Vehicle maintenance method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle maintenance method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining use data of a vehicle; the pure electric driving level of the vehicle is determined according to the use data, and the smaller the pure electric driving level is, the more excellent the pure electric driving habit of the user during historical vehicle driving is; when it is detected that the pure electric driving level is equal to a preset level, taking a preset basic maintenance mileage as a first recommended mileage for next maintenance of the vehicle; when it is detected that the pure electric driving level is smaller than a preset level, the use data are input into a preset algorithm model, so that the preset algorithm model outputs the maintenance predicted mileage of the vehicle according to the use data; a second recommended mileage of next maintenance of the vehicle is obtained according to the predicted maintenance mileage, and the second recommended mileage is larger than the first recommended mileage. According to the method, the vehicle maintenance scheme can be customized for the user with a good pure electric driving habit, and the vehicle maintenance cost is reduced while the vehicle use experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle maintenance method, device, electronic equipment and storage medium. Background Art

[0002] With the increase in the number of extended-range vehicles, the maintenance of extended-range vehicle engines has gradually attracted the attention of users. The existing maintenance plan for extended-range vehicle engines is generally based on regular or fixed-mileage maintenance, for example, one year or 10,000 kilometers, whichever comes first, to maintain the extended-range vehicle engine. However, the current extended-range vehicle engine maintenance plan based on the above-mentioned fixed time or fixed mileage is only based on the oil characteristics in the vehicle, such as the change in the oil characteristics of the engine oil to change the mileage and replacement time. For extended-range vehicles, the engine's operating time and operating characteristics are significantly different from those of traditional fuel vehicles. As long as the traditional fuel vehicle is started, the engine will operate; while the extended-range vehicle's engine will only operate when there is a need for the range extender to work, and the operating characteristics of the range extender are also significantly different due to the different habits of each driver. The maintenance method of traditional fuel vehicles based on regular or fixed mileage is not accurate for maintenance prediction of extended-range vehicles, and it will increase the user's maintenance cost. Summary of the invention

[0003] In view of this, the present application provides a vehicle maintenance method, device, electronic device and storage medium, which can personalize vehicle maintenance plans for users with good pure electric driving habits, thereby improving the user's car experience and reducing the vehicle's maintenance costs.

[0004] According to a first aspect of the present application, a vehicle maintenance method is provided, comprising: obtaining vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle; determining the pure electric driving level of the vehicle based on the usage data, wherein the smaller the pure electric driving level, the better the pure electric driving habits of the user when driving the vehicle in the past; when it is detected that the pure electric driving level is equal to a preset level, using a pre-set basic maintenance mileage as a first recommended mileage for the next maintenance of the vehicle; when it is detected that the pure electric driving level is less than the preset level, inputting the usage data into a preset algorithm model, so that the preset algorithm model outputs the maintenance predicted mileage of the vehicle according to the usage data; obtaining a second recommended mileage for the next maintenance of the vehicle based on the maintenance predicted mileage, wherein the second recommended mileage is greater than the first recommended mileage.

[0005] Compared with the related art, the embodiments of the present application have at least the following advantages: by obtaining the vehicle usage data, since the usage data includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle, the pure electric driving level of the vehicle can be determined based on the usage data; and since the smaller the pure electric driving level, the better the pure electric driving habits of the user when driving the vehicle in the past, therefore, when it is detected that the pure electric driving level is equal to the preset level, it indicates that the user rarely performs pure electric driving when driving the vehicle in the past, which means that the engine running time is longer during the historical use of the vehicle, and the basic maintenance mileage is used as the first recommended mileage for the next maintenance of the vehicle to ensure the normal use of the vehicle. When it is detected that the pure electric driving level is lower than the preset level, it indicates that the user often performs pure electric driving in the historical driving of the vehicle, which means that the engine running time is short during the historical use of the vehicle. By inputting the usage data into the preset algorithm model, the preset algorithm model outputs the vehicle's predicted maintenance mileage according to the usage data, and then obtains the second recommended mileage for the next maintenance of the vehicle based on the predicted maintenance mileage. This enables personalized recommendations for customized vehicle maintenance plans for users with excellent pure electric driving habits. Since the second recommended mileage is greater than the first recommended mileage, the engine maintenance cycle is extended, thereby reducing the vehicle's maintenance cost. In addition, the vehicle will not remind users to perform maintenance based on the basic maintenance mileage, thereby improving the user's car experience.

