WO2022237266A1 - 车辆保养信息的确定方法、装置、设备及介质 - Google Patents

车辆保养信息的确定方法、装置、设备及介质 Download PDF

Info

Publication number
WO2022237266A1
WO2022237266A1 PCT/CN2022/076917 CN2022076917W WO2022237266A1 WO 2022237266 A1 WO2022237266 A1 WO 2022237266A1 CN 2022076917 W CN2022076917 W CN 2022076917W WO 2022237266 A1 WO2022237266 A1 WO 2022237266A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
data
parameters
state
component
Prior art date
Application number
PCT/CN2022/076917
Other languages
English (en)
French (fr)
Inventor
邵军杰
Original Assignee
北京车和家信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京车和家信息技术有限公司 filed Critical 北京车和家信息技术有限公司
Publication of WO2022237266A1 publication Critical patent/WO2022237266A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance

Definitions

  • the present disclosure relates to the technical field of vehicle maintenance, and in particular to a method, device, equipment and medium for determining vehicle maintenance information.
  • car maintenance mostly adopts the method of fixed mileage or fixed cycle.
  • the maintenance method of fixed mileage or fixed cycle is for users who usually use cars in good condition. There is no need for maintenance, and mandatory maintenance wastes resources and time of customers.
  • the car may have problems before the maintenance cycle, and the user cannot be reminded to maintain the car in time; and according to The status of the car (that is, whether the parts are abnormal) is used to remind the user of maintenance. It can only be prompted when the car is abnormal. While causing inconvenience to the user, the risk factor is also relatively large.
  • the present disclosure provides a method, device, device and medium for determining vehicle maintenance information.
  • an embodiment of the present disclosure provides a method for determining vehicle maintenance information, including:
  • the data of multiple working condition characteristic parameters are respectively processed to obtain multiple state parameter data corresponding to the component;
  • the maintenance information of the vehicle is determined according to the plurality of state parameter data corresponding to the parts, and the maintenance information includes the parts to be maintained and the corresponding maintenance time.
  • the method also includes:
  • a plurality of preset working condition characteristic parameters for predicting the component state are selected from the multiple working condition parameters.
  • the multiple operating condition characteristic parameters include one or more of vehicle environment, vehicle speed, vehicle load, driver's driving characteristics, total vehicle mileage, braking duration, and braking distance.
  • the maintenance information of the vehicle is determined according to multiple state parameter data corresponding to the components, including:
  • the multiple status parameters include one or more of component status, component failure status, component wear degree, performance cracking data, and component remaining quantity.
  • the state prediction model is trained in the following manner:
  • sample data of a plurality of operating condition characteristic parameters is calculated based on vehicle data generated by the vehicle driving within a first preset time period
  • Acquiring feedback data of a plurality of state parameters corresponding to each component the feedback data is obtained based on vehicle maintenance performed by the vehicle after the end of the first preset time period;
  • the neural network model is trained to obtain the state prediction model corresponding to each component.
  • the method further includes:
  • the verification data is calculated based on vehicle data generated by the vehicle driving within a second preset time period
  • the verification data of multiple working condition characteristic parameters are respectively processed through the state prediction model corresponding to each component, and the prediction data of multiple state parameters corresponding to each component are obtained;
  • the method also includes:
  • an embodiment of the present disclosure provides a device for determining vehicle maintenance information, including:
  • An acquisition module used to acquire vehicle data
  • An extraction module configured to obtain a plurality of operating condition characteristic parameter data corresponding to the vehicle data according to the vehicle data and a plurality of preset operating condition characteristic parameters
  • the processing module is used to process the data of a plurality of working condition characteristic parameters through the state prediction model corresponding to the parts, so as to obtain the data of a plurality of state parameters corresponding to the parts;
  • the determination module is used to determine the maintenance information of the vehicle according to the plurality of state parameter data corresponding to the parts, and the maintenance information includes the parts to be maintained and the corresponding maintenance time.
  • an embodiment of the present disclosure provides a device for determining vehicle maintenance information, including:
  • the computer program is stored in the memory and is configured to be executed by the processor to realize the above method.
  • an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented.
  • a method for determining vehicle maintenance information obtains vehicle data, obtains multiple working condition characteristic parameter data corresponding to the vehicle data according to the vehicle data and multiple preset working condition characteristic parameters, and obtains multiple working condition characteristic parameter data corresponding to the vehicle data.
  • the corresponding state prediction model processes the characteristic parameter data of multiple working conditions respectively, and obtains multiple state parameter data corresponding to the parts, and determines the maintenance information of the vehicle according to the multiple state parameter data corresponding to the parts; through real-time acquisition of vehicle Vehicle data during driving, and the status of the current vehicle parts can be determined according to the vehicle data, and the maintenance information of the vehicle for maintenance can be determined in real time, quickly and accurately. State, minimize the waste of resources, and at the same time enhance the security of the vehicle and improve the user experience.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a training method of a state prediction model provided by an embodiment of the present disclosure
  • FIG. 3 is a flow chart of a training method of a state prediction model provided by an embodiment of the present disclosure
  • FIG. 4 is a flowchart of a method for determining vehicle maintenance information provided by an embodiment of the present disclosure
  • FIG. 5 is a flow chart of a method for determining vehicle maintenance information provided by an embodiment of the present disclosure
  • FIG. 6 is a flowchart of a method for determining vehicle maintenance information provided by an embodiment of the present disclosure
  • FIG. 7 is a schematic structural diagram of an apparatus for determining vehicle maintenance information provided by an embodiment of the present disclosure.
  • Fig. 8 is a schematic structural diagram of a device for determining vehicle maintenance information provided by an embodiment of the present disclosure.
  • the maintenance time is mostly set by a fixed mileage interval or a fixed time interval, such as engine oil, machine filter, spark plug, air filter, air filter element, brake fluid, brake disc, reducer oil, etc. , according to a certain mileage interval (such as 20000km) or a certain time interval (such as 1 year) to set the maintenance time of the vehicle; also according to the state of the vehicle, that is, whether the parts are abnormal, to remind the user to maintain the abnormal parts .
  • a certain mileage interval such as 20000km
  • a certain time interval such as 1 year
  • the present disclosure provides a method for determining vehicle maintenance information, which will be specifically introduced below in conjunction with specific embodiments.
  • a method for determining vehicle maintenance information may be executed by the vehicle or the server.
  • the vehicle end or the server can determine multiple state parameter data corresponding to the parts through the state prediction model.
  • the execution subject of the training method of the state prediction model and the execution subject of the determination method of the vehicle maintenance information may be the same or different.
  • the server 12 trains a state prediction model.
  • the vehicle 11 obtains the trained state prediction model from the server 12, the vehicle 11 obtains the vehicle data, processes the vehicle data through the trained state prediction model, and determines the state of the components in the vehicle 11.
  • This application scenario is through the server 12 Train the state prediction model and transmit it to the vehicle end 11.
  • the vehicle end 11 obtains vehicle data, uses the state prediction model to obtain the state of the parts, and determines the maintenance information of the vehicle according to the state of the parts.
  • the server 12 trains the state prediction model. Further, the server 12 determines the status of components in the vehicle 11 through the trained status prediction model.
  • the vehicle data received by the server 12 can be acquired by the vehicle 11 and transmitted to the server 12 for processing.
  • the server 12 transmits the maintenance information to the vehicle 11, and the vehicle 11 reminds the user to maintain the vehicle through the maintenance information.
  • This application scenario is that the vehicle 11 collects vehicle data. The data is transmitted to the server 12 for processing, and the server 12 transmits the output result, that is, the maintenance information to the vehicle 11, and the vehicle 11 reminds the user to perform maintenance according to the maintenance information.
  • the vehicle 11 trains a state prediction model. Further, the vehicle 11 determines the state of components in the vehicle 11 through the trained state prediction model.
  • the state prediction model is trained by the server 12, the vehicle end 11 transmits the vehicle data to the server 12, the state prediction model of the server 12 processes the vehicle data, obtains the state parameters corresponding to the parts, and determines the state parameters of the vehicle 11 according to the state parameters of the parts.
  • the application scenario in which the maintenance information is sent to the vehicle 11 is taken as an example, and the following embodiments are further described.
  • FIG. 2 is a flow chart of a state prediction model training method provided by an embodiment of the present disclosure. Training the state prediction model through the server 12 includes the following steps S210 to S230 as shown in FIG. 2 .
  • step S210 sample data of a plurality of operating condition characteristic parameters are acquired, and the sample data is calculated based on vehicle data generated by the vehicle driving within a first preset time period.
  • the multiple operating condition characteristic parameters include one or more of vehicle environment, vehicle speed, vehicle load, driver's driving characteristics, total vehicle mileage, braking duration, and braking distance.
  • the vehicle data generated during the driving process of the vehicle within the first preset time period is counted, wherein the vehicle data may include but not limited to vehicle speed distribution, engine speed distribution, generator speed distribution, speed reducer speed distribution, engine oil temperature
  • vehicle speed distribution may include but not limited to vehicle speed distribution, engine speed distribution, generator speed distribution, speed reducer speed distribution, engine oil temperature
  • the distribution, the oil temperature distribution of the reducer, the frequency of use of the air conditioner, and the data in the above-mentioned operating condition characteristic parameters can be statistically analyzed on the vehicle data acquired within the first preset time period to obtain sample data of multiple operating condition characteristic parameters.
  • a plurality of working condition characteristic parameters used to reflect the state of the component is selected from the multiple working condition parameters.
  • the contribution to the performance of the component state is classified and sorted, and the characteristic parameters of the vehicle working condition that have a greater impact on the performance of the component state are screened out, that is, the most can reflect the zero
  • the operating condition characteristic parameters of the component state where each component has one or more corresponding operating condition characteristic parameters.
  • the operating condition characteristic parameters that have a greater impact on lubricating oil include: speed and vehicle load.
  • the acquisition of the vehicle data within the first preset time period may be the vehicle data generated during the driving of the vehicle, such as the vehicle speed and the total mileage of the vehicle in Table 1, wherein the driving characteristics of the vehicle driver may refer to
  • the situation of the driver driving the vehicle can be divided into two options: intense driving and smooth driving, indicating the situation of the driver driving the vehicle within the first preset time period; the vehicle load can refer to the impact on the building when the vehicle is stationary or moving.
  • the active force generated can limit the state of the vehicle load, including full load, half load and no load;
  • the braking duration can refer to the time used by the vehicle from the start of braking to the complete stop of the vehicle;
  • the moving distance can refer to the distance traveled by the vehicle from the start of braking to the complete standstill at a certain speed per hour.
