029] In this embodiment, the vehicle mileage value recovery method based on decision generation includes steps S10~S40: Step S10: Obtain target mileage data and vehicle identification information; It should be noted that the target mileage data is a collection of multi-source heterogeneous mileage evidence chain data that is strongly correlated with the vehicle's mileage, including various mileage-related raw and converted data collected by different controllers and terminals of the vehicle.

[0030] In addition, vehicle identification information is the unique identifier of a vehicle, namely the vehicle identification number, which is the core identifier that distinguishes different vehicles and can be used as the core basis for mileage data management.

[0031] Understandably, relevant mileage data is collected from the instrument cluster, powertrain controller, positioning terminal, and chassis controller, respectively, and integrated to form target mileage data. At the same time, the vehicle's unique identifier is extracted as vehicle identification information.

[0032] Reference Figure 2 , Figure 2 This is a schematic diagram of the system architecture and data flow of the first embodiment of the vehicle mileage value recovery method based on decision generation in this application.

[0033] like Figure 2As shown, the cloud layer contains three core modules: a multi-source data fusion calibration engine, a vehicle database, and an intelligent recovery decision engine. The multi-source data fusion calibration engine outputs the optimal calibration mileage through Kalman or machine learning fusion algorithms. This engine writes the calibrated mileage value into the vehicle database for time-series storage based on the Vehicle Identification Number (VIN). At the same time, the intelligent recovery decision engine can read historical calibration values ​​from the vehicle database for subsequent decision-making. The vehicle-side layer includes a positioning terminal, chassis controller, power controller, instrument cluster, body gateway, and vehicle-to-everything (V2X) terminal. The positioning terminal provides M_gps positioning mileage evidence based on the Global Positioning System (GPS) or BeiDou system. The chassis controller provides M_chassis chassis mileage evidence based on the Anti-lock Braking System (ABS) or Electronic Stability Program (ESP). The power controller provides M_power mileage evidence based on the Electric Drive Unit (EDU) or Motor Control Unit (MCU). The instrument cluster, as the primary data source, stores the M_cluster total mileage and is responsible for writing the final mileage. The body gateway and V2X terminal, as the core hub of the vehicle-side layer, are responsible for collecting data from each controller and storing it in time sequence, while also encrypting and uploading multi-source evidence to the cloud via a cellular network. The network layer is a cellular network, supporting 4G or 5G communication, and handles data transmission between the vehicle and the cloud. In terms of data flow, various data sources on the vehicle send evidence such as M_gps, M_chassis, M_power, and M_cluster to the vehicle gateway and vehicle networking terminal. After encryption, the data is uploaded to the multi-source data fusion calibration engine in the cloud via the cellular network. After fusion processing, the engine generates M_cloud_calibrated cloud calibration mileage and stores it in the vehicle database. When recovery is required, the intelligent recovery decision engine reads historical calibration values ​​from the vehicle database and makes state machine decisions in combination with local backups. If an anomaly is detected, an error correction alarm is triggered. Finally, a recovery command is sent to the vehicle via the cellular network, and the vehicle gateway supervises the instrument cluster to complete the final mileage writing.

[0034] In one feasible implementation, step S10 may include steps S11 to S15: Step S11: Obtain the driving trajectory integral, wheel speed signal, and target energy consumption and target working time of the motor controller or engine; It should be noted that the driving trajectory integral is a parameter obtained by the positioning terminal after integrating the vehicle driving trajectory information collected by the Global Positioning System or the Beidou Satellite Navigation System. It is a core basic parameter for extrapolating the actual driving mileage of the vehicle based on satellite positioning data, and can accurately reflect the spatial trajectory changes of the vehicle.

[0035] In addition, the wheel speed signal is an electrical signal obtained by the chassis braking-related controller after collecting the rotation speed of each wheel of the vehicle in real time. It is raw data that directly reflects the rotation state and rotation duration of the wheel and has a direct physical correlation with the actual mileage of the vehicle.

[0036] Furthermore, the target energy consumption is the total energy consumption value generated by the motor controller or engine throughout the entire vehicle driving cycle. It is a key data reflecting the vehicle's driving status from the power output level, and this data is continuously collected and stored by the power system controller.

[0037] Furthermore, the target working time is the total duration for which the motor controller or engine is in working condition throughout the entire vehicle driving cycle. It is the core quantitative data of the power system's operating status and is recorded and accumulated in real time by the power system controller.

[0038] Understandably, the vehicle's driving trajectory integral, which has already undergone integral calculation, is retrieved from the positioning terminal; the wheel speed signals, which are collected in real time and continuously stored, are extracted from the chassis's braking-related controller; and the target energy consumption and target operating time of the motor controller or engine, which are pre-statistically calculated and stored, are obtained from the power system controller.

