Vehicle defect misjudgment identification method and system based on model rules

Abstract

The present invention discloses a vehicle defect misjudgment identification method and system based on model rules, the method comprising: obtaining vehicle sensor data and vehicle information of a vehicle to be detected; based on a defect prediction algorithm model, predicting a defect prediction result corresponding to the vehicle to be detected according to the vehicle sensor data; screening out at least one analog vehicle detection record from multiple historical vehicle detection records according to the vehicle information of the vehicle to be detected; and correcting the defect prediction result according to the vehicle defect detection result in the analog vehicle detection record to obtain a corrected defect prediction result corresponding to the vehicle to be detected. It can be seen that the present invention can reduce vehicle defect misjudgments or missed detections caused by failure of the prediction algorithm or overfitting, improve the accuracy and efficiency of vehicle defect detection, and improve vehicle safety.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a vehicle defect misjudgment identification method and system based on model rules. Background Art

[0002] With the development of intelligent recognition algorithms and the improvement of intelligent vehicle defect detection technology, more and more vehicle production or maintenance organizations have begun to adopt more efficient data processing algorithms to achieve automatic vehicle defect detection to improve the safety of vehicle production or maintenance. When detecting vehicle defects, most of the existing technologies only consider the sensor data characteristics of the target detection vehicle itself, and do not fully combine the historical vehicle inspection records of the same or similar vehicles to adjust or correct the defect detection results. Therefore, its detection results may be limited by the prediction ability of the model and may result in false detection or missed detection, thereby causing detection accidents or even production accidents. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a vehicle defect misjudgment identification method and system based on model rules, which can reduce vehicle defect misjudgment or missed detection caused by failure of prediction algorithm or overfitting, improve the accuracy and efficiency of vehicle defect detection, and improve vehicle safety.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a vehicle defect misjudgment identification method based on model rules, the method comprising:

[0005] Acquire vehicle sensor data and vehicle information of the vehicle to be detected;

[0006] Based on the defect prediction algorithm model, according to the vehicle sensor data, predict the defect prediction result corresponding to the vehicle to be inspected;

[0007] Filtering at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected;

[0008] According to the vehicle defect detection result in the analog vehicle inspection record, the defect prediction result is corrected to obtain a corrected defect prediction result corresponding to the vehicle to be inspected.

[0009] As an optional embodiment, in the first aspect of the present invention, the vehicle sensor data includes vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data and vehicle temperature and humidity data; the vehicle information includes vehicle model, vehicle type, vehicle physical parameters, vehicle power parameters and vehicle internal component parameters; the vehicle physical parameters include vehicle length, vehicle width, vehicle height and vehicle interior space parameters.

[0010] As an optional implementation, in the first aspect of the present invention, the defect prediction result corresponding to the vehicle to be inspected is predicted based on the defect prediction algorithm model according to the vehicle sensor data, including:

[0011] Based on a preset part division rule, the vehicle sensor data is divided into sensor data corresponding to a plurality of vehicle parts to obtain a plurality of part sensor data sets;

[0012] Inputting each of the part sensor data sets into a defect detection algorithm model corresponding to the corresponding vehicle part to obtain the part defect type and detection probability corresponding to each of the part sensor data sets;

[0013] The part defect type and the corresponding vehicle part whose detection probability is greater than a preset probability threshold are determined as the defect prediction result corresponding to the vehicle to be detected.

[0014] As an optional embodiment, in the first aspect of the present invention, the defect detection algorithm model is an RNN neural network, which is trained by a training data set including training sensor data corresponding to multiple vehicle parts and corresponding defect annotations; the vehicle parts are doors, front of the vehicle, body, chassis, roof, rear of the vehicle, trunk, interior space or wheels.

[0015] As an optional implementation, in the first aspect of the present invention, the step of selecting at least one analog vehicle detection record from a plurality of historical vehicle detection records based on the vehicle information of the vehicle to be detected comprises:

[0016] For each historical vehicle inspection record, determine the vehicle information corresponding to each inspection record in the historical vehicle inspection record;

[0017] Calculating the information similarity between the vehicle information corresponding to each detection record in the historical vehicle detection record and the vehicle information of the vehicle to be detected;

[0018] Calculate the weighted sum average of the information similarities corresponding to all the detection records in the historical vehicle detection record to obtain a record similarity parameter corresponding to the historical vehicle detection record;

[0019] All the historical vehicle detection records whose record similarity parameters are greater than a preset parameter threshold are screened out to obtain at least one analog vehicle detection record.

[0020] As an optional embodiment, in the first aspect of the present invention, when calculating the record similarity parameters, the weighted calculation weight corresponding to the information similarity corresponding to each detection record includes a first weight and a second weight; the first weight is greater than a first weight threshold when the vehicle model in the vehicle information of the corresponding detection record is the same as the vehicle to be detected; the second weight is proportional to the vehicle defect degree value in the detection result corresponding to the corresponding detection record.

