Automobile maintenance guiding system and method based on cloud platform

Abstract

The invention relates to the technical field of data processing, in particular to an automobile maintenance guiding system and method based on a cloud platform, and the method comprises the steps: obtaining a maintenance record of a maintenance station and a data set during the detection of a to-be-detected automobile, and obtaining the influence degree of data of each dimension on each fault, and the processing capability of each maintenance station for each fault; according to the data of the same dimension in all the maintenance records under the same fault and the data of the to-be-detected vehicle, obtaining suspected faults of the to-be-detected vehicle and the possibility of containing each suspected fault; and the optimal maintenance station of the to-be-detected vehicle is obtained by combining the distance between each maintenance station and the to-be-detected vehicle and the processing capacity of each maintenance station for each fault. The invention aims to solve the problem that when a user detects an automobile, the user cannot select the optimal maintenance station because different maintenance stations have different processing capacities for different faults.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a cloud platform-based automobile maintenance guidance system and method. Background Art

[0002] The cloud-based automobile maintenance guidance system achieves efficient and accurate vehicle fault detection and maintenance guidance through real-time monitoring and intelligent diagnosis. It uses big data and machine learning algorithms to automatically generate maintenance plans, reducing errors in manual judgment, and improving the ability to handle complex faults through remote support functions. In addition, the system can continuously optimize the diagnostic model, so that maintenance efficiency and accuracy gradually improve over time, greatly reducing maintenance costs and time, and bringing intelligent, data-driven innovation to the automotive service industry.

[0003] Currently, when a car breaks down, drivers must go to a car repair shop in person for inspection and repair. However, it is often difficult for drivers to accurately identify the fault in their car, which causes them to invest a lot of time and resources in seeking solutions from multiple repair shops. In addition, due to differences in technical level and service quality among repair shops, drivers may face additional financial burdens and maintenance quality issues. These issues together constitute the problem of information asymmetry and service opacity in the car maintenance process. Summary of the invention

[0004] The present invention provides a car maintenance guidance system and method based on a cloud platform, so as to solve the problem that existing users cannot select the best maintenance station when repairing their cars.

[0005] The present invention provides a cloud platform-based automobile maintenance guidance system and method using the following technical solutions: The present invention proposes a car maintenance guidance method based on a cloud platform, which comprises the following steps: Obtaining the maintenance records of the maintenance station, data of multiple dimensions when the vehicle to be tested is tested, and the distance between the vehicle to be tested and the maintenance station; the maintenance records of the maintenance station include the fault, data of the vehicle in various dimensions when the fault occurs, user satisfaction, and the time it takes to handle the fault; According to the data distribution of the same dimension in the maintenance records of the same fault in the maintenance station, the influence degree of the data of each dimension on each fault is obtained; Based on the data of the same dimension in all maintenance records under the same fault, the possibility of each fault being contained in each value under each dimension is obtained; the possibility of each fault being contained in the vehicle to be tested is obtained by combining the influence of the data of each dimension on each fault and the data of the vehicle to be tested in each dimension, and then the suspected faults of the vehicle to be tested and the possibility of each suspected fault being contained in the vehicle to be tested are obtained; According to the distance between each maintenance station and the vehicle to be tested, the adjacent maintenance stations of the vehicle to be tested are obtained; according to the number of maintenance records of each fault of each adjacent maintenance station of the vehicle to be tested, the processing time of the fault in the maintenance records and the user satisfaction, the processing capacity of each adjacent maintenance station of the vehicle to be tested for each fault is obtained; combined with the possibility that the vehicle to be tested contains each suspected fault, the adaptability of each adjacent maintenance station of the vehicle to be tested and the vehicle to be tested is obtained; according to the distance between each adjacent maintenance station of the vehicle to be tested and the vehicle to be tested and the distribution of the adaptability of all adjacent maintenance stations of the vehicle to be tested and the vehicle to be tested, the recommendation degree of each adjacent maintenance station of the vehicle to be tested for the vehicle to be tested is obtained, and then the best maintenance station for the vehicle to be tested is obtained.