[0039] Step S12: Determine the driving range data based on the target energy consumption and the target working time; It should be noted that the power mileage data is the equivalent mileage value obtained by substituting the target energy consumption and target working time of the power system into the preset mileage conversion algorithm. It is mileage evidence data formed from the dimension of vehicle power output, and has clear physical meaning and professional calculation basis.

[0040] Understandably, a mileage conversion algorithm adapted to the vehicle's power type is pre-configured in the processing unit. The target energy consumption and target operating time obtained from the power system controller are simultaneously substituted into the preset algorithm. After professional calculation and numerical conversion by the algorithm, power mileage data matching the vehicle's power operating status is obtained.

[0041] Step S13: Calculate the positioning mileage data based on the integrated driving trajectory. It should be noted that the positioning mileage data is a mileage value obtained by performing professional calculations on the integral of the driving trajectory based on the mileage calculation logic of satellite positioning. It is mileage evidence data formed from the dimension of vehicle spatial driving trajectory, which can intuitively reflect the mileage distance corresponding to the actual driving trajectory of the vehicle.

[0042] Understandably, in accordance with the professional mileage calculation logic corresponding to the Global Positioning System or the BeiDou Navigation Satellite System, the driving trajectory integrals obtained from the positioning terminal are subjected to precise numerical calculations and dimensional conversions. The corresponding positioning mileage data is obtained through the quantification and spatial extrapolation of the trajectory integrals.

[0043] Step S14: Calculate chassis mileage data based on the wheel speed signal; It should be noted that chassis mileage data is a comprehensive mileage value obtained after continuous statistical analysis and calculation of wheel speed signals. It is mileage evidence data formed from the mechanical operation of the vehicle chassis and is professionally deduced based on the physical characteristics of wheel rotation.

[0044] Understandably, based on the fixed circumference of the vehicle wheel rotation and the physical correspondence between the wheel rotation speed and the actual vehicle speed, the wheel speed signal extracted from the chassis braking-related controller is statistically analyzed and continuously calculated throughout the entire cycle, and the corresponding chassis mileage data is obtained after quantization.

[0045] Step S15: Determine the target mileage data based on the power mileage data, the positioning mileage data, and the chassis mileage data.

[0046] Understandably, the power mileage data, positioning mileage data, and chassis mileage data obtained through professional conversion are comprehensively collected and systematically integrated. These three types of heterogeneous mileage data obtained from different physical dimensions are integrated into a complete data set, and this multi-source heterogeneous mileage data set is directly determined as the target mileage data.

[0047] Step S20: Generate time-series data records based on the target mileage data and the vehicle identification information; It should be noted that time-series data recording is a structured data record formed by organizing and arranging target mileage data according to the actual collection time, while also associating it with vehicle identification information. This record can completely preserve the trajectory of each mileage data point over time and the information of the collection nodes.

[0048] Understandably, the process involves matching the corresponding collection time information to each target mileage data point, sorting and organizing the target mileage data in chronological order, and then binding and integrating the sorted target mileage data with vehicle identification information to form a structured time-series data record.

[0049] Step S30: Perform weight calibration on the time-series data records to obtain cloud-calibrated mileage values; It should be noted that weight calibration is an operation that dynamically evaluates the instantaneous reliability of each mileage data source in the time series data record based on different vehicle driving scenarios and the actual state of data collection, assigns corresponding weights, and then integrates and adjusts the multi-source data according to the weights.

[0050] In addition, the cloud-calibrated mileage value is the mileage value obtained after weight calibration and multi-source data fusion calculation of time-series data records. It is the statistically optimal value and more closely matches the actual mileage of the vehicle.

[0051] Understandably, based on the credible weights of each data source in the dynamic evaluation time-series data record of the vehicle driving scenario, the multi-source mileage data in the time-series data record is fused and calculated according to the weights, and after calibration and adjustment, the cloud-calibrated mileage value is obtained.

[0052] Reference Figure 3 , Figure 3 This is a schematic diagram of the cloud data fusion and calibration model of the first embodiment of the vehicle mileage value recovery method based on decision generation in this application.

[0053] like Figure 3As shown in the figure, the timeline is represented by a small person icon on the left, displaying the data evolution of four time slices from top to bottom. Each time slice contains five consecutive mileage records starting from 10000. The first row shows the trajectory of the M_power mileage evidence, with values ​​of 10000, 10078, 10148, 10190, 10245, and 10310, showing a normal growth trend, marked as normal growth. The second row shows the trajectory of the M_gps positioning mileage evidence, with values ​​of 10000, 10079, 10149, 10188, 10244, and 10309, calculated based on trajectory integration. The third row shows the trajectory of the M_cluster instrument cluster mileage, with values ​​of 10000, 10080, 10150, 10200, 10200, and 10200, showing a pause at the fourth to sixth time points, marked as an abnormal jump, indicating a possible instrument malfunction. The fourth row shows the trajectory of the cloud-calibrated mileage, with values ​​of 10000, 10079, 10149, 10189, 10244, and 10309 respectively. This data is obtained by fusing data from three sources: M_power, M_gps, and M_cluster. The bottom of the graph uses a small person icon to represent the fused timeline, with the identifiers of the four data sources (M_power, M_gps, M_cluster, and M_cloud_calibrated) arranged from left to right, indicating the alignment of each data source on a unified time dimension. The bottom of the graph indicates that the fused output is naturally immune to abnormal jumps. This means that when an abnormal jump occurs in M_cluster, the cloud-based fusion model can perform weighted calculations based on normal data from M_power and M_gps, automatically identifying and smoothing instrument anomalies, and outputting calibration mileage values ​​that more closely resemble actual driving conditions. This demonstrates the technical advantages of multi-source data fusion in resisting single points of failure.