[0021] As an optional implementation, in the first aspect of the present invention, the defect prediction result is corrected according to the vehicle defect detection result in the analog vehicle inspection record to obtain the corrected defect prediction result corresponding to the vehicle to be inspected, including:

[0022] For each part defect type corresponding to each vehicle part in the defect prediction result, determine a record proportion parameter corresponding to the part defect type according to the vehicle defect detection result in the analog vehicle detection record;

[0023] Calculating a record reference probability proportional to the record proportion parameter;

[0024] Calculate the probability difference between the detection probability corresponding to the defect type of the part and the recorded reference probability;

[0025] When the probability difference is a positive number and is greater than a first difference threshold, the defect type of the part is determined as an untrustworthy defect;

[0026] When the probability difference is a negative number and is greater than a second difference threshold, the defect type of the part is determined as an important defect of concern;

[0027] When the probability difference is less than the third difference threshold and greater than the fourth difference threshold, the defect degree value corresponding to the defect type of the part is determined as the average of the detection probability and the recorded reference probability; the fourth difference threshold is less than the third difference threshold; the third difference threshold is less than the first difference threshold and the second difference threshold.

[0028] As an optional implementation, in the first aspect of the present invention, determining the record proportion parameter corresponding to the defect type of the part according to the vehicle defect detection result in the analog vehicle inspection record includes:

[0029] Counting the number of occurrences of the defect type corresponding to the vehicle part in the vehicle defect detection result of each analog vehicle detection record;

[0030] Calculate the weighted sum average of the occurrence times corresponding to all the analog vehicle inspection records to obtain the number parameter corresponding to the defect type of the part; wherein the weighted sum calculation weight corresponding to each occurrence time is proportional to the average value of the vehicle defect degree value in the inspection results of all records of the defect type of the part in the corresponding analog vehicle inspection record;

[0031] Determine the sum of the number parameters corresponding to each defect type in all the analog vehicle inspection records of all other defect types, and obtain a total number parameter; the other defect types are the other defect types in the defect prediction results except the defect type of the part;

[0032] The ratio of the number parameter corresponding to the defect type of the part to the total number parameter is calculated to obtain the record proportion parameter corresponding to the defect type of the part.

[0033] A second aspect of an embodiment of the present invention discloses a vehicle defect misjudgment identification system based on model rules, the system comprising:

[0034] An acquisition module, used to acquire vehicle sensor data and vehicle information of a vehicle to be detected;

[0035] A prediction module, used to predict the defect prediction result corresponding to the vehicle to be inspected based on the defect prediction algorithm model and the vehicle sensor data;

[0036] A screening module, configured to screen out at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected;

[0037] The correction module is used to correct the defect prediction result according to the vehicle defect detection result in the analog vehicle detection record to obtain a corrected defect prediction result corresponding to the vehicle to be detected.

[0038] As an optional embodiment, in the second aspect of the present invention, the vehicle sensor data includes vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data and vehicle temperature and humidity data; the vehicle information includes vehicle model, vehicle type, vehicle physical parameters, vehicle power parameters and vehicle internal component parameters; the vehicle physical parameters include vehicle length, vehicle width, vehicle height and vehicle interior space parameters.

[0039] As an optional implementation, in the second aspect of the present invention, the prediction module predicts the defect prediction result corresponding to the vehicle to be detected based on the defect prediction algorithm model and the vehicle sensor data, including:

[0040] Based on a preset part division rule, the vehicle sensor data is divided into sensor data corresponding to a plurality of vehicle parts to obtain a plurality of part sensor data sets;

[0041] Inputting each of the part sensor data sets into a defect detection algorithm model corresponding to the corresponding vehicle part to obtain the part defect type and detection probability corresponding to each of the part sensor data sets;

[0042] The part defect type and the corresponding vehicle part whose detection probability is greater than a preset probability threshold are determined as the defect prediction result corresponding to the vehicle to be detected.

[0043] As an optional embodiment, in the second aspect of the present invention, the defect detection algorithm model is an RNN neural network, which is trained by a training data set including training sensor data corresponding to multiple vehicle parts and corresponding defect annotations; the vehicle parts are doors, fronts, bodies, chassis, roofs, rear ends, trunks, interior spaces or wheels.

[0044] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module screens out at least one analogous vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected includes:

[0045] For each historical vehicle inspection record, determine the vehicle information corresponding to each inspection record in the historical vehicle inspection record;

[0046] Calculating the information similarity between the vehicle information corresponding to each detection record in the historical vehicle detection record and the vehicle information of the vehicle to be detected;

[0047] Calculate the weighted sum average of the information similarities corresponding to all the detection records in the historical vehicle detection record to obtain a record similarity parameter corresponding to the historical vehicle detection record;

[0048] All the historical vehicle detection records whose record similarity parameters are greater than a preset parameter threshold are screened out to obtain at least one analog vehicle detection record.

[0049] As an optional embodiment, in the second aspect of the present invention, when calculating the record similarity parameters, the weighted calculation weight corresponding to the information similarity corresponding to each detection record includes a first weight and a second weight; the first weight is greater than a first weight threshold when the vehicle model in the vehicle information of the corresponding detection record is the same as the vehicle to be detected; the second weight is proportional to the vehicle defect degree value in the detection result corresponding to the corresponding detection record.