  • the sample data of multiple operating condition characteristic parameters may be as shown in Table 1.
  • the first preset time period is 10 days
  • the server receives 10 vehicle data in total, and performs statistical analysis on 10 vehicle data , it is obtained that the proportion of high temperature is 60%, that of low temperature is 20%, and that of normal temperature is 20%.
  • step S220 the feedback data of a plurality of state parameters corresponding to each component is acquired, and the feedback data is obtained based on the vehicle maintenance performed by the vehicle after the first preset time period ends.
  • the feedback data of multiple status parameters corresponding to each component may include one or more of component status, component failure status, component wear degree, performance cracking data, and component remaining quantity.
  • the server 12 obtains from the after-sales system Feedback data of a plurality of state parameters corresponding to each component in the first preset time period, wherein, in the first preset time period, the feedback data corresponds to the sample data, that is, the feedback data can be indirectly obtained from the sample data, namely There is a corresponding relationship between the sample data and the feedback data.
  • the status of parts in the above feedback data can indicate the condition of each part in the vehicle, including whether there is damage or not; the fault status of parts can be whether a part is faulty, and can include two options of yes or no;
  • the performance cracking data may refer to the change in the performance of parts; the remaining amount of parts may refer to the remaining amount of parts with a certain amount of storage, such as lubricating oil.
  • the feedback data of multiple state parameters corresponding to each component may be as shown in Table 2.
  • the status of parts and components can be expressed by intact, good, and poor.
  • the performance cracking data of No. 2 as an example, it can be expressed as the viscosity of lubricating oil drops by 30%.
  • the remaining amount is 90%, but there is no remaining amount in the brake disc, which can be represented by an empty state.
  • step S230 the neural network model is trained according to the sample data of a plurality of operating condition characteristic parameters and the feedback data of a plurality of state parameters corresponding to each component to obtain a state prediction model corresponding to each component.
  • the server 12 trains the neural network model according to the sample data of multiple operating condition characteristic parameters and the feedback data of multiple state parameters corresponding to each component, wherein the neural network model
  • the state prediction model corresponding to each component can be obtained by constructing a convolutional neural network, that is, the sample data is used as the input of the neural network model, and the feedback data is used as the label of the neural network model, that is, the output result.
  • the embodiment of the present disclosure provides a training method for a state prediction model.
  • sample data of a plurality of operating condition characteristic parameters the sample data is calculated based on the vehicle data generated by the vehicle driving within the first preset time period, and each zero is obtained.
  • Feedback data of a plurality of state parameters corresponding to a component The feedback data is obtained based on vehicle maintenance after the first preset time period ends.
  • train the neural network model According to the sample data of a plurality of working condition characteristic parameters and the data Feedback data, train the neural network model, and obtain the state prediction model corresponding to each component.
  • the relationship between the state parameters corresponding to each component, that is, the feedback data, and the working condition characteristic parameters, that is, the sample data can be established, and the corresponding component state parameters can be directly obtained through the working condition characteristic parameters, and the processing speed is fast. High accuracy.
  • step S310 the verification data of a plurality of operating condition characteristic parameters are obtained, and the verification data is calculated based on the vehicle data generated by the vehicle driving within the second preset time period.
  • the vehicle data generated during the driving process of the vehicle within the second preset time period is counted, wherein the vehicle data may include but not limited to vehicle speed distribution, engine speed distribution, generator speed distribution, speed reducer speed distribution, engine oil temperature
  • vehicle speed distribution may include but not limited to vehicle speed distribution, engine speed distribution, generator speed distribution, speed reducer speed distribution, engine oil temperature
  • the distribution, the oil temperature distribution of the reducer, the frequency of use of the air conditioner, and the data in the above-mentioned operating condition characteristic parameters can be statistically analyzed on the vehicle data acquired in the second preset time period, and the verification data of multiple operating condition characteristic parameters can be obtained.
  • a plurality of working condition characteristic parameters used to reflect the state of the component is selected from the multiple working condition parameters.
  • the contribution degree of the performance in the component state is classified and sorted, and the characteristic parameters of the vehicle working condition that have a greater impact on the performance of the component state are screened out, that is, the most reflective components
  • the working condition characteristic parameters of the state wherein each component has one or more corresponding working condition characteristic parameters.
  • the acquisition and calculation methods of the verification data and the above sample data may be the same, and based on the vehicle data obtained in different time periods, the multiple operating condition characteristic parameters determined by screening the vehicle data may be different.
  • step S320 the feedback data of a plurality of state parameters corresponding to each component is acquired, and the feedback data is obtained based on the vehicle maintenance performed by the vehicle after the second preset time period ends.
  • the user goes to the after-sales department to maintain the vehicle, and the after-sales personnel dismantle the parts in the vehicle, check and detect the status of the parts, and obtain the vehicle loading after the second preset time period ends.
  • a plurality of state parameters corresponding to each component and perform statistics and analysis on a plurality of state parameters corresponding to each detected component, generate feedback data, and upload the feedback data to the after-sales system, and the server 12 obtains from the after-sales system Feedback data to multiple state parameters corresponding to each component, wherein, within the second preset time period, the feedback data corresponds to the sample data, that is, the feedback data can be indirectly obtained from the sample data, and there is a correspondence between the sample data and the feedback data relation.
  • step S330 the verification data of a plurality of operating condition characteristic parameters are respectively processed through the state prediction model corresponding to each component to obtain the prediction data of a plurality of state parameters corresponding to each component.
  • the state prediction model that has been trained above is used to identify the verification data of a plurality of operating condition characteristic parameters, and output the prediction data of a plurality of state parameters corresponding to each component.
  • step S340 it is judged whether the predicted data and the feedback data match, and if so, the corresponding state prediction model is saved; Data, modify the corresponding state prediction model.
  • the predicted data obtained by the trained state prediction model matches the feedback data, that is, whether the predicted data and the verification data are within a certain range, and if so, save the current
  • the state prediction model of the test the matching of the prediction data and the feedback data also indicates that the accuracy of the current training completed state prediction model is relatively high;
  • the state prediction model is trained, and the above state prediction model used for testing is corrected.
  • the current state prediction model is corrected in time according to the acquired verification data and feedback data of different preset time periods, so as to improve the accuracy of the state prediction model.
  • the verification data of a plurality of operating condition characteristic parameters is obtained, and the verification data is calculated based on the vehicle data generated by the vehicle driving within the second preset time period, and each zero is obtained.
  • the feedback data is obtained based on the vehicle maintenance after the second preset time period ends, and the verification data of multiple working condition characteristic parameters are respectively carried out through the state prediction model corresponding to each component Processing, to obtain the prediction data of multiple state parameters corresponding to each component, judge whether the prediction data matches the feedback data, if so, save the corresponding state prediction model; if not, then according to the verification data of multiple working condition characteristic parameters and
  • the feedback data of multiple state parameters corresponding to each component is used to correct the corresponding state prediction model.
  • FIG. 4 is a flow chart of a method for determining vehicle maintenance information provided by the embodiments of the present disclosure.
  • the state prediction model trained in the above embodiments is used to process the vehicle data, including the method shown in FIG. 4
  • the following steps S410 to S440 are shown.
  • step S410 vehicle data is acquired.
  • the server 12 receives the vehicle data transmitted by the vehicle 11 in real time.
  • vehicle data may include one or more operating condition parameters mentioned above.
  • the operating condition parameters may include but not limited to one or more of vehicle speed distribution, engine speed distribution, generator speed distribution, reducer speed distribution, engine oil temperature distribution, reducer oil temperature distribution, and air conditioner usage frequency.
  • step S420 a plurality of operating condition characteristic parameter data corresponding to the vehicle data is obtained according to the vehicle data and a plurality of preset operating condition characteristic parameters.
  • the server 12 performs statistical analysis on the acquired vehicle data to obtain a plurality of working condition characteristic parameter data corresponding to the vehicle data, wherein the working condition characteristic parameter data is included in the vehicle data, that is, the working condition parameter data.
  • the number of preset working condition characteristic parameters corresponds to the quantity of working condition characteristic parameter data.
  • step S430 a plurality of operating condition characteristic parameter data are respectively processed through the state prediction model corresponding to the component to obtain a plurality of state parameter data corresponding to the component.
  • step S440 the maintenance information of the vehicle is determined according to the plurality of state parameter data corresponding to the components, and the maintenance information includes the components to be maintained and the corresponding maintenance time.
  • the maintenance information of the vehicle that sends the vehicle data to the server is determined according to the plurality of state parameter data corresponding to the parts obtained by the state prediction model.
  • a method for determining vehicle maintenance information obtains vehicle data, obtains multiple working condition characteristic parameter data corresponding to the vehicle data according to the vehicle data and multiple preset working condition characteristic parameters, and obtains multiple working condition characteristic parameter data corresponding to the vehicle data.
  • the corresponding state prediction model processes the characteristic parameter data of multiple working conditions respectively, and obtains multiple state parameter data corresponding to the parts, and determines the maintenance information of the vehicle according to the multiple state parameter data corresponding to the parts.
  • One or more parts to be maintained and the corresponding maintenance time by obtaining the vehicle data during the driving process in real time, and determining the status of the current vehicle parts according to the vehicle data, it is possible to determine the maintenance time of the vehicle in real time, quickly and accurately
  • the maintenance information is determined more intelligently. According to the maintenance information, the status of the vehicle can be understood in a timely and comprehensive manner, the waste of resources can be minimized, the safety of the vehicle can be enhanced, and the user experience can be improved.
  • processing the vehicle data acquired in step S410 also includes the following steps S510 to S520 as shown in FIG. 5 .
  • step S510 a plurality of operating condition parameters are determined, and the operating condition parameters are parameters that can be calculated based on vehicle data.
  • the vehicle data transmitted from the vehicle to the server can be obtained, and the vehicle data within the first preset time period can be counted, and the acquired vehicle data can be processed by accumulative sum calculation, proportional calculation, difference value or average value, etc.
