Prediction method and prediction system for vehicle maintenance plan

Abstract

The embodiment of the present invention provides a prediction method and prediction system for a vehicle maintenance plan, the prediction method for the vehicle maintenance plan includes: collecting owner data, vehicle data and vehicle model maintenance indicators; making a preliminary maintenance prediction based on the owner data, the vehicle data and the vehicle model maintenance indicators in combination with the maintenance cycle; and making an accurate maintenance prediction based on the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan. The accurate vehicle maintenance plan predicted by this method is more suitable for the user's consumption needs, and the user can independently participate in the formulation of the maintenance plan, thereby improving the accuracy of the value chain and customer satisfaction. In addition, by collecting vehicle data submitted by on-board sensors and users, forming a closed loop of data collection, and generating a vehicle maintenance plan, the range of users who can perform vehicle maintenance can be expanded, improving customer experience and company profits.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a prediction method and a prediction system for a vehicle maintenance plan. Background Art

[0002] Intelligent car networking systems represented by OnStar provide online services to car owners through wireless technology and global positioning system satellites. On the one hand, they help car owners solve problems through voice help from the customer service center, and on the other hand, they provide vehicle maintenance guidance to car owners through real-time monitoring of vehicle indexes. The customer service voice collaboration includes: automatic collision assistance, emergency rescue assistance, full voice-controlled hands-free phone, and full voice-controlled navigation services; the data guidance of the network and vehicle sensors includes: vehicle condition detection report, stolen vehicle location, remote emergency door opening, and remote vehicle search.

[0003] The Internet of Vehicles systems on the market are based on brand operations. The main data source is the main component information regularly transmitted to the Internet of Vehicles service end by the sensors pre-installed in the above vehicles. At present, the data sent back by the vehicle sensors is combined with the preset value plan of component maintenance to remind the car owner to perform regular maintenance. The main component information usually includes reports on the engine, gearbox, ABS anti-lock braking system, electronic stability control system, airbag module, tires and other components to help car owners understand the condition of their vehicles and recommend that car owners complete maintenance at 4S stores. However, the disadvantages of this type of technology are: the pre-setting is based on the data sent back by the sensors, and only vehicles with higher configurations have this function, and there is a threshold for enjoying the service; the relevant data reports are only available to 4S stores, and car owners cannot participate in the formulation of maintenance decisions and maintenance plans, and cannot choose other repair shops for maintenance selection, and lose decision-making autonomy; and the maintenance suggestions cannot be combined with the maintenance categories, and car owners cannot choose and judge the maintenance materials such as oil and oil filter in advance.

[0004] Therefore, the inventors believe that the above-mentioned maintenance plan prediction and recommendation method has great limitations. Only a small number of car owners can implement several predetermined maintenance plans. There are problems such as difficulty in meeting user needs and a small scope of application. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a prediction method and prediction system for a vehicle maintenance plan, which is based on a network connection, supports the collection of data from vehicle-mounted sensors and the collection of data submitted by users on their own initiative, evaluates the maintenance status of the vehicle based on the collected owner data and vehicle data, and generates a preliminary maintenance package in combination with vehicle model maintenance indicators, in conjunction with cloud-based equipment management, big data analysis and other technologies, obtains a consumption weight value based on maintenance history data, and performs a secondary accurate vehicle maintenance plan prediction based on the consumption weight value, thereby expanding the range of users who can perform vehicle maintenance and improving customer experience and company profits.

[0006] According to a first aspect of the present invention, there is provided a method for predicting a vehicle maintenance plan, comprising: collecting vehicle owner data, vehicle data and vehicle model maintenance indicators; performing preliminary maintenance prediction based on the vehicle owner data, the vehicle data and the vehicle model maintenance indicators in combination with maintenance cycles; and performing precise maintenance prediction based on consumption weight values ​​and the results of the preliminary maintenance prediction to obtain a maintenance plan.

[0007] Preferably, the prediction method further comprises: a user submitting vehicle owner data.

[0008] Preferably, the prediction method further includes: vehicle-mounted sensors and user-submitted vehicle data.

[0009] Preferably, the prediction method further comprises: obtaining the consumption weight value according to the vehicle owner data, the vehicle data and the maintenance history data.

[0010] Preferably, the maintenance plan includes a recommended maintenance package, and the types and prices of the skin care products in the maintenance package are selectable.

[0011] Preferably, the vehicle data includes basic vehicle information data, maintenance data, vehicle condition data and driving data; the vehicle type maintenance index includes preset vehicle maintenance plans for vehicles of various types.

[0012] Preferably, performing preliminary maintenance prediction based on the vehicle owner data, the vehicle data and the vehicle model maintenance index in combination with the maintenance cycle includes: traversing all vehicles and establishing vehicle models of all vehicles based on the vehicle data and the maintenance history data; establishing a first simulation condition to exclude scrapped vehicles whose vehicle data do not meet the first simulation condition among all the vehicles; establishing a second simulation condition to select vehicles whose vehicle data meet the second simulation condition as vehicles to be maintained, and the remaining vehicles as remaining vehicles; and establishing a third simulation condition and a fourth simulation condition to select vehicles whose vehicle data meet both the third simulation condition and the fourth simulation condition among the remaining vehicles as vehicles to be maintained.