[0050] As an optional implementation, in the second aspect of the present invention, the correction module corrects the defect prediction result according to the vehicle defect detection result in the analog vehicle inspection record, and obtains the corrected defect prediction result corresponding to the vehicle to be inspected, including:

[0051] For each part defect type corresponding to each vehicle part in the defect prediction result, determine a record proportion parameter corresponding to the part defect type according to the vehicle defect detection result in the analog vehicle detection record;

[0052] Calculating a record reference probability proportional to the record proportion parameter;

[0053] Calculate the probability difference between the detection probability corresponding to the defect type of the part and the recorded reference probability;

[0054] When the probability difference is a positive number and is greater than a first difference threshold, the defect type of the part is determined as an untrustworthy defect;

[0055] When the probability difference is a negative number and is greater than a second difference threshold, the defect type of the part is determined as an important defect of concern;

[0056] When the probability difference is less than the third difference threshold and greater than the fourth difference threshold, the defect degree value corresponding to the defect type of the part is determined as the average of the detection probability and the recorded reference probability; the fourth difference threshold is less than the third difference threshold; the third difference threshold is less than the first difference threshold and the second difference threshold.

[0057] As an optional implementation, in the second aspect of the present invention, the correction module determines the specific manner of the record proportion parameter corresponding to the defect type of the part according to the vehicle defect detection result in the analog vehicle inspection record, including:

[0058] Counting the number of occurrences of the defect type corresponding to the vehicle part in the vehicle defect detection result of each analog vehicle detection record;

[0059] Calculate the weighted sum average of the occurrence times corresponding to all the analog vehicle inspection records to obtain the number parameter corresponding to the defect type of the part; wherein the weighted sum calculation weight corresponding to each occurrence time is proportional to the average value of the vehicle defect degree value in the inspection results of all records of the defect type of the part in the corresponding analog vehicle inspection record;

[0060] Determine the sum of the number parameters corresponding to each defect type in all the analog vehicle inspection records of all other defect types, and obtain a total number parameter; the other defect types are the other defect types in the defect prediction results except the defect type of the part;

[0061] The ratio of the number parameter corresponding to the defect type of the part to the total number parameter is calculated to obtain the record proportion parameter corresponding to the defect type of the part.

[0062] The third aspect of the present invention discloses another vehicle defect misjudgment identification system based on model rules, the system comprising:

[0063] A memory storing executable program code;

[0064] a processor coupled to the memory;

[0065] The processor calls the executable program code stored in the memory to execute part or all of the steps in the vehicle defect misjudgment identification method based on model rules disclosed in the first aspect of the present invention.

[0066] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the vehicle defect misjudgment identification method based on model rules disclosed in the first aspect of the present invention.

[0067] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0068] The present invention can predict the defect prediction results corresponding to the vehicle to be inspected according to the vehicle sensor data based on the defect prediction algorithm model, and then screen out at least one analog vehicle inspection record from multiple historical vehicle inspection records, so as to correct the defect prediction results based on the vehicle defect detection results in the analog vehicle inspection records to obtain more accurate defect prediction results, thereby reducing the misjudgment or missed detection of vehicle defects caused by failure of the prediction algorithm or overfitting, improving the accuracy and efficiency of vehicle defect detection, and improving vehicle safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0070] Figure 1The present invention is a flowchart of a vehicle defect misjudgment identification method based on model rules disclosed in an embodiment of the present invention.

[0071] Figure 2 It is a structural schematic diagram of a vehicle defect misjudgment identification system based on model rules disclosed in an embodiment of the present invention.

[0072] Figure 3 It is a structural schematic diagram of another vehicle defect misjudgment identification system based on model rules disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] The terms "first", "second", etc. in the description and drawings of the present invention are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0075] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0076] The present invention discloses a vehicle defect misjudgment identification method and system based on model rules, which can predict the defect prediction result corresponding to the vehicle to be detected based on the vehicle sensor data based on the defect prediction algorithm model, and then select at least one analog vehicle detection record from multiple historical vehicle detection records, so as to correct the defect prediction result based on the vehicle defect detection result in the analog vehicle detection record to obtain a more accurate defect prediction result, thereby reducing the vehicle defect misjudgment or missed detection caused by the failure of the prediction algorithm or overfitting, improving the accuracy and efficiency of vehicle defect detection, and improving vehicle safety. The following are detailed descriptions.

[0077] Embodiment 1

[0078] See also Figure 1 , Figure 1 1 is a flow chart of a vehicle defect misjudgment identification method based on model rules disclosed in an embodiment of the present invention. Figure 1 The described vehicle defect misjudgment identification method based on model rules can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the vehicle defect misjudgment identification method based on model rules may include the following operations:

[0079] 101. Obtain vehicle sensor data and vehicle information of the vehicle to be detected.

[0080] 102. Based on the defect prediction algorithm model, according to the vehicle sensor data, the defect prediction result corresponding to the vehicle to be inspected is predicted.

[0081] 103. Filter out at least one analogous vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected.

[0082] 104. According to the vehicle defect detection result in the analog vehicle inspection record, the defect prediction result is corrected to obtain a corrected defect prediction result corresponding to the vehicle to be inspected.