[0054] In one feasible implementation, step S30 may include steps S31 to S33: Step S31: Parse the time-series data record to obtain the vehicle driving scenario corresponding to the time-series data record; It should be noted that the vehicle driving scenario is a classification and definition of the actual driving conditions during the vehicle's journey, including road type, signal acquisition status, and driving environment. It covers various actual driving conditions such as highway driving sections, satellite signal loss sections, and ordinary road driving sections, and is the core basis for dynamically assessing the reliability of mileage data sources.

[0055] Understandably, a comprehensive analysis and processing of time-series data records is conducted to extract key information such as mileage data acquisition environment, satellite signal status, and vehicle speed. Based on preset scenario classification standards, the vehicle driving scenario corresponding to the time-series data record is matched and determined.

[0056] Step S32: Evaluate the instantaneous reliability weight of the time-series data record based on the vehicle driving scenario to obtain the target weight value; It should be noted that the instantaneous credibility weight is a quantitative value assigned after dynamically evaluating the true credibility of each mileage data source in the time series data record under the current driving scenario of the vehicle. The instantaneous credibility weight of different mileage data sources will be allocated differently under different driving scenarios.

[0057] In addition, the target weight value is the final set of quantified weight values ​​corresponding to each data source obtained after evaluating the instantaneous reliable weight of all mileage data sources in the time series data record. It is the core calculation basis for subsequent mileage data weight calibration.

[0058] Understandably, based on the preset weight evaluation rules and combined with the determined vehicle driving scenario, the credibility of each mileage data source in the time series data record is dynamically evaluated, and each data source is assigned a corresponding quantitative weight value. After integration, the target weight value is obtained.

[0059] In one feasible implementation, step S32 may include steps S321 to S323: Step S321: Identify the scene type based on the vehicle driving scene; It should be noted that the scenario type is a precise classification and definition of vehicle driving scenarios according to preset classification standards, covering specific types such as highway driving sections, satellite signal loss sections, and ordinary road driving sections. Different scenario types correspond to different levels of credibility of each mileage data source, and are the direct and core basis for carrying out instantaneous credibility weight assessment of mileage data sources.

[0060] Understandably, the process involves retrieving a pre-defined classification standard for vehicle driving scenarios, comparing and matching the analyzed vehicle driving scenarios with the features of each scenario in the standard, and accurately classifying the scenarios based on core features such as satellite signal reception status, road driving type, and vehicle speed, thereby identifying the specific scenario type corresponding to the vehicle driving scenario.

[0061] Step S322: Input the scenario type into the preset mileage data fusion model to evaluate the instantaneous reliability weight of the time series data record, and obtain the power mileage weight, positioning mileage weight and chassis mileage weight. It should be noted that the preset mileage data fusion model is a professional algorithm model built in advance in the cloud for mileage data fusion calculation and data source credibility weight assessment. It has built-in professional algorithms such as Kalman filtering or machine learning regression, which can dynamically and accurately assess the credibility of each mileage data source according to different scenario types.

[0062] In addition, the instantaneous reliability weight is a value obtained by combining the identified specific scenario type and quantifying the reliability of the real-time data of each mileage data source in the time series data record under that scenario. It can intuitively and accurately reflect the validity of the data of each mileage data source under the current driving scenario.

[0063] Furthermore, the power mileage weight is an instantaneous reliable weight obtained by the preset mileage data fusion model based on the power mileage data in the time-series data records and combined with the scenario type evaluation. It serves as the basis for the proportion of power mileage data in subsequent fusion calibration calculations.

[0064] Furthermore, the positioning mileage weight is an instantaneous reliable weight obtained by the preset mileage data fusion model based on the positioning mileage data in the time-series data records and combined with the scene type evaluation. It serves as the basis for the proportion of positioning mileage data in subsequent fusion calibration calculations.

[0065] Furthermore, the chassis mileage weight is an instantaneous reliable weight obtained by the preset mileage data fusion model based on the chassis mileage data in the time-series data records and combined with the scenario type evaluation. It serves as the basis for the proportion of chassis mileage data in subsequent fusion calibration calculations.