[0006] In some embodiments, the preset algorithm model is trained in the following manner: obtaining training sample data, wherein the training sample data includes the percentage of pure electric mileage, total refueling volume, and maintenance mileage interval of other vehicles in historical use; repeatedly executing the cross-validation step to obtain a cross-validation result, wherein the cross-validation result includes multiple test results; calculating the error rate of each of the training sample data according to the cross-validation result, and updating the model parameters of the initial algorithm model according to the error rate to obtain the preset algorithm model; wherein the cross-validation step includes: dividing the training sample data into a training set and a test set; training the initial algorithm model according to the training set to obtain a trained algorithm model; and testing the test set using the algorithm model to obtain a test result.

[0007] In some embodiments, the obtaining of training sample data includes: obtaining multiple initial sample data of multiple sample vehicles, wherein each of the sample vehicles corresponds to one initial sample data, and each of the initial sample data includes the maintenance mileage interval and failure rate of the sample vehicle during historical use, and the failure rate is the number of fault codes reported by the sample vehicle between two adjacent maintenances; calculating the maintenance score of each of the sample vehicles based on the failure rate and the maintenance mileage interval; and using the initial sample data corresponding to the sample vehicle whose maintenance score meets the preset scoring rules as the training sample data.

[0008] In some embodiments, calculating the maintenance score of each of the sample vehicles based on the failure rate and the maintenance mileage interval includes: normalizing the failure rate and the maintenance mileage interval, respectively; calculating the failure rate score of the sample vehicle based on the normalized failure rate; calculating the maintenance mileage interval score of the sample vehicle based on the normalized maintenance mileage interval; and calculating the maintenance score based on the failure rate score and the maintenance mileage interval score.

[0009] In some embodiments, the training sample data includes multiple data categories; before inputting the usage data into the preset algorithm model, it also includes: detecting whether the usage data includes all the data categories in the training sample data; inputting the usage data into the preset algorithm model includes: after detecting that the usage data includes all the data categories in the training sample data, inputting the usage data into the preset algorithm model.

[0010] In some embodiments, the method further includes: setting multiple maintenance mileage ranges, wherein the multiple maintenance mileage ranges do not intersect with each other, and each maintenance mileage range corresponds to a target maintenance mileage; obtaining the second recommended mileage for the next maintenance of the vehicle based on the predicted maintenance mileage, including: determining a specific interval range of the predicted maintenance mileage in the multiple maintenance mileage ranges, and obtaining the matching target maintenance mileage, and using the target maintenance mileage as the second recommended mileage.

[0011] In some embodiments, determining the pure electric driving level of the vehicle based on the usage data includes: inputting the usage data into a preset clustering algorithm model, and using the output result of the preset clustering algorithm model as the pure electric driving level; wherein the preset clustering algorithm model is obtained by training vehicle characteristic data, and the vehicle characteristic data includes at least the pure electric driving mileage percentage and total fuel consumption of other vehicles in historical usage.

[0012] According to a second aspect of the present application, a vehicle maintenance device is provided, comprising: an acquisition module, a confirmation module and a detection module; the acquisition module is used to acquire vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle; the confirmation module is used to determine the pure electric driving level of the vehicle based on the usage data, wherein the smaller the pure electric driving level, the better the pure electric driving habits of the user when driving the vehicle in the past; the detection module is used to, when it is detected that the pure electric driving level is equal to the preset level, use the pre-set basic maintenance mileage as the first recommended mileage for the next maintenance of the vehicle; when it is detected that the pure electric driving level is less than the preset level, input the usage data into a preset algorithm model, so that the preset algorithm model outputs the maintenance predicted mileage of the vehicle according to the usage data; the detection device is also used to obtain the second recommended mileage for the next maintenance of the vehicle based on the maintenance predicted mileage, wherein the second recommended mileage is greater than the first recommended mileage.

[0013] According to a third aspect of the present application, an electronic device is provided, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the above-mentioned vehicle maintenance method.

[0014] According to a fourth aspect of the present application, a storage medium is provided, wherein the storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned vehicle maintenance method.

[0015] It can be understood that the device of the second aspect provided above, the electronic device provided in the third aspect and the storage medium of the fourth aspect all correspond to the vehicle maintenance method of the first aspect mentioned above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a vehicle maintenance method provided in an embodiment of the present application.

[0017] Figure 2 A schematic flow chart of a vehicle maintenance method provided in an embodiment of the present application.

[0018] Figure 3 A schematic diagram of functional modules of a vehicle maintenance device provided in an embodiment of the present application.