[0006] Furthermore, the influence degree of each dimension of data on each fault is obtained according to the data distribution of the same dimension in the maintenance records of the same fault of the maintenance station, including the specific method of: Get the fault as All maintenance records of the fault The value of the dimension is obtained Failure A dataset with 1 dimension; According to Failure All the values ​​in the data set of dimensions are obtained Failure The kurtosis of the data set of dimensions is denoted as Failure The kurtosis of the data in each dimension; The first Failure The difference between the maximum value and the minimum value in the data set of the dimension is recorded as Failure The data span of the dimension; The maximum value of the data in the dimension minus the value of the The difference after the minimum value of the data in the dimensions is recorded as the The data span of the dimension; The calculation formula for obtaining the influence of each dimension of data on each fault is as follows: In the formula, Indicates The data of the dimension The impact of a fault, Indicates Failure The kurtosis of the data in the dimension Indicates all faults. The data span of dimensions, Indicates Failure The data span of dimensions, To prevent hyperparameters with denominators equal to zero, represents the weight normalization function.

[0007] Furthermore, the method of obtaining the possibility of each fault being contained in each value under each dimension based on the data of the same dimension in all maintenance records under the same fault includes the following specific methods: In the formula, Indicates The first dimension The value occurs The possibility of a failure, Indicates that the fault is The number of maintenance records for each fault, Indicates that the fault is the first Failure and The data value of the dimension is The first dimension The number of maintenance records with the specified value.

[0008] Furthermore, the method of combining the influence degree of each fault on the data of each dimension and the data of the vehicle to be detected in each dimension to obtain the possibility that the vehicle to be detected contains each fault includes the following specific methods: In the formula, Indicates that the vehicle to be tested contains The possibility of a failure, Indicates the preset number of dimensions, Indicates the vehicle to be detected. The data value of the dimension The possibility of a failure, Indicates The data of the dimension The impact of a fault.

[0009] Furthermore, the specific method of obtaining the suspected faults of the vehicle to be detected and the possibility that the vehicle to be detected contains each suspected fault includes: Preset likelihood threshold , if the vehicle to be detected contains The probability of a failure is greater than the probability threshold , will Each fault is recorded as a suspected fault of the vehicle to be detected; according to the possibility that the vehicle to be detected contains each fault, the possibility that the vehicle to be detected contains each suspected fault is obtained.

[0010] Furthermore, the processing capability of each neighboring maintenance station of the vehicle to be detected for each fault is obtained according to the number of maintenance records of each fault of each neighboring maintenance station of the vehicle to be detected, the processing time of the fault in the maintenance records and the user satisfaction, including the specific method of: In the formula, Indicates the vehicle to be detected. The nearest maintenance station Fault handling capability, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. The number of maintenance records for each fault, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. The average troubleshooting time for all maintenance records of a fault, Indicates that the fault is the first The average troubleshooting time for all maintenance records of a fault, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. Average customer satisfaction of all repair records of faults, represents the linear normalization function.

[0011] Furthermore, the method of combining the possibility that the vehicle to be detected contains each suspected fault to obtain the degree of compatibility between each adjacent maintenance station of the vehicle to be detected and the vehicle to be detected includes the following specific methods: In the formula, Indicates the vehicle to be detected. The degree of compatibility between the adjacent repair station and the vehicle to be tested, Indicates the number of suspected faults of the vehicle to be detected, Indicates that the vehicle to be detected has A possible malfunction, Indicates the vehicle to be detected. The nearest maintenance station The ability to handle suspected failures.

[0012] Furthermore, the method of obtaining the recommended degree of each adjacent maintenance station of the vehicle to be detected for the vehicle to be detected based on the distance between each adjacent maintenance station of the vehicle to be detected and the vehicle to be detected and the distribution of the degree of adaptation between all adjacent maintenance stations of the vehicle to be detected and the vehicle to be detected includes the following specific methods: In the formula, Indicates the vehicle to be detected. The recommendation level of the nearby repair station for the vehicle to be inspected, represents the variance of the degree of fit between all adjacent repair stations of the vehicle to be tested and the vehicle to be tested, It represents the average value of the adaptability of all adjacent repair stations of the vehicle to be tested to the vehicle to be tested, Indicates the vehicle to be detected. The degree of compatibility between the adjacent repair station and the vehicle to be tested, Indicates the vehicle to be detected. The distance between the adjacent maintenance station and the vehicle to be tested.

[0013] Furthermore, the specific method of obtaining the best maintenance station for the vehicle to be detected includes: The adjacent maintenance station of the vehicle to be detected corresponding to the maximum value of the recommendation degree of the vehicle to be detected is taken as the best maintenance station for the vehicle to be detected.