[0013] Preferably, performing preliminary maintenance prediction based on the owner data, the vehicle data and the vehicle model maintenance index in combination with the maintenance cycle also includes: retrieving the accessories standard index value data of all vehicles that meet the first simulation condition; and generating a preliminary maintenance package for all the vehicles to be maintained according to the vehicle model maintenance index, the preliminary maintenance package including a collection of maintenance products for vehicle maintenance.

[0014] Preferably, the vehicle model is: Car = [type, factory, maintain, staus, trade], wherein Car is a vehicle registered by the owner t, type is vehicle model information, factory is vehicle factory condition, maintain is maintenance data, staus is vehicle condition data, and trade is maintenance history data.

[0015] Preferably, the first simulation condition is C1=CarAvail αβ (Car), where (α=20, β=600000) means that the vehicle age is less than 20 years and the mileage is less than 600,000 kilometers; the second simulation condition is C2=C1.staus.erro, where staus.erro means that the vehicle condition is faulty and an alarm will be issued; the third simulation condition is C3=CarMap key (C1.staus,T σh ), where C1.staus is the latest vehicle status data, T σh Indicates the standard index value of the accessories corresponding to vehicle C1, function CarMap key Indicates that the current index value of some accessory key in the accessory index value data in the vehicle condition data corresponding to vehicle C1 is not within the accessory standard index value T σh The fourth simulation condition is Among them, maintain.date represents the maintenance date set. is the most recent date in the maintenance schedule, now is the current date, (T σh .period) is the recommended maintenance period for the vehicle, and λ is the floating number of days;

[0016] The standard index value of the accessories is T σh Represented as T σh =valYear(CarType σh ), where σ is the current age of vehicle C1, h is the current mileage of vehicle C1, CarType σh =[key,minValue,maxValue], where key is the accessory identifier, minValue is the minimum health value of the accessory within h kilometers in the σth year, and maxValue is the maximum health value of the accessory within h kilometers in the σth year.

[0017] Preferably, obtaining the consumption weight value according to the owner data, the vehicle data and the maintenance history data includes: traversing the owner data, the vehicle data and the maintenance history data of the vehicle to be maintained; summing up all historical consumption amounts and all historical maintenance times of each vehicle to be maintained as the first model parameter and the second model parameter respectively; taking the difference between the maintenance-free time and the maintenance cycle of each vehicle to be maintained as the third model parameter and generating a fourth model parameter according to the third model parameter; and generating the consumption weight value according to the first parameter model, the second parameter model and the fourth parameter model.

[0018] Preferably, accurate maintenance prediction is performed based on the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan, including: generating a closed range of maintenance product prices based on the consumption weight value; selecting a set of maintenance products whose prices fall within the closed range of prices from among all the sets of maintenance products in the preliminary maintenance package; and using the selected set of maintenance products as the recommended maintenance package.

[0019] Preferably, the first model parameter is The second model parameter is The third model parameter is d3=(now-max C .maintain.date)-T σh .period, where maintain.date represents the maintenance date set, max C .maintain.date is the most recent maintenance date, now is the current date, T σh .period is the recommended maintenance period (days); the fourth model parameter is determined by the third model parameter, when d3≤0, then d4=0, when 0≤d3, then d4 represents the vehicle risk rate. The longer the time from the last maintenance, the greater the vehicle risk rate.

[0020] Preferably, the consumption weight value is Among them, the average consumption The higher the value is, and the higher the vehicle risk rate d4 is, the higher the consumption weight value is; the amount closed interval is

[0021] According to a second aspect of the present invention, a vehicle maintenance plan prediction system is provided, comprising: a data acquisition unit for collecting vehicle owner data, vehicle data and vehicle model maintenance indicators; a preliminary maintenance prediction unit for performing preliminary maintenance prediction based on the vehicle owner data, the vehicle data and the vehicle model maintenance indicators in combination with the maintenance cycle; and a maintenance plan generation unit for performing accurate maintenance prediction based on the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan.

[0022] Preferably, the prediction system further comprises: a consumption weight value generating unit, configured to obtain the consumption weight value according to the vehicle owner data, the vehicle data and the maintenance history data.

[0023] Preferably, the preliminary maintenance prediction unit includes: a vehicle model building unit, used to build vehicle models of all vehicles based on the vehicle data and the maintenance history data; a simulation condition building unit, used to establish first to fourth simulation conditions, and select vehicles to be maintained according to the degree of compliance of the vehicle data with the first to fourth simulation conditions; and a preliminary judgment package generating unit, used to generate a preliminary judgment maintenance package for all the vehicles to be maintained according to the vehicle model maintenance index, and the preliminary judgment maintenance package includes a collection of maintenance products for vehicle maintenance.

[0024] Preferably, the maintenance plan generation unit includes: a closed amount interval generation unit, used to generate a closed amount interval for skin care products according to the consumption weight value; a selection unit, used to select the skin care product set whose amount falls within the closed amount interval from all the skin care product sets in the preliminary maintenance package; and a recommended package generation unit, which uses the selected skin care product set as the recommended maintenance package.

[0025] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed, the prediction method as described above is implemented.

[0026] According to a fourth aspect of the present invention, there is provided a vehicle maintenance plan selection device, comprising: a memory for storing computer instructions; a processor coupled to the memory, the processor being configured to execute and implement the prediction method as described above based on the computer instructions stored in the memory.