[0019] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the implementation methods of the present application and the features in the implementation methods can be combined with each other without conflict.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The described implementations are only part of the implementations of the present application, rather than all the implementations.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0023] It should be further noted that, in this article, the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0024] In this application, "at least one" means one or more, and "more" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0025] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0026] With the development of the Internet of Vehicles and big data, more and more vehicles are connecting and interacting with the outside world through Internet of Vehicles technology. By collecting and analyzing the large amount of data generated by vehicles, automobile companies can understand information such as vehicle health status, user travel behavior, vehicle usage habits, charging habits, and refueling habits.

[0027] However, the existing maintenance policy for plug-in hybrid vehicles is that the vehicle needs to be maintained when it reaches a fixed mileage or a fixed time, and the maintenance mileage is not reasonable. For example, when the smart maintenance function on the instrument reaches a fixed mileage, it will always remind the user that the vehicle maintenance is overdue. Many users do not go to 4S stores for maintenance, or they do maintenance after a certain mileage, which causes the smart maintenance function of the instrument to remind the user that the vehicle needs maintenance every time the power is turned on according to the fixed mileage, resulting in a poor user experience. In addition, for users who are more accustomed to pure electric vehicles, the vehicle uses the engine for a short time and mileage, so the vehicle's maintenance mileage and maintenance time can be extended to reduce the vehicle's maintenance costs.

[0028] In view of this, the present application provides a vehicle maintenance method, which personalizes vehicle maintenance plans for users with good pure electric driving habits based on vehicle usage data, thereby improving the user's vehicle experience while reducing the vehicle's maintenance costs.

[0029] Please refer to Figure 1 , Figure 1 This is a flowchart of the steps in an embodiment of the vehicle maintenance method of the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. The control method can be applied to the cloud, but is not limited to this, and the embodiments of the present application are not limited to this.

[0030] Specifically, the cloud can be an independent server, or a server network or server cluster composed of servers. For example, the cloud described in the embodiments of the present application includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.

[0031] The specific process of this embodiment is as follows Figure 1 As shown, the following steps are included: Step 101, obtaining vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the vehicle's historical use.

[0032] In some embodiments, the usage data further includes one of the following or any combination thereof: the number of weekly charging times of the vehicle during historical use, the average duration of each charging, the daily mileage, the time interval between two adjacent refuelings, and the average amount of fuel consumed per refueling.

[0033] Specifically, when the user uses the vehicle, the vehicle controller records the vehicle usage data, such as the number of times the vehicle is charged per week, the average charging time per time, the interval between two adjacent refuelings, the average amount of fuel per refueling, etc. The vehicle controller then uploads the recorded usage data to the cloud through the Internet of Vehicles.

[0034] It is understandable that the present embodiment does not specifically limit the method for obtaining the usage data, which may be determined based on the actual model and configuration of the vehicle.

[0035] Step 102 , determining the pure electric driving level of the vehicle based on the usage data, wherein the smaller the pure electric driving level, the better the pure electric driving habits of the user in the historical driving of the vehicle.

[0036] In some embodiments, the usage data is input into a preset clustering algorithm model, and the output result of the preset clustering algorithm model is used as the pure electric driving level; wherein, the preset clustering algorithm model is obtained by training the vehicle characteristic data, and the vehicle characteristic data at least includes the pure electric driving mileage percentage and total refueling amount of other vehicles in the historical use process.

[0037] In some embodiments, the preset clustering algorithm model is a K-Means model. For ease of understanding, the training process of the K-Means model in this embodiment is specifically described below: 1. Select the number of clusters (K): The optimal number of clusters (K value) is estimated by the Elbow Method. Specifically, the Elbow Method calculates the loss function by changing the number of clusters K, and finds the point where the rate of decrease of the loss function is significantly slowed down, that is, the "elbow point", as the recommended number of clusters. In this embodiment, when the value of K is between 1 and 3, the curve of the loss function drops rapidly; when the value of K is greater than 3, the curve of the loss function tends to be stable. The elbow method believes that the inflection point is the best value of K, that is, 3 categories are the optimal number of clusters.

[0038] 2. Initialize cluster centers: Randomly select K data points as initial cluster centers, which represent the center of each cluster.

[0039] 3. Assign data points to the nearest cluster center: For each data point, that is, the vehicle feature data corresponding to each vehicle, calculate its distance from each cluster center and assign it to the cluster with the nearest cluster center.

[0040] 4. Update the cluster center: For each cluster, calculate the average value of all data points in the cluster and use this average value as the new cluster center.