[0014] The present invention also proposes a cloud platform-based automobile maintenance guidance system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above method.

[0015] The beneficial effects of the technical solution of the present invention are as follows: when recommending a maintenance station for a vehicle to be tested, the present invention firstly follows the feature that when a fault occurs in the vehicle, if the data distribution of one dimension is relatively dense, then the data of this dimension has a strong correlation with the fault; according to the data distribution of each dimension under each fault in the maintenance records of the same model of automobile, the influence of the data of each dimension on the fault is obtained, so that the influence reflects the degree of aggregation of automobile data of the corresponding dimension under one fault; according to the data of each dimension in the maintenance record and the data of each dimension of the vehicle to be tested, the possible faults of the vehicle to be tested are obtained; when obtaining the best maintenance station for the vehicle to be tested, according to the variance of the degree of adaptation of the maintenance stations around the vehicle to be tested and the vehicle to be tested, the variance of the degree of adaptation of the vehicle to be tested and the surrounding maintenance stations is reflected. The difference in the maintenance capabilities of the maintenance stations around the vehicle to be detected for the vehicle to be detected; and the mean of the degree of adaptation of the maintenance stations around the vehicle to be detected and the vehicle to be detected, reflects the characteristics of the overall maintenance capabilities of the maintenance stations around the vehicle to be detected for the vehicle to be detected; according to the mean and variance of the degree of adaptation of the maintenance stations around the vehicle to be detected and the vehicle to be detected, a weight is respectively given to the degree of adaptation of the maintenance station and the vehicle to be detected and the distance between the vehicle to be detected and the maintenance station, so that when the difference in the maintenance capabilities of the maintenance stations around the vehicle to be detected for the vehicle to be detected is greater, the weight of the distance is lower, and when the difference in the maintenance capabilities of the maintenance stations around the vehicle to be detected is smaller, the weight of the distance is greater, so that the maintenance station is recommended on the premise of repairing the user's car, which reduces the time for the user to find the maintenance station. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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 or the description of the prior art 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.

[0017] Figure 1 The present invention is a flowchart of the steps of a cloud platform-based automobile maintenance guidance method. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a cloud-based automobile maintenance guidance system and method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The following is a detailed description of a specific solution of a cloud platform-based automobile maintenance guidance system and method provided by the present invention in conjunction with the accompanying drawings.

[0021] See also Figure 1 , which shows a flowchart of a method for guiding automobile maintenance based on a cloud platform according to an embodiment of the present invention, the method comprising the following steps: Step S001: Obtain the maintenance record of the maintenance station, data of multiple dimensions during the inspection of the vehicle to be inspected, and the distance between the vehicle to be inspected and the maintenance station.

[0022] Specifically, obtain the vehicle to be detected at the time of detection Dimensional data, to obtain data of multiple dimensions when the vehicle to be tested is tested. Obtained in the maintenance system of all maintenance stations The maintenance records of vehicles with the same make and model as the vehicle to be tested within 1 day, and the maintenance records contain only one fault. The maintenance records of the repair station include the fault, the time when the fault occurred, The number of dimensions preset in this embodiment is , and the four dimensions are respectively the tire pressure, the speed, the acceleration and the height of the vehicle collected by the height sensor on the shock absorber. In other implementations, the number of dimensions can be set to other values, or other dimensions can be selected; the dimension selected for the vehicle to be detected is the same as the dimension obtained in the maintenance record when the fault occurs; and the distance between the vehicle to be detected and each maintenance station is obtained. The collection time preset in this embodiment , this is used as an example for description, and other values ​​may be set in other implementation modes.

[0023] Step S002: according to the data distribution of the same dimension in the maintenance records of the same fault of the maintenance station, the influence degree of the data of each dimension on each fault is obtained.

[0024] It should be noted that when judging whether each car needs repair and recommending a suitable repair station for each car through the cloud platform, the data of the vehicle to be tested in various dimensions during the test is compared with the historical repair data of other cars to determine how many faults the car may have. Based on the historical repair data of each repair station, the repair capacity of each repair station for each fault is obtained. Based on the possible faults of the car, the repair capacity of each repair station for each fault, and the distance between the car and each repair station, the most suitable repair station for the vehicle to be tested is obtained.