[0027] The embodiments of the present invention have the following advantages or beneficial effects: by collecting vehicle owner data, vehicle data and vehicle model maintenance indicators, evaluating the vehicle maintenance status based on these data and making a preliminary maintenance prediction based on the maintenance cycle, and then making an accurate maintenance prediction based on the consumption weight and the result of the preliminary maintenance prediction, a maintenance plan is obtained. The vehicle maintenance plan selected by this method adds a consumption weight value, so it is more suitable for the user's consumption needs, and a secondary prediction is made to make the package recommendation more accurate. Furthermore, the user can independently participate in the formulation of the maintenance plan, thereby improving the accuracy of the value chain and customer satisfaction.

[0028] Another preferred embodiment of the present invention has the following advantages or beneficial effects: vehicle-mounted sensors and user-submitted vehicle data realize a closed loop of data collection, and the vehicle maintenance plan selected by this method can be applicable to the vast majority of users without being restricted by vehicle type, thereby expanding the scope of service.

[0029] Another preferred embodiment of the present invention has the following advantages or beneficial effects: a consumption weight value is obtained according to vehicle data and maintenance history data, so that the recommendation of the maintenance plan is more in line with the customer's own consumption level. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other objects, features and advantages of the present invention will become more apparent through the description of the embodiments of the present invention with reference to the following drawings, in which:

[0031] Figure 1 A flow chart showing a method for predicting a vehicle maintenance plan in an embodiment of the present invention is shown;

[0032] Figure 2 A flow chart showing a method for predicting vehicle maintenance plans summarized in an embodiment of the present invention;

[0033] Figure 3 Shows Figure 1 The specific flow chart of step S102 shown;

[0034] Figure 4 Shows Figure 2 The specific flow chart of step S205 and step S206 shown;

[0035] Figure 5 A structural diagram of a prediction system for vehicle maintenance plans summarized in an embodiment of the present invention is shown;

[0036] Figure 6a and Figure 6b They are shown respectively Figure 5 The structural diagram of the preliminary maintenance prediction unit and the maintenance plan generation unit;

[0037] Figure 7The structure diagram of the vehicle maintenance plan selection device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0038] The present invention is described below based on embodiments, but the present invention is not limited to these embodiments. In the detailed description of the present invention below, some specific details are described in detail. It is possible for a person skilled in the art to fully understand the present invention without the description of these details. In order to avoid confusing the essence of the present invention, known methods, processes, and procedures are not described in detail. In addition, the drawings are not necessarily drawn to scale.

[0039] Figure 1 A flow chart of a method for predicting a vehicle maintenance plan in an embodiment of the present invention is shown, and specific steps include S101-S103.

[0040] In step S101, the vehicle owner data, vehicle data and vehicle model maintenance index are collected.

[0041] In step S102, a preliminary maintenance prediction is performed based on the vehicle owner data, vehicle data and vehicle model maintenance indicators in combination with the maintenance cycle.

[0042] In step S103, accurate maintenance prediction is performed according to the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan.

[0043] As described in the background technology, the prediction and recommendation of existing vehicle maintenance plans are based on the data regularly sent back by the vehicle sensors. Regular maintenance is performed according to the preset maintenance plan. The maintenance plan list cannot be selected by the user independently, resulting in a lack of user selectivity.

[0044] Therefore, in this embodiment, the owner data, vehicle data and vehicle model maintenance indicators are first collected, and the data are sorted according to the vehicle; then the maintenance status of the vehicle is evaluated based on the collected data, and the vehicle data of different vehicles collected are analyzed separately in combination with the maintenance cycle to determine whether the vehicle needs maintenance, and a preliminary judgment is made on whether the vehicle needs maintenance; and a rough preliminary judgment maintenance package is generated for the vehicle that needs maintenance (the vehicle to be maintained) based on the vehicle model maintenance data; finally, the preliminary judgment maintenance package is screened according to the consumption weight value, and the recommended maintenance package that meets the consumption weight value is selected to generate a maintenance plan, wherein the consumption weight value is added to the prediction result, and a secondary prediction is performed. The consumption weight value represents the user's consumption demand for the maintenance plan, which can affect the recommended maintenance time and the price of the maintenance plan.

[0045] The vehicle maintenance plan selected by this method is suitable for the vast majority of users. A secondary prediction is performed to make the package recommendation more accurate. In addition, the consumption weight value is added to predict the vehicle maintenance plan, which is more suitable for the user's consumption needs. Users can participate in the formulation of maintenance plans independently, thereby improving the accuracy of the value chain and customer satisfaction.

[0046] Figure 2 A flow chart of a method for predicting vehicle maintenance plans summarized in an embodiment of the present invention is shown, which specifically includes the following steps.

[0047] In step S201 , the user submits the vehicle owner data.

[0048] In step S202 , the vehicle-mounted sensors and the user submit vehicle data.

[0049] In step S203, the vehicle owner data, vehicle data and vehicle model maintenance index are collected.

[0050] In step S204, a preliminary maintenance prediction is performed based on the vehicle owner data, vehicle data and vehicle model maintenance indicators in combination with the maintenance cycle.

[0051] In step S205, a consumption weight value is obtained according to the vehicle owner data, the vehicle data and the maintenance history data.

[0052] In step S206, accurate maintenance prediction is performed based on the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan.

[0053] This embodiment is a more complete vehicle maintenance plan prediction method than the previous embodiment. Figure 1 Steps S101-S103 are the same as those in the embodiment and will not be described in detail here.