[0041] 5. Repeat steps 3 and 4 until the cluster center no longer changes significantly or the predetermined number of iterations is reached.

[0042] The K-Means model trained in the above way can be used to find the typical behaviors of users in different clusters by viewing the eigenvalue distribution of each cluster center in the K-Means model. As mentioned above, the pure electric driving level of vehicles can be divided into three categories, namely: Category 1: Indicates that the pure electric driving mileage accounts for a high proportion, the charging frequency is high, and the refueling interval is long. Category 2: Indicates that the pure electric driving mileage accounts for a moderate proportion, and the charging and refueling frequencies are balanced. Category 3: Indicates that the pure electric driving mileage accounts for a low proportion, the charging frequency is low, and the refueling frequency is high.

[0043] In some embodiments, vehicle characteristic data can be obtained in the following ways: obtaining initial key data of other vehicles, such as the proportion of pure electric mileage, daily mileage, weekly charging times, time between two refuelings and total refueling volume of other vehicles in historical use; filling missing values ​​of the initial key data with the median, and then standardizing the filled initial key data to obtain vehicle characteristic data.

[0044] Specifically, due to the influence of signals and other aspects, the initial key data of other vehicles recorded in the cloud may be missing. For example, the cloud records the charging times of vehicle A in the first week, third week, fourth week and fifth week respectively, and the charging times of vehicle A in the second week is missing. In this case, the median of the charging times of vehicle A in the first week, third week, fourth week and fifth week will be used as the charging times of vehicle A in the second week.

[0045] It is worth noting that the method of filling the missing values ​​of the initial key data is not limited to the above-mentioned filling by the median, and can also be filled by other methods. For example, the number of times vehicle A was charged in the second week in the above example is missing, and the number of times vehicle A was charged in the second week can be estimated by the pure electric mileage of vehicle A in the second week.

[0046] Step 103 , detect whether the pure electric driving level is greater than or equal to a preset level. When it is detected that the pure electric driving level is greater than or equal to the preset level, execute step 104 ; otherwise, execute step 105 .

[0047] In some embodiments, the preset level is Category 3. When the pure electric driving level is equal to Category 3, it indicates that the vehicle's pure electric driving mileage accounts for a low proportion, the charging frequency is low, and the refueling frequency is high.

[0048] Step 104 , using the preset basic maintenance mileage as the first recommended mileage for the next vehicle maintenance.

[0049] In some embodiments, the preset basic maintenance mileage may be equal to the normal maintenance mileage of a gasoline vehicle, such as 5,000 kilometers, 10,000 kilometers, etc. This embodiment does not specifically limit the size of the basic maintenance mileage, and it can be set according to actual needs.

[0050] Step 105 , inputting the usage data into a preset algorithm model so that the preset algorithm model outputs a maintenance prediction mileage of the vehicle according to the usage data.

[0051] In some embodiments, the preset algorithm model is trained in the following manner: obtaining training sample data, wherein the training sample data includes the percentage of pure electric mileage, total refueling volume, and maintenance mileage intervals of other vehicles in historical use; repeatedly executing the cross-validation step to obtain a cross-validation result, wherein the cross-validation result includes multiple test results; calculating the error rate of each of the training sample data according to the cross-validation result, and updating the model parameters of the initial algorithm model according to the error rate to obtain the preset algorithm model; wherein the cross-validation step includes: dividing the training sample data into a training set and a test set; training the initial algorithm model according to the training set to obtain a trained algorithm model; and testing the test set using the algorithm model to obtain a test result.

[0052] Specifically, the preset algorithm model of this embodiment is the LightGBM model. The programming language python is used to build the regression model of LightGBM, and the main parameters of the regression model are configured, such as "num_leaves" (the number of leaves in the tree), "learning_rate" (learning rate), "n_estimators" (the number of trees), "max_depth" (the maximum depth of the tree), etc., and then the training sample data is used to train the configured regression model.

[0053] In some embodiments, when the test set is tested using the algorithm model, the root mean square error (RMSE) can be used to measure the deviation between the predicted value and the actual value, and the deviation between the predicted value and the actual value can be used as the test result.