[0025] It should be further explained that when obtaining the number of possible faults of the vehicle to be tested, since the structures of the same brand and model of the vehicle are exactly the same, the maintenance records of the vehicle with the same brand and model as the vehicle to be tested have a strong reference value for the vehicle to be tested. Therefore, according to the data of each dimension when the vehicle with the same brand and model as the vehicle to be tested in all repair stations fails, the influencing factors of each dimension on each fault and the possibility of each fault occurring in the vehicle under each value of the data of each dimension are obtained, and the possible faults of the vehicle are obtained.

[0026] It should be further explained that when obtaining the influencing factors of each fault for each dimension of data, The dimension of the car appears When a fault has a greater impact, The fault is When the data of the first dimension has a greater impact, When a fault occurs, The data values ​​under the dimensions are relatively similar; The dimension of the car appears If the first fault does not have a significant impact, When a fault occurs, The data values ​​under each dimension are relatively messy. Since the kurtosis reflects the degree of aggregation of multiple data, the influence of each dimension on each fault is obtained based on the distribution of the data values ​​of the same dimension in the maintenance records of all the same faults.

[0027] It should be further explained that, due to the different discrete degrees of data in different dimensions under normal circumstances, for example, The data of the first dimension is in the range of 20-150. The data of the first dimension is in the range of 5-10; if the The data of the first dimension The faults have no strong correlation, while the The data of the first dimension The faults have a strong correlation, so that when the When a fault occurs, The data of the first dimension is in the range of 0-15, then The maintenance record of the fault The kurtosis of the data in the first dimension may be smaller than that in the The kurtosis of the data in each dimension is calculated, and thus the kurtosis of the data in each dimension is corrected.

[0028] It should be further explained that when the data of one dimension has a strong correlation with a fault, the data of this dimension is within a smaller range when the fault occurs. Therefore, the difference between the maximum and minimum values ​​of the data of one dimension in all maintenance records and the difference between the maximum and minimum values ​​of the data of one dimension in the maintenance records under a fault can be used to obtain the degree of influence of each dimension on each fault.

[0029] Specifically, the fault is obtained as All maintenance records of the fault The value of the dimension is obtained Failure The dataset is a dataset of dimensions. Failure The data sets of dimensions can contain the same value. Failure All the values ​​in the data set of dimensions are obtained Failure The kurtosis of the data set of dimensions is denoted as Failure The kurtosis of data in one dimension is obtained by calculating the kurtosis of data in one dimension. The method of obtaining the kurtosis of a one-dimensional data set is a well-known technique and will not be described in detail in this embodiment.

[0030] Furthermore, Failure The difference between the maximum value and the minimum value in the data set of the dimension is recorded as Failure The data span of each dimension. The maximum value of the data in the dimension minus the value of the The difference after the minimum value of the data in the dimensions is recorded as the The data span of the dimension.

[0031] Further, get the The data of the dimension The calculation formula for the impact of a fault is as follows: In the formula, Indicates The data of the dimension The impact of a fault, Indicates Failure The kurtosis of the data in the dimension Indicates all faults. The data span of dimensions, Indicates Failure The data span of dimensions, Indicates Failure No. The data aggregation of the dimensions, Represents the weight normalization function, whose input is the The degree of data aggregation in each dimension of each fault; To prevent the hyperparameter from having a denominator of 0, this embodiment sets , can be set to other values ​​in other implementations.

[0032] It should be noted that The larger the value, the more Failure time The smaller the fluctuation of the data value of each dimension, the more in line with the current The dimension of the car appears The greater the impact of a fault, the The smaller the difference in the data values ​​under the dimension, the smaller the feature The data of the dimension The greater the impact of a fault, the greater the When the value of is large, it means that the Failure time The fluctuation of the data value of the first dimension is much smaller than that of the first dimension when other faults occur. The fluctuation of the data value of each dimension is more consistent with the current The dimension of the car appears The greater the impact of a fault, the The smaller the difference in data values ​​under each dimension, the smaller the feature.

[0033] At this point, the impact of the data in each dimension on each fault is obtained.

[0034] Step S003: Based on the data of the same dimension in all maintenance records under the same fault, obtain the possibility that each value under each dimension contains each fault; combine the influence of the data of each dimension on each fault and the data of the vehicle to be tested in each dimension to obtain the possibility that the vehicle to be tested contains each fault, and then obtain the suspected faults of the vehicle to be tested and the possibility that the vehicle to be tested contains each suspected fault.