[0054] Step S201-Step S202 is a preparatory step for collecting data for prejudgment, which involves the source of data. In step S201, the user submits the owner data, and all the owner data is concentrated in the owner data center for further processing. In step S02, the vehicle sensors and users submit vehicle data. For vehicles with vehicle sensors, the vehicle data is automatically uploaded to the Internet of Vehicles. For vehicles without vehicle sensors, users can submit vehicle data independently, realizing the multi-faceted nature of data collection and matching the owner data and vehicle data. In general, the owner data and vehicle data can be submitted together for easy sorting.

[0055] Step S206 involves obtaining the consumption weight value. The consumption weight value is calculated based on the vehicle data and maintenance history data provided by the user. A secondary prediction is made based on the customer's consumption level and preference. The recommended maintenance package is more in line with the customer's preferences and needs.

[0056] According to the embodiment of the present invention, a closed loop of data collection is achieved, and consumption weight values ​​are calculated based on vehicle data and maintenance history data, thereby expanding the service scope, allowing more customers to enjoy maintenance package recommendations, and making maintenance plan recommendations more in line with the customer's own consumption level, thereby improving customer satisfaction.

[0057] In one embodiment, the maintenance plan includes a recommended maintenance package, and the categories and prices of the maintenance products in the maintenance package are optional, so that customers can make maintenance choices based on their own circumstances and participate in the maintenance plan, thereby meeting the different needs of different customers and improving service quality.

[0058] In one embodiment, the vehicle data includes basic vehicle information data, maintenance data, vehicle condition data, and driving data. Figure 1 According to the vehicle condition data and driving data, the health status of the vehicle can be quickly judged, and combined with the vehicle maintenance cycle, whether maintenance is needed in the near future can be quickly predicted; according to the vehicle basic information data and vehicle condition data, some maintenance plans that may be suitable for the vehicle user can be roughly predicted; combined with the maintenance data and maintenance history data, the vehicle owner's demand for the category and price of maintenance plans can be understood, and the consumption weight value can be set accordingly. The final recommended package is selected according to the consumption weight value, so that the recommended accurate vehicle maintenance plan is more in line with the customer's actual consumption situation.

[0059] Figure 3 Shows Figure 1 The specific flow chart of step S102 shown is a specific process of preliminary maintenance prediction, which specifically includes the following steps.

[0060] In step S1021, all vehicles are traversed, and vehicle models of all vehicles are established based on vehicle data and maintenance history data. All vehicle data collected from vehicle sensors and vehicle data submitted by users are sorted, and all vehicles corresponding to each user and vehicle data of each vehicle are sorted in the same data table. Vehicle data includes, for example, basic vehicle information data, maintenance data, vehicle condition data, and driving data.

[0061] The vehicle model of all vehicles is established based on the sorted vehicle data and maintenance history data. For example, the vehicle model of a vehicle registered by owner t is: Car = [type, factory, maintain, staus, trade], where Car is a vehicle q registered by owner t, type is the vehicle model information, and factory is the vehicle factory condition. The personal situation of owner t and the vehicle under his name are the owner information. The vehicle Car, the vehicle model information type and the vehicle factory condition factory are all basic vehicle information data; maintain is maintenance data, for example, it can be the αth maintenance record, specifically, it can include the maintenance time, the maintenance plan cycle, the type of maintenance products used, etc.; staus is vehicle condition data, preferably it can include the current accessory index value of vehicle q, and trade is maintenance history data, mainly the vehicle online service transaction record, such as the number of historical maintenance and the consumption amount, etc.

[0062] The following specifically describes how to traverse the vehicle according to the defined vehicle data and rules to form a prediction result of the vehicle that needs maintenance. First, the owner's vehicle Car is judged to confirm whether the vehicle has entered the maintenance stage, and the prediction result is obtained. Then, a preliminary vehicle maintenance plan is predicted based on the prediction result.

[0063] In step S1022, a first simulation condition is established to exclude scrapped vehicles whose vehicle data do not meet the first simulation condition from all vehicles. The first simulation condition is set to C1 = CarAvail αβ (Car), where (α=20, β=600000), C1 represents a vehicle with a vehicle age of less than 20 years and a mileage of less than 600,000 kilometers; extract the driving data from the vehicle data corresponding to vehicle q, such as the mileage and driving years since the purchase of the vehicle, and substitute the driving data into the first simulation condition. If the vehicle meets the condition C1, it is considered normal. If the vehicle age is more than 20 years or the mileage exceeds 600,000 kilometers, it is considered invalid data or a scrapped vehicle and is excluded. Excluding invalid data can save unnecessary package recommendations, save time, and make recommendations more accurate.

[0064] In step S1023, a second simulation condition is established, and vehicles whose vehicle data meets the first simulation condition and the second simulation condition are selected as vehicles to be maintained, and the rest of the vehicles are the remaining vehicles. The second simulation condition is C2 = C1.staus.erro, where staus.erro indicates a vehicle condition failure and an alarm will be issued.

[0065] In the previous step, the driving condition of the vehicle is checked, and scrapped vehicles are excluded. The remaining vehicles are traversed and checked according to the vehicle condition data staus to determine whether the vehicle condition is good or not. If it meets the second simulation condition, that is, the vehicle condition is faulty, an alarm is issued, and the alarm data is sent back, indicating that the vehicle needs maintenance.

[0066] In step S1024, the accessory standard index value data of all vehicles that meet the first simulation condition are retrieved. In one embodiment, the vehicles filtered by condition C1 are counted, and the accessory standard index value data of each vehicle is retrieved.