[0054] It is worth noting that the present embodiment can obtain training sample data in the following manner: obtain multiple initial sample data of multiple sample vehicles, wherein each of the sample vehicles corresponds to one initial sample data, and each of the initial sample data includes the maintenance mileage interval and failure rate of the sample vehicle during historical use, wherein the failure rate is the number of fault codes reported by the sample vehicle between two adjacent maintenances; calculate the maintenance score of each of the sample vehicles according to the failure rate and the maintenance mileage interval; and use the initial sample data corresponding to the sample vehicle whose maintenance score meets the preset scoring rules as the training sample data. Since there is no direct label of whether the maintenance cycle is reasonable in the initial sample data, the above method can filter out the training sample data with a reasonable maintenance cycle from the initial sample data, thereby improving the prediction accuracy of the preset algorithm model trained by the training sample data.

[0055] In some embodiments, the maintenance score of each of the sample vehicles is calculated based on the failure rate and the maintenance mileage interval, including: normalizing the failure rate and the maintenance mileage interval, respectively; calculating the failure rate score of the sample vehicle based on the normalized failure rate; calculating the maintenance mileage interval score of the sample vehicle based on the normalized maintenance mileage interval; calculating the maintenance score based on the failure rate score and the maintenance mileage interval score.

[0056] Specifically, the maintenance score is defined as follows: (1) Failure rate FR: the number of fault codes reported between two maintenances. A lower failure rate should receive a higher score. (2) Vehicle maintenance mileage interval MI: the mileage of the vehicle from the last maintenance to the next maintenance. A longer mileage interval indicates a longer maintenance cycle, which can save more costs and should receive a higher score.

[0057] Since the magnitude and distribution of failure rate and maintenance mileage interval may be different, these indicators need to be normalized to ensure that they have the same weight when calculating the total score. Therefore, in this embodiment, the failure rate score and maintenance mileage interval score can be calculated by the following formula: Failure rate score: (1-normalized FR)*100, i.e. the lower the failure rate, the higher the score; Maintenance mileage interval score: (normalized MI)*100, that is, the longer the mileage interval, the higher the score.

[0058] In some embodiments, the maintenance score is the average of the sum of the failure rate score and the maintenance mileage interval score. It should be noted that the maintenance score can also be calculated by other methods, such as calculating the weighted average of the failure rate score and the maintenance mileage interval score. This embodiment does not specifically limit the calculation method of the maintenance score, and it can be set according to actual needs.

[0059] In some embodiments, the preset scoring rule may be: using the upper quartile of multiple initial sample data as training sample data. It should be noted that the training sample data may also be obtained in other ways, such as setting a target score and using all initial sample data with maintenance scores greater than the target score as training sample data. This embodiment does not specifically limit the screening method of the training sample data and may be set according to actual needs.

[0060] In some embodiments, the training sample data includes multiple data categories; before inputting the usage data into the preset algorithm model, it also includes: detecting whether the usage data includes all the data categories in the training sample data; inputting the usage data into the preset algorithm model includes: after detecting that the usage data includes all the data categories in the training sample data, inputting the usage data into the preset algorithm model.

[0061] Specifically, assuming that the training sample data includes four categories, namely, the proportion of pure electric mileage, the number of charging times per week, the time between two refuelings, and the total amount of refueling, the usage data must also include the above four categories. In this way, the prediction accuracy of the preset algorithm model can be further improved, thereby further ensuring the rationality of the maintenance prediction mileage.

[0062] Step 106 , obtaining a second recommended mileage for the next vehicle maintenance according to the predicted maintenance mileage, wherein the second recommended mileage is greater than the first recommended mileage.

[0063] It should be noted that how to obtain the second recommended mileage of the vehicle is described in detail in subsequent embodiments, and will not be described again here to avoid repetition.

[0064] Compared with the related art, the embodiments of the present application have at least the following advantages: by obtaining the vehicle usage data, since the usage data includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle, the pure electric driving level of the vehicle can be determined based on the usage data; and since the smaller the pure electric driving level, the better the pure electric driving habits of the user when driving the vehicle in the past, therefore, when it is detected that the pure electric driving level is equal to the preset level, it indicates that the user rarely performs pure electric driving when driving the vehicle in the past, which means that the engine running time is longer during the historical use of the vehicle, and the basic maintenance mileage is used as the first recommended mileage for the next maintenance of the vehicle to ensure the normal use of the vehicle. When it is detected that the pure electric driving level is lower than the preset level, it indicates that the user often performs pure electric driving in the historical driving of the vehicle, which means that the engine running time is short during the historical use of the vehicle. By inputting the usage data into the preset algorithm model, the preset algorithm model outputs the vehicle's predicted maintenance mileage according to the usage data, and then obtains the second recommended mileage for the next maintenance of the vehicle based on the predicted maintenance mileage. This enables personalized recommendations for customized vehicle maintenance plans for users with excellent pure electric driving habits. Since the second recommended mileage is greater than the first recommended mileage, the engine maintenance cycle is extended, thereby reducing the vehicle's maintenance cost. In addition, the vehicle will not remind users to perform maintenance based on the basic maintenance mileage, thereby improving the user's car experience.