  • Multiple working condition parameters are obtained by counting and calculating the data of multiple working conditions in the vehicle data.
  • step S520 based on the preset contribution degree of the multiple working condition parameters to the component state, a plurality of preset working condition characteristic parameters for predicting the component state are selected from the multiple working condition parameters.
  • the contribution degree of the performance in the state of the parts is classified and sorted according to the multiple working condition parameters, and the characteristic parameters of the working conditions of the vehicle that have a greater impact on the performance of the state of the parts are screened out, That is, the operating condition characteristic parameters that can best reflect the state of the components are used as the preset operating condition characteristic parameters, where each component has one or more corresponding operating condition characteristic parameters, for example, the serial number 1 lubricating oil in Table 1
  • the characteristic parameters of operating conditions that have a greater impact on lubricants during vehicle driving include: total mileage of the vehicle, driving characteristics of the driver, vehicle speed, and vehicle load.
  • the characteristic parameters of operating conditions that have a greater impact on lubricants may cause lubricants to For example, the proportion of intense driving in the driving characteristics of the driver in the operating condition parameters is relatively high, which may lead to the performance cracking data of the lubricating oil, that is, the viscosity of the lubricating oil decreases, and may also cause the brake disc
  • the degree of wear increases, etc. that is, according to the determined characteristic parameters of the operating conditions that have a greater impact on the lubricating oil, the current state parameter data of the lubricating oil can be obtained through the state prediction model.
  • An embodiment of the present disclosure provides a method for determining vehicle maintenance information.
  • the working condition parameters are parameters that can be calculated based on vehicle data, and based on the preset contributions of multiple working condition parameters to the state of components degree, and filter out multiple preset working condition characteristic parameters used to predict the state of components from multiple working condition parameters.
  • Preliminary statistics and processing are performed on the acquired vehicle data, and the characteristic parameter data of multiple preset working conditions that have a greater impact on the contribution to the parts are screened, which can reduce the amount of data and preserve the characteristics of the vehicle data to the greatest extent. While improving the processing speed of the state prediction model, it can also ensure accurate prediction of the state of parts.
  • the maintenance information of the vehicle is determined, which also includes the following steps S610 to S620 as shown in FIG. 6 .
  • step S610 a correspondence relationship between a plurality of state parameters corresponding to components and maintenance time is acquired.
  • the feedback data corresponding to the parts can be obtained according to the above-mentioned first preset time period and the second preset time period, that is, the historical vehicle data obtained during the driving of the vehicle and after each preset time period
  • the state parameters of the parts obtained by detecting the state of the parts are used to establish the corresponding relationship between the multiple state parameters corresponding to each part and the maintenance time, that is, the maintenance time of the part is determined through the state of each part, and the maintenance time can be It is a reasonable time range or an accurate time period, and the determined corresponding relationship is stored.
  • the maintenance time of lubricating oil is between 30 days and 40 days. If the remaining amount of lubricating oil is 90 %, the corresponding maintenance time will increase correspondingly; if the wear degree of the parts of the brake disc reaches 60%, the corresponding maintenance time of the brake disc may be between 20 days and 30 days, and the corresponding relationship can be based on the actual situation of the user. It is determined by using historical operating condition data and historical component status of the vehicle, which is not limited here.
  • step S620 the corresponding relationship is searched according to the plurality of state parameter data corresponding to the parts, and the maintenance information of the vehicle is determined.
  • the corresponding corresponding relationship is searched according to the multiple state parameter data corresponding to each component, and the different state parameters of each component correspond to different maintenance times, and the current vehicle is determined according to the corresponding relationship.
  • maintenance information wherein the maintenance information includes one or more components to be maintained and the maintenance time corresponding to the components.
  • the method for determining the vehicle maintenance information further includes: sending the maintenance information to the vehicle, so that the vehicle reminds the user of the parts to be maintained and the corresponding maintenance time according to the maintenance information.
  • the server 12 sends the determined maintenance information to the control device of the vehicle 11.
  • the vehicle 11 is a vehicle that sends vehicle data to the server 12.
  • the control device of the vehicle 11 can directly remind The status and maintenance time of each component of the user.
  • a method for determining vehicle maintenance information obtains the corresponding relationship between multiple state parameters corresponding to each component and the maintenance time, and searches for the corresponding relationship according to the multiple state parameter data corresponding to each component to determine the vehicle maintenance information.
  • maintenance information wherein the maintenance information includes one or more components to be maintained and the corresponding maintenance time.
  • the corresponding relationship is determined according to the historical parts status and maintenance time of the vehicle, and the corresponding relationship is searched according to the multiple state parameter data corresponding to each part in the current vehicle, so that the maintenance time corresponding to each part can be quickly determined, and the processing speed is relatively fast.
  • the determined maintenance information has a high accuracy rate.
  • FIG. 7 is a schematic structural diagram of an apparatus for determining vehicle maintenance information provided by an embodiment of the present disclosure.
  • An apparatus for determining vehicle maintenance information provided in an embodiment of the present disclosure may execute a processing flow provided in an embodiment of a method for determining vehicle maintenance information.
  • an apparatus 700 for determining vehicle maintenance information includes:
  • An acquisition module 710 configured to acquire vehicle data
  • An extraction module 720 configured to obtain a plurality of operating condition characteristic parameter data corresponding to the vehicle data according to the vehicle data and a plurality of preset operating condition characteristic parameters;
  • the processing module 730 is used to process a plurality of working condition characteristic parameter data respectively through the state prediction model corresponding to the parts to obtain a plurality of state parameter data corresponding to the parts;
  • the determination module 740 is used to determine the maintenance information of the vehicle according to the multiple state parameter data corresponding to the parts, and the maintenance information includes the parts to be maintained and the corresponding maintenance time;
  • the sending module 750 is configured to send maintenance information to the vehicle, so that the vehicle can remind the user of the parts to be maintained and the maintenance time according to the maintenance information.
  • the device 700 for determining vehicle maintenance information further includes: a characteristic module, configured to determine a plurality of working condition parameters, where the working condition parameters are parameters that can be calculated based on vehicle data;
  • the preset contribution degree of the state is to filter out multiple preset working condition characteristic parameters used to predict the state of parts from multiple working condition parameters.
  • the device 700 for determining vehicle maintenance information further includes: a training module, configured to acquire sample data of a plurality of operating condition characteristic parameters, the sample data is calculated based on the vehicle data generated when the vehicle is driven within a first preset time period Obtaining; obtaining feedback data of multiple state parameters corresponding to each component, the feedback data is obtained based on vehicle maintenance after the end of the first preset time period; according to the sample data of multiple working condition characteristic parameters and the corresponding The feedback data of multiple state parameters is used to train the neural network model to obtain the state prediction model corresponding to each component.
  • a training module configured to acquire sample data of a plurality of operating condition characteristic parameters, the sample data is calculated based on the vehicle data generated when the vehicle is driven within a first preset time period Obtaining; obtaining feedback data of multiple state parameters corresponding to each component, the feedback data is obtained based on vehicle maintenance after the end of the first preset time period; according to the sample data of multiple working condition characteristic parameters and the corresponding The feedback data of multiple state parameters is used to train the neural network
  • the multiple operating condition characteristic parameters in the extraction module 720 include one or more of vehicle environment, vehicle speed, vehicle load, driver's driving characteristics, total vehicle mileage, braking duration, and braking distance.
  • the determination module 740 determines the maintenance information of the vehicle according to the multiple state parameter data corresponding to the parts, which is specifically used to: obtain the corresponding relationship between the multiple state parameters corresponding to the parts and the maintenance time; Corresponding multiple state parameter data are searched for correspondence, and the maintenance information of the vehicle is determined.
  • the plurality of state parameters in the determination module 740 includes one or more of the state of the component, the fault state of the component, the degree of wear of the component, performance cracking data, and the remaining quantity of the component.
  • the neural network model is trained in the training module, it is specifically used to: acquire verification data of a plurality of operating condition characteristic parameters, and the verification data is calculated based on vehicle data generated by the vehicle driving within a second preset time period; Feedback data of a plurality of state parameters corresponding to each component is obtained, and the feedback data is obtained based on vehicle maintenance after the second preset time period ends; The verification data is processed to obtain the prediction data of multiple state parameters corresponding to each component; judge whether the prediction data matches the feedback data, and if so, save the corresponding state prediction model; Verify the data and the feedback data of multiple state parameters corresponding to each component, and correct the corresponding state prediction model.
  • a device for determining vehicle maintenance information in the embodiment shown in FIG. 7 can be used to implement the technical solution of the above-mentioned method embodiment, and its implementation principle and technical effect are similar, and will not be repeated here.
  • Fig. 8 is a schematic structural diagram of a device for determining vehicle maintenance information provided by an embodiment of the present disclosure.
  • the device for determining the vehicle maintenance information may be the above server or the vehicle.
  • the device for determining vehicle maintenance information provided by the embodiment of the present disclosure can execute the processing flow provided by the embodiment of the method for determining vehicle maintenance information.
  • the device 800 for determining vehicle maintenance information includes: a processor 810 and a communication interface 820 and a memory 830; wherein, the computer program is stored in the memory 830 and is configured to be executed by the processor 810 as the method for determining vehicle maintenance information as described above.
  • an embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the method for determining vehicle maintenance information in the above-mentioned embodiments.
  • an embodiment of the present disclosure also provides a computer program product, the computer program product includes a computer program or an instruction, and when the computer program or instruction is executed by a processor, the above method for determining vehicle maintenance information is realized.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Probability & Statistics with Applications (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Human Resources & Organizations (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种车辆保养信息的确定方法包括获取车辆数据，根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据，通过零部件对应的状态预测模型分别对多个工况特征参数数据进行处理，得到与零部件对应的多个状态参数数据，根据零部件对应的多个状态参数数据，确定车辆的保养信息，保养信息包括待保养的零部件以及对应的保养时间。

