Vehicle health assessment method, device and system based on artificial intelligence and storage medium

Abstract

The invention provides a vehicle health assessment method, device and system based on artificial intelligence and a storage medium, and the method comprises the steps: obtaining the basic attribute information of a to-be-assessed vehicle and a detection report of the to-be-assessed vehicle, and setting the attribute sets E1 and E2 of the to-be-assessed vehicle according to the basic attribute information and the detection report; and finally, performing health assessment on the to-be-assessed vehicle through the health value assessment model. According to the invention, based on the historical health value data and market environment information of the vehicle, the accuracy and transaction efficiency of vehicle automatic evaluation are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle health assessment based on artificial intelligence. Specifically, the embodiments of the present invention relate to a vehicle health assessment method, device, system and storage medium based on artificial intelligence. Background Art

[0002] At present, in the used car trading market, accurately determining the health value of used cars is crucial for both buyers and sellers. Traditional methods for evaluating the health value of used cars mainly rely on the experience of appraisers, which is highly subjective and difficult to guarantee accuracy. With the development of big data and artificial intelligence technologies, using data-driven methods to determine the health value of used cars has become a trend. However, existing data-based methods often have problems such as low accuracy and poor generalization when dealing with complex relationships between vehicle attributes and historical transaction health values. Summary of the invention

[0003] In order to improve the above problems, the present invention proposes a vehicle health assessment method based on artificial intelligence, which includes the following steps:

[0004] Step 1: Obtain basic attribute information of the vehicle to be evaluated, including brand information, model information, vehicle age information, mileage information, vehicle body color information, and historical transaction health value information of the same vehicle as the vehicle to be evaluated;

[0005] Step 2: Obtain a test report of the vehicle to be evaluated, wherein the test report of the vehicle to be evaluated includes the test results of the experts in the expert database on the vehicle to be evaluated. Specifically, after the user uploads the basic attribute information of the vehicle to be evaluated, at least one expert in the expert database tests the vehicle to be evaluated and generates a corresponding test report;

[0006] Step 3: Set the attribute set E1 of the vehicle to be evaluated, E1 = {e pp ,e xh , e cl , e lc , e ys}, where e pp Represents the brand attribute value of the vehicle to be evaluated, where e xh Represents the attribute value of the vehicle model to be evaluated, where e cl Represents the attribute value of the vehicle age information to be evaluated, where e lc Represents the mileage attribute value of the vehicle to be evaluated, where e ys Indicates the color attribute value of the vehicle to be evaluated;

[0007] Set the attribute set E2 of the vehicle to be evaluated, E2 = {e zj ,e bm , e fdj, e bsx , e zd}, where e zj An attribute value indicating whether the documents of the vehicle to be evaluated are complete and perfect, wherein the documents of the vehicle to be evaluated include the driving license, registration certificate, vehicle technical file, vehicle purchase tax payment certificate, and compulsory motor vehicle traffic accident liability insurance policy; bm An attribute value indicating whether the code of the vehicle to be evaluated matches, wherein whether the code of the vehicle to be evaluated matches includes whether the engine number code, frame number code, and vehicle identification code code match those on the registration certificate; fdj Indicates the engine attribute value of the vehicle to be evaluated; e bsx represents the transmission attribute value of the vehicle to be evaluated; e zd Indicates the brake system attribute value of the vehicle to be evaluated;

[0008] Step 4: Use the health value assessment model to assess the health value of the vehicle to be assessed. Each vehicle reviewer obtains the attribute set E1 and the attribute set E2 of the vehicle to be assessed based on the inspection report of the vehicle to be assessed, and converts the attribute set E1 and the attribute set E2 into the basic attribute matrix E 1ij And the basic attribute matrix E 2ij , and set the basic attribute matrix E 1ij The weight of each attribute value is ω 1ij , and the basic attribute matrix E 2ij The weight of each attribute value in 2ij , i and j represent the attribute values ​​of the i-th row and j-th column of the matrix. Specifically, the health value of each car reviewer is obtained by the following formula:

[0009]

[0010] Among them, P cpi represents the health value of the evaluation given by the i-th car reviewer, a cpi 、b cpi 、c cpi represents the weight value set by the i-th car reviewer, P yj represents the initial health value of the vehicle to be evaluated, P bj represents the expected health value of the vehicle to be evaluated by the owner, P ls It represents the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period.

[0011] Then, the corresponding average percentage error MAPE is calculated by the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within the preset period. cpi ,Right now:

[0012]

[0013] Where N represents the total number of car reviewers. The corresponding average percentage error MAPE is calculated by obtaining the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period. cpi After that, the final evaluation health value of the vehicle to be determined is obtained by the following formula:

[0014] P cpi =∑MAPE cpi *P bj .

[0015] Among them, when calculating the attribute value of the vehicle age information to be evaluated, it is determined by the following formula:

[0016]

[0017] Among them, e cl represents the attribute value of the vehicle age information to be evaluated, C y represents the number of years the vehicle to be evaluated has traveled to the yth year, C y-1 represents the number of years the vehicle to be evaluated has traveled to the y-1th year, C ym It means that the vehicle to be evaluated has traveled to the mth month of the yth year.

[0018] Among them, when calculating the mileage attribute value of the vehicle to be evaluated, it is determined by the following formula:

[0019]

[0020] Among them, e lc It represents the mileage attribute value of the vehicle to be evaluated, S1 represents the mileage of the vehicle to be evaluated, and S2 represents the preset scrapped mileage of the vehicle to be evaluated.