[0066] Understandably, the specific vehicle driving scenario type identified is completely input into a pre-built mileage data fusion model in the cloud. Based on the built-in professional algorithm and combined with the core features of the scenario type, the model performs instantaneous reliable weight quantification and calculation on the power mileage data, positioning mileage data, and chassis mileage data in the time-series data records. After the model completes the calculation, it outputs the corresponding power mileage weight, positioning mileage weight, and chassis mileage weight respectively.

[0067] Step S323: Determine the target weight value based on the power mileage weight, the positioning mileage weight, and the chassis mileage weight.

[0068] It should be noted that the target weight value is a complete set of weight values ​​formed by systematically collecting and integrating the power mileage weight, positioning mileage weight, and chassis mileage weight. This set fully covers the corresponding proportion of each mileage data source in the fusion calibration calculation and is the core quantitative basis for subsequent weight calibration of the mileage data recorded in the time series data.

[0069] Understandably, the power mileage weight, positioning mileage weight, and chassis mileage weight obtained after evaluation and calculation by the preset mileage data fusion model are comprehensively and systematically collected and integrated. These three independent weight values ​​are combined into a complete set of weight values, and the set covering the weights of multi-source mileage data is directly determined as the target weight value.

[0070] Step S33: Perform weight calibration on the mileage data recorded in the time series data according to the target weight value to obtain the cloud-calibrated mileage value.

[0071] Understandably, the target weight value is associated and matched with the corresponding mileage data sources in the time series data records. The proportion of fusion calculation of each data source is determined according to the target weight value. Based on this, the multi-source mileage data is fused, calculated, calibrated, and adjusted to obtain the cloud-calibrated mileage value.

[0072] Step S40: When a mileage data recovery request is detected, a decision is made based on the cloud-calibrated mileage value to generate a target recovery mileage value, and mileage value recovery is performed based on the target recovery mileage value.

[0073] It should be noted that the mileage data recovery request is a value acquisition request initiated to the vehicle gateway after the vehicle's instrument cluster has been replaced and powered on. The purpose is to obtain total mileage data that matches the actual vehicle condition in order to complete the writing of mileage data to the new instrument cluster.

[0074] In addition, the decision processing combines cloud-calibrated mileage values ​​with locally backed-up mileage values ​​and cloud-stored historical mileage values, and performs multi-dimensional comparison, judgment and selection operations based on preset logic.

[0075] Furthermore, the target recovery mileage value is the final mileage value determined after decision processing for vehicle mileage recovery. It is the value that is closest to the actual mileage of the vehicle after cross-validation of multi-source data.

[0076] Furthermore, mileage recovery involves encrypting and sending the determined target mileage value to the vehicle, then writing the value into the vehicle's new instrument cluster and completing the data verification process.

[0077] Understandably, upon detecting a mileage data recovery request, the system retrieves the locally backed-up mileage value and the historical mileage value stored in the cloud. It then performs multi-dimensional data comparison and logical judgment in conjunction with the cloud-calibrated mileage value. After decision processing, it generates the target recovery mileage value, encrypts and sends it out, and writes it into the new instrument cluster to complete the mileage value recovery.

[0078] In one feasible implementation, step S40 may include steps S41 to S43: Step S41: When a mileage data recovery request is detected, obtain the local backup mileage value and the cloud historical mileage record; It should be noted that the local backup mileage value is a backup of the most recent valid total mileage of the instrument cluster stored locally on the vehicle. It is a local mileage reference data that the vehicle has reserved in advance for mileage recovery and has the feature of instant retrieval.

[0079] Additionally, the cloud-based historical mileage record is a record of the vehicle's full-cycle mileage data stored in a time-series database built on the cloud with vehicle identification information as its core. It includes historical values ​​and change trajectories of various mileage data sources.

[0080] Understandably, upon detecting a mileage data recovery request, the system reads the most recently valid local backup mileage value from the vehicle's local storage area and retrieves the corresponding vehicle's cloud-based historical mileage record from the vehicle's time-series database.

[0081] Step S42: Compare and analyze the local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value to obtain the data comparison result; It should be noted that the comparative analysis is a professional analytical operation that involves multi-dimensional numerical comparison, deviation quantification calculation, and data consistency verification of local backup mileage values, cloud historical mileage records, and cloud calibration mileage values.

[0082] In addition, the data comparison results are obtained after comparison and analysis. They can intuitively reflect the degree of numerical deviation and the overall feedback of data consistency among the three sets of data, and are the core basis for selecting a recovery strategy.

[0083] Understandably, the data comparison results are obtained by comparing the local backup mileage values, the cloud historical mileage records, and the cloud calibration mileage values ​​in all dimensions, accurately calculating the deviation values ​​between each set of data and verifying the data consistency, and making a comprehensive judgment.

[0084] Step S43: Execute the corresponding target recovery logic based on the data comparison results to generate the target recovery mileage value.