Description

车辆保养信息的确定方法、装置、设备及介质
相关申请的交叉引用
本申请基于申请号为202110520811.4、申请日为2021年05月13日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及车辆保养技术领域，尤其涉及一种车辆保养信息的确定方法、装置、设备及介质。
背景技术
随着汽车技术的发展，汽车的应用愈加广泛，汽车在给用户提供便利的同时，用户也需要对汽车的零部件进行保养。
目前，汽车保养多是采用定里程或定周期的方式，但是，定里程或定周期的保养方式，对于平时用车工状况较好的用户，到保养周期后，汽车的零部件状态比较好，还不需要进行保养，强制保养浪费资源也浪费客户的时间，对于用车状况不好的用户，还没到保养周期时，汽车可能就出现了问题，不能及时的提醒用户对汽车进行保养；而根据汽车状态(即零部件是否出现异常)来提醒用户保养，只能在汽车出现异常的时候才提示，为用户带来不便的同时，危险系数也比较大。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种车辆保养信息的确定方法、装置、设备及介质。
第一方面，本公开实施例提供一种车辆保养信息的确定方法，包括：
获取车辆数据；
根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据；
通过零部件对应的状态预测模型分别对多个工况特征参数数据进行处理，得到与零部件对应的多个状态参数数据；
根据零部件对应的多个状态参数数据，确定车辆的保养信息，保养信息包括待保养的零部件以及对应的保养时间。
在一个实施例中，方法还包括：
确定多个工况参数，工况参数为能够基于车辆数据计算得到的参数；
基于多个工况参数对零部件状态的预设贡献度，从多个工况参数中筛选出用于预测零部件状态的多个预设工况特征参数。
在一个实施例中，多个工况特征参数包括用车环境、车速、车辆载荷、驾驶员驾驶特性、车辆总里程、制动时长、制动距离中的一种或多种。
在一个实施例中，根据零部件对应的多个状态参数数据，确定车辆的保养信息，包括：
获取零部件对应的多个状态参数与保养时间的对应关系；
根据零部件对应的多个状态参数数据查找对应关系，确定车辆的保养信息。
在一个实施例中，多个状态参数包括零部件状态、零部件故障状态、零部件磨损程度、性能裂化数据、零部件剩余量中的一种或多种。
在一个实施例中，状态预测模型通过以下方式训练得到：
获取多个工况特征参数的样本数据，样本数据基于车辆在第一预设时间段内行驶产生的车辆数据计算得到；
获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第一预设时间段结束后进行车辆保养得到；
根据多个工况特征参数的样本数据以及各零部件对应的多个状态参数的反馈数据，训练神经网络模型，得到各零部件对应的状态预测模型。
在一个实施例中，训练神经网络模型之后，方法还包括：
获取多个工况特征参数的验证数据，验证数据基于车辆在第二预设时间段内行驶产生的车辆数据计算得到；
获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第二预设时间段结束后进行车辆保养得到；
通过各零部件对应的状态预测模型分别对多个工况特征参数的验证数据进行处理，得到各零部件对应的多个状态参数的预测数据；
判断预测数据与反馈数据是否匹配，若是，则保存对应的状态预测模型；若否，则根据多个工况特征参数的验证数据以及各零部件对应的多个状态参数的反馈数据，修正对应的状态预测模型。
在一个实施例中，方法还包括：
向车辆发送保养信息，以使车辆根据保养信息提醒用户待保养的零部件以及对应的保养时间。
第二方面，本公开实施例提供一种车辆保养信息的确定装置，包括：
获取模块，用于获取车辆数据；
提取模块，用于根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据；
处理模块，用于通过零部件对应的状态预测模型分别对多个工况特征参数数据进行处理，得到与零部件对应的多个状态参数数据；
确定模块，用于根据零部件对应的多个状态参数数据，确定车辆的保养信息，保养信息包括待保养的零部件以及对应的保养时间。
第三方面，本公开实施例提供一种车辆保养信息的确定设备，包括：
存储器；
处理器；以及
计算机程序；
其中，计算机程序存储在存储器中，并被配置为由处理器执行以实现如上述的方法。
第四方面，本公开实施例提供一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现如上述的方法。
本公开实施例提供的技术方案与现有技术相比具有如下优点：
本公开实施例提供的一种车辆保养信息的确定方法，通过获取车辆数据，根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据，通过零部件对应的状态预测模型分别对多个工况特征参数数据进行处理，得到与零部件对应的多个状态参数数据，根据零部件对应的多个状态参数数据，确定车辆的保养信息；通过实时获取车辆行驶过程中的车辆数据，并根据车辆数据确定当前车辆零部件的状态，能够实时、快速、准确的确定车辆进行保养的保养信息，确定方法更加智能化，根据保养信息能够及时全面的了解车辆的状态，最大限度的减少资源的浪费，同时加强车辆的安全性，提高用户体验。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种应用场景的示意图；
图2为本公开实施例提供的一种状态预测模型的训练方法的流程图；
图3为本公开实施例提供的一种状态预测模型的训练方法的流程图；
图4为本公开实施例提供的一种车辆保养信息的确定方法的流程图；
图5为本公开实施例提供的一种车辆保养信息的确定方法的流程图；
图6为本公开实施例提供的一种车辆保养信息的确定方法的流程图；
图7为本公开实施例提供一种车辆保养信息的确定装置的结构示意图；
图8为本公开实施例提供一种车辆保养信息的确定设备的结构示意图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面将对本公开的方案进行进一步描述。需要说明的是，在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本公开，但本公开还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本公开的一部分实施例，而不 是全部的实施例。
需要说明的是，本公开的实施方式中记载的各个步骤的标号并不用于限定步骤间的执行先后关系，可以按照不同的顺序执行，和/或，并行执行。
现有技术中，多是通过定里程间隔或定时间间隔设定保养时间，如车辆上用的机油、机滤、火花塞、空滤、空调滤芯、制动液、制动盘、减速器油等，按照一定的里程间隔(如20000km)或一定的时间间隔(如1年)设定车辆的保养时间；还根据车辆状态即零部件是否出现异常后，来提醒用户对出现异常的零部件进行保养。但是，定里程或时间设定保养时间，对于平时用车工况较好的用户，到保养时间后，车辆零部件状态完好，不需要进行保养，如果进行强制保养浪费资源；而根据车辆状态即零部件出现异常提醒用户保养，对于车辆以及用户的安全性比较低。因此，针对上述问题，本公开提供一种车辆保养信息的确定方法，下面结合具体的实施例对该方法进行具体介绍。
具体的，一种车辆保养信息的确定方法可以由车辆或服务器来执行。具体的，车端或服务器可以通过状态预测模型确定零部件对应的多个状态参数数据。状态预测模型的训练方法的执行主体和车辆保养信息的确定方法的执行主体可以相同，也可以不同。
例如，在一种应用场景中，如图1所示，服务器12对状态预测模型进行训练。车辆11从服务器12获取训练完成的状态预测模型，车辆11获取车辆数据，通过该训练完成的状态预测模型对车辆数据进行处理，确定车辆11中零部件的状态，此种应用场景是通过服务器12训练状态预测模型并传输至车端11，车端11获取车辆数据，利用状态预测模型得到零部件的状态，并根据零部件的状态确定车辆的保养信息。
在另一种应用场景中，服务器12对状态预测模型进行训练。进一步，服务器12通过训练完成的状态预测模型确定车辆11中零部件的状态。服务器12接收的车辆数据可以由车辆11获取并传输至服务器12进行处理，服务器12将保养信息传输至车辆11，车辆11通过保养信息提醒用户对车辆进行保养，此种应用场景是车辆11采集车辆数据传输至服务器端12进行处理，服务器端12将输出结果即保养信息传输至车辆11，车辆11根据保养信息提醒用户进行保养。
在又一种应用场景中，车辆11对状态预测模型进行训练。进一步，车辆11通过训练完成的状态预测模型确定车辆11中零部件的状态。
可以理解的是，本公开实施例提供的车辆保养信息的确定方法并不限于如上的几种可能场景。
通过服务器12训练状态预测模型，车端11将车辆数据传输至服务器12，服务器12的状态预测模型对车辆数据进行处理，得到与零部件对应的状态参数，根据零部件的状态参数确定车辆11的保养信息，并将保养信息发送至车辆11的应用场景为例，对下述实施例进一步说明。
图2为本公开实施例提供的一种状态预测模型的训练方法的流程图，通过服务器12训练状态预测模型，包括如图2所示的如下步骤S210至S230。
在步骤S210中，获取多个工况特征参数的样本数据，样本数据基于车辆在第一预设时 间段内行驶产生的车辆数据计算得到。
在一个实施例中，多个工况特征参数包括用车环境、车速、车辆载荷、驾驶员驾驶特性、车辆总里程、制动时长、制动距离中的一种或多种。