[0021] Wherein, when calculating the engine attribute value e of the vehicle to be evaluated fdj When , the calculation formula is:

[0022] e fdj =0.5max(p gl )+0.5min(p xhl )

[0023]

[0024] At the same time, the variable constraints of the engine attribute value are:

[0025]

[0026] Among them, max(p gl) represents the maximum engine power of the vehicle to be evaluated and is calculated by f1(). min(p xhl ) represents the minimum fuel consumption rate of the engine of the vehicle to be evaluated, and is calculated by f2(), v zs represents the engine speed of the vehicle to be evaluated, l ym Indicates the opening and closing degree of the engine throttle valve of the vehicle to be evaluated, p jq Indicates the engine throttle valve inlet pressure of the vehicle to be evaluated, p pq Indicates the engine throttle valve exhaust port pressure of the vehicle to be evaluated, t wd Indicates the engine cool-down temperature of the vehicle being evaluated.

[0027] The present invention also proposes a vehicle health assessment device based on artificial intelligence, the device includes a basic attribute information module of a vehicle to be assessed, a detection report module of a vehicle to be assessed, a property set module of a vehicle to be assessed, and a health value assessment module of a vehicle to be assessed, specifically including:

[0028] The basic attribute information module of the vehicle to be evaluated is used to obtain the basic attribute information of the vehicle to be evaluated, wherein the basic attribute information includes brand information, model information, vehicle age information, mileage information, vehicle body color information, and vehicle historical transaction health value information that is the same as the vehicle to be evaluated;

[0029] The vehicle inspection report module is used to obtain the inspection report of the vehicle to be evaluated, wherein the inspection report of the vehicle to be evaluated includes the inspection results of the vehicle to be evaluated by the experts in the expert database. Specifically, after the user uploads the basic attribute information of the vehicle to be evaluated, at least one expert in the expert database inspects the vehicle to be evaluated and generates a corresponding inspection report;

[0030] The vehicle attribute set module to be evaluated is used to set the attribute set E1 of the vehicle to be evaluated, where E1 = {e pp ,e xh , e cl , e lc , e ys}, where e pp Represents the brand attribute value of the vehicle to be evaluated, where e xh Represents the attribute value of the vehicle model to be evaluated, where e cl Represents the attribute value of the vehicle age information to be evaluated, where e lc Represents the mileage attribute value of the vehicle to be evaluated, where e ys Indicates the color attribute value of the vehicle to be evaluated;

[0031] Set the attribute set E2 of the vehicle to be evaluated, E2 = {e zj ,e bm , e fdj , ebsx , e zd}, where e zj An attribute value indicating whether the documents of the vehicle to be evaluated are complete and perfect, wherein the documents of the vehicle to be evaluated include the driving license, registration certificate, vehicle technical file, vehicle purchase tax payment certificate, and compulsory motor vehicle traffic accident liability insurance policy; bm An attribute value indicating whether the code of the vehicle to be evaluated matches, wherein whether the code of the vehicle to be evaluated matches includes whether the engine number code, frame number code, and vehicle identification code code match those on the registration certificate; fdj Indicates the engine attribute value of the vehicle to be evaluated; e bsx represents the transmission attribute value of the vehicle to be evaluated; e zd Indicates the brake system attribute value of the vehicle to be evaluated;

[0032] The health value evaluation module of the vehicle to be evaluated is used to evaluate the health value of the vehicle to be evaluated through the health value evaluation model. Each vehicle reviewer obtains the attribute set E1 and the attribute set E2 of the vehicle to be evaluated according to the inspection report of the vehicle to be evaluated, and converts the attribute set E1 and the attribute set E2 into the basic attribute matrix E 1ij And the basic attribute matrix E 2ij , and set the basic attribute matrix E 1ij The weight of each attribute value is ω 1ij , and the basic attribute matrix E 2ij The weight of each attribute value in 2ij , i and j represent the attribute values ​​of the i-th row and j-th column of the matrix. Specifically, the health value of each car reviewer is obtained by the following formula:

[0033]

[0034] Among them, P cpi represents the health value of the evaluation given by the i-th car reviewer, a cpi 、b cpi 、c cpi represents the weight value set by the i-th car reviewer, P yj represents the initial health value of the vehicle to be evaluated, P bj represents the expected health value of the vehicle to be evaluated by the owner, P ls It represents the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period.

[0035] Then, the corresponding average percentage error MAPE is calculated by the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within the preset period. cpi ,Right now:

[0036]

[0037] Where N represents the total number of car reviewers. The corresponding average percentage error MAPE is calculated by obtaining the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period. cpi After that, the final evaluation health value of the vehicle to be determined is obtained by the following formula:

[0038] P cpi =∑MAPE cpi *P bj .

[0039] Among them, when calculating the attribute value of the vehicle age information to be evaluated, it is determined by the following formula:

[0040]

[0041] Among them, e cl represents the attribute value of the vehicle age information to be evaluated, C y represents the number of years the vehicle to be evaluated has traveled to the yth year, C y-1 represents the number of years the vehicle to be evaluated has traveled to the y-1th year, C ym It means that the vehicle to be evaluated has traveled to the mth month of the yth year.

[0042] Among them, when calculating the mileage attribute value of the vehicle to be evaluated, it is determined by the following formula:

[0043]

[0044] Among them, e lc It represents the mileage attribute value of the vehicle to be evaluated, S1 represents the mileage of the vehicle to be evaluated, and S2 represents the preset scrapped mileage of the vehicle to be evaluated.