[0085] It should be noted that the target recovery logic is a differentiated mileage recovery strategy pre-set for different data comparison results, and each data state corresponds to a unique and suitable recovery execution rule.

[0086] In addition, the target recovery mileage value is the final mileage value that best matches the actual mileage of the vehicle, selected or calculated based on the matching target recovery logic. It is the core reference data for mileage value recovery.

[0087] Understandably, the data comparison results are precisely matched with various preset recovery logics, the corresponding target recovery logic that is successfully matched is executed, and the value is selected or calculated based on the logic and determined as the target recovery mileage value.

[0088] In one feasible implementation, step S43 may include steps S431 to S434: Step S431: Obtain multi-source mileage evidence chain data; It should be noted that the multi-source mileage evidence chain data is a collection of diverse and heterogeneous mileage data that is strongly correlated with the vehicle's mileage. It covers various types of mileage data collected and converted from the power system, positioning terminal, and chassis controller. It is an independent data basis for verifying the vehicle's actual mileage from different physical dimensions, and is pre-stored and managed in the cloud.

[0089] Understandably, data extraction and preparation are completed by retrieving pre-encrypted, multi-source heterogeneous mileage evidence chain data strongly correlated with vehicle mileage from a time-series database built on the cloud with vehicle identification information as the core, in order to provide comprehensive evidence data support for recovery decisions under different data comparison results.

[0090] Step S432: When the data comparison result shows that the local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are consistent, the local backup mileage value is determined as the target recovery mileage value. Understandably, the first step is to verify that the data comparison results show a high degree of consistency between the local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value. Based on this, the local backup mileage value is determined to be reliable and valid mileage data, and is directly selected as the target recovery mileage value for vehicle mileage recovery.

[0091] Step S433: When the data comparison result shows an abnormal difference between the local backup mileage value and the cloud-calibrated mileage value, and the cloud-calibrated mileage value is the same as the multi-source mileage evidence chain data, the cloud-calibrated mileage value is determined as the target recovery mileage value. It should be noted that abnormal difference values ​​refer to the numerical deviation between the local backup mileage value and the cloud-calibrated mileage value that exceeds the preset reasonable deviation threshold. This is not a minor data deviation caused by normal vehicle driving. This numerical deviation can directly reflect the possibility that the local backup mileage value is unreliable.

[0092] Understandably, the process involves first verifying that the data comparison results show an abnormal difference between the local backup mileage value and the cloud-calibrated mileage value. Then, the matching status of the cloud-calibrated mileage value and the acquired multi-source mileage evidence chain data is further checked. If the two values ​​are confirmed to be the same, it is determined that the local backup mileage value is damaged or is outdated data. The cloud-calibrated mileage value is then directly determined as the target recovery mileage value for vehicle mileage recovery.

[0093] Step S434: When the data comparison result shows that there is an abnormal jump in the cloud historical mileage record and the local backup mileage value is an abnormal value of the abnormal jump, the target recovery mileage value is determined through the multi-source mileage evidence chain data.

[0094] It should be noted that abnormal jumps refer to sudden and unnatural increases or decreases in the mileage value recorded in the cloud-based historical mileage records. These changes do not conform to the natural growth pattern of the vehicle's actual mileage and are a typical manifestation of abnormal mileage data.

[0095] Additionally, outliers refer to the mileage values ​​that occur when there are abnormal jumps in the cloud-based historical mileage records. These values ​​are not the mileage values ​​corresponding to the actual driving conditions of the vehicle and do not have the reliability to be used as reference data for mileage recovery.

[0096] Understandably, the first step is to verify that the data comparison results show an abnormal jump in the cloud-based historical mileage record, and the local backup mileage value happens to be the abnormal value corresponding to this abnormal jump. Based on this, the local backup mileage value is determined to be invalid data and is rejected. Relying on the multi-source mileage evidence chain data that has been obtained, the most likely true mileage value when the vehicle experiences a data abnormality failure is calculated through a preset professional algorithm. The calculated value is then determined as the target recovery mileage value for vehicle mileage value recovery.

[0097] This embodiment provides a vehicle mileage value recovery method based on decision generation. By constructing a three-layer architecture of multi-source heterogeneous data acquisition at the vehicle end, cloud-based fusion calibration, and intelligent decision recovery, it uses Kalman filtering or machine learning algorithms to dynamically evaluate the instantaneous reliability weight of each data source and generate cloud-calibrated mileage values. Combined with a state machine decision engine, it performs multi-dimensional comparative analysis of local backups, cloud historical records, and calibration values. This solves the reliability risk caused by single-point dependence of total vehicle mileage data and the technical problems of traditional backup recovery schemes lacking intelligent decision-making capabilities. It achieves the beneficial effects of resisting single-point failures, realizing intelligent error correction and recovery, enhancing after-sales authority, and providing forward-looking fault warnings.