[0035] It should be noted that when obtaining the possible faults of the vehicle to be detected based on the values ​​of the data of each dimension of the vehicle to be detected and the degree of influence of the data of each dimension on each fault. When a fault occurs The proportion of each value under the dimension is obtained The first The probability of a fault is obtained according to the value of the vehicle to be detected in each dimension. The possibility of a fault. Combining the impact of each dimension of data on each fault, the number of possible faults of the vehicle to be tested is obtained.

[0036] Specifically, get the The first The specific calculation formula for the probability of a failure is as follows: In the formula, Indicates The first dimension The value occurs The possibility of a failure, Indicates that the fault is The number of maintenance records for each fault, Indicates that the fault is the first Failure and The data value of the dimension is The first dimension The number of maintenance records with the specified value.

[0037] It should be noted that The larger the value is, the more likely it is that a car with the same brand and model as the vehicle to be tested will have When a fault occurs, The value of the dimension is The first dimension The greater the probability of the value; that is, when the vehicle to be detected is The data value of the dimension is The first dimension When the value is The greater the possibility of a failure.

[0038] Further, the vehicle to be detected contains the first The specific calculation formula for the probability of a failure is as follows: In the formula, Indicates that the vehicle to be tested contains The possibility of a failure, Indicates the preset number of dimensions, Indicates the vehicle to be detected. The data value of the dimension The possibility of a failure, Indicates The data of the dimension The impact of a fault.

[0039] It should be noted that The larger the value is, the more The data of the dimensions show that the vehicle to be detected contains The greater the possibility of a fault, the greater the probability of a fault. The greater the possibility of a failure.

[0040] Furthermore, a preset possibility threshold If the vehicle to be detected contains The probability of a failure is greater than the probability threshold , then the The faults are recorded as suspected faults of the vehicle to be detected; according to the possibility that the vehicle to be detected contains each fault, the possibility that the vehicle to be detected contains each suspected fault is obtained. , this is used as an example for description, and other values ​​may be set in other implementation modes.

[0041] Thus, the suspected faults of the vehicle to be detected and the possibility that the vehicle to be detected contains each suspected fault are obtained.

[0042] Step S004: based on the distance between each maintenance station and the vehicle to be detected, obtain the adjacent maintenance stations of the vehicle to be detected; based on the number of maintenance records of each fault of each adjacent maintenance station of the vehicle to be detected, the processing time of the fault in the maintenance records and the user satisfaction, obtain the processing capacity of each adjacent maintenance station of the vehicle to be detected for each fault; based on the possibility that the vehicle to be detected contains each suspected fault, obtain the degree of adaptation of each adjacent maintenance station of the vehicle to be detected and the vehicle to be detected; based on the distance between each adjacent maintenance station of the vehicle to be detected and the vehicle to be detected and the distribution of the degree of adaptation of all adjacent maintenance stations of the vehicle to be detected and the vehicle to be detected, obtain the recommendation degree of each adjacent maintenance station of the vehicle to be detected for the vehicle to be detected, and then obtain the best maintenance station for the vehicle to be detected.

[0043] It should be noted that, according to the historical maintenance records of each maintenance station, when obtaining the processing capacity of each maintenance station for each fault: the more times a maintenance station handles a fault, the stronger the processing capacity of the maintenance station for the fault; the faster a maintenance station handles a fault, the stronger the processing capacity of the maintenance station for the fault; the higher the user satisfaction after a maintenance station handles a fault, the stronger the processing capacity of the maintenance station for the fault. Therefore, according to the number and time of each maintenance station handling each fault and the user satisfaction after handling each fault, the processing capacity of each maintenance station for each fault is obtained.

[0044] It should be further explained that after the degree of compatibility between each maintenance station and the vehicle to be tested is obtained based on the ability of each maintenance station to handle each fault and the possibility that the vehicle to be tested contains each fault, since the distances between the vehicle to be tested and different maintenance stations are different, the recommended degree of each maintenance station for the vehicle to be tested is obtained based on the degree of compatibility between each maintenance station around the vehicle to be tested and the distances between the vehicle to be tested and different maintenance stations.