[0045] Wherein, when calculating the engine attribute value e of the vehicle to be evaluated fdj When , the calculation formula is:

[0046] e fdj =0.5max(p gl )+0.5min(p xhl )

[0047]

[0048] At the same time, the variable constraints of the engine attribute value are:

[0049]

[0050] Among them, max(p gl) represents the maximum engine power of the vehicle to be evaluated and is calculated by f1(). min(p xhl ) represents the minimum fuel consumption rate of the engine of the vehicle to be evaluated, and is calculated by f2(), v zs represents the engine speed of the vehicle to be evaluated, l ym Indicates the opening and closing degree of the engine throttle valve of the vehicle to be evaluated, p jq Indicates the engine throttle valve inlet pressure of the vehicle to be evaluated, p pq Indicates the engine throttle valve exhaust port pressure of the vehicle to be evaluated, t wd Indicates the engine cool-down temperature of the vehicle being evaluated.

[0051] The present invention also provides an electronic device, comprising a processor and a memory: the memory is used to store program code and transmit the program code to the processor, and the processor is used to execute the above-mentioned artificial intelligence-based vehicle health assessment method according to instructions in the program code.

[0052] The present invention also provides a computer-readable storage medium, which is used to store program code and transmit the program code to a processor, and the processor is used to execute the above-mentioned artificial intelligence-based vehicle health assessment method according to the instructions in the program code.

[0053] The present invention also proposes an electronic device, which includes a processor and a memory: the memory is used to store program code and transmit the program code to the processor, and the processor is used to execute the above-mentioned artificial intelligence-based vehicle health assessment method according to the instructions in the program code.

[0054] The present invention also proposes a computer-readable storage medium, which is used to store program code and transmit the program code to a processor, and the processor is used to execute the above-mentioned artificial intelligence-based vehicle health assessment method according to the instructions in the program code.

[0055] Therefore, according to the artificial intelligence-based vehicle health assessment method and device described in the present invention, the vehicle parameter information can be effectively evaluated by the vehicle reviewer based on the vehicle parameter information set, and the accurate assessment health value can be further determined in combination with the historical transaction health value of the same vehicle. The present invention is based on the vehicle's historical health value data and market environment information, which effectively improves the accuracy of automatic vehicle evaluation and transaction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0057] Figure 1 It is a flow chart of a vehicle health assessment method based on artificial intelligence;

[0058] Figure 2 It is a module schematic diagram of a vehicle health assessment device based on artificial intelligence. DETAILED DESCRIPTION

[0059] like Figure 1 As shown, a vehicle health assessment method based on artificial intelligence, the specific steps are as follows:

[0060] Step 1: Obtain basic attribute information of the vehicle to be evaluated, including brand information, model information, vehicle age information, mileage information, vehicle body color information, and historical transaction health value information of the same vehicle as the vehicle to be evaluated;

[0061] Step 2: Obtain a test report of the vehicle to be evaluated, wherein the test report of the vehicle to be evaluated includes the test results of the experts in the expert database on the vehicle to be evaluated. Specifically, after the user uploads the basic attribute information of the vehicle to be evaluated, at least one expert in the expert database tests the vehicle to be evaluated and generates a corresponding test report;

[0062] Obtaining evaluation information of the vehicle to be evaluated by at least one vehicle reviewer within a predetermined time; specifically, the at least one vehicle reviewer obtains a test report of the vehicle to be evaluated, and gives a vehicle review predicted health value according to the test report of the vehicle to be evaluated;

[0063] Specifically, in this process, the at least one vehicle reviewer obtains the expected health value information of the owner of the vehicle to be evaluated from the inspection report of the vehicle to be evaluated and the inspection information in the inspection report of the vehicle to be evaluated provided by the at least one expert. It can be understood that each expert determines the vehicle condition information of the vehicle to be evaluated based on the basic attribute information of the vehicle to be evaluated;

[0064] The inspection items of each expert on the vehicle to be evaluated include the owner's driving license, motor vehicle registration certificate, vehicle technical files, vehicle purchase tax payment certificate, motor vehicle traffic accident liability compulsory insurance policy, and whether the vehicle to be evaluated meets the national mandatory scrapping standards, whether the restricted engine number prohibited by the state is consistent with the registration number of the motor vehicle registration certificate, whether the vehicle to be evaluated has traces of chiseling, and whether the frame number or vehicle identification code is consistent with the registration number of the motor vehicle registration certificate, whether the vehicle to be evaluated has a legal and authentic vehicle legal certificate, or traces of tampering, whether the vehicle to be evaluated is a vehicle prohibited from trading by laws and regulations, whether the engine body of the vehicle to be evaluated has serious oil leakage, water leakage, air leakage or whether the engine oil is mixed with coolant, whether the instrument indication is abnormal, including water temperature, oil pressure, air pressure information or whether there is a fault alarm, whether the braking system of the vehicle to be evaluated is abnormal or the brake is deviating, whether the vehicle to be evaluated has serious shaking or serious deviation during driving, and whether the vehicle to be evaluated has other serious faults. For each of the above inspection items, each expert needs to give specific inspection results and evaluation results.