[0098] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 The vehicle mileage value recovery method based on decision generation, step S20, further includes steps S21-S22: Step S21: Use the vehicle identification information as a unique identifier to generate a cloud-based time-series database of the vehicle corresponding to the vehicle identification information. It should be noted that the cloud-based time-series database is a dedicated database built in the cloud. It is a database carrier that stores, manages, and traces vehicle-related data with time as its core dimension. It is specifically used to retain various mileage-related data of vehicles and has the exclusive feature of retrieving and analyzing data by time.

[0099] It is understandable that vehicle identification information is used as the unique identifier for the cloud database. A dedicated database storage space is built for each vehicle corresponding to this identifier in the cloud. The internal storage structure of the database is built according to the storage rules and management logic of time-series data, and the generation operation of the dedicated cloud time-series database for this vehicle is completed.

[0100] Step S22: Store the target mileage data in the cloud time-series database according to the collection time sequence to generate time-series data records.

[0101] It should be noted that the collection time order refers to the order in which target mileage data is actually collected by various controllers and terminals on the vehicle. It is the core basis for the orderly storage of multi-source heterogeneous target mileage data and can clearly reflect the actual acquisition nodes of each mileage data.

[0102] Understandably, each target mileage data item is first matched with the actual time information collected by various controllers and terminals on the vehicle. Then, in strict accordance with the order of collection time, the target mileage data with exclusive time information are classified and stored one by one into the cloud time-series database of the corresponding vehicle. After orderly storage and structured organization, a complete time-series data record is formed.

[0103] This embodiment provides a vehicle mileage value recovery method based on decision generation. By building a cloud-based time-series database with vehicle identification information as the unique identifier, and strictly classifying and storing multi-source heterogeneous target mileage data into this dedicated database according to the collection time sequence, it solves the technical problems of lack of a unified time-series management carrier for vehicle life cycle mileage data, difficulty in data traceability, and difficulty in aligning and analyzing multi-source data according to the time dimension. It achieves the beneficial effects of realizing refined time-series management of vehicle mileage data, supporting cloud fusion algorithms to accurately call data according to the time axis, and providing a complete data chain for historical fault tracing and intelligent recovery decision-making.

[0104] For example, to help understand the implementation process of the vehicle mileage value recovery method based on decision generation obtained by combining this embodiment with the above embodiment one, please refer to... Figure 5 , Figure 5 A simplified flowchart of a vehicle mileage recovery method based on decision generation is provided, specifically: The process begins with the new instrument cluster powering on and initiating a recovery request. The vehicle gateway then reads the local backup value M_backup_local and requests a recovery decision from the cloud, including M_backup_local in the request for comparison and analysis. The cloud first determines if M_backup_local is valid. If valid, it proceeds to the left branch, performing recovery using the cloud calibration value M_cloud_calibrated and recording an invalid local backup log. This branch corresponds to scenarios where the local backup is corrupted or lost. If M_backup_local is valid, it enters the right main branch, further determining if its deviation from M_cloud_calibrated is less than or equal to a threshold. If yes, it performs recovery using M_backup_local. This branch corresponds to scenarios where the three values ​​are highly consistent and the data is reliable. If the deviation exceeds the threshold, it continues to check if the historical evidence chain supports M_backup_local. If yes, it also performs recovery using M_backup_local. This branch corresponds to scenarios where the local backup differs from the cloud calibration value but is still reliable based on historical data verification. If the historical evidence chain does not support M_backup_local, the process flows to the rightmost branch, where the estimated value from the evidence chain is used for recovery, and a potential instrument malfunction alarm is reported. This branch corresponds to error correction scenarios where the local backup itself contains abnormal jump values. After each branch is completed, the process merges into the diamond-shaped confluence node below, ultimately leading to the upload of the recovery completion result to the cloud for archiving. The process ends with a circle symbol.

[0105] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle mileage value recovery method based on decision generation in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0106] This application also provides a vehicle mileage value recovery device based on decision generation; please refer to... Figure 6 The vehicle mileage value recovery device based on decision generation includes: Data acquisition module 10 is used to acquire target mileage data and vehicle identification information; The record generation module 20 is used to generate time-series data records based on the target mileage data and the vehicle identification information; The weight calibration module 30 is used to perform weight calibration on the time-series data records to obtain cloud calibration mileage values; The mileage recovery module 40 is used to perform decision processing based on the cloud-calibrated mileage value when a mileage data recovery request is detected, generate a target recovery mileage value, and perform mileage recovery based on the target recovery mileage value.

