Vehicle energy consumption analysis method and device, computer equipment and storage medium

Abstract

The invention relates to a vehicle energy consumption analysis method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring target vehicle driving data of a target vehicle in a driving process; wherein the target vehicle driving data at least comprise total mass, gradient and vehicle speed data of the target vehicle; inputting the target vehicle driving data into the target energy consumption analysis model to obtain target energy consumption data of the target vehicle in the driving process; and under the condition that the target energy consumption data exceeds a preset threshold value, providing driving behavior guidance for a driver driving the target vehicle so as to reduce the target energy consumption data of the target vehicle. According to the scheme, the target energy consumption analysis model is adopted, the energy consumption data of the target vehicle can be analyzed in real time based on the driving data of the target vehicle, and the real-time performance of vehicle energy consumption analysis is improved compared with a laboratory test or field test mode.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a vehicle energy consumption analysis method, device, computer equipment and storage medium. Background Art

[0002] Commercial vehicles are vehicles designed specifically for commercial purposes, including vehicles that transport people, goods, or provide professional services. Due to the high frequency of use and long driving distance of commercial vehicles during transportation, they are often accompanied by high energy consumption. Therefore, how to analyze the causes of high energy consumption during the use of commercial vehicles is of great significance to reducing energy consumption.

[0003] In traditional technology, laboratory testing or field testing is usually used to evaluate the energy consumption of commercial vehicles. However, this method has the problem of real-time analysis of energy consumption. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle energy consumption analysis method, device, computer equipment and storage medium to address the above technical problems, which can improve the real-time performance of vehicle energy consumption analysis.

[0005] In a first aspect, the present application provides a vehicle energy consumption analysis method, the method comprising:

[0006] Acquire target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes total mass, slope and vehicle speed data of the target vehicle;

[0007] Inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving;

[0008] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to a driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0009] In one embodiment, providing driving behavior guidance to a driver of the target vehicle includes:

[0010] Acquire at least one reference vehicle driving data in the historical vehicle driving data having the same total mass and slope as the target vehicle in the target vehicle driving data;

[0011] Determine the historical energy consumption data corresponding to the driving data of each reference vehicle;

[0012] Using historical vehicle speed data corresponding to historical energy consumption data lower than the target energy consumption data as a driving behavior guide;

[0013] Providing driving behavior guidance to a driver of the target vehicle.

[0014] In one embodiment, when there are at least two historical energy consumption data lower than the target energy consumption data, using the historical vehicle speed data corresponding to the historical energy consumption data lower than the target energy consumption data as the driving behavior guidance includes:

[0015] Obtaining environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data;

[0016] Determine the matching degree between the environmental data corresponding to the target vehicle driving data and the environmental data corresponding to each historical energy consumption data lower than the target energy consumption data;

[0017] The historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest matching degree is used as a guide for driving behavior.

[0018] In one embodiment, the target energy consumption analysis model is trained in the following manner:

[0019] Acquire candidate sample data; wherein the candidate sample data includes multi-dimensional data and energy consumption data of the sample vehicle; wherein the multi-dimensional data includes at least engine data, vehicle speed data, throttle data, slope, total mass, gravity acceleration and vehicle resistance data;

[0020] According to the correlation between each dimension data and energy consumption data in the candidate sample data, the total mass, slope, speed data and energy consumption data of the sample vehicle are used as target sample data;

[0021] The target sample data is input into the initial energy consumption analysis model for training to obtain the target energy consumption analysis model.

[0022] In one embodiment, before inputting the target sample data into the initial energy consumption analysis model for training, the method further includes:

[0023] Inputting the target sample data into an anomaly detection model to obtain a data score corresponding to the target sample data;

[0024] If the data score of the target sample data is an outlier, the target sample data is discarded;

[0025] If the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0026] In one of the embodiments, the target energy consumption analysis model is at least one of an extreme gradient boosting model, a support vector machine model, and a decision tree model.