[0065] Please refer to 2, Figure 2 This is a flowchart of the steps in an embodiment of the vehicle maintenance method of the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. The control method can be applied to the controller of the vehicle, but is not limited thereto, and the embodiments of the present application are not limited thereto.

[0066] This embodiment is a specific description of the above embodiment, and further illustrates how to determine the second recommended mileage.

[0067] The specific process of this embodiment is as follows Figure 2 As shown, the following steps are included: Step 201, obtaining vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the vehicle's historical use.

[0068] Step 202 , determining the pure electric driving level of the vehicle based on the usage data, wherein the smaller the pure electric driving level, the better the pure electric driving habits of the user in historical driving of the vehicle.

[0069] Step 203 , detect whether the pure electric driving level is greater than or equal to a preset level. When it is detected that the pure electric driving level is greater than or equal to the preset level, execute step 204 ; otherwise, execute step 205 .

[0070] Step 204 , using the preset basic maintenance mileage as the first recommended mileage for the next vehicle maintenance.

[0071] Step 205 , input the usage data into a preset algorithm model so that the preset algorithm model outputs the maintenance prediction mileage of the vehicle according to the usage data.

[0072] Steps 201 to 205 of this embodiment are similar to steps 101 to 105 of the aforementioned embodiment, and are not described again here to avoid repetition.

[0073] Step 206 , setting a plurality of maintenance mileage ranges, wherein the plurality of maintenance mileage ranges are mutually exclusive and each maintenance mileage range corresponds to a target maintenance mileage.

[0074] Step 207, determining a specific interval range of the predicted maintenance mileage in the multiple maintenance mileage ranges, and obtaining a matching target maintenance mileage, and using the target maintenance mileage as the second recommended mileage.

[0075] For ease of understanding, the following specifically describes how to determine the second recommended mileage in this embodiment: The maintenance mileage ranges are set as Range 1: 15000km to 16000km; Range 2: 16000km to 17000km; Range 3: 17000km to 18000km; Range 4: 18000km to 19000km; Range 5: 19000km to 20000km. The target maintenance mileage for Range 1 is 16000km, the target maintenance mileage for Range 2 is 17000km, the target maintenance mileage for Range 3 is 18000km, the target maintenance mileage for Range 4 is 19000km, and the target maintenance mileage for Range 5 is 20000km.

[0076] Assume that the maintenance prediction mileage output by the preset algorithm model is 18600 km. Since 18600 km is within range 4, the target maintenance mileage of 19000 km corresponding to range 4 is used as the second recommended mileage.

[0077] It is worth noting that through the vehicle maintenance method of this embodiment, on the car manufacturer side, the car manufacturer can develop engine accessory materials that are suitable for plug-in hybrid models based on the user's pure electric usage habits, thereby reducing parts costs; in view of the fact that the existing smart maintenance function is not intelligent, when the vehicle reaches a fixed mileage or a fixed time, the instrument always reminds the user of the negative impact of vehicle maintenance. Based on the vehicle maintenance information of 4S stores across the country, combined with the user's vehicle usage habits and maintenance mileage, the user is provided with the estimated time and mileage for the next maintenance, and the closed loop is notified through the mobile phone APP.

[0078] On the user side, the cloud customizes a more reasonable maintenance mileage. Based on the clustering result analysis, the next maintenance mileage for users with pure electric driving levels in categories 1, 2, and 3 is predicted. For example, based on the model prediction of the original 15,000km mileage of the car-using habits of category 2 users, the next maintenance mileage is output as 20,000km for maintenance. If the pure electric car-using habits of category 2 users improve and meet the user characteristics of category 1, the prediction model will output the next maintenance mileage, such as changing the original 20,000km mileage to 25,000km, thereby further improving the user experience. In addition, the vehicle can also send prompt information to the user to inform the user of the current pure electric driving level. If the user with excellent pure electric driving wants to reduce maintenance costs, he can use lower-cost engine accessories for maintenance.