[0067] Assume that the standard index value of accessories for a certain model within the σth year and h kilometers is: CarType σh = [key,minValue,maxValue], where key is the accessory identifier, minValue is the minimum health value of the accessory within the σth year and h kilometers (can be null), maxValue is the maximum health value of the accessory within the σth year and h kilometers (cannot be null), σ is within 20 years, and h is within 600,000 kilometers. If the index value of some accessories of a vehicle q exceeds the maximum health value, it is considered that the health status of the vehicle needs attention and maintenance is recommended.

[0068] Then, based on the age σ and mileage h of any vehicle q after the C1 condition, the function T of the accessory standard index value is obtained: σh , T σh =valYear(CarType σh ), where σ is the current age of vehicle C1, h is the current mileage of vehicle C1, if CarType σh In the function, the vehicle age and mileage are matched to two sets of indicators, and the set of indicators closest to the mileage is selected.

[0069] In step S1025, the third simulation condition and the fourth simulation condition are established, and the vehicles whose vehicle data meet both the third simulation condition and the fourth simulation condition are selected as the vehicles to be maintained. In step S1023, the vehicles in good condition are selected as the remaining vehicles, and other tests are performed to determine whether maintenance is required.

[0070] Set the third simulation condition to C3 = CarMap key (C1.staus,T σh ), where C1.staus is the latest vehicle status data, T σh Indicates the standard index value of the accessories corresponding to vehicle C1, function CarMap key Indicates that the current index number of some accessory keys in the accessory index value data in the vehicle condition data corresponding to vehicle C1 is not within the accessory standard index value T σhrange; so the third simulation condition C3 means that by traversing the function CarMap key , the standard index value T of the accessories corresponding to vehicle C1 σh If the index number of the current accessory is greater than the health value maxValue, the accessory key is found, and the vehicle is used as a candidate vehicle to be maintained and the fourth simulation condition is tested.

[0071] The fourth simulation condition is set according to the maintenance cycle: Among them, maintain.date represents the maintenance date set. is the most recent date in the maintenance schedule, now is the current date, (T σh .period) is the recommended maintenance period for the vehicle, and λ is the floating days. Condition C4 indicates that the vehicle is such that the time between the current date and the most recent maintenance date exceeds the recommended maintenance period plus the floating days. Such vehicles have not been maintained for a long time and may have hidden dangers, so maintenance is recommended.

[0072] Vehicles that meet condition C3 are tested under condition C4. If vehicle q has an accessory key whose accessory index value is greater than the maximum health value, and the maintenance-free time of the vehicle exceeds the maximum allowed time, then this type of vehicle must be maintained.

[0073] In the above, through steps S1022-S1025, the vehicles are traversed according to the set simulation conditions C1-C4, and a preliminary maintenance prediction is made based on the owner data, vehicle data and vehicle model maintenance indicators combined with the maintenance cycle to form a predicted result of the vehicles to be maintained. Vehicles with vehicle condition failures and accessory indicators exceeding the maximum health value and without maintenance for a long time are suitable to be selected as vehicles to be maintained.

[0074] In step S1026, for all vehicles to be maintained, a preliminary maintenance package is generated according to the vehicle model maintenance index, and the preliminary maintenance package includes a set of maintenance products for vehicle maintenance.

[0075] For maintenance models, a new preliminary maintenance plan is integrated based on the maintenance data of the model stored in advance and the maintenance data of other similar models. The maintenance plan includes multiple categories of maintenance products. The maintenance product set of the corresponding maintenance plan is sku[C], thereby generating a preliminary maintenance package.

[0076] The above process is the initial selection process for the maintenance cycle. Figure 4 The matching process of the maintenance plan is further explained.

[0077] Figure 4 Shows Figure 2The specific flow chart of step S205 and step S206 shown in the figure specifically includes the following steps: step S401 to step S404 are the process of calculating the consumption weight value, and step S405 to step S407 are the process of matching the precise maintenance plan according to the consumption weight value.

[0078] In step S401, the owner data, vehicle data and maintenance history data of the vehicle to be maintained are traversed. The maintenance history data and maintenance consumption records of the vehicle to be maintained are traversed to facilitate the subsequent calculation of the maintenance consumption weight value D of the vehicle.

[0079] In step S402, all historical maintenance consumption amounts and all historical maintenance times of each vehicle to be maintained are summed up as the first model parameter and the second model parameter. The first model parameter is The second model parameter is

[0080] In step S403, the difference between the maintenance-free time and the maintenance cycle of each vehicle to be maintained is used as a third model parameter and a fourth model parameter is generated according to the third model parameter.

[0081] The third model parameter is d3 = (now-max C .maintain.date)-T σh .period, where maintain.date represents the maintenance date set, max C .maintain.date is the most recent maintenance date, now is the current date, T σh .period is the recommended maintenance period (days); the third model parameter d3 represents the time difference between the current maintenance-free time and the recommended maintenance period.

[0082] The fourth model parameter is determined by the third model parameter. When d3≤0, that is, the maintenance time does not exceed the recommended maintenance period, then d4=0, d4 represents the vehicle risk rate; when 0≤d3, that is, maintenance has not been performed for a long time, then d4 represents the vehicle risk rate. The longer the time from the last maintenance, the greater the vehicle risk rate (the number of days of delayed maintenance as a percentage of the recommended maintenance cycle days).