[0027] In a second aspect, the present application also provides a vehicle energy consumption analysis device, the device comprising:

[0028] An acquisition module, used to acquire target vehicle driving data during the driving process of the target vehicle; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle;

[0029] An analysis module, used for inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving;

[0030] The guidance module is used to provide driving behavior guidance to the driver of the target vehicle when the target energy consumption data exceeds a preset threshold value, so as to reduce the target energy consumption data of the target vehicle.

[0031] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0032] Acquire target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes total mass, slope and vehicle speed data of the target vehicle;

[0033] Inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving;

[0034] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to a driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0036] Acquire target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes total mass, slope and vehicle speed data of the target vehicle;

[0037] Inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving;

[0038] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to a driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0039] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0040] Acquire target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes total mass, slope and vehicle speed data of the target vehicle;

[0041] Inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving;

[0042] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to a driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0043] The above-mentioned vehicle energy consumption analysis method, device, computer equipment and storage medium obtain the target vehicle driving data of the target vehicle during the driving process; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle; and input the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during the driving process; when the target energy consumption data exceeds a preset threshold, provide driving behavior guidance to the driver of the target vehicle to reduce the target energy consumption data of the target vehicle. In the above scheme, the target energy consumption analysis model is adopted, and the energy consumption data of the target vehicle can be analyzed in real time based on the target vehicle driving data, which improves the real-time performance of the vehicle energy consumption analysis compared to the laboratory test or field test method. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of a process flow of a vehicle energy consumption analysis method in one embodiment;

[0045] Figure 2 A schematic diagram of a process for providing driving behavior guidance to a driver in one embodiment;

[0046] Figure 3 A schematic diagram of a process for determining driving behavior guidance in one embodiment;

[0047] Figure 4 A schematic diagram of a process for obtaining a target energy consumption analysis model in an embodiment;

[0048] Figure 5 A schematic diagram of a process for determining abnormal sample data in one embodiment;

[0049] Figure 6 A schematic diagram of a process flow of a vehicle energy consumption analysis method in another embodiment;

[0050] Figure 7is a structural block diagram of a vehicle energy consumption analysis device in one embodiment;

[0051] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The vehicle energy consumption analysis method provided in the embodiment of the present application can be applied to analyze the energy consumption data of commercial vehicles. The method can be executed by a server or by a terminal with a certain computing power. Among them, the server can be implemented by an independent server or a server cluster composed of multiple servers. Terminal 1 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0054] In one embodiment, Figure 1 As shown, a vehicle energy consumption analysis method is provided, which is described by taking the method applied to a server as an example, and includes the following steps:

[0055] S101, obtaining target vehicle driving data during the driving process of the target vehicle.

[0056] Exemplarily, the target vehicle can be any model of vehicle, for example, any model of commercial vehicle. Due to the high frequency of use and long driving distance of commercial vehicles during transportation, they are often accompanied by high energy consumption. Therefore, the method provided in the embodiment of the present application can be used to analyze whether the energy consumption of commercial vehicles is too high, and then analyze the reasons for the high energy consumption, so as to save energy.

[0057] Exemplarily, the target vehicle driving data collected by the Internet of Vehicles device in the target vehicle during the driving process can be obtained, wherein the target vehicle driving data at least includes the total mass, slope and vehicle speed data of the target vehicle; the vehicle speed data may include the vehicle's driving speed and acceleration data.

[0058] Optionally, the acquired target vehicle data may be vehicle driving data corresponding to a period of time or a distance, or may be vehicle data obtained in real time.

[0059] S102, inputting the target vehicle driving data into a target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving.

[0060] Exemplarily, the target energy consumption analysis model is a model pre-trained based on sample vehicle driving data, for example, it can be at least one of an extreme gradient boosting model (Extreme Gradient Boosting, XGBoost), a support vector machine model and a decision tree model.