可理解的，统计第一预设时间段内车辆在行驶过程中产生的车辆数据，其中，车辆数据可以包括但不限于车速分布、发动机转速分布、发电机转速分布、减速器转速分布、机油温度分布、减速器油温分布、空调使用频率以及上述工况特征参数中的数据，可以对第一预设时间段内获取的车辆数据进行统计分析，得到多个工况特征参数的样本数据。
在一个实施例中，基于多个工况参数对零部件状态的预设贡献度，从多个工况参数中筛选出用于反映零部件状态的多个工况特征参数。
可理解的，按照上述多个工况参数对零部件状态中性能的贡献度进行分类排序，筛选出对零部件状态中对性能影响较大的用车工况特征参数，即最能反映出零部件状态的工况特征参数，其中，各零部件分别存在对应的一个或多个工况特征参数，例如，对润滑油影响较大的工况特征参数包括：车辆总里程、驾驶员驾驶特性、车速以及车辆载荷。
可理解的，获取第一预设时间段内的车辆数据，可以是由车辆行驶过程中产生的车辆数据，例如表1中的车速、车辆总里程等，其中，车辆驾驶员的驾驶特性可以指驾驶员驾驶车辆的情况，可以分为激烈驾驶和平稳驾驶两个选项，表示第一预设时间段内驾驶员驾驶车辆的情况；车辆载荷可以指车辆在建筑物上静止或运动时对建筑物产生的作用力，优选的，可以对车辆载荷的状态进行限定，包括满载、半载和空载的情况；制动时长可以指行驶中的车辆从开始刹车到车辆完全停下来所用的时间；制动距离可以指车辆在某一时速的情况下，从开始制动到完全静止时，车辆所驶过的路程。
示例性的，多个工况特征参数的样本数据可以如表1所示。对于样本数据的计算方式以表1中序号1的工况特征参数用车环境为例，第一预设时间段为10天，服务器共接收到10个车辆数据，对10个车辆数据进行统计分析，得到高温占比60％、低温占比20％以及常温占比20％。
表1
Figure PCTCN2022076917-appb-000001
Figure PCTCN2022076917-appb-000002
在步骤S220中，获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第一预设时间段结束后进行车辆保养得到。
在一个实施例中，各零部件对应的多个状态参数的反馈数据可以包括零部件状态、零部件故障状态、零部件磨损程度、性能裂化数据、零部件剩余量中的一种或多种。
可理解的，车辆进行交付后，用户到售后部门对车辆进行保养，售后人员拆解车辆中的零部件，并对零部件状态进行查验和检测，得到车辆行驶第一预设时间段结束后，各零部件对应的多个状态参数，并对检测到的各零部件对应的多个状态参数进行统计和分析，生成反馈数据，并将反馈数据上传至售后系统，服务器12从售后系统中获取到第一预设时间段内各零部件对应的多个状态参数的反馈数据，其中，在第一预设时间段内，反馈数据与样本数据相对应，即由样本数据可以间接得到反馈数据，即样本数据与反馈数据存在对应关系。
可理解的，上述反馈数据中零部件状态可以表示车辆中各零部件的情况，包括是否有损坏等情况；零部件故障状态可以是零部件是否出现了故障，可以包括是或否两种选项；性能裂化数据可以指零部件的性能发生了改变；零部件剩余量可以指有一定存储量的零部件的剩余量，例如润滑油等。
示例性的，各零部件对应的多个状态参数的反馈数据可以如表2所示。以表2中序号1为例，零部件状态可以通过完好、良好、差来表述各零部件当前的状态，以序号2性能裂化数据为例，可以表示为润滑油粘度下降30％，以序号5中剩余量为例，润滑油的剩余量为90％，而制动盘不存在剩余量，可以用空的状态表示。
表2
序号 零部件状态参数 润滑油 制动盘
1 零部件状态 良好 差
2 性能裂化数据 30％ 50％
3 零部件是否故障 否 否
4 零部件磨损程度 30％ 60％
5 剩余量 90％ NA
6 是否需要更换 否 是
在步骤S230中，根据多个工况特征参数的样本数据以及各零部件对应的多个状态参数的反馈数据，训练神经网络模型，得到各零部件对应的状态预测模型。
可理解的，在上述步骤S210和S220的基础上，服务器12根据多个工况特征参数的样本数据以及各零部件对应的多个状态参数的反馈数据，训练神经网络模型，其中，神经网络 模型可以通过卷积神经网络构建，得到各零部件对应的状态预测模型，即样本数据作为神经网络模型的输入，反馈数据作为神经网络模型的标签即输出结果。
本公开实施例提供的一种状态预测模型的训练方法，通过获取多个工况特征参数的样本数据，样本数据基于车辆在第一预设时间段内行驶产生的车辆数据计算得到，获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第一预设时间段结束后进行车辆保养得到，根据多个工况特征参数的样本数据以及各零部件对应的多个状态参数的反馈数据，训练神经网络模型，得到各零部件对应的状态预测模型。通过训练神经网络模型，建立各零部件对应的状态参数即反馈数据与工况特征参数即样本数据之间的关联关系，能够通过工况特征参数直接得到对应的零部件状态参数，处理速度快，准确率高。
在上述实施例的基础上，可选的，训练神经网络模型，生成状态预测模型之后，还包括如图3所示的如下步骤S310至S340。
在步骤S310中，获取多个工况特征参数的验证数据，验证数据基于车辆在第二预设时间段内行驶产生的车辆数据计算得到。
可理解的，统计第二预设时间段内车辆在行驶过程中产生的车辆数据，其中，车辆数据可以包括但不限于车速分布、发动机转速分布、发电机转速分布、减速器转速分布、机油温度分布、减速器油温分布、空调使用频率以及上述工况特征参数中的数据，可以对第二预设时间段获取的车辆数据进行统计分析，得到多个工况特征参数的验证数据。
在一个实施例中，基于多个工况参数对零部件状态的预设贡献度，从多个工况参数中筛选出用于反映零部件状态的多个工况特征参数。
可理解的，按照上述多个工况参数对零部件状态中性能的贡献度进行分类排序，筛选出对零部件状态中性能影响较大的用车工况特征参数，即最能反映出零部件状态的工况特征参数，其中，各零部件分别存在对应的一个或多个工况特征参数。
可理解的，验证数据与上述样本数据的获取方式以及计算方式可以相同，基于不同时间段内得到的车辆数据，根据车辆数据筛选确定的多个工况特征参数可能不同。
在步骤S320中，获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第二预设时间段结束后进行车辆保养得到。
可理解的，车辆进行交付后，用户到售后部门对车辆进行保养，售后人员拆解车辆中的各零部件，并对零部件状态进行查验和检测，得到车辆装载第二预设时间段结束后，各零部件对应的多个状态参数，并对检测到的各零部件对应的多个状态参数进行统计和分析，生成反馈数据，并将反馈数据上传至售后系统，服务器12从售后系统中获取到各零部件对应的多个状态参数的反馈数据，其中，在第二预设时间段内，反馈数据与样本数据相对应，即由样本数据间接可以得到反馈数据，样本数据与反馈数据存在对应关系。
在步骤S330中，通过各零部件对应的状态预测模型分别对多个工况特征参数的验证数据进行处理，得到各零部件对应的多个状态参数的预测数据。
可理解的，在上述步骤S310的基础上，通过上述训练完成的状态预测模型对多个工况特征参数的验证数据进行识别，输出各零部件对应的多个状态参数的预测数据。
在步骤S340中，判断预测数据与反馈数据是否匹配，若是，则保存对应的状态预测模型；若否，则根据多个工况特征参数的验证数据以及各零部件对应的多个状态参数的反馈数据，修正对应的状态预测模型。
可理解的，在上述步骤S320和S330的基础上，判断通过训练完成的状态预测模型得到的预测数据与反馈数据是否匹配，即预测数据与验证数据是否在一定范围内相同，若是，则保存当前测试的状态预测模型，预测数据与反馈数据相匹配也表明当前训练完成的状态预测模型的准确率比较高；若否，则根据第二预设时间段内获得的验证数据以及反馈数据对当前测试的状态预测模型进行训练，修正上述用来测试的状态预测模型。
可理解的，根据获取到的不同预设时段的验证数据以及反馈数据，及时修正当前的状态预测模型，以提高状态预测模型的准确率。
本公开实施例提供的一种状态预测模型的训练方法，通过获取多个工况特征参数的验证数据，验证数据基于车辆在第二预设时间段内行驶产生的车辆数据计算得到，获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第二预设时间段结束后进行车辆保养得到，通过各零部件对应的状态预测模型分别对多个工况特征参数的验证数据进行处理，得到各零部件对应的多个状态参数的预测数据，判断预测数据与反馈数据是否匹配，若是，则保存对应的状态预测模型；若否，则根据多个工况特征参数的验证数据以及各零部件对应的多个状态参数的反馈数据，修正对应的状态预测模型。通过对训练完成的状态预测模型进行修正，提高了状态预测模型的准确率，使得状态预测模型的普适性增强，同时也提高了处理效率。
在上述实施例的基础上，图4为本公开实施例提供的一种车辆保养信息的确定方法的流程图，利用上述实施例中训练完成的状态预测模型对车辆数据进行处理，包括图4所示的如下步骤S410至S440。
在步骤S410中，获取车辆数据。
可理解的，服务器12实时接收由车辆11传输的车辆数据。车辆在使用过程中会产生大量的车辆数据，其中，车辆数据可以包括上述的一个或多个工况参数。
可理解的，工况参数可以包括但不限于车速分布、发动机转速分布、发电机转速分布、减速器转速分布、机油温度分布、减速器油温分布、空调使用频率中的一种或多种。
在步骤S420中，根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据。
可理解的，在上述步骤S410的基础上，服务器12对获取的车辆数据进行统计分析，得到与车辆数据对应的多个工况特征参数数据，其中，工况特征参数数据包含在车辆数据即工况参数中，预设工况特征参数的数量与工况特征参数数据的数量对应。