[0107] The vehicle mileage recovery device based on decision generation provided in this application, employing the vehicle mileage recovery method based on decision generation in the above embodiments, can solve the technical problem of ensuring the authenticity, continuity, and reliability of total vehicle mileage data even when multiple potential sources of error exist, in cases of replacement of key vehicle components or data anomalies. Compared with the prior art, the beneficial effects of the vehicle mileage recovery device based on decision generation provided in this application are the same as those of the vehicle mileage recovery method based on decision generation provided in the above embodiments, and other technical features in the vehicle mileage recovery device based on decision generation are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0108] In one embodiment, the weight calibration module 30 is further configured to parse the time-series data record to obtain the vehicle driving scenario corresponding to the time-series data record; The instantaneous reliability weight of the time-series data records is evaluated based on the vehicle driving scenario to obtain the target weight value; The mileage data recorded in the time series data is weighted and calibrated according to the target weight value to obtain the cloud-calibrated mileage value.

[0109] In one embodiment, the weight calibration module 30 is further configured to identify the scene type based on the vehicle driving scene; The scenario type is input into a preset mileage data fusion model to evaluate the instantaneous reliability weight of the time-series data record, thereby obtaining the power mileage weight, positioning mileage weight, and chassis mileage weight. The target weight value is determined based on the power mileage weight, the positioning mileage weight, and the chassis mileage weight.

[0110] In one embodiment, the mileage value recovery module 40 is further configured to obtain local backup mileage values ​​and cloud historical mileage records when a mileage data recovery request is detected; The local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are compared and analyzed to obtain the data comparison results; Based on the data comparison results, the corresponding target recovery logic is executed to generate the target recovery mileage value.

[0111] In one embodiment, the mileage recovery module 40 is further configured to acquire multi-source mileage evidence chain data; When the data comparison results show that the local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are consistent, the local backup mileage value will be determined as the target recovery mileage value. If the data comparison result shows an abnormal difference between the local backup mileage value and the cloud-calibrated mileage value, and the cloud-calibrated mileage value is the same as the multi-source mileage evidence chain data, then the cloud-calibrated mileage value is determined as the target recovery mileage value. When the data comparison result indicates that there is an abnormal jump in the cloud-based historical mileage record and the local backup mileage value is an abnormal value of the abnormal jump, the target recovery mileage value is determined through the multi-source mileage evidence chain data.

[0112] In one embodiment, the record generation module 20 is further configured to use the vehicle identification information as a unique identifier to generate a cloud-based time-series database of the vehicle corresponding to the vehicle identification information. The target mileage data is stored in the cloud time-series database according to the collection time sequence to generate time-series data records.

[0113] In one embodiment, the data acquisition module 10 is further configured to acquire driving trajectory integral, wheel speed signal, and target energy consumption and target working time of motor controller or engine; The driving range data is determined based on the target energy consumption and the target working time; The positioning mileage data is calculated based on the integration of the driving trajectory. Calculate chassis mileage data based on the wheel speed signals; The target mileage data is determined based on the power mileage data, the positioning mileage data, and the chassis mileage data.

[0114] This application provides a vehicle mileage recovery device based on decision generation. The vehicle mileage recovery device based on decision generation includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the vehicle mileage recovery method based on decision generation in the first embodiment described above.

[0115] The following is for reference. Figure 7 This document illustrates a structural diagram suitable for implementing a decision-based vehicle mileage recovery device according to embodiments of this application. The decision-based vehicle mileage recovery device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The vehicle mileage recovery device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0116] like Figure 7 As shown, the decision-based vehicle mileage recovery device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the decision-based vehicle mileage recovery device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the decision-based vehicle odometer recovery device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a decision-based vehicle odometer recovery device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0117] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0118] The vehicle mileage recovery device based on decision generation provided in this application, employing the vehicle mileage recovery method based on decision generation in the above embodiments, can solve the technical problem of ensuring the authenticity, continuity, and reliability of total vehicle mileage data even when multiple potential sources of error exist, in cases of replacement of key vehicle components or data anomalies. Compared with the prior art, the beneficial effects of the vehicle mileage recovery device based on decision generation provided in this application are the same as those of the vehicle mileage recovery method based on decision generation provided in the above embodiments, and other technical features in this vehicle mileage recovery device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0119] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0120] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0121] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle mileage value recovery method based on decision generation in the above embodiments.

[0122] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), Erasable Programmable Read Only Memory (EPROM), optical fiber, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may 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. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0123] The aforementioned computer-readable storage medium may be included in a decision-based vehicle mileage recovery device; or it may exist independently and not be assembled into a decision-based vehicle mileage recovery device.

[0124] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a decision-based vehicle mileage recovery device, cause the decision-based vehicle mileage recovery device to: acquire target mileage data and vehicle identification information; generate time-series data records based on the target mileage data and the vehicle identification information; perform weight calibration on the time-series data records to obtain cloud-calibrated mileage values; and, upon detecting a mileage data recovery request, perform decision processing based on the cloud-calibrated mileage values ​​to generate a target recovery mileage value, and perform mileage recovery based on the target recovery mileage value.