[0061] S103, when the target energy consumption data exceeds a preset threshold, providing driving behavior guidance to the driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0062] Exemplarily, the preset threshold value can be set according to different vehicle models and empirical data to indicate a high critical value of the energy consumption data.

[0063] When the target energy consumption data exceeds a preset threshold, driving behavior guidance can be provided to the driver of the target vehicle, wherein the driving behavior guidance can be prompt information for adjusting the vehicle's driving data, for example, it can be information prompting to adjust the vehicle speed data, acceleration data, or the mass of the vehicle's load, so as to provide driving behavior guidance to the driver of the target vehicle and achieve the purpose of saving energy.

[0064] The above-mentioned vehicle energy consumption analysis method obtains the target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle; and inputs the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving; when the target energy consumption data exceeds a preset threshold, provides driving behavior guidance to the driver of the target vehicle to reduce the target energy consumption data of the target vehicle. In the above scheme, the target energy consumption analysis model is adopted, and the energy consumption data of the target vehicle can be analyzed in real time based on the target vehicle driving data, which improves the real-time performance of the vehicle energy consumption analysis compared with the laboratory test or field test method.

[0065] In some optional implementations, see Figure 2 , Figure 2 A flow chart of providing driving behavior guidance to a driver of a target vehicle is provided, which specifically includes the following steps:

[0066] S201, obtaining at least one reference vehicle driving data in the historical vehicle driving data having the same total mass and slope as the target vehicle in the target vehicle driving data.

[0067] Exemplarily, the acquired historical vehicle driving data and its corresponding historical energy consumption data can be stored in a database in advance, and the historical vehicle driving data can be acquired in the database, and at least one reference vehicle driving data having the same total mass and slope as the target vehicle in the target vehicle driving data can be screened out from the historical vehicle driving data, that is, the total mass of the vehicle in the reference vehicle driving data is the same as the total mass in the target vehicle driving data, and the slope in the reference vehicle driving data is the same as the slope in the target vehicle driving data.

[0068] S202, determining the historical energy consumption data corresponding to the driving data of each reference vehicle.

[0069] Furthermore, historical energy consumption data corresponding to each reference vehicle driving data may be determined in the database.

[0070] S203: Use historical vehicle speed data corresponding to historical energy consumption data that is lower than the target energy consumption data as a driving behavior guide.

[0071] Furthermore, historical vehicle driving data corresponding to historical energy consumption data that is lower than the target energy consumption data is determined, and historical vehicle speed data in the historical vehicle driving data is used as a driving behavior guide to guide the driver to adjust the speed data and acceleration data of the target vehicle according to the historical vehicle speed data.

[0072] S204: providing driving behavior guidance to the driver of the target vehicle.

[0073] Exemplarily, the prompt may be given in the form of a voice prompt, or a question prompt message suggesting adjustment to historical vehicle speed data may be displayed on a display screen, or the prompt may be given in the form of a combination of a voice prompt and a text prompt.

[0074] In an embodiment of the present application, in the historical vehicle driving data, when the vehicle mass is the same as the target vehicle driving data and the vehicle is at the same slope, a reasonable vehicle speed data is provided to the driver, which can reduce the energy consumption of the target vehicle and improve energy utilization.

[0075] Further, see Figure 3 , Figure 3 A schematic diagram of a process for determining driving behavior guidance is provided, which specifically includes the following steps:

[0076] S301, obtaining environmental data corresponding to target vehicle driving data and environmental data corresponding to each historical energy consumption data lower than the target energy consumption data.

[0077] It should be noted that the energy consumption data of the target vehicle is affected by many factors, such as road congestion and weather data. Therefore, when there are at least two historical energy consumption data lower than the target energy consumption data, the environmental data corresponding to the target vehicle's driving data can be obtained, including road congestion data and weather data, as well as environmental data corresponding to each historical energy consumption data lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data.