[0065] Step 3: Set the attribute set E1 of the vehicle to be evaluated, E1 = {e pp ,e xh , e cl , e lc , e ys}, where e pp Represents the brand attribute value of the vehicle to be evaluated, where e xh Represents the attribute value of the vehicle model to be evaluated, where e cl Represents the attribute value of the vehicle age information to be evaluated, where e lc Represents the mileage attribute value of the vehicle to be evaluated, where e ys Indicates the color attribute value of the vehicle to be evaluated; it is understandable that when setting the vehicle brand attribute value, vehicle model attribute value and vehicle color attribute value, the score is determined according to the brand value, market circulation and number of vehicles owned by the car company. Each car reviewer will determine the vehicle age information attribute value, vehicle model attribute value and vehicle color attribute value of the vehicle to be evaluated according to the vehicle brand, market circulation and number of vehicles owned; and the vehicle age information attribute value and vehicle mileage attribute value of the vehicle to be evaluated are determined by the following formula:

[0066]

[0067] Among them, e cl represents the attribute value of the vehicle age information to be evaluated, C y represents the number of years the vehicle to be evaluated has traveled to the yth year, C y-1represents the number of years the vehicle to be evaluated has traveled to the y-1th year, C ym It means that the vehicle to be evaluated has traveled to the mth month of the yth year, e lc It represents the mileage attribute value of the vehicle to be evaluated, S1 represents the mileage of the vehicle to be evaluated, and S2 represents the preset scrapped mileage of the vehicle to be evaluated.

[0068] Furthermore, the attribute set E2 of the vehicle to be evaluated is set, E2 = {e zj ,e bm , e fdj , e bsx , e zd}, where e zj An attribute value indicating whether the documents of the vehicle to be evaluated are complete and perfect, wherein the documents of the vehicle to be evaluated include the driving license, registration certificate, vehicle technical file, vehicle purchase tax payment certificate, and compulsory motor vehicle traffic accident liability insurance policy; bm An attribute value indicating whether the code of the vehicle to be evaluated matches, wherein whether the code of the vehicle to be evaluated matches includes whether the engine number code, frame number code, and vehicle identification code code match those on the registration certificate; fdj Indicates the engine attribute value of the vehicle to be evaluated; e bsx represents the transmission attribute value of the vehicle to be evaluated; e zd Indicates the brake system attribute value of the vehicle to be evaluated.

[0069] Specifically, when setting the attribute value of whether the documents of the vehicle to be evaluated are complete and perfect and the attribute value of whether the code of the vehicle to be evaluated matches, each vehicle reviewer will determine the attribute value of whether the documents of the vehicle to be evaluated are complete and perfect according to the completeness and matching degree of the documents, certificates, files and certifications, as well as the matching degree of the frame number and engine number. zj The attribute value e that indicates whether the code of the vehicle to be evaluated matches bm , further, the engine attribute value e of the vehicle to be evaluated is determined by the following formula fdj , the transmission attribute value e of the vehicle to be evaluated bsx , the braking system attribute value e of the vehicle to be evaluated zd , other problem attribute values ​​e of the vehicle to be evaluated qt :

[0070] Wherein, when calculating the engine attribute value e of the vehicle to be evaluated fdj When , the calculation formula is:

[0071] e fdj =0.5max(p gl )+0.5min(p xhl )

[0072]

[0073] At the same time, the variable constraints of the engine attribute value are:

[0074]

[0075] Among them, max(p gl ) represents the maximum engine power of the vehicle to be evaluated and is calculated by f1(). min(p xhl ) represents the minimum fuel consumption rate of the engine of the vehicle to be evaluated, and is calculated by f2(), v zs represents the engine speed of the vehicle to be evaluated, l ym Indicates the opening and closing degree of the engine throttle valve of the vehicle to be evaluated, p jq Indicates the engine throttle valve inlet pressure of the vehicle to be evaluated, p pq Indicates the engine throttle valve exhaust port pressure of the vehicle to be evaluated, t wd Indicates the engine cool-down temperature of the vehicle being evaluated.

[0076] In calculating the transmission attribute value e of the vehicle to be evaluated bsx When , the calculation formula is:

[0077]

[0078] Among them, L ms represents the gearbox wear travel of the vehicle to be evaluated, S ms represents the gearbox friction plate surface area of ​​the vehicle to be evaluated, V bsx Indicates the volume of the gearbox friction plate of the vehicle to be evaluated, L pl represents the separation gap of the transmission clutch of the vehicle to be evaluated, μ bsx represents the gearbox friction coefficient of the vehicle to be evaluated;

[0079] In the calculation, the braking system attribute value e of the vehicle to be evaluated is represented zd When the brake material is subjected to thermal fatigue, the corresponding friction surface strength and elasticity of the brake material need to be calculated. This is because the position relationship and friction relationship of the brake disc change during the braking process. Therefore, the brake system attribute value e of the vehicle to be evaluated is determined by the heat flux density load. zd , which is obtained by the following calculation formula:

[0080]

[0081] Among them, σ pl Indicates the fatigue degree of the brake disc of the vehicle to be evaluated, μ mc represents the friction coefficient of the brake disc of the vehicle to be evaluated, ρ rl represents the heat flux density of the brake disc of the vehicle to be evaluated, smc Indicates the brake disc friction area of ​​the vehicle to be evaluated, F tx Indicates the elastic deformation of the brake disc of the vehicle to be evaluated;

[0082] Step 4: Use the health value assessment model to assess the health value of the vehicle to be assessed. Each vehicle reviewer obtains the attribute set E1 and the attribute set E2 of the vehicle to be assessed based on the inspection report of the vehicle to be assessed, and converts the attribute set E1 and the attribute set E2 into the basic attribute matrix E 1ij And the basic attribute matrix E 2ij , and set the basic attribute matrix E 1ij The weight of each attribute value is ω 1ij , and the basic attribute matrix E 2ij The weight of each attribute value in 2ij , i and j represent the attribute values ​​of the i-th row and j-th column of the matrix. Specifically, the health value of each car reviewer is obtained by the following formula:

[0083]

[0084] Among them, P cpi represents the health value of the evaluation given by the i-th car reviewer, a cpi 、b cpi 、c cpi represents the weight value set by the i-th car reviewer, P yj represents the initial health value of the vehicle to be evaluated, P bj represents the expected health value of the vehicle to be evaluated by the owner, P ls It represents the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period.