在步骤S430中，通过零部件对应的状态预测模型分别对多个工况特征参数数据进行处理，得到与零部件对应的多个状态参数数据。
可理解的，在上述步骤S420的基础上，通过上述训练完成的状态预测模型，对多个工况特征参数数据进行处理识别，得到与零部件对应的多个状态参数数据。
在步骤S440中，根据零部件对应的多个状态参数数据，确定车辆的保养信息，保养信息包括待保养的零部件以及对应的保养时间。
可理解的，在上述步骤S430的基础上，根据状态预测模型得到的零部件对应的多个状态参数数据，确定向服务器发送车辆数据的车辆的保养信息。
本公开实施例提供的一种车辆保养信息的确定方法，通过获取车辆数据，根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据，通过零部件对应的状态预测模型分别对多个工况特征参数数据进行处理，得到与零部件对应的多个状态参数数据，根据零部件对应的多个状态参数数据，确定车辆的保养信息，保养信息包括待保养的一个或多个零部件以及对应的保养时间；通过实时获取车辆行驶过程中的车辆数据，并根据车辆数据确定当前车辆各零部件的状态，能够实时、快速、准确的确定车辆进行保养的保养信息，确定方法更加智能化，根据保养信息能够及时全面的了解车辆的状态，最大限度的减少资源的浪费，同时加强车辆的安全性，提高用户体验。
在上述实施例的基础上，可选的，对步骤S410获取的车辆数据进行处理，还包括如图5所示的如下步骤S510至S520。
在步骤S510中，确定多个工况参数，工况参数为能够基于车辆数据计算得到的参数。
可理解的，获取车辆传输至服务器的车辆数据，可以统计第一预设时间内的车辆数据，可以通过累计求和计算、比例计算、取差值或均值等方式对获取的车辆数据进行处理，通过统计和计算车辆数据中多个工况的数据，得到多个工况参数。
在步骤S520中，基于多个工况参数对零部件状态的预设贡献度，从多个工况参数中筛选出用于预测零部件状态的多个预设工况特征参数。
可理解的，在上述步骤S510的基础上，按照多个工况参数对零部件状态中性能的贡献度进行分类排序，筛选出对零部件状态中性能影响较大的用车工况特征参数，即最能反映出零部件状态的工况特征参数，作为预设工况特征参数，其中，各零部件分别存在对应的一个或多个工况特征参数，例如，以表1中序号1润滑油为例，车辆行驶过程中对润滑油影响较大的工况特征参数包括：车辆总里程、驾驶员驾驶特性、车速以及车辆载荷，对润滑油影响较大的工况特征参数可能会导致润滑油的状态参数发生相应的变化，例如，工况参数中驾驶员驾驶特性中激烈驾驶的占比比较高，可能会导致润滑油的性能裂化数据即润滑油的粘性下降，也可能会导致制动盘的磨损程度增加等，即根据确定的对润滑油影响较大的工况特征参数，通过状态预测模型可以得到润滑油当前的状态参数数据。
本公开实施例提供的一种车辆保养信息的确定方法，通过确定多个工况参数，工况参数为能够基于车辆数据计算得到的参数，基于多个工况参数对零部件状态的预设贡献度，从多个工况参数中筛选出用于预测零部件状态的多个预设工况特征参数。对获取到的车辆数据进行初步的统计和处理，筛选得到对零部件贡献度即影响较大的多个预设工况特征参数数据，能够减少数据量，最大限度的保存车辆数据的特征，在提高状态预测模型处理速度的同时，也能够确保对零部件状态进行准确的预测。
在上述实施例的基础上，可选的，根据零部件对应的多个状态参数数据，确定车辆的保 养信息，还包括如图6所示的如下步骤S610至S620。
在步骤S610中，获取零部件对应的多个状态参数与保养时间的对应关系。
可理解的，可以根据上述第一预设时间段以及第二预设时间段得到的零部件对应的反馈数据，也就是指车辆行驶过程中获取到的历史车辆数据以及每个预设时间段后对零部件状态进行检测得到的零部件状态参数，建立各零部件对应的多个状态参数与保养时间的对应关系，即通过各零部件的状态确定该零部件的保养时间，其中，保养时间可以是合理的时间范围或是准确的时间段，并将确定的对应关系进行存储。
示例性的，以表1中零部件状态参数为例，若润滑油的性能裂化数据下降30％，可以确定润滑油的保养时间为30天到40天之间，若润滑油的剩余量为90％，则对应的保养时间也会相应的增加；若制动盘的零部件磨损程度达到60％，则制动盘对应的保养时间可能在20天到30天之间，对应关系可以根据用户实际使用车辆的历史工况数据以及历史零部件状态来确定，在此不作限定。
在步骤S620中，根据零部件对应的多个状态参数数据查找对应关系，确定车辆的保养信息。
可理解的，在上述步骤S610的基础上，根据各零部件对应的多个状态参数数据查找相应的对应关系，各零部件的不同状态参数分别对应不同的保养时间，根据对应关系确定给当前车辆的保养信息，其中，保养信息包括待保养的一个或多个零部件以及与零部件对应的保养时间。
在一个实施例中，车辆保养信息的确定方法还包括：向车辆发送保养信息，以使车辆根据保养信息提醒用户待保养的零部件以及对应的保养时间。
可理解的，在上述步骤S620的基础上，服务器12将确定的保养信息发送至车辆11的控制设备，车辆11为发送车辆数据至服务器12的车辆，车辆11的控制设备可以根据保养信息直接提醒用户各零部件的状态以及保养时间。
本公开实施例提供的一种车辆保养信息的确定方法，通过获取各零部件对应的多个状态参数与保养时间的对应关系，根据各零部件对应的多个状态参数数据查找对应关系，确定车辆的保养信息，其中，保养信息包括待保养的一个或多个零部件以及对应的保养时间。根据车辆的历史零部件状态与保养时间确定了对用关系，根据当前车辆中各零部件对应的多个状态参数数据查找对应关系，能够快速确定各零部件对应的保养时间，处理速度比较快，确定的保养信息准确率较高。
图7为本公开实施例提供的一种车辆保养信息的确定装置的结构示意图。本公开实施例提供的一种车辆保养信息的确定装置可以执行一种车辆保养信息的确定方法实施例提供的处理流程，如图7所示，车辆保养信息的确定装置700包括：
获取模块710，用于获取车辆数据；
提取模块720，用于根据车辆数据和多个预设工况特征参数，得到与车辆数据对应的多个工况特征参数数据；
处理模块730，用于通过零部件对应的状态预测模型分别对多个工况特征参数数据进行 处理，得到与零部件对应的多个状态参数数据；
确定模块740，用于根据零部件对应的多个状态参数数据，确定车辆的保养信息，保养信息包括待保养的零部件以及对应的保养时间；
发送模块750，用于向车辆发送保养信息，以使车辆根据保养信息提醒用户待保养的零部件以及保养时间。
在一个实施例中，车辆保养信息的确定装置700还包括：特征模块，用于确定多个工况参数，工况参数为能够基于车辆数据计算得到的参数；基于多个工况参数对零部件状态的预设贡献度，从多个工况参数中筛选出用于预测零部件状态的多个预设工况特征参数。
在一个实施例中，车辆保养信息的确定装置700还包括：训练模块，用于获取多个工况特征参数的样本数据，样本数据基于车辆在第一预设时间段内行驶产生的车辆数据计算得到；获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第一预设时间段结束后进行车辆保养得到；根据多个工况特征参数的样本数据以及各零部件对应的多个状态参数的反馈数据，训练神经网络模型，得到各零部件对应的状态预测模型。
在一个实施例中，提取模块720中多个工况特征参数包括用车环境、车速、车辆载荷、驾驶员驾驶特性、车辆总里程、制动时长、制动距离中的一种或多种。
在一个实施例中，确定模块740中根据零部件对应的多个状态参数数据，确定车辆的保养信息，具体用于：获取零部件对应的多个状态参数与保养时间的对应关系；根据零部件对应的多个状态参数数据查找对应关系，确定车辆的保养信息。
在一个实施例中，确定模块740中多个状态参数包括零部件状态、零部件故障状态、零部件磨损程度、性能裂化数据、零部件剩余量中的一种或多种。
在一个实施例中，训练模块中训练神经网络模型之后，具体用于：获取多个工况特征参数的验证数据，验证数据基于车辆在第二预设时间段内行驶产生的车辆数据计算得到；获取各零部件对应的多个状态参数的反馈数据，反馈数据基于车辆在第二预设时间段结束后进行车辆保养得到；通过各零部件对应的状态预测模型分别对多个工况特征参数的验证数据进行处理，得到各零部件对应的多个状态参数的预测数据；判断预测数据与反馈数据是否匹配，若是，则保存对应的状态预测模型；若否，则根据多个工况特征参数的验证数据以及各零部件对应的多个状态参数的反馈数据，修正对应的状态预测模型。
图7所示实施例的一种车辆保养信息的确定装置可用于执行上述方法实施例的技术方案，其实现原理和技术效果类似，此处不再赘述。
图8为本公开实施例提供的一种车辆保养信息的确定设备的结构示意图。该车辆保养信息的确定设备可以是如上的服务器或车辆。本公开实施例提供的车辆保养信息的确定设备可以执行车辆保养信息的确定方法的实施例提供的处理流程，如图8所示，车辆保养信息的确定设备800包括：处理器810、通讯接口820和存储器830；其中，计算机程序存储在存储器830中，并被配置为由处理器810执行如上述的车辆保养信息的确定方法。
另外，本公开实施例还提供一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行以实现上述实施例的车辆保养信息的确定方法。
此外，本公开实施例还提供了一种计算机程序产品，该计算机程序产品包括计算机程序或指令，该计算机程序或指令被处理器执行时实现如上的车辆保养信息的确定方法。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (15)