[0078] S302, determining a matching degree between environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data lower than the target energy consumption data.

[0079] It should be noted that different energy consumption data are caused by different vehicle speed data under the same vehicle mass and slope, and the same road congestion data and weather data. Therefore, it is necessary to determine the matching degree between the road congestion data and weather data corresponding to the target vehicle driving data and the road congestion data and weather data corresponding to each historical energy consumption data lower than the target energy consumption data.

[0080] S303: Use the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest matching degree as a driving behavior guide.

[0081] Furthermore, the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest matching degree may be used as a driving behavior guide, so as to more accurately reduce the energy consumption data of the target vehicle.

[0082] In the embodiment of the present application, in the process of determining driving behavior guidance, the influence of road congestion data and weather data on energy consumption data is eliminated, which can provide more reasonable historical vehicle speed data, and thus can more accurately reduce vehicle energy consumption data.

[0083] In some optional implementations, see Figure 4 , Figure 4 A schematic diagram of a process for obtaining a target energy consumption analysis model is provided, which specifically includes the following steps:

[0084] S401, obtaining candidate sample data.

[0085] Exemplarily, the candidate sample data may be multidimensional data that may be related to the energy consumption data of the vehicle. For example, the candidate sample data includes multidimensional data and energy consumption data of the sample vehicle, and the multidimensional data includes but is not limited to the engine data, vehicle speed data, throttle data, slope, total mass, gravity acceleration, vehicle resistance data and altitude data of the sample vehicle. Among them, the sample vehicle is a vehicle of the same model as the target vehicle; the engine data includes but is not limited to the engine type, engine speed and engine torque; the vehicle resistance data includes but is not limited to the mechanical efficiency of the transmission system, the wheel rolling radius, the vehicle rolling resistance coefficient, the vehicle frontal area, and the vehicle air resistance coefficient. Similarly, the vehicle networking equipment in the sample vehicle can be obtained to collect candidate sample data, and the collection frequency can be 1HZ.

[0086] It should be noted that the gross vehicle weight and slope in the candidate sample data need to be calculated based on other candidate sample data. For example, the slope data can be calculated using altitude data. In order to ensure the accuracy of the calculation, the altitude signal needs to be filtered first. The filtering process usually removes high-frequency noise and useless information in the data through a filtering algorithm. Then, the slope information can be calculated based on the filtered altitude data. The slope information can be obtained by calculating the ratio of the difference in altitude between adjacent moments to the horizontal distance between the two moments.

[0087] The calculation of the total mass can be done by combining vehicle speed data, engine speed, engine torque, etc. First, these data also need to be processed to remove noise and interference. Then, based on the principles of mechanics and the vehicle's dynamics model, the relationship between these data and the total mass of the vehicle can be established. For example, the vehicle's dynamics equation can be used to estimate the vehicle's traction or resistance through parameters such as vehicle speed data, engine speed, and engine torque. Combined with information such as the vehicle's driving status and road conditions, the total mass of the vehicle can be calculated.

[0088] Optionally, the vehicle speed data in the candidate sample data includes vehicle speed and vehicle acceleration, wherein the vehicle speed includes the global positioning system (GPS) speed and the instrument speed. When the GPS speed is <5km / h, the instrument speed is used to correct the GPS speed, that is, the instrument speed value is used to replace the GPS speed value; in other cases, the GPS speed value is used as the vehicle speed data. The vehicle acceleration can be calculated based on the vehicle speed data at at least two moments.

[0089] Exemplarily, after the candidate sample data are acquired, the candidate sample data may be cleaned and preprocessed, for example, duplicate values, null values, and abnormal values ​​may be removed.

[0090] Furthermore, the data can be preprocessed by dividing the obtained candidate sample data according to the travel distance, for example, dividing it into sections of 10 kilometers each, and taking the candidate sample data corresponding to a section as a group of sample data. Alternatively, the candidate sample data may not be divided, and the candidate sample data at each moment may be taken as a group of data.