[0079] Compared with the related art, the embodiments of the present application have at least the following advantages: by obtaining the vehicle usage data, since the usage data includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle, the pure electric driving level of the vehicle can be determined based on the usage data; and since the smaller the pure electric driving level, the better the pure electric driving habits of the user when driving the vehicle in the past, therefore, when it is detected that the pure electric driving level is equal to the preset level, it indicates that the user rarely performs pure electric driving when driving the vehicle in the past, which means that the engine running time is longer during the historical use of the vehicle, and the basic maintenance mileage is used as the first recommended mileage for the next maintenance of the vehicle to ensure the normal use of the vehicle. When it is detected that the pure electric driving level is lower than the preset level, it indicates that the user often performs pure electric driving in the historical driving of the vehicle, which means that the engine running time is short during the historical use of the vehicle. By inputting the usage data into the preset algorithm model, the preset algorithm model outputs the vehicle's predicted maintenance mileage according to the usage data, and then obtains the second recommended mileage for the next maintenance of the vehicle based on the predicted maintenance mileage. This enables personalized recommendations for customized vehicle maintenance plans for users with excellent pure electric driving habits. Since the second recommended mileage is greater than the first recommended mileage, the engine maintenance cycle is extended, thereby reducing the vehicle's maintenance cost. In addition, the vehicle will not remind users to perform maintenance based on the basic maintenance mileage, thereby improving the user's car experience.

[0080] Based on the same concept as the vehicle maintenance method in the above embodiment, the present application also provides a vehicle maintenance device, which can be used to perform the above vehicle maintenance method. For ease of explanation, the structural diagram of the vehicle maintenance device embodiment only shows the parts related to the embodiment of the present application. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown in the diagram, or combine certain components, or arrange the components differently.

[0081] Please refer to Figure 3The vehicle maintenance device 30 includes an acquisition module 301 , a confirmation module 302 and a detection module 303 .

[0082] The acquisition module 301 is used to acquire the vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle; the confirmation module 302 is used to determine the pure electric driving level of the vehicle based on the usage data, wherein the smaller the pure electric driving level, the better the pure electric driving habits of the user when driving the vehicle in the past; the detection module 303 is used to, when it is detected that the pure electric driving level is greater than or equal to the preset level, use the pre-set basic maintenance mileage as the first recommended mileage for the next maintenance of the vehicle; when it is detected that the pure electric driving level is less than the preset level, input the usage data into the preset algorithm model, so that the preset algorithm model outputs the maintenance predicted mileage of the vehicle according to the usage data; the detection device 303 is also used to obtain the second recommended mileage for the next maintenance of the vehicle based on the maintenance predicted mileage, wherein the second recommended mileage is greater than the first recommended mileage.

[0083] Please refer to Figure 4 , Figure 4 This is a schematic diagram of an embodiment of an electronic device of the present application.

[0084] The electronic device 1000 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and executable on the processor 30. When the processor 30 executes the computer program 40, the steps in the above vehicle maintenance method embodiment are implemented, for example Figure 1 Steps 101 to 106 are shown.

[0085] Exemplarily, the computer program 40 may also be divided into one or more modules / units, one or more modules / units are stored in the memory 20, and executed by the processor 30. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 40 in the electronic device 1000.

[0086] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 1000 and does not constitute a limitation of the electronic device 1000. The electronic device 1000 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 1000 may also include input and output devices, network access devices, buses, etc.

[0087] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, a single-chip microcomputer, or the processor 30 may also be any conventional processor, etc.

[0088] The memory 20 can be used to store the computer program 40 and / or the module / unit. The processor 30 realizes various functions of the electronic device 1000 by running or executing the computer program and / or the module / unit stored in the memory 20 and calling the data stored in the memory 20. The memory 20 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 1000, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0089] If the module / unit integrated in the electronic device 1000 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed electronic device and method can be implemented in other ways. For example, the electronic device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation.

[0091] In addition, each functional unit in each embodiment of the present application may be integrated into the same processing unit, each unit may exist physically separately, or two or more units may be integrated into the same unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0092] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or electronic devices stated in the electronic device claim can also be implemented by the same unit or electronic device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the above embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A vehicle maintenance method, characterized in that: include: Obtaining vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of fuel refueled during the historical use of the vehicle; Determining the pure electric driving level of the vehicle according to the usage data, wherein the smaller the pure electric driving level is, the better the pure electric driving habits of the user when driving the vehicle in the past are; When it is detected that the pure electric driving level is greater than or equal to a preset level, a preset basic maintenance mileage is used as a first recommended mileage for the next maintenance of the vehicle; When it is detected that the pure electric driving level is less than the preset level, the usage data is input into a preset algorithm model, so that the preset algorithm model outputs the maintenance prediction mileage of the vehicle according to the usage data; A second recommended mileage for the next maintenance of the vehicle is obtained according to the predicted maintenance mileage, wherein the second recommended mileage is greater than the first recommended mileage.