  1. 一种车辆保养信息的确定方法，其特征在于，针对车辆的零部件，预先建立所述零部件对应的状态预测模型，所述方法包括：
    获取车辆数据；
    根据所述车辆数据和多个预设工况特征参数，得到与所述车辆数据对应的多个工况特征参数数据；
    通过所述零部件对应的状态预测模型分别对所述多个工况特征参数数据进行处理，得到与所述零部件对应的多个状态参数数据；
    根据所述零部件对应的多个状态参数数据，确定所述车辆的保养信息，所述保养信息包括待保养的零部件以及对应的保养时间。
  2. 根据权利要求1所述的方法，其中所述多个预设工况特征参数通过以下方式确定：
    确定多个工况参数，所述工况参数为能够基于车辆数据计算得到的参数；
    基于所述多个工况参数对零部件状态的预设贡献度，从所述多个工况参数中筛选出用于预测零部件状态的多个预设工况特征参数。
  3. 根据权利要求2所述的方法，其中所述多个工况特征参数包括用车环境、车速、车辆载荷、驾驶员驾驶特性、车辆总里程、制动时长、制动距离中的一种或多种。
  4. 根据权利要求1所述的方法，其中所述根据所述零部件对应的多个状态参数数据，确定所述车辆的保养信息，包括：
    获取零部件对应的多个状态参数与保养时间的对应关系；
    根据所述零部件对应的多个状态参数数据查找所述对应关系，确定所述车辆的保养信息。
  5. 根据权利要求4所述的方法，其中所述多个状态参数包括零部件状态、零部件故障状态、零部件磨损程度、性能裂化数据、零部件剩余量中的一种或多种。
  6. 根据权利要求1所述的方法，其中所述状态预测模型通过以下方式训练得到：
    获取多个工况特征参数的样本数据，所述样本数据基于车辆在第一预设时间段内行驶产生的车辆数据计算得到；
    获取各零部件对应的多个状态参数的反馈数据，所述反馈数据基于车辆在所述第一预设时间段结束后进行车辆保养得到；
    根据所述多个工况特征参数的样本数据以及所述各零部件对应的多个状态参数的反馈数据，训练神经网络模型，得到各零部件对应的状态预测模型。
  7. 根据权利要求6所述的方法，其中所述训练神经网络模型之后，所述方法还包括：
    获取多个工况特征参数的验证数据，所述验证数据基于车辆在第二预设时间段内行驶产生的车辆数据计算得到；
    获取各零部件对应的多个状态参数的反馈数据，所述反馈数据基于车辆在所述第二 预设时间段结束后进行车辆保养得到；
    通过所述各零部件对应的状态预测模型分别对所述多个工况特征参数的验证数据进行处理，得到各零部件对应的多个状态参数的预测数据；
    判断所述预测数据与所述反馈数据是否匹配，若是，则保存对应的状态预测模型；若否，则根据所述多个工况特征参数的验证数据以及所述各零部件对应的多个状态参数的反馈数据，修正对应的状态预测模型。
  8. 根据权利要求1-7任一项所述的方法，其中所述方法还包括：
    向所述车辆发送所述保养信息，以使所述车辆根据所述保养信息提醒用户待保养的零部件以及对应的保养时间。
  9. 一种车辆保养信息的确定装置，包括：
    获取模块，用于获取车辆数据；
    提取模块，用于根据所述车辆数据和多个预设工况特征参数，得到与所述车辆数据对应的多个工况特征参数数据，其中，所述预设工况特征参数的数量与所述工况特征参数数据的数量对应；
    处理模块，用于通过所述零部件对应的状态预测模型分别对所述多个工况特征参数数据进行处理，得到与所述零部件对应的多个状态参数数据；
    确定模块，用于根据所述零部件对应的多个状态参数数据，确定所述车辆的保养信息，所述保养信息包括待保养的零部件以及对应的保养时间。
  10. 根据权利要求9所述的装置，其中所述装置还包括：
    发送模块，用于向所述车辆发送所述保养信息，以使所述车辆根据所述保养信息提醒用户待保养的零部件以及对应的保养时间。
  11. 根据权利要求9所述的装置，其中所述装置还包括：
    特征模块，用于确定多个工况参数，所述工况参数为能够基于车辆数据计算得到的参数；基于所述多个工况参数对零部件状态的预设贡献度，从所述多个工况参数中筛选出用于预测零部件状态的多个预设工况特征参数。
  12. 根据权利要求9所述的装置，其中所述装置还包括：
    训练模块，用于获取多个工况特征参数的样本数据，所述样本数据基于车辆在第一预设时间段内行驶产生的车辆数据计算得到；获取各零部件对应的多个状态参数的反馈数据，所述反馈数据基于车辆在所述第一预设时间段结束后进行车辆保养得到；根据所述多个工况特征参数的样本数据以及所述各零部件对应的多个状态参数的反馈数据，训练神经网络模型，得到各零部件对应的状态预测模型。
  13. 根据权利要求9所述的装置，其中所述确定模块还用于：获取零部件对应的多个状态参数与保养时间的对应关系；根据所述零部件对应的多个状态参数数据查找所述对应关系，确定所述车辆的保养信息。
  14. 一种车辆保养信息的确定设备，包括：
    存储器；
    处理器；以及
    计算机程序；
    其中，所述计算机程序存储在所述存储器中，并被配置为由所述处理器执行以实现如权利要求1-8中任一所述的方法。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其中所述计算机程序被处理器执行时实现如权利要求1-8中任一项所述的方法。
PCT/CN2022/076917 2021-05-13 2022-02-18 车辆保养信息的确定方法、装置、设备及介质 WO2022237266A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110520811.4A CN113221457B (zh) 2021-05-13 2021-05-13 一种车辆保养信息的确定方法、装置、设备及介质
CN202110520811.4 2021-05-13