[0083] It can be seen that the above-mentioned embodiment of the invention can predict the defect prediction results corresponding to the vehicle to be inspected according to the vehicle sensor data based on the defect prediction algorithm model, and then screen out at least one analog vehicle inspection record from multiple historical vehicle inspection records, so as to correct the defect prediction results based on the vehicle defect detection results in the analog vehicle inspection records to obtain more accurate defect prediction results, thereby reducing the misjudgment or missed detection of vehicle defects caused by failure of the prediction algorithm or overfitting, improving the accuracy and efficiency of vehicle defect detection, and improving vehicle safety.

[0084] As an optional embodiment, in the above steps, the vehicle sensor data includes vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data and vehicle temperature and humidity data; the vehicle information includes vehicle model, vehicle type, vehicle physical parameters, vehicle power parameters and vehicle internal component parameters; the vehicle physical parameters include vehicle length, vehicle width, vehicle height and vehicle interior space parameters.

[0085] It can be seen that through the above optional embodiments, the specific content of vehicle sensor data and vehicle information is limited, which can fully characterize the situation of the vehicle to be detected, and is subsequently used to accurately predict and correct the vehicle defect detection results, thereby assisting in reducing the misjudgment or missed detection of vehicle defects due to failure of the prediction algorithm or overfitting, improving the accuracy and efficiency of vehicle defect detection, and improving vehicle safety.

[0086] As an optional embodiment, in the above steps, based on the defect prediction algorithm model and according to the vehicle sensor data, predicting the defect prediction result corresponding to the vehicle to be inspected includes:

[0087] Based on a preset part division rule, the vehicle sensor data is divided into sensor data corresponding to multiple vehicle parts to obtain multiple part sensor data sets;

[0088] Input each part sensor data set into the defect detection algorithm model corresponding to the corresponding vehicle part to obtain the part defect type and detection probability corresponding to each part sensor data set;

[0089] The defect type of the part with a detection probability greater than a preset probability threshold and the corresponding vehicle part are determined as the defect prediction result corresponding to the vehicle to be inspected.

[0090] It can be seen that through the above-mentioned optional embodiments, the vehicle sensor data can be divided based on the preset part division rules to obtain the sensor data corresponding to different vehicle parts, and the defect detection results for the parts can be realized based on the defect detection models corresponding to the parts, so as to obtain more accurate vehicle detection results, facilitate subsequent result correction, and assist in reducing the misjudgment or missed detection of vehicle defects caused by failure of the prediction algorithm or overfitting, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0091] As an optional embodiment, in the above steps, the defect detection algorithm model is an RNN neural network, which is trained by a training data set including training sensor data of multiple corresponding vehicle parts and corresponding defect annotations; the vehicle parts are doors, front, body, chassis, roof, rear, trunk, interior space or wheels.

[0092] It can be seen that through the above-mentioned optional embodiments, the algorithm details and training details of the defect detection algorithm model are limited, which can accurately achieve defect detection results for the parts, obtain more accurate vehicle detection results, facilitate subsequent result corrections, and assist in reducing vehicle defect misjudgments or missed detections due to prediction algorithm failure or overfitting, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0093] As an optional embodiment, in the above step, selecting at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected includes:

[0094] For each historical vehicle inspection record, determine the vehicle information corresponding to each inspection record in the historical vehicle inspection record;

[0095] Calculating the information similarity between the vehicle information corresponding to each detection record in the historical vehicle detection record and the vehicle information of the vehicle to be detected;

[0096] Calculate the weighted average of the information similarities corresponding to all the inspection records in the historical vehicle inspection record to obtain a record similarity parameter corresponding to the historical vehicle inspection record;

[0097] All historical vehicle detection records whose record similarity parameters are greater than a preset parameter threshold are screened out to obtain at least one analog vehicle detection record.

[0098] It can be seen that through the above-mentioned optional embodiments, it is possible to calculate the information similarity between the vehicle information in each historical vehicle inspection record and the vehicle information of the vehicle to be inspected and screen the threshold value, so as to accurately screen out the vehicle inspection records that can analogize and correct the current inspection results, facilitate subsequent result correction, and assist in reducing the misjudgment or missed detection of vehicle defects due to failure of the prediction algorithm or overfitting, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0099] As an optional embodiment, in the above steps, when calculating the record similarity parameters, the weighted calculation weight corresponding to the information similarity corresponding to each detection record includes a first weight and a second weight; the first weight is greater than the first weight threshold when the vehicle model in the vehicle information of the corresponding detection record is the same as the vehicle to be detected; the second weight is proportional to the vehicle defect degree value in the detection result corresponding to the corresponding detection record.

[0100] It can be seen that through the above-mentioned optional embodiments, the limited details of the weighted weights when calculating the record similarity parameters are defined, so that the calculated record similarity parameters can fully and emphatically consider the records of vehicles of exactly the same model in the historical inspection records and the records of vehicles with sufficient defect inspections, thereby improving the accuracy of the record similarity parameters, so as to accurately screen out vehicle inspection records that can be used to analogize and correct the current inspection results, facilitate subsequent result corrections, and assist in reducing the misjudgment or missed detection of vehicle defects due to failure or overfitting of the prediction algorithm, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0101] As an optional embodiment, in the above steps, the defect prediction result is corrected according to the vehicle defect detection result in the analog vehicle inspection record to obtain the corrected defect prediction result corresponding to the vehicle to be inspected, including:

[0102] For each defect type corresponding to each vehicle part in the defect prediction result, determine the record proportion parameter corresponding to the defect type of the part according to the vehicle defect detection result in the analog vehicle inspection record;

[0103] Calculate the record reference probability proportional to the record proportion parameter;

[0104] Calculate the probability difference between the detection probability corresponding to the defect type of the part and the recorded reference probability;

[0105] When the probability difference is a positive number and is greater than the first difference threshold, the defect type of the part is determined as an untrustworthy defect;

[0106] When the probability difference is a negative number and is greater than the second difference threshold, the defect type of the part is determined as an important defect of concern;

[0107] When the probability difference is less than the third difference threshold and greater than the fourth difference threshold, the defect degree value corresponding to the defect type of the part is determined as the average of the detection probability and the recorded reference probability; optionally, the fourth difference threshold is less than the third difference threshold; the third difference threshold is less than the first difference threshold and the second difference threshold.

[0108] It can be seen that through the above-mentioned optional embodiments, a reference probability proportional to the record proportion parameter of the defect type in the current defect prediction result in the analog vehicle inspection record can be calculated, and the difference between the detection probability corresponding to the defect type and the reference probability can be judged to identify unreliable misjudged defects and important defects that may be missed, or the actual defect degree of the defect type can be corrected on average to obtain an accurate defect prediction result, reduce vehicle defect misjudgment or missed detection due to failure or overfitting of the prediction algorithm, improve the accuracy and efficiency of vehicle defect detection, and improve vehicle safety.

[0109] As an optional embodiment, in the above steps, determining the record proportion parameter corresponding to the defect type of the part according to the vehicle defect detection result in the analog vehicle inspection record includes:

[0110] Count the number of occurrences of the defect type corresponding to the vehicle part in the vehicle defect detection results of each analog vehicle detection record;

[0111] Calculate the weighted sum average of the number of occurrences corresponding to all analog vehicle inspection records to obtain the number parameter corresponding to the defect type of the part; optionally, the weight of the weighted sum calculation corresponding to each number of occurrences is proportional to the average value of the vehicle defect degree value in the inspection results of all records with the defect type of the part in the corresponding analog vehicle inspection record;

[0112] Determine the sum of the number of times parameters corresponding to each defect type in all analog vehicle inspection records of all other defect types, and obtain a total number parameter; optionally, the other defect types are other defect types in the defect prediction results except the defect type of the part;

[0113] Calculate the ratio of the number parameter corresponding to the defect type of the part to the total number parameter to obtain the record proportion parameter corresponding to the defect type of the part.

[0114] It can be seen that through the above-mentioned optional embodiments, the record proportion parameter can be obtained based on the ratio of the number of occurrences of the defect type in the current defect prediction result in the analog vehicle inspection record to the number of occurrences of all other defect types, so as to effectively characterize the frequency of occurrence of each defect type in the analog vehicle inspection record, so as to obtain accurate defect prediction results, reduce vehicle defect misjudgment or missed detection due to failure or overfitting of the prediction algorithm, improve the accuracy and efficiency of vehicle defect detection, and improve vehicle safety.

[0115] Embodiment 2

[0116] See also Figure 2 , Figure 2 1 is a schematic diagram of a vehicle defect misjudgment identification system based on model rules disclosed in an embodiment of the present invention. Figure 2 The vehicle defect misjudgment identification system based on model rules described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the vehicle defect misjudgment identification system based on model rules may include:

[0117] The acquisition module 201 is used to acquire the vehicle sensor data and vehicle information of the vehicle to be detected.

[0118] The prediction module 202 is used to predict the defect prediction result corresponding to the vehicle to be inspected based on the defect prediction algorithm model and the vehicle sensor data.

[0119] The screening module 203 is used to screen out at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected.

[0120] The correction module 204 is used to correct the defect prediction result according to the vehicle defect detection result in the analog vehicle detection record to obtain a corrected defect prediction result corresponding to the vehicle to be detected.

[0121] It can be seen that the above-mentioned embodiment of the invention can predict the defect prediction results corresponding to the vehicle to be inspected according to the vehicle sensor data based on the defect prediction algorithm model, and then screen out at least one analog vehicle inspection record from multiple historical vehicle inspection records, so as to correct the defect prediction results based on the vehicle defect detection results in the analog vehicle inspection records to obtain more accurate defect prediction results, thereby reducing the misjudgment or missed detection of vehicle defects caused by failure of the prediction algorithm or overfitting, improving the accuracy and efficiency of vehicle defect detection, and improving vehicle safety.

[0122] As an optional embodiment, the vehicle sensor data includes vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data and vehicle temperature and humidity data; the vehicle information includes vehicle model, vehicle type, vehicle physical parameters, vehicle power parameters and vehicle internal component parameters; the vehicle physical parameters include vehicle length, vehicle width, vehicle height and vehicle interior space parameters.

[0123] It can be seen that through the above optional embodiments, the specific content of vehicle sensor data and vehicle information is limited, which can fully characterize the situation of the vehicle to be detected, and is subsequently used to accurately predict and correct the vehicle defect detection results, thereby assisting in reducing the misjudgment or missed detection of vehicle defects due to failure of the prediction algorithm or overfitting, improving the accuracy and efficiency of vehicle defect detection, and improving vehicle safety.