2. The vehicle maintenance method according to claim 1, characterized in that: The preset algorithm model is trained in the following way: Acquire training sample data, wherein the training sample data includes the pure electric driving mileage ratio, total refueling amount, and maintenance mileage interval of other vehicles in historical use; Execute the cross-validation step in a loop to obtain a cross-validation result, wherein the cross-validation result includes a plurality of test results; Calculating the error rate of each of the training sample data according to the cross-validation result, and updating the model parameters of the initial algorithm model according to the error rate to obtain the preset algorithm model; The cross-validation step includes: Dividing the training sample data into a training set and a test set; Training the initial algorithm model according to the training set to obtain a trained algorithm model; The test set is tested using the algorithm model to obtain a test result.

3. The vehicle maintenance method according to claim 2, characterized in that: The obtaining of training sample data comprises: Acquire multiple initial sample data of multiple sample vehicles, wherein each sample vehicle corresponds to one initial sample data, and each initial sample data includes the maintenance mileage interval and failure rate of the sample vehicle during historical use, and the failure rate is the number of fault code reports of the sample vehicle between two adjacent maintenances; Calculating a maintenance score for each of the sample vehicles according to the failure rate and the maintenance mileage interval; The initial sample data corresponding to the sample vehicle whose maintenance score meets the preset scoring rule is used as the training sample data.

4. The vehicle maintenance method according to claim 3, characterized in that: The calculating the maintenance score of each of the sample vehicles according to the failure rate and the maintenance mileage interval includes: Normalizing the failure rate and the maintenance mileage interval respectively; Calculating a failure rate score of the sample vehicle according to the normalized failure rate; Calculating the maintenance mileage interval score of the sample vehicle according to the normalized maintenance mileage interval; The maintenance score is calculated based on the failure rate score and the maintenance mileage interval score.

5. The vehicle maintenance method according to claim 2, characterized in that: The training sample data includes multiple data categories; before the usage data is input into the preset algorithm model, it also includes: Detecting whether the usage data includes all the data categories in the training sample data; The step of inputting the usage data into a preset algorithm model comprises: After detecting that the usage data includes all of the data categories in the training sample data, the usage data is input into a preset algorithm model.

6. The vehicle maintenance method according to claim 1, characterized in that: The method further comprises: Setting a plurality of maintenance mileage ranges, wherein the plurality of maintenance mileage ranges do not intersect with each other, and each of the maintenance mileage ranges corresponds to a target maintenance mileage; The obtaining a second recommended mileage for the next maintenance of the vehicle according to the predicted maintenance mileage includes: Determine a specific interval range of the predicted maintenance mileage in the multiple maintenance mileage ranges, obtain the matching target maintenance mileage, and use the target maintenance mileage as the second recommended mileage.

7. The vehicle maintenance method according to claim 1, characterized in that: The determining the pure electric driving level of the vehicle according to the usage data includes: Inputting the usage data into a preset clustering algorithm model, and using an output result of the preset clustering algorithm model as the pure electric driving level; Among them, the preset clustering algorithm model is obtained by training vehicle characteristic data, and the vehicle characteristic data at least includes the proportion of pure electric mileage and total refueling amount of other vehicles in historical use.

8. A vehicle maintenance device, characterized in that: include: Acquisition module, confirmation module and detection module; The acquisition module is used to acquire vehicle usage data, wherein the usage data at least includes the percentage of pure electric driving mileage and the total amount of refueling of the vehicle during historical use; The confirmation module is used to determine the pure electric driving level of the vehicle according to the usage data, wherein the smaller the pure electric driving level is, the better the pure electric driving habits of the user when driving the vehicle in the past are; The detection module is used to, when detecting that the pure electric driving level is greater than or equal to a preset level, use the preset basic maintenance mileage as the first recommended mileage for the next maintenance of the vehicle; when detecting that the pure electric driving level is less than the preset level, input the usage data into a preset algorithm model so that the preset algorithm model outputs the maintenance prediction mileage of the vehicle according to the usage data; The detection device is also used to obtain a second recommended mileage for the next maintenance of the vehicle based on the predicted maintenance mileage, wherein the second recommended mileage is greater than the first recommended mileage.

9. An electronic device, comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the vehicle maintenance method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed on the electronic device, the electronic device executes the vehicle maintenance method according to any one of claims 1 to 7.

Images