[0085] Then, the corresponding average percentage error MAPE is calculated by the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within the preset period. cpi ,Right now:

[0086]

[0087] Where N represents the total number of car reviewers. The corresponding average percentage error MAPE is calculated by obtaining the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period. cpi After that, the final evaluation health value of the vehicle to be determined is obtained by the following formula:

[0088] P cpi =∑MAPE cpi *P bj

[0089] Furthermore, after receiving the final assessed health value of the ordered vehicle, the vehicle owner modifies the expected health value of the vehicle to be assessed according to actual needs to complete the transaction process of the vehicle to be assessed.

[0090] Example 2

[0091] like Figure 2 As shown, a vehicle health assessment device based on artificial intelligence includes a basic attribute information module of a vehicle to be assessed, a detection report module of a vehicle to be assessed, a property set module of a vehicle to be assessed, and a health value assessment module of a vehicle to be assessed, specifically including:

[0092] The basic attribute information module of the vehicle to be evaluated is used to obtain the basic attribute information of the vehicle to be evaluated, wherein the basic attribute information includes brand information, model information, vehicle age information, mileage information, vehicle body color information, and vehicle historical transaction health value information that is the same as the vehicle to be evaluated;

[0093] The vehicle inspection report module is used to obtain the inspection report of the vehicle to be evaluated, wherein the inspection report of the vehicle to be evaluated includes the inspection results of the vehicle to be evaluated by the experts in the expert database. Specifically, after the user uploads the basic attribute information of the vehicle to be evaluated, at least one expert in the expert database inspects the vehicle to be evaluated and generates a corresponding inspection report;

[0094] Obtaining evaluation information of the vehicle to be evaluated by at least one vehicle reviewer within a predetermined time; specifically, the at least one vehicle reviewer obtains a test report of the vehicle to be evaluated, and gives a vehicle review predicted health value according to the test report of the vehicle to be evaluated;

[0095] Specifically, in this process, the at least one vehicle reviewer obtains the expected health value information of the owner of the vehicle to be evaluated from the inspection report of the vehicle to be evaluated and the inspection information in the inspection report of the vehicle to be evaluated provided by the at least one expert. It can be understood that each expert determines the vehicle condition information of the vehicle to be evaluated based on the basic attribute information of the vehicle to be evaluated;

[0096] The inspection items of each expert on the vehicle to be evaluated include the owner's driving license, motor vehicle registration certificate, vehicle technical files, vehicle purchase tax payment certificate, motor vehicle traffic accident liability compulsory insurance policy, and whether the vehicle to be evaluated meets the national mandatory scrapping standards, whether the restricted engine number prohibited by the state is consistent with the registration number of the motor vehicle registration certificate, whether the vehicle to be evaluated has traces of chiseling, and whether the frame number or vehicle identification code is consistent with the registration number of the motor vehicle registration certificate, whether the vehicle to be evaluated has a legal and authentic vehicle legal certificate, or traces of tampering, whether the vehicle to be evaluated is a vehicle prohibited from trading by laws and regulations, whether the engine body of the vehicle to be evaluated has serious oil leakage, water leakage, air leakage or whether the engine oil is mixed with coolant, whether the instrument indication is abnormal, including water temperature, oil pressure, air pressure information or whether there is a fault alarm, whether the braking system of the vehicle to be evaluated is abnormal or the brake is deviating, whether the vehicle to be evaluated has serious shaking or serious deviation during driving, and whether the vehicle to be evaluated has other serious faults. For each of the above inspection items, each expert needs to give specific inspection results and evaluation results.

[0097] The vehicle attribute set module to be evaluated is used to set the attribute set E1 of the vehicle to be evaluated, where E1 = {e pp ,e xh , e cl , e lc , e ys}, where e pp Represents the brand attribute value of the vehicle to be evaluated, where e xh Represents the attribute value of the vehicle model to be evaluated, where e cl Represents the attribute value of the vehicle age information to be evaluated, where e lc Represents the mileage attribute value of the vehicle to be evaluated, where e ys Indicates the color attribute value of the vehicle to be evaluated; it is understandable that when setting the vehicle brand attribute value, vehicle model attribute value and vehicle color attribute value, the score is determined according to the brand value, market circulation and number of vehicles owned by the car company. Each car reviewer will determine the vehicle age information attribute value, vehicle model attribute value and vehicle color attribute value of the vehicle to be evaluated according to the vehicle brand, market circulation and number of vehicles owned; and the vehicle age information attribute value and vehicle mileage attribute value of the vehicle to be evaluated are determined by the following formula:

[0098]

[0099] Among them, e cl represents the attribute value of the vehicle age information to be evaluated, C y represents the number of years the vehicle to be evaluated has traveled to the yth year, C y-1represents the number of years the vehicle to be evaluated has traveled to the y-1th year, C ym It means that the vehicle to be evaluated has traveled to the mth month of the yth year, e lc It represents the mileage attribute value of the vehicle to be evaluated, S1 represents the mileage of the vehicle to be evaluated, and S2 represents the preset scrapped mileage of the vehicle to be evaluated.