[0124] As an optional embodiment, the prediction module predicts the defect prediction result corresponding to the vehicle to be inspected based on the defect prediction algorithm model and the vehicle sensor data, including:

[0125] Based on a preset part division rule, the vehicle sensor data is divided into sensor data corresponding to multiple vehicle parts to obtain multiple part sensor data sets;

[0126] Input each part sensor data set into the defect detection algorithm model corresponding to the corresponding vehicle part to obtain the part defect type and detection probability corresponding to each part sensor data set;

[0127] The defect type of the part with a detection probability greater than a preset probability threshold and the corresponding vehicle part are determined as the defect prediction result corresponding to the vehicle to be inspected.

[0128] It can be seen that through the above-mentioned optional embodiments, the vehicle sensor data can be divided based on the preset part division rules to obtain the sensor data corresponding to different vehicle parts, and the defect detection results for the parts can be realized based on the defect detection models corresponding to the parts, so as to obtain more accurate vehicle detection results, facilitate subsequent result correction, and assist in reducing the misjudgment or missed detection of vehicle defects caused by failure of the prediction algorithm or overfitting, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0129] As an optional embodiment, the defect detection algorithm model is an RNN neural network, which is trained by a training data set including training sensor data of multiple corresponding vehicle parts and corresponding defect annotations; the vehicle parts are doors, front of the vehicle, body, chassis, roof, rear of the vehicle, trunk, interior space or wheels.

[0130] It can be seen that through the above-mentioned optional embodiments, the algorithm details and training details of the defect detection algorithm model are limited, which can accurately achieve defect detection results for the parts, obtain more accurate vehicle detection results, facilitate subsequent result corrections, and assist in reducing vehicle defect misjudgments or missed detections due to prediction algorithm failure or overfitting, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0131] As an optional embodiment, the specific manner in which the screening module screens out at least one analogous vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected includes:

[0132] For each historical vehicle inspection record, determine the vehicle information corresponding to each inspection record in the historical vehicle inspection record;

[0133] Calculating the information similarity between the vehicle information corresponding to each detection record in the historical vehicle detection record and the vehicle information of the vehicle to be detected;

[0134] Calculate the weighted average of the information similarities corresponding to all the inspection records in the historical vehicle inspection record to obtain a record similarity parameter corresponding to the historical vehicle inspection record;

[0135] All historical vehicle detection records whose record similarity parameters are greater than a preset parameter threshold are screened out to obtain at least one analog vehicle detection record.

[0136] It can be seen that through the above-mentioned optional embodiments, it is possible to calculate the information similarity between the vehicle information in each historical vehicle inspection record and the vehicle information of the vehicle to be inspected and screen the threshold value, so as to accurately screen out the vehicle inspection records that can analogize and correct the current inspection results, facilitate subsequent result correction, and assist in reducing the misjudgment or missed detection of vehicle defects due to failure of the prediction algorithm or overfitting, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0137] As an optional embodiment, when calculating record similarity parameters, the weighted calculation weight corresponding to the information similarity corresponding to each detection record includes a first weight and a second weight; the first weight is greater than a first weight threshold when the vehicle model in the vehicle information of the corresponding detection record is the same as the vehicle to be detected; the second weight is proportional to the vehicle defect degree value in the detection result corresponding to the corresponding detection record.

[0138] It can be seen that through the above-mentioned optional embodiments, the limited details of the weighted weights when calculating the record similarity parameters are defined, so that the calculated record similarity parameters can fully and emphatically consider the records of vehicles of exactly the same model in the historical inspection records and the records of vehicles with sufficient defect inspections, thereby improving the accuracy of the record similarity parameters, so as to accurately screen out vehicle inspection records that can be used to analogize and correct the current inspection results, facilitate subsequent result corrections, and assist in reducing the misjudgment or missed detection of vehicle defects due to failure or overfitting of the prediction algorithm, thereby improving the accuracy and efficiency of vehicle defect detection and improving vehicle safety.

[0139] As an optional embodiment, the correction module corrects the defect prediction result according to the vehicle defect detection result in the analog vehicle inspection record, and obtains the corrected defect prediction result corresponding to the vehicle to be inspected, including:

[0140] For each defect type corresponding to each vehicle part in the defect prediction result, determine the record proportion parameter corresponding to the defect type of the part according to the vehicle defect detection result in the analog vehicle inspection record;

[0141] Calculate the record reference probability proportional to the record proportion parameter;

[0142] Calculate the probability difference between the detection probability corresponding to the defect type of the part and the recorded reference probability;

[0143] When the probability difference is a positive number and is greater than the first difference threshold, the defect type of the part is determined as an untrustworthy defect;

[0144] When the probability difference is a negative number and is greater than the second difference threshold, the defect type of the part is determined as an important defect of concern;

[0145] When the probability difference is less than the third difference threshold and greater than the fourth difference threshold, the defect degree value corresponding to the defect type of the part is determined as the average of the detection probability and the recorded reference probability; optionally, the fourth difference threshold is less than the third difference threshold; the third difference threshold is less than the first difference threshold and the second difference threshold.