[0091] S402, based on the correlation between the data of each dimension and the energy consumption data in the candidate sample data, the total mass, slope, speed data and energy consumption data of the sample vehicle are used as target sample data.

[0092] Furthermore, according to the correlation between each dimension data and energy consumption data in the candidate sample data, the total mass, slope, speed data and energy consumption data of the sample vehicle can be used as the target sample data. The correlation between each dimension data and energy consumption data in the candidate sample data can be constructed in the following way:

[0093]

[0094] Among them, X is a certain dimension data in the candidate sample data, and Y is the energy consumption data in the candidate sample data; X i is the i-th data in a set of dimensional data; Y i is the i-th energy consumption data in a set of energy consumption data; n is the number of data in a set of candidate sample data; is the average value of a set of n-dimensional data; is the average value of a group of n energy consumption data. is the covariance.

[0095] If the covariance is positive, it means that the change trends of the two variables are consistent and the two variables are positively correlated; if the covariance is equal to 0, it means that the two variables are independent of each other and the two variables are uncorrelated. After calculation, the covariance calculated from the total mass, slope, speed data and energy consumption data of the sample vehicle is positive, so the total mass, slope, speed data and energy consumption data of the sample vehicle are used as the target sample data.

[0096] S403: Input the target sample data into the initial energy consumption analysis model for training to obtain a target energy consumption analysis model.

[0097] Furthermore, the target sample data is input into the initial energy consumption analysis model for training. For example, the model evaluation indicators include mean square error (MSE), root mean square error (RMSE) and determination coefficient (R-squared, R²). MSE calculates the mean of the sum of squares of the errors of the sample points corresponding to the fitted data and the original data. The smaller the value, the better the model fitting effect. RMSE is the square root of MSE. The smaller the value, the higher the model accuracy. The R² value range is [0,1]. The closer the result is to 1, the higher the model accuracy.

[0098] The model parameters are optimized based on the model evaluation index, that is, based on the comprehensive evaluation of the three evaluation indicators of MSE, RMSE and R², the model parameters with the best results are saved to obtain the target energy consumption analysis model.

[0099] In an embodiment of the present application, in the process of training the target energy consumption analysis model, sample data related to vehicle energy consumption data can be first determined, and then the target energy consumption analysis model can be trained using the sample data, which can improve the accuracy of energy consumption data analysis of the target energy consumption analysis model.

[0100] Furthermore, before inputting the target sample data into the initial energy consumption analysis model for training, abnormal sample data may be removed first to avoid the influence of the abnormal sample data on the model training.

[0101] For example, see Figure 5 , Figure 5 A flowchart for determining abnormal sample data is provided, which specifically includes the following steps:

[0102] S501, input the target sample data into the anomaly detection model to obtain the data score corresponding to the target sample data.

[0103] Exemplarily, the target sample data can be input into the anomaly detection model to obtain the data score corresponding to the target sample data. The anomaly detection model can be a pre-trained model for identifying abnormal sample data, such as an isolation forest model. An anomaly detection model can be constructed using an isolation forest algorithm. The isolation forest algorithm is an anomaly detection method based on ensemble learning, which identifies anomalies in the data by constructing multiple isolation trees. The basic principle of the algorithm is that outliers are usually easier to isolate, that is, they are separated at a shallow depth in the decision tree.

[0104] S502: If the data score of the target sample data is an outlier, the target sample data is discarded.

[0105] Furthermore, if the data score of the target sample data is an outlier, where the outlier value is a preset threshold, such as -1, it means that the target sample data is abnormal, which will affect the model training results and the target sample data needs to be discarded.

[0106] S503: If the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0107] Furthermore, if the data score of the target sample data is a normal value, where normal is a pre-established threshold value, for example, it can be set to 1, it means that there is no problem with the target sample data, and the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0108] In the embodiment of the present application, by eliminating abnormal