[0083] In step S404, a consumption weight value is generated according to the first parameter model, the second parameter model and the fourth parameter model.

[0084] First, the first model parameter d1 obtained in step S402 is compared with the second model parameter d2 to obtain the average consumption of each maintenance. This is just one implementation method, and other methods can also be used first, such as calculating the weighted average to obtain the maintenance consumption mean. Then, combined with step S403 and the risk rate d4, the consumption weight value is obtained, and the consumption weight value is a function related to d1, d2 and d4: Among them, the average consumption The higher the value is and the higher the vehicle risk rate d4 is, the higher the consumption weight value will be.

[0085] In step S405, a closed range of skin care product prices is generated according to the consumption weight values.

[0086] The consumption weight is Among them, the average consumption The higher the value, and the higher the vehicle risk rate d4, the higher the consumption weight index value; based on the vehicle maintenance consumption weight D, the consumption amount closed interval of the recommended maintenance product set sku[C], for example, the amount closed interval is but:

[0087]

[0088] In step S406, a set of skin care products whose price falls within a closed range of price is selected from all sets of skin care products in the preliminary determined skin care package.

[0089] In step S407, the selected skin care product set is used as a recommended skin care package.

[0090] A maintenance product set sku[C] that meets the above conditions is selected as a recommended maintenance package. Combined with the categories and prices of the maintenance products, the final and accurate vehicle maintenance plan is recommended to the user, who then makes his or her own selection.

[0091] In one embodiment, weight values ​​in more directions are implanted as constraints for selecting precise vehicle maintenance plans, so as to find a maintenance plan that better meets the needs of the customer.

[0092] In another embodiment, maintenance product recommendations or weight recommendations from expert technicians may be added, and users may independently determine whether to consider the expert recommendations in this maintenance forecast, thereby increasing the participation of more car owners in decision-making.

[0093] It should be noted that the present invention is not limited to the simulation conditions and parameter model rules provided in the above embodiments. Other simulation conditions and parameter model rules can also be used to implement the vehicle maintenance plan prediction method provided in the embodiments of the present invention.

[0094] Figure 5The structure diagram of the vehicle maintenance plan prediction system summarized in the embodiment of the present invention is shown; the vehicle maintenance plan prediction system 500 includes a data acquisition unit 501, a preliminary maintenance prediction unit 502, a consumption weight value generation unit 503 and a maintenance plan generation unit 504.

[0095] The data acquisition unit 501 is used to collect vehicle owner data, vehicle data and vehicle model maintenance indicators.

[0096] The preliminary maintenance prediction unit 502 is used to perform preliminary maintenance prediction based on the vehicle owner data, vehicle data and vehicle model maintenance indicators in combination with the maintenance cycle.

[0097] The consumption weight value generating unit 503 is used to obtain the consumption weight value according to the vehicle owner data, the vehicle data and the maintenance history data.

[0098] The maintenance plan generating unit 504 is used to perform accurate maintenance prediction according to the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan.

[0099] In this embodiment, a preliminary maintenance prediction is made based on the collected owner data, vehicle data and vehicle model maintenance indicators in combination with the maintenance cycle, and the maintenance plan is predicted twice based on the weight value formed by the collected vehicle data and consumption data. This can improve the accuracy of the prediction. The precise vehicle maintenance plan predicted by this method is more suitable for the user's consumption needs, and the user can independently participate in the formulation of the maintenance plan, thereby improving the accuracy of the value chain and customer satisfaction.

[0100] At the same time, the consumption weight value is calculated based on vehicle data and maintenance history data, so that the recommended maintenance plan is more in line with the customer's own consumption level.

[0101] In one embodiment, the consumption weight value generating unit 503 includes: a data screening unit (not shown in the figure), a model parameter establishing unit (not shown in the figure) and a calculation unit (not shown in the figure), wherein the screening unit is used to traverse the vehicle data and maintenance history data of the vehicle to be maintained; the model parameter establishing unit is used to establish the first model parameter to the fourth model parameter according to the vehicle data and the maintenance history data; the calculation unit is used to generate the consumption weight value according to the first parameter model, the second parameter model and the fourth parameter model.

[0102] Figure 6a and Figure 6b They are shown respectively Figure 5 The structural diagram of the preliminary maintenance prediction unit 502 and the maintenance plan generation unit 504. Figure 6a and Figure 6bAs shown, the preliminary maintenance prediction unit 502 includes: a vehicle model establishment unit 5021, a simulation condition establishment unit 5022 and a preliminary judgment package generation unit 5023. The maintenance plan generation unit 504 includes: a closed range amount generation unit 5041, a selection unit 5042 and a precise package generation unit 5043.

[0103] The vehicle model establishment unit 5021 is used to establish vehicle models for all vehicles based on vehicle data and maintenance history data; the simulation condition establishment unit 5022 is used to establish first to fourth simulation conditions, and select vehicles to be maintained based on the degree of compliance of the vehicle data with the first to fourth simulation conditions; the preliminary judgment package generation unit 5023 is used to generate preliminary judgment maintenance packages for all vehicles to be maintained based on vehicle model maintenance indicators, and the preliminary judgment maintenance packages include a collection of maintenance products for vehicle maintenance.

[0104] The closed amount interval generating unit 5041 is used to generate a closed amount interval for skin care products according to the consumption weight value; the selecting unit 5042 is used to select a skin care product set whose amount falls within the closed amount interval from all the skin care product sets in the preliminary skin care package; the precise package generating unit 5043 is used to use the selected skin care product set as the recommended skin care package.