[0100] Furthermore, the attribute set E2 of the vehicle to be evaluated is set, E2 = {e zj ,e bm , e fdj , e bsx , e zd}, where e zj An attribute value indicating whether the documents of the vehicle to be evaluated are complete and perfect, wherein the documents of the vehicle to be evaluated include the driving license, registration certificate, vehicle technical file, vehicle purchase tax payment certificate, and compulsory motor vehicle traffic accident liability insurance policy; bm An attribute value indicating whether the code of the vehicle to be evaluated matches, wherein whether the code of the vehicle to be evaluated matches includes whether the engine number code, frame number code, and vehicle identification code code match those on the registration certificate; fdj Indicates the engine attribute value of the vehicle to be evaluated; e bsx represents the transmission attribute value of the vehicle to be evaluated; e zd Indicates the brake system attribute value of the vehicle to be evaluated.

[0101] Specifically, when setting the attribute value of whether the documents of the vehicle to be evaluated are complete and perfect and the attribute value of whether the code of the vehicle to be evaluated matches, each vehicle reviewer will determine the attribute value of whether the documents of the vehicle to be evaluated are complete and perfect according to the completeness and matching degree of the documents, certificates, files and certifications, as well as the matching degree of the frame number and engine number. zj The attribute value e that indicates whether the code of the vehicle to be evaluated matches bm , further, the engine attribute value e of the vehicle to be evaluated is determined by the following formula fdj , the transmission attribute value e of the vehicle to be evaluated bsx , the braking system attribute value e of the vehicle to be evaluated zd , other problem attribute values ​​e of the vehicle to be evaluated qt :

[0102] Wherein, when calculating the engine attribute value e of the vehicle to be evaluated fdj When , the calculation formula is:

[0103] e fdj =0.5max(p gl )+0.5min(p xhl )

[0104]

[0105] At the same time, the variable constraints of the engine attribute value are:

[0106]

[0107] Among them, max(p gl ) represents the maximum engine power of the vehicle to be evaluated and is calculated by f1(). min(p xhl ) represents the minimum fuel consumption rate of the engine of the vehicle to be evaluated, and is calculated by f2(), v zs represents the engine speed of the vehicle to be evaluated, l ym Indicates the opening and closing degree of the engine throttle valve of the vehicle to be evaluated, p jq Indicates the engine throttle valve inlet pressure of the vehicle to be evaluated, p pq Indicates the engine throttle valve exhaust port pressure of the vehicle to be evaluated, t wd Indicates the engine cool-down temperature of the vehicle being evaluated.

[0108] In calculating the transmission attribute value e of the vehicle to be evaluated bsx When , the calculation formula is:

[0109]

[0110] Among them, L ms represents the gearbox wear travel of the vehicle to be evaluated, S ms represents the gearbox friction plate surface area of ​​the vehicle to be evaluated, V bsx Indicates the volume of the gearbox friction plate of the vehicle to be evaluated, L pl represents the separation gap of the transmission clutch of the vehicle to be evaluated, μ bsx represents the gearbox friction coefficient of the vehicle to be evaluated;

[0111] In the calculation, the braking system attribute value e of the vehicle to be evaluated is represented zd When the brake material is subjected to thermal fatigue, the corresponding friction surface strength and elasticity of the brake material need to be calculated. This is because the position relationship and friction relationship of the brake disc change during the braking process. Therefore, the brake system attribute value e of the vehicle to be evaluated is determined by the heat flux density load. zd , which is obtained by the following calculation formula:

[0112]

[0113] Among them, σ pl Indicates the fatigue degree of the brake disc of the vehicle to be evaluated, μ mc represents the friction coefficient of the brake disc of the vehicle to be evaluated, ρ rl represents the heat flux density of the brake disc of the vehicle to be evaluated, smc Indicates the brake disc friction area of ​​the vehicle to be evaluated, F tx Indicates the elastic deformation of the brake disc of the vehicle to be evaluated;

[0114] The health value evaluation module of the vehicle to be evaluated is used to evaluate the health value of the vehicle to be evaluated through the health value evaluation model. Each vehicle reviewer obtains the attribute set E1 and the attribute set E2 of the vehicle to be evaluated according to the inspection report of the vehicle to be evaluated, and converts the attribute set E1 and the attribute set E2 into the basic attribute matrix E 1ij And the basic attribute matrix E 2ij , and set the basic attribute matrix E 1ij The weight of each attribute value is ω 1ij , and the basic attribute matrix E 2ij The weight of each attribute value in 2ij , i and j represent the attribute values ​​of the i-th row and j-th column of the matrix. Specifically, the health value of each car reviewer is obtained by the following formula:

[0115]

[0116] Among them, P cpi represents the health value of the evaluation given by the i-th car reviewer, a cpi 、b cpi 、c cpi represents the weight value set by the i-th car reviewer, P yj represents the initial health value of the vehicle to be evaluated, P bj represents the expected health value of the vehicle to be evaluated by the owner, P ls It represents the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period.

[0117] Then, the corresponding average percentage error MAPE is calculated by the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within the preset period. cpi ,Right now:

[0118]

[0119] Where N represents the total number of car reviewers. The corresponding average percentage error MAPE is calculated by obtaining the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period. cpi After that, the final evaluation health value of the vehicle to be determined is obtained by the following formula:

[0120] P cpi =∑MAPE cpi *P bj

[0121] Furthermore, after receiving the final assessed health value of the ordered vehicle, the vehicle owner modifies the expected health value of the vehicle to be assessed according to actual needs to complete the transaction process of the vehicle to be assessed.

[0122] The present invention also relates to an electronic device, characterized in that the electronic device includes a processor and a memory: the memory is used to store program code and transmit the program code to the processor, and the processor is used to execute an artificial intelligence-based vehicle health assessment method described in the above method embodiment according to instructions in the program code.