[0045] It should be further explained that, when a user goes to repair his car, he selects one of the multiple repair stations around him as the target repair station. Therefore, according to the distance between each repair station and the vehicle to be detected, the adjacent repair stations of the vehicle to be detected are obtained, and then the recommendation degree of the adjacent repair stations of the vehicle to be detected for the vehicle to be detected is obtained.

[0046] It should be further explained that when the user goes to the area to repair the car, the primary purpose is to repair the car, and then choose a maintenance station that is closer to the car on the basis of being able to repair the car. Therefore, when obtaining the recommended degree of each maintenance station for the vehicle to be detected, the mean value of the degree of adaptation of all maintenance stations around the vehicle to be detected and the vehicle to be detected reflects the difficulty of the maintenance station around the vehicle to be detected to handle the fault of the vehicle to be detected. The larger the value, the easier it is for the maintenance station around the vehicle to be detected to handle the fault of the vehicle to be detected, and the greater the weight should be given to the distance between the vehicle to be detected and the maintenance station. The variance of the degree of adaptation of all maintenance stations around the vehicle to be detected and the vehicle to be detected reflects the difference in the degree of handling of the fault of the vehicle to be detected by the maintenance stations around the vehicle to be detected. The larger the value, the greater the difference in the ability of different maintenance stations around the vehicle to be detected to handle the fault of the vehicle to be detected; therefore, the smaller the weight should be given to the distance between the vehicle to be detected and the maintenance station. Therefore, according to the degree of adaptation of each maintenance station around the vehicle to be detected and the vehicle to be detected, the importance of the maintenance of the vehicle to be detected is obtained, and then the recommended degree of each maintenance station for the vehicle to be detected is obtained.

[0047] Specifically, the distance between the vehicle to be detected is less than The maintenance station within kilometers is recorded as the adjacent maintenance station of the vehicle to be detected. The distance threshold preset in this embodiment is , this is used as an example for description, and other values ​​may be set in other implementation modes.

[0048] Further, obtain the first The nearest maintenance station The specific calculation formula for the handling capacity of a fault is as follows: In the formula, Indicates the vehicle to be detected. The nearest maintenance station Fault handling capability, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. The number of maintenance records for each fault, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. The average troubleshooting time for all maintenance records of a fault, Indicates that the fault is the first The average troubleshooting time for all maintenance records of a fault, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. Average customer satisfaction of all repair records of faults, represents the linear normalization function.

[0049] It should be noted that The larger the value is, the more The nearest repair station The more faults there are, the more The nearest maintenance station The stronger the ability to handle a single fault; The larger the value is, the more The nearest repair station The shorter the time of each fault, the shorter the time of the first fault of the vehicle to be detected. The nearest maintenance station The stronger the ability to handle a single fault; The larger the value is, the more The nearest maintenance station has completed the After a failure, the higher the user's rating, the higher the probability that the vehicle to be tested The nearest maintenance station The stronger the ability to handle a fault.

[0050] Further, obtain the first The specific calculation formula for the degree of compatibility between a nearby maintenance station and the vehicle to be tested is as follows: In the formula, Indicates the vehicle to be detected. The degree of compatibility between the adjacent repair station and the vehicle to be tested, Indicates the number of suspected faults of the vehicle to be detected, Indicates that the vehicle to be detected has A possible malfunction, Indicates the vehicle to be detected. The nearest maintenance station The ability to handle suspected failures.

[0051] It should be noted that The larger the value is, the more likely it is that the vehicle to be detected contains The greater the possibility of a suspected fault; The larger the value is, the more The nearest maintenance station The stronger the processing capability of a suspected fault is, the better the The closer the repair station is, the better the compatibility between it and the vehicle to be tested.

[0052] Furthermore, the specific calculation formula for obtaining the recommendation degree of each adjacent maintenance station of the vehicle to be tested for the vehicle to be tested is as follows: In the formula, Indicates the vehicle to be detected. The recommendation level of the nearby repair station for the vehicle to be inspected, represents the variance of the degree of fit between all adjacent repair stations of the vehicle to be tested and the vehicle to be tested, It represents the average value of the adaptability of all adjacent repair stations of the vehicle to be tested to the vehicle to be tested, Indicates the vehicle to be detected. The degree of compatibility between the adjacent repair station and the vehicle to be tested, Indicates the vehicle to be detected. The distance between the adjacent maintenance station and the vehicle to be tested.