[0105] It should be understood that the system and method of the embodiments of the present invention correspond to each other, and therefore, the description of the system is relatively brief.

[0106] Figure 7 The device shown in FIG7 is only an example and shall not limit the functions and application scope of the embodiment of the present invention.

[0107] refer to Figure 7, the vehicle maintenance plan selection device includes a processor 701, a memory 702 and an input-output device 703 connected by a bus. The memory 702 includes a read-only memory (ROM) and a random access memory (RAM). The memory 702 stores various computer instructions and data required for executing system functions. The processor 701 reads various computer instructions from the memory 702 to perform various appropriate actions and processes. The input-output device includes an input part such as a keyboard, a mouse, etc.; an output part such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part such as a hard disk; and a communication part such as a network interface card such as a LAN card, a modem, etc. The memory 702 also stores the following computer instructions to complete the operations specified in the vehicle maintenance plan prediction method of the embodiment of the present invention: collecting owner data, vehicle data and vehicle model maintenance indicators; performing preliminary maintenance prediction based on the owner data, vehicle data and vehicle model maintenance indicators in combination with the maintenance cycle; and performing accurate maintenance prediction based on the consumption weight value and the result of the preliminary maintenance prediction to obtain a maintenance plan.

[0108] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed, the operations specified by the above-mentioned vehicle maintenance plan prediction method are implemented.

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the possible system frameworks, functions and operations of the systems, methods and devices of the embodiments of the present invention. The boxes on the flowcharts and block diagrams can represent a module, a program segment or just a piece of code, and the modules, program segments and codes are all executable instructions for implementing the specified logical functions. It should also be noted that the executable instructions for implementing the specified logical functions can be recombined to generate new modules and program segments. Therefore, the boxes and the order of the boxes in the accompanying drawings are only used to better illustrate the process and steps of the embodiments, and should not be used as a limitation on the invention itself.

[0110] Each module or unit of the system can be implemented by hardware, firmware or software. Software, for example, includes a coding program formed by various programming languages ​​such as JAVA, C / C++ / C#, SQL, etc. Although the steps and the order of the steps of the embodiment of the present invention are given in the method and the method legend, the executable instructions for the steps to implement the specified logical functions can be recombined to generate new steps. The order of the steps should not be limited to the order of the steps in the method and the method legend, and can be adjusted at any time according to the needs of the function. For example, some of the steps are executed in parallel or in reverse order.

[0111] The system and method according to the present invention can be deployed on a single or multiple servers. For example, different modules can be deployed on different servers to form dedicated servers. Alternatively, the same functional unit, module or system can be deployed in a distributed manner on multiple servers to reduce load pressure. The servers include but are not limited to multiple PCs, PC servers, blade computers, supercomputers, etc. connected in the same local area network and via the Internet.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting a vehicle maintenance plan, characterized in that: include: Collect owner data, vehicle data and model maintenance indicators; Performing preliminary maintenance prediction based on the vehicle owner data, the vehicle data and the vehicle model maintenance index in combination with the maintenance cycle to determine whether the vehicle needs maintenance, and generating a preliminary maintenance package for the vehicle that needs maintenance, the preliminary maintenance package including a collection of maintenance products for vehicle maintenance; as well as Obtaining a consumption weight value, performing an accurate maintenance prediction based on the consumption weight value and the result of the preliminary maintenance prediction, selecting a recommended maintenance package that meets the consumption weight value from the preliminary maintenance packages, and obtaining a maintenance plan, wherein this step specifically includes: Traversing the owner data, vehicle data and maintenance history data of the vehicle to be maintained; summing up all historical consumption amounts and all historical maintenance times of each vehicle to be maintained as the first model parameter and the second model parameter respectively; taking the difference between the unmaintained time and the maintenance cycle of each vehicle to be maintained as the third model parameter and generating a fourth model parameter according to the third model parameter, wherein the fourth parameter model is a vehicle risk rate associated with the difference; generating a consumption weight value according to the first model parameter, the second model parameter and the fourth model parameter; generating a closed interval of maintenance product amount according to the consumption weight value; selecting a maintenance product set whose amount falls within the closed interval of maintenance product amount from all the maintenance product sets in the preliminary maintenance package; and using the selected maintenance product set as the recommended maintenance package, The first model parameter is ; The second model parameter is ; The third model parameter is ,in, Indicates the maintenance date set. The most recent maintenance date. is the current date, is the recommended maintenance cycle (days); The fourth model parameter is determined by the third model parameter. ,when , , d4 represents the vehicle risk rate. The longer the time from the last maintenance, the greater the vehicle risk rate. The consumption weight value is , where the mean consumption The higher the risk of the vehicle The higher it is, the higher the consumption weight value is; The closed range of the amount of skin care products is .

2. The prediction method according to claim 1, characterized in that: Also includes: The user submits the vehicle owner data.

3. The prediction method according to claim 1, characterized in that: Also includes: On-board sensors and user submission of said vehicle data.

4. The prediction method according to claim 1, characterized in that: The maintenance plan includes a recommended maintenance package, and the categories and prices of the recommended maintenance package are optional.

5. The prediction method according to claim 1, characterized in that: The vehicle data includes basic vehicle information data, maintenance data, vehicle condition data and driving data; The vehicle type maintenance index includes preset vehicle maintenance plans for vehicles of various vehicle types.