[0123] The present invention also relates to a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code and transmit the program code to a processor, and the processor is used to execute an artificial intelligence-based vehicle health assessment method described in the above method embodiment according to instructions in the program code.

[0124] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A vehicle health assessment method based on artificial intelligence, characterized in that The following steps are involved: Step 1: Obtain basic attribute information of the vehicle to be evaluated, including brand information, model information, vehicle age information, mileage information, vehicle body color information, and historical transaction health value information of the same vehicle as the vehicle to be evaluated; Step 2: Obtain a test report of the vehicle to be evaluated, wherein the test report of the vehicle to be evaluated includes the test results of the experts in the expert database on the vehicle to be evaluated. Specifically, after the user uploads the basic attribute information of the vehicle to be evaluated, at least one expert in the expert database tests the vehicle to be evaluated and generates a corresponding test report; Step 3: Set the attribute set E1 of the vehicle to be evaluated, E1 = {e pp , e xh , e cl , e lc , e ys }, where e pp Represents the brand attribute value of the vehicle to be evaluated, where e xh Represents the attribute value of the vehicle model to be evaluated, where e cl Represents the attribute value of the vehicle age information to be evaluated, where e lc Represents the mileage attribute value of the vehicle to be evaluated, where e ys Indicates the color attribute value of the vehicle to be evaluated; Set the attribute set E2 of the vehicle to be evaluated, E2 = {e zj , e bm , e fdj , e bsx , e zd }, where e zj An attribute value indicating whether the documents of the vehicle to be evaluated are complete and perfect, wherein the documents of the vehicle to be evaluated include the driving license, registration certificate, vehicle technical file, vehicle purchase tax payment certificate, and compulsory motor vehicle traffic accident liability insurance policy; bm An attribute value indicating whether the code of the vehicle to be evaluated matches, wherein whether the code of the vehicle to be evaluated matches includes whether the engine number code, frame number code, and vehicle identification code code match those on the registration certificate; fdj Indicates the engine attribute value of the vehicle to be evaluated; e bsx represents the transmission attribute value of the vehicle to be evaluated; e zd Indicates the brake system attribute value of the vehicle to be evaluated; Step 4: The health value of the vehicle to be evaluated is evaluated by the health value evaluation model. Each vehicle reviewer obtains the attribute set E1 and the attribute set E2 of the vehicle to be evaluated according to the inspection report of the vehicle to be evaluated, and converts the attribute set E1 and the attribute set E2 into the basic attribute matrix E 1ij And the basic attribute matrix E 2ij , and set the basic attribute matrix E respectively 1ij The weight of each attribute value is ω 1ij , and the basic attribute matrix E 2ij The weight of each attribute value in 2ij , i and j represent the attribute values ​​of the i-th row and j-th column of the matrix. Specifically, the health value of each car reviewer is obtained by the following formula: Among them, P cpi represents the health value of the evaluation given by the i-th car reviewer, a cpi , b cpi 、c cpi represents the weight value set by the i-th car reviewer, P yj represents the initial health value of the vehicle to be evaluated, P bj represents the expected health value of the vehicle to be evaluated by the owner, P ls Indicates the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period; Then, the corresponding average percentage error MAPE is calculated by the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within the preset period. cpi ,Right now: Where N represents the total number of car reviewers. The corresponding average percentage error MAPE is calculated by obtaining the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period. cpi After that, the final evaluation health value of the vehicle to be determined is obtained by the following formula: P cpi =∑MAPE cpi *P bj 。 2. The vehicle health assessment method based on artificial intelligence according to claim 1 is characterized in that: When calculating the attribute value of the vehicle age information to be evaluated, it is determined by the following formula: Among them, e cl represents the attribute value of the vehicle age information to be evaluated, C y represents the number of years the vehicle to be evaluated has traveled to the yth year, C y-1 represents the number of years the vehicle to be evaluated has traveled to the y-1th year, C ym It means that the vehicle to be evaluated has traveled to the mth month of the yth year.

3. The vehicle health assessment method based on artificial intelligence according to claim 1 is characterized in that: When calculating the mileage attribute value of the vehicle to be evaluated, it is determined by the following formula: Among them, e lc It represents the mileage attribute value of the vehicle to be evaluated, S1 represents the mileage of the vehicle to be evaluated, and S2 represents the preset scrapped mileage of the vehicle to be evaluated.

4. The vehicle health assessment method based on artificial intelligence according to claim 1 is characterized in that: When calculating the engine attribute value e of the vehicle to be evaluated fdj When , the calculation formula is: e fdj =0.5max(p gl )+0.5min(p xhl ) At the same time, the variable constraints of the engine attribute value are: Among them, max(p gl ) represents the maximum engine power of the vehicle to be evaluated and is calculated by f1(). min(p xhl ) represents the minimum fuel consumption rate of the engine of the vehicle to be evaluated, and is calculated by f2(), v zs represents the engine speed of the vehicle to be evaluated, l ym Indicates the opening and closing degree of the engine throttle valve of the vehicle to be evaluated, p jq Indicates the engine throttle valve inlet pressure of the vehicle to be evaluated, p pq Indicates the engine throttle valve exhaust port pressure of the vehicle to be evaluated, t wd Indicates the engine cool-down temperature of the vehicle being evaluated.