[0053] It should be noted that The larger the value of is, the more compatible the maintenance stations around the vehicle to be tested are with the vehicle to be tested, that is, the easier it is for the maintenance stations around the vehicle to be tested to repair the vehicle to be tested, and the more attention should be paid to the distance between the vehicle to be tested and the maintenance stations. The smaller the value is, the more compatible the maintenance stations around the vehicle to be tested are with the vehicle to be tested, that is, the maintenance stations around the vehicle to be tested have similar capabilities to repair possible faults of the vehicle to be tested, and the more attention should be paid to the distance between the vehicle to be tested and the maintenance stations; The smaller the value is, the greater the weight should be given to the distance. The larger the value is, the more The probability that the next neighboring repair station is the best repair station for the vehicle to be tested is stronger.

[0054] Furthermore, the adjacent maintenance station of the vehicle to be detected corresponding to the maximum value of the recommendation degree of the vehicle to be detected is used as the best maintenance station for the vehicle to be detected, and the vehicle to be detected is sent to the best maintenance station for maintenance.

[0055] At this point, this embodiment is completed.

[0056] Another embodiment of the present invention provides a cloud platform-based automobile maintenance guidance system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the above method steps S001 to S004 are implemented.

[0057] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A car maintenance guidance method based on a cloud platform, characterized in that: The method comprises the following steps: Obtaining the maintenance records of the maintenance station, data of multiple dimensions when the vehicle to be tested is tested, and the distance between the vehicle to be tested and the maintenance station; the maintenance records of the maintenance station include the fault, data of the vehicle in various dimensions when the fault occurs, user satisfaction, and the time it takes to handle the fault; According to the data distribution of the same dimension in the maintenance records of the same fault in the maintenance station, the influence degree of the data of each dimension on each fault is obtained; Based on the data of the same dimension in all maintenance records under the same fault, the possibility of each fault being contained in each value under each dimension is obtained; the possibility of each fault being contained in the vehicle to be tested is obtained by combining the influence of the data of each dimension on each fault and the data of the vehicle to be tested in each dimension, and then the suspected faults of the vehicle to be tested and the possibility of each suspected fault being contained in the vehicle to be tested are obtained; According to the distance between each maintenance station and the vehicle to be tested, the adjacent maintenance stations of the vehicle to be tested are obtained; according to the number of maintenance records of each fault of each adjacent maintenance station of the vehicle to be tested, the processing time of the fault in the maintenance records and the user satisfaction, the processing capacity of each adjacent maintenance station of the vehicle to be tested for each fault is obtained; combined with the possibility that the vehicle to be tested contains each suspected fault, the adaptability of each adjacent maintenance station of the vehicle to be tested and the vehicle to be tested is obtained; according to the distance between each adjacent maintenance station of the vehicle to be tested and the vehicle to be tested and the distribution of the adaptability of all adjacent maintenance stations of the vehicle to be tested and the vehicle to be tested, the recommendation degree of each adjacent maintenance station of the vehicle to be tested for the vehicle to be tested is obtained, and then the best maintenance station for the vehicle to be tested is obtained.

2. The cloud platform-based automobile maintenance guidance method according to claim 1, characterized in that: The specific method of obtaining the influence degree of each dimension of data on each fault according to the data distribution of the same dimension in the maintenance records of the same fault of the maintenance station is as follows: Get the fault as All maintenance records of the fault The value of the dimension is obtained Failure A dataset with 1 dimension; According to Failure All the values ​​in the data set of dimensions are obtained Failure The kurtosis of the data set of dimensions is denoted as Failure The kurtosis of the data in each dimension; The first Failure The difference between the maximum value and the minimum value in the data set of the dimension is recorded as Failure The data span of the dimension; The maximum value of the data in the dimension minus the value of the The difference after the minimum value of the data in the dimensions is recorded as the The data span of the dimension; The calculation formula for obtaining the influence of each dimension of data on each fault is as follows: In the formula, Indicates The data of the dimension The impact of a fault, Indicates Failure The kurtosis of the data in the dimension Indicates all faults. The data span of dimensions, Indicates Failure The data span of dimensions, To prevent hyperparameters with denominators equal to zero, represents the weight normalization function.