[0146] It can be seen that through the above-mentioned optional embodiments, a reference probability proportional to the record proportion parameter of the defect type in the current defect prediction result in the analog vehicle inspection record can be calculated, and the difference between the detection probability corresponding to the defect type and the reference probability can be judged to identify unreliable misjudged defects and important defects that may be missed, or the actual defect degree of the defect type can be corrected on average to obtain an accurate defect prediction result, reduce vehicle defect misjudgment or missed detection due to failure or overfitting of the prediction algorithm, improve the accuracy and efficiency of vehicle defect detection, and improve vehicle safety.

[0147] As an optional embodiment, the correction module determines the specific method of the record proportion parameter corresponding to the defect type of the part according to the vehicle defect detection result in the analog vehicle inspection record, including:

[0148] Count the number of occurrences of the defect type corresponding to the vehicle part in the vehicle defect detection results of each analog vehicle detection record;

[0149] Calculate the weighted sum average of the number of occurrences corresponding to all analog vehicle inspection records to obtain the number parameter corresponding to the defect type of the part; optionally, the weight of the weighted sum calculation corresponding to each number of occurrences is proportional to the average value of the vehicle defect degree value in the inspection results of all records with the defect type of the part in the corresponding analog vehicle inspection record;

[0150] Determine the sum of the number of times parameters corresponding to each defect type in all analog vehicle inspection records of all other defect types, and obtain a total number parameter; optionally, the other defect types are other defect types in the defect prediction results except the defect type of the part;

[0151] Calculate the ratio of the number parameter corresponding to the defect type of the part to the total number parameter to obtain the record proportion parameter corresponding to the defect type of the part.

[0152] It can be seen that through the above-mentioned optional embodiments, the record proportion parameter can be obtained based on the ratio of the number of occurrences of the defect type in the current defect prediction result in the analog vehicle inspection record to the number of occurrences of all other defect types, so as to effectively characterize the frequency of occurrence of each defect type in the analog vehicle inspection record, so as to obtain accurate defect prediction results, reduce vehicle defect misjudgment or missed detection due to failure or overfitting of the prediction algorithm, improve the accuracy and efficiency of vehicle defect detection, and improve vehicle safety.

[0153] Embodiment 3

[0154] See also Figure 3 , Figure 3 It is another vehicle defect misjudgment identification system based on model rules disclosed in an embodiment of the present invention. Figure 3 The vehicle defect misjudgment identification system based on model rules is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the vehicle defect misjudgment identification system based on model rules may include:

[0155] A memory 301 storing executable program codes;

[0156] a processor 302 coupled to the memory 301;

[0157] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the vehicle defect misjudgment identification method based on model rules described in the first embodiment.

[0158] Embodiment 4

[0159] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the vehicle defect misjudgment identification method based on model rules described in the first embodiment.

[0160] Embodiment 5

[0161] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the vehicle defect misjudgment identification method based on model rules described in Example 1.

[0162] The above describes a specific embodiment of the present specification. In some cases, the recorded actions or steps can be performed in a different order than in the embodiment and still achieve the desired result. In addition, the process depicted in the accompanying drawings does not necessarily have to be in the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0163] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0164] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0165] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0166] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0169] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0170] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0171] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0172] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0173] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0174] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0175] Finally, it should be noted that the vehicle defect misjudgment identification method and system based on model rules disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A vehicle defect misjudgment identification method based on model rules, characterized in that: The method comprises: Acquire vehicle sensor data and vehicle information of the vehicle to be detected; Based on the defect prediction algorithm model and according to the vehicle sensor data, predicting the defect prediction result corresponding to the vehicle to be inspected includes: Based on a preset part division rule, the vehicle sensor data is divided into sensor data corresponding to a plurality of vehicle parts to obtain a plurality of part sensor data sets; Inputting each of the part sensor data sets into a defect detection algorithm model corresponding to the corresponding vehicle part to obtain the part defect type and detection probability corresponding to each of the part sensor data sets; Determine the part defect type and the corresponding vehicle part whose detection probability is greater than a preset probability threshold as the defect prediction result corresponding to the vehicle to be detected; Filtering at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected; According to the vehicle defect detection result in the analog vehicle detection record, the defect prediction result is corrected to obtain a corrected defect prediction result corresponding to the vehicle to be detected, including: For each part defect type corresponding to each vehicle part in the defect prediction result, counting the number of occurrences of the part defect type corresponding to the vehicle part in the vehicle defect detection result of each analog vehicle detection record; Calculate the weighted sum average of the occurrence times corresponding to all the analog vehicle inspection records to obtain the number parameter corresponding to the defect type of the part; wherein the weighted sum calculation weight corresponding to each occurrence time is proportional to the average value of the vehicle defect degree value in the inspection results of all records of the defect type of the part in the corresponding analog vehicle inspection record; Determine the sum of the number parameters corresponding to each defect type in all the analog vehicle inspection records of all other defect types, and obtain a total number parameter; the other defect types are the other defect types in the defect prediction results except the defect type of the part; Calculate the ratio of the number parameter corresponding to the defect type of the part to the total number parameter to obtain the record proportion parameter corresponding to the defect type of the part; Calculating a record reference probability proportional to the record proportion parameter; Calculate the probability difference between the detection probability corresponding to the defect type of the part and the recorded reference probability; When the probability difference is a positive number and is greater than a first difference threshold, the defect type of the part is determined as an untrustworthy defect; When the probability difference is a negative number and is greater than a second difference threshold, the defect type of the part is determined as an important defect of concern; When the probability difference is less than the third difference threshold and greater than the fourth difference threshold, the defect degree value corresponding to the defect type of the part is determined as the average of the detection probability and the recorded reference probability; the fourth difference threshold is less than the third difference threshold; the third difference threshold is less than the first difference threshold and the second difference threshold.