6. The prediction method according to claim 1, characterized in that: According to the vehicle owner data, the vehicle data and the vehicle model maintenance index, a preliminary maintenance prediction is performed in combination with the maintenance cycle, including: Traversing all vehicles, and establishing vehicle models of all vehicles according to the vehicle data and the maintenance history data; Establishing a first simulation condition, and excluding scrapped vehicles whose vehicle data do not meet the first simulation condition from among all the vehicles; Establishing a second simulation condition, selecting the vehicles whose vehicle data meet the second simulation condition as vehicles to be maintained, and selecting the remaining vehicles as remaining vehicles; and A third simulation condition and a fourth simulation condition are established, and vehicles whose vehicle data meet both the third simulation condition and the fourth simulation condition are selected from the remaining vehicles as vehicles to be maintained.

7. The prediction method according to claim 6, characterized in that: Also includes: Retrieving the standard index value data of accessories of all vehicles that meet the first simulation condition; as well as For all the vehicles to be maintained, a preliminary maintenance package is generated according to the vehicle model maintenance index.

8. The prediction method according to claim 7, characterized in that: The vehicle model is: , where Car is a car registered by owner t, type is the car model information, factory is the factory status of the vehicle, maintain is the maintenance data, staus is the vehicle condition data, and trade is the maintenance history data.

9. The prediction method according to claim 8, characterized in that: The first simulation condition is , where (α=20,β=600000) means vehicles with a vehicle age of less than 20 years and a mileage of less than 600,000 kilometers; The second simulation condition is , where staus. erro means the vehicle is in a faulty condition and an alarm will be sounded; The third simulation condition is , where C1.staus is the latest vehicle status data, ,function Indicates that the current index number of some accessory keys in the accessory index value data in the vehicle condition data corresponding to vehicle C1 is not within the accessory standard index value within the scope; The fourth simulation condition is , where maintain.date represents the maintenance date set, is the most recent date in the maintenance schedule, now is the current date, The recommended maintenance interval for the vehicle is It is a floating number of days; Expressed as ,in, is the current age of vehicle C1, h is the current mileage of vehicle C1, , where key is the accessory identifier, It is The minimum health value of accessories within h kilometers per year, It is The maximum health value of accessories within h kilometers per year.

10. A vehicle maintenance plan prediction system, used to implement the vehicle maintenance plan prediction method according to any one of claims 1 to 9, characterized in that: The prediction system of the vehicle maintenance plan includes: A data acquisition unit, which is used to collect owner data, vehicle data, and vehicle model maintenance indicators; a preliminary maintenance prediction unit, configured to make a preliminary maintenance prediction based on the vehicle owner data, the vehicle data and the vehicle model maintenance index in combination with the maintenance cycle, determine whether the vehicle needs maintenance, and generate a preliminary maintenance package for the vehicle that needs maintenance, wherein the preliminary maintenance package includes a set of maintenance products for vehicle maintenance; and a consumption weight value generating unit, configured to obtain the consumption weight value according to the vehicle owner data, the vehicle data and the maintenance history data; A maintenance plan generating unit is used to perform accurate maintenance prediction according to the consumption weight value and the result of the preliminary maintenance prediction, select a recommended maintenance package that meets the consumption weight value from the preliminary maintenance package, and obtain a maintenance plan. The consumption weight value generating unit includes: a screening unit, which is used to traverse the vehicle data and maintenance history data of the vehicle to be maintained; a model parameter establishing unit, which is used to establish the first model parameter to the fourth model parameter according to the vehicle data and the maintenance history data, and to sum up all the historical consumption amounts and all the historical maintenance times of each vehicle to be maintained as the first model parameter and the second model parameter respectively, and to take the difference between the maintenance time and the maintenance cycle of each vehicle to be maintained as the third model parameter, and to generate the fourth model parameter according to the third model parameter, and the fourth parameter model is the vehicle risk rate related to the difference; a calculation unit, which is used to generate the consumption weight value according to the first model parameter, the second model parameter and the fourth model parameter; The maintenance plan generating unit includes: a closed amount interval generating unit, used for generating a closed amount interval of maintenance products according to the consumption weight value; a selecting unit, used for selecting the set of maintenance products whose amount falls within the closed amount interval of maintenance products from all the sets of maintenance products in the preliminary maintenance package; and a recommended package generating unit, which uses the selected set of maintenance products as the recommended maintenance package.

11. The prediction system according to claim 10, characterized in that: The preliminary maintenance prediction unit comprises: a vehicle model building unit, configured to build vehicle models of all vehicles according to the vehicle data and the maintenance history data; a simulation condition establishing unit, configured to establish first to fourth simulation conditions, and select a vehicle to be maintained according to the degree of compliance of the vehicle data with the first to fourth simulation conditions; and The preliminary judgment package generating unit is used to generate a preliminary judgment maintenance package for all the vehicles to be maintained according to the vehicle model maintenance index, and the preliminary judgment maintenance package includes a set of maintenance products for vehicle maintenance.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed, the prediction method according to any one of claims 1 to 9 is implemented.

13. A vehicle maintenance plan prediction device, characterized in that: include: Memory, for storing computer instructions; A processor is coupled to the memory, and the processor is configured to execute the prediction method according to any one of claims 1 to 9 based on computer instructions stored in the memory.

Images