3. The cloud platform-based automobile maintenance guidance method according to claim 1, characterized in that: The method of obtaining the possibility of each fault being contained in each value under each dimension based on the data of the same dimension in all maintenance records under the same fault includes the following specific methods: In the formula, Indicates The first dimension The value occurs The possibility of a failure, Indicates that the fault is The number of maintenance records for each fault, Indicates that the fault is the first Failure and The data value of the dimension is The first dimension The number of maintenance records with the specified value.

4. The cloud platform-based automobile maintenance guidance method according to claim 1, characterized in that: The method of combining the influence degree of each fault on the data of each dimension and the data of the vehicle to be detected in each dimension to obtain the possibility of the vehicle to be detected containing each fault includes the following specific methods: In the formula, Indicates that the vehicle to be tested contains The possibility of a failure, Indicates the preset number of dimensions, Indicates the vehicle to be detected. The data value of the dimension The possibility of a failure, Indicates The data of the dimension The impact of a fault.

5. The automobile maintenance guidance method based on a cloud platform according to claim 1, characterized in that: The specific method of obtaining the suspected faults of the vehicle to be detected and the possibility that the vehicle to be detected contains each suspected fault includes: Preset likelihood threshold , if the vehicle to be detected contains The probability of a failure is greater than the probability threshold , will Each fault is recorded as a suspected fault of the vehicle to be detected; according to the possibility that the vehicle to be detected contains each fault, the possibility that the vehicle to be detected contains each suspected fault is obtained.

6. The cloud platform-based automobile maintenance guidance method according to claim 1, characterized in that: The specific method of obtaining the processing capability of each neighboring maintenance station for each fault of the vehicle to be detected based on the number of maintenance records of each fault of each neighboring maintenance station of the vehicle to be detected, the processing time of the fault in the maintenance records and the user satisfaction is as follows: In the formula, Indicates the vehicle to be detected. The nearest maintenance station Fault handling capability, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. The number of maintenance records for each fault, Indicates the vehicle to be detected. The fault is in the maintenance record of the adjacent maintenance station. The average troubleshooting time for all maintenance records of a fault, Indicates that the fault is the first The average troubleshooting time for all maintenance records of a fault, Indicates the vehicle to be detected. The fault is in the maintenance record of the neighboring maintenance station. Average customer satisfaction of all repair records of faults, represents the linear normalization function.

7. The cloud platform-based automobile maintenance guidance method according to claim 1, characterized in that: The method of combining the possibility that the vehicle to be detected contains each suspected fault to obtain the degree of compatibility between each adjacent maintenance station of the vehicle to be detected and the vehicle to be detected includes the following specific methods: In the formula, Indicates the vehicle to be detected. The degree of compatibility between the adjacent repair station and the vehicle to be tested, Indicates the number of suspected faults of the vehicle to be detected, Indicates that the vehicle to be detected has A possible malfunction, Indicates the vehicle to be detected. The nearest maintenance station The ability to handle suspected failures.

8. The cloud platform-based automobile maintenance guidance method according to claim 1, characterized in that: The method of obtaining the recommendation degree of each adjacent maintenance station of the vehicle to be detected for the vehicle to be detected based on the distance between each adjacent maintenance station of the vehicle to be detected and the vehicle to be detected and the distribution of the adaptation degree between all adjacent maintenance stations of the vehicle to be detected and the vehicle to be detected includes the following specific methods: In the formula, Indicates the vehicle to be detected. The recommendation level of the nearby repair station for the vehicle to be inspected, represents the variance of the degree of fit between all adjacent repair stations of the vehicle to be tested and the vehicle to be tested, It represents the average value of the adaptability of all adjacent repair stations of the vehicle to be tested to the vehicle to be tested, Indicates the vehicle to be detected. The degree of compatibility between the adjacent repair station and the vehicle to be tested, Indicates the vehicle to be detected. The distance between the adjacent maintenance station and the vehicle to be tested.

9. The automobile maintenance guidance method based on a cloud platform according to claim 1, characterized in that: The specific method of obtaining the best maintenance station for the vehicle to be detected includes: The adjacent maintenance station of the vehicle to be detected corresponding to the maximum value of the recommendation degree of the vehicle to be detected is taken as the best maintenance station for the vehicle to be detected.

10. A car maintenance guidance system based on a cloud platform, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the cloud platform-based automobile maintenance guidance method as described in any one of claims 1 to 9 are implemented.

Images