5. A vehicle health assessment device based on artificial intelligence, the device includes a basic attribute information module of a vehicle to be assessed, a detection report module of a vehicle to be assessed, a property set module of a vehicle to be assessed, and a health value assessment module of a vehicle to be assessed, specifically including: The basic attribute information module of the vehicle to be evaluated is used to obtain the basic attribute information of the vehicle to be evaluated, wherein the basic attribute information includes brand information, model information, vehicle age information, mileage information, vehicle body color information, and vehicle historical transaction health value information that is the same as the vehicle to be evaluated; The vehicle inspection report module is used to obtain the inspection report of the vehicle to be evaluated, wherein the inspection report of the vehicle to be evaluated includes the inspection results of the vehicle to be evaluated by the experts in the expert database. Specifically, after the user uploads the basic attribute information of the vehicle to be evaluated, at least one expert in the expert database inspects the vehicle to be evaluated and generates a corresponding inspection report; The vehicle attribute set module to be evaluated is used to set the attribute set E1 of the vehicle to be evaluated, where E1 = {e pp , e xh , e cl , e lc , e ys }, where e pp Represents the brand attribute value of the vehicle to be evaluated, where e xh Represents the attribute value of the vehicle model to be evaluated, where e cl Represents the attribute value of the vehicle age information to be evaluated, where e lc Represents the mileage attribute value of the vehicle to be evaluated, where e ys Indicates the color attribute value of the vehicle to be evaluated; Set the attribute set E2 of the vehicle to be evaluated, E2 = {e zj , e bm , e fdj , e bsx , e zd }, where e zj An attribute value indicating whether the documents of the vehicle to be evaluated are complete and perfect, wherein the documents of the vehicle to be evaluated include the driving license, registration certificate, vehicle technical file, vehicle purchase tax payment certificate, and compulsory motor vehicle traffic accident liability insurance policy; bm An attribute value indicating whether the code of the vehicle to be evaluated matches, wherein whether the code of the vehicle to be evaluated matches includes whether the engine number code, frame number code, and vehicle identification code code match those on the registration certificate; fdj Indicates the engine attribute value of the vehicle to be evaluated; e bsx represents the transmission attribute value of the vehicle to be evaluated; e zd Indicates the brake system attribute value of the vehicle to be evaluated; The health value evaluation module of the vehicle to be evaluated is used to evaluate the health value of the vehicle to be evaluated through the health value evaluation model. Each vehicle reviewer obtains the attribute set E1 and the attribute set E2 of the vehicle to be evaluated according to the inspection report of the vehicle to be evaluated, and converts the attribute set E1 and the attribute set E2 into the basic attribute matrix E 1ij And the basic attribute matrix E 2ij , and set the basic attribute matrix E respectively 1ij The weight of each attribute value is ω 1ij , and the basic attribute matrix E 2ij The weight of each attribute value in 2ij , i and j represent the attribute values ​​of the i-th row and j-th column of the matrix. Specifically, the health value of each car reviewer is obtained by the following formula: Among them, P cpi represents the health value of the evaluation given by the i-th car reviewer, a cpi , b cpi 、c cpi represents the weight value set by the i-th car reviewer, P yj represents the initial health value of the vehicle to be evaluated, P bj represents the expected health value of the vehicle to be evaluated by the owner, P ls Indicates the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period; Then, the corresponding average percentage error MAPE is calculated by the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within the preset period. cpi ,Right now: Where N represents the total number of car reviewers. The corresponding average percentage error MAPE is calculated by obtaining the evaluation health value given by the i-th car reviewer and the average value of the historical transaction health value information of the same vehicle as the vehicle to be evaluated within a preset period. cpi After that, the final evaluation health value of the vehicle to be determined is obtained by the following formula: P cpi =∑MAPE cpi *P bj 。 6. The vehicle health assessment device based on artificial intelligence according to claim 5, characterized in that: When calculating the attribute value of the vehicle age information to be evaluated, it is determined by the following formula: Among them, e cl represents the attribute value of the vehicle age information to be evaluated, C y represents the number of years the vehicle to be evaluated has traveled to the yth year, C y-1 represents the number of years the vehicle to be evaluated has traveled to the y-1th year, C ym It means that the vehicle to be evaluated has traveled to the mth month of the yth year.

7. The vehicle health assessment device based on artificial intelligence according to claim 5, characterized in that: When calculating the mileage attribute value of the vehicle to be evaluated, it is determined by the following formula: Among them, e lc It represents the mileage attribute value of the vehicle to be evaluated, S1 represents the mileage of the vehicle to be evaluated, and S2 represents the preset scrapped mileage of the vehicle to be evaluated.

8. The vehicle health assessment device based on artificial intelligence according to claim 5, characterized in that: When calculating the engine attribute value e of the vehicle to be evaluated fdj When , the calculation formula is: e fdj =0.5max(p gl )+0.5min(p xhl ) At the same time, the variable constraints of the engine attribute value are: Among them, max(p gl ) represents the maximum engine power of the vehicle to be evaluated and is calculated by f1(). min(p xhl ) represents the minimum fuel consumption rate of the engine of the vehicle to be evaluated, and is calculated by f2(), v zs represents the engine speed of the vehicle to be evaluated, l ym Indicates the opening and closing degree of the engine throttle valve of the vehicle to be evaluated, p jq Indicates the engine throttle valve inlet pressure of the vehicle to be evaluated, p pq Indicates the engine throttle valve exhaust port pressure of the vehicle to be evaluated, t wd Indicates the engine cool-down temperature of the vehicle being evaluated.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory: the memory is used to store program code and transmit the program code to the processor, and the processor is used to execute the artificial intelligence-based vehicle health assessment method described in any one of claims 1 to 4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code and transmit the program code to a processor, and the processor is used to execute the artificial intelligence-based vehicle health assessment method described in any one of claims 1 to 4 according to the instructions in the program code.

Images