2. The vehicle defect misjudgment identification method based on model rules according to claim 1 is characterized in that: The vehicle sensor data includes vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data and vehicle temperature and humidity data; the vehicle information includes vehicle model, vehicle type, vehicle physical parameters, vehicle power parameters and vehicle internal component parameters; the vehicle physical parameters include vehicle length, vehicle width, vehicle height and vehicle internal space parameters.

3. The vehicle defect misjudgment identification method based on model rules according to claim 1 is characterized in that: The defect detection algorithm model is an RNN neural network, which is trained by a training data set including training sensor data corresponding to multiple vehicle parts and corresponding defect annotations; the vehicle parts are doors, front, body, chassis, roof, rear, trunk, interior space or wheels.

4. The vehicle defect misjudgment identification method based on model rules according to claim 1 is characterized in that: The step of selecting at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected includes: For each historical vehicle inspection record, determine the vehicle information corresponding to each inspection record in the historical vehicle inspection record; Calculating the information similarity between the vehicle information corresponding to each detection record in the historical vehicle detection record and the vehicle information of the vehicle to be detected; Calculate the weighted sum average of the information similarities corresponding to all the detection records in the historical vehicle detection record to obtain a record similarity parameter corresponding to the historical vehicle detection record; All the historical vehicle detection records whose record similarity parameters are greater than a preset parameter threshold are screened out to obtain at least one analog vehicle detection record.

5. The vehicle defect misjudgment identification method based on model rules according to claim 4 is characterized in that: When calculating the record similarity parameters, the weighted calculation weight corresponding to the information similarity corresponding to each detection record includes a first weight and a second weight; the first weight is greater than a first weight threshold when the vehicle model in the vehicle information of the corresponding detection record is the same as the vehicle to be detected; the second weight is proportional to the vehicle defect degree value in the detection result corresponding to the corresponding detection record.

6. A vehicle defect misjudgment identification system based on model rules, characterized in that: The system comprises: An acquisition module, used to acquire vehicle sensor data and vehicle information of a vehicle to be detected; A prediction module is used to predict the defect prediction result corresponding to the vehicle to be inspected based on the defect prediction algorithm model and the vehicle sensor data, including: Based on a preset part division rule, the vehicle sensor data is divided into sensor data corresponding to a plurality of vehicle parts to obtain a plurality of part sensor data sets; Inputting each of the part sensor data sets into a defect detection algorithm model corresponding to the corresponding vehicle part to obtain the part defect type and detection probability corresponding to each of the part sensor data sets; Determine the part defect type and the corresponding vehicle part whose detection probability is greater than a preset probability threshold as the defect prediction result corresponding to the vehicle to be detected; A screening module, configured to screen out at least one analog vehicle detection record from a plurality of historical vehicle detection records according to the vehicle information of the vehicle to be detected; A correction module, used to correct the defect prediction result according to the vehicle defect detection result in the analog vehicle detection record to obtain a corrected defect prediction result corresponding to the vehicle to be detected, including: For each part defect type corresponding to each vehicle part in the defect prediction result, counting the number of occurrences of the part defect type corresponding to the vehicle part in the vehicle defect detection result of each analog vehicle detection record; Calculate the weighted sum average of the occurrence times corresponding to all the analog vehicle inspection records to obtain the number parameter corresponding to the defect type of the part; wherein the weighted sum calculation weight corresponding to each occurrence time is proportional to the average value of the vehicle defect degree value in the inspection results of all records of the defect type of the part in the corresponding analog vehicle inspection record; Determine the sum of the number parameters corresponding to each defect type in all the analog vehicle inspection records of all other defect types, and obtain a total number parameter; the other defect types are the other defect types in the defect prediction results except the defect type of the part; Calculate the ratio of the number parameter corresponding to the defect type of the part to the total number parameter to obtain the record proportion parameter corresponding to the defect type of the part; Calculating a record reference probability proportional to the record proportion parameter; Calculate the probability difference between the detection probability corresponding to the defect type of the part and the recorded reference probability; When the probability difference is a positive number and is greater than a first difference threshold, the defect type of the part is determined as an untrustworthy defect; When the probability difference is a negative number and is greater than a second difference threshold, the defect type of the part is determined as an important defect of concern; When the probability difference is less than the third difference threshold and greater than the fourth difference threshold, the defect degree value corresponding to the defect type of the part is determined as the average of the detection probability and the recorded reference probability; the fourth difference threshold is less than the third difference threshold; the third difference threshold is less than the first difference threshold and the second difference threshold.

7. A vehicle defect misjudgment identification system based on model rules, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the vehicle defect misjudgment identification method based on model rules as described in any one of claims 1-5.

Images