[0125] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0127] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0128] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described decision-based vehicle mileage recovery method. This solves the technical problem of ensuring the authenticity, continuity, and reliability of vehicle total mileage data even when multiple potential sources of error exist, in cases of replacement of critical vehicle components or data anomalies. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the decision-based vehicle mileage recovery method provided in the above embodiments, and will not be repeated here.

[0129] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the decision-based vehicle mileage value recovery method described above.

[0130] The computer program product provided in this application solves the technical problem of ensuring the authenticity, continuity, and reliability of vehicle total mileage data even when multiple potential sources of error exist, in the event of replacement of critical vehicle components or data anomalies. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the decision-based vehicle mileage value recovery method provided in the above embodiments, and will not be elaborated upon here.

[0131] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for restoring vehicle mileage values ​​based on decision generation, characterized in that, The method includes: Acquire target mileage data and vehicle identification information; Generate time-series data records based on the target mileage data and the vehicle identification information; The time-series data records are weighted and calibrated to obtain cloud-calibrated mileage values; When a mileage data recovery request is detected, a decision is made based on the cloud-calibrated mileage value to generate a target recovery mileage value, and mileage value recovery is performed based on the target recovery mileage value.

2. The method as described in claim 1, characterized in that, The step of performing weight calibration on the time-series data records to obtain cloud-calibrated mileage values ​​includes: The time-series data records are parsed to obtain the vehicle driving scenario corresponding to the time-series data records; The instantaneous reliability weight of the time-series data records is evaluated based on the vehicle driving scenario to obtain the target weight value; The mileage data recorded in the time series data is weighted and calibrated according to the target weight value to obtain the cloud-calibrated mileage value.

3. The method as described in claim 2, characterized in that, The step of evaluating the instantaneous reliability weight of the time-series data record based on the vehicle driving scenario to obtain the target weight value includes: Identify the scene type based on the vehicle driving scenario; The scenario type is input into a preset mileage data fusion model to evaluate the instantaneous reliability weight of the time-series data record, thereby obtaining the power mileage weight, positioning mileage weight, and chassis mileage weight. The target weight value is determined based on the power mileage weight, the positioning mileage weight, and the chassis mileage weight.

4. The method as described in claim 1, characterized in that, The step of generating a target recovery mileage value by making a decision based on the cloud-calibrated mileage value when a mileage data recovery request is detected includes: Upon detecting a mileage data recovery request, retrieve local backup mileage values ​​and historical mileage records from the cloud; The local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are compared and analyzed to obtain the data comparison results; Based on the data comparison results, the corresponding target recovery logic is executed to generate the target recovery mileage value.

5. The method as described in claim 4, characterized in that, The step of executing the corresponding target recovery logic based on the data comparison results to generate the target recovery mileage value includes: Obtain multi-source mileage evidence chain data; When the data comparison results show that the local backup mileage value, the cloud historical mileage record, and the cloud calibration mileage value are consistent, the local backup mileage value will be determined as the target recovery mileage value. If the data comparison result shows an abnormal difference between the local backup mileage value and the cloud-calibrated mileage value, and the cloud-calibrated mileage value is the same as the multi-source mileage evidence chain data, then the cloud-calibrated mileage value is determined as the target recovery mileage value. When the data comparison result indicates that there is an abnormal jump in the cloud-based historical mileage record and the local backup mileage value is an abnormal value of the abnormal jump, the target recovery mileage value is determined through the multi-source mileage evidence chain data.

6. The method as described in claim 1, characterized in that, The step of generating time-series data records based on the target mileage data and the vehicle identification information includes: The vehicle identification information is used as a unique identifier to generate a cloud-based time-series database of the vehicle corresponding to the vehicle identification information. The target mileage data is stored in the cloud time-series database according to the collection time sequence to generate time-series data records.

7. The method as described in claim 1, characterized in that, The steps for obtaining target mileage data include: Acquire the driving trajectory integral, wheel speed signal, and target energy consumption and target operating time of the motor controller or engine; The driving range data is determined based on the target energy consumption and the target working time; The positioning mileage data is calculated based on the integration of the driving trajectory. Calculate chassis mileage data based on the wheel speed signals; The target mileage data is determined based on the power mileage data, the positioning mileage data, and the chassis mileage data.

8. A vehicle mileage value recovery device based on decision generation, characterized in that, The device includes: The data acquisition module is used to acquire target mileage data and vehicle identification information; A record generation module is used to generate time-series data records based on the target mileage data and the vehicle identification information; The weight calibration module is used to perform weight calibration on the time-series data records to obtain cloud calibration mileage values; The mileage recovery module is used to make a decision based on the cloud-calibrated mileage value when a mileage data recovery request is detected, generate a target recovery mileage value, and perform mileage recovery based on the target recovery mileage value.

9. A vehicle mileage recovery device based on decision generation, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the decision-based vehicle mileage recovery method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle mileage value recovery method based on decision generation as described in any one of claims 1 to 7.

Images