Publications (1)

Publication Number Publication Date
WO2022237266A1 true WO2022237266A1 (zh) 2022-11-17

Family

ID=77095635

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/076917 WO2022237266A1 (zh) 2021-05-13 2022-02-18 车辆保养信息的确定方法、装置、设备及介质

Country Status (2)

Country Link
CN (1) CN113221457B (zh)
WO (1) WO2022237266A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113221457B (zh) * 2021-05-13 2024-06-14 北京车和家信息技术有限公司 一种车辆保养信息的确定方法、装置、设备及介质
CN115086377B (zh) * 2022-06-29 2023-05-23 东风商用车有限公司 基于大数据的机油保养地点预测方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108068730A (zh) * 2016-11-08 2018-05-25 大陆汽车投资（上海）有限公司 用于提醒车辆保养的方法和车辆保养提醒系统
CN111368366A (zh) * 2018-12-06 2020-07-03 比亚迪股份有限公司 车辆零部件健康状态分析的方法和装置、及存储介质
US20200377123A1 (en) * 2019-05-29 2020-12-03 CEO Vision, Inc (dba Croquet Studios) Systems and methods for vehicle flocking for improved safety and traffic optimization
CN112785016A (zh) * 2021-02-20 2021-05-11 南京领行科技股份有限公司 基于机器学习的新能源汽车保养维护与故障监测诊断方法
CN113221457A (zh) * 2021-05-13 2021-08-06 北京车和家信息技术有限公司 一种车辆保养信息的确定方法、装置、设备及介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102320382A (zh) * 2011-07-07 2012-01-18 中国国际航空股份有限公司 飞机性能检测方法
CN104627065B (zh) * 2013-11-11 2017-02-08 比亚迪股份有限公司 车辆保养提示方法和系统
CN105270293A (zh) * 2015-06-24 2016-01-27 广州爱亿信息科技有限公司 一种基于云服务的车辆保养提醒方法及其车载终端装置
CN111667604B (zh) * 2020-06-10 2022-04-26 上海安吉星信息服务有限公司 一种车辆保养信息的处理方法、装置和电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108068730A (zh) * 2016-11-08 2018-05-25 大陆汽车投资（上海）有限公司 用于提醒车辆保养的方法和车辆保养提醒系统
CN111368366A (zh) * 2018-12-06 2020-07-03 比亚迪股份有限公司 车辆零部件健康状态分析的方法和装置、及存储介质
US20200377123A1 (en) * 2019-05-29 2020-12-03 CEO Vision, Inc (dba Croquet Studios) Systems and methods for vehicle flocking for improved safety and traffic optimization
CN112785016A (zh) * 2021-02-20 2021-05-11 南京领行科技股份有限公司 基于机器学习的新能源汽车保养维护与故障监测诊断方法
CN113221457A (zh) * 2021-05-13 2021-08-06 北京车和家信息技术有限公司 一种车辆保养信息的确定方法、装置、设备及介质

Also Published As

Publication number Publication date
CN113221457A (zh) 2021-08-06
CN113221457B (zh) 2024-06-14

Similar Documents

Publication Publication Date Title
WO2022237266A1 (zh) 车辆保养信息的确定方法、装置、设备及介质
CN111241154B (zh) 一种基于大数据的蓄电池故障预警方法及系统
WO2019153487A1 (zh) 系统性能的度量方法、装置、存储介质和服务器
CN103617110A (zh) 服务器设备状态检修系统
CN108345670B (zh) 一种用于95598电力工单的服务热点发现方法
CN103778050B (zh) 一种数据库服务器高可用性能检测系统
CN112561289A (zh) 一种能源管理体系认证中的能源绩效集成验证方法
CN103577882A (zh) 一种基于uml的量化项目资源控制方法
CN115221218A (zh) 车辆数据的质量评估方法、装置、计算机设备和存储介质
CN111311044A (zh) 一种车辆定损方法及其系统
CN115114124A (zh) 主机风险的评估方法及评估装置
CN110826827B (zh) 基于能源互联网的企业在线能源审计系统及方法
CN107870848A (zh) Cpu性能冲突的检测方法、装置和系统
US20220099474A1 (en) Vehicle Fuel Volume Consumption Estimation And Accuracy Analysis Systems And Methods
CN114884813A (zh) 一种网络架构确定方法、装置、电子设备及存储介质
CN114419894A (zh) 一种路内停车泊位设置与使用监测的方法与系统
CN112699490A (zh) 一种车辆维修结果验证方法和装置
CN110596540A (zh) 基于实时数据驱动的电量异常在线分析检测方法和装置
WO2020107142A1 (zh) 一种软件质量度量方法及系统
CN112734144A (zh) 驾驶行为评估方法、装置、存储介质和计算机设备
CN116861199B (zh) 一种燃油清净增效剂的减排测评方法、设备和存储介质
CN116611819B (zh) 空调压缩机故障预测方法、系统、终端设备及存储介质
CN116227999B (zh) 市场监管软件运维服务质量评价指标定量测算系统及方法
KR102445622B1 (ko) 클라우드를 이용한 차량 연료 분석 시스템
CN112734173B (zh) 电梯部件生产者评价系统与评价方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22806243

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 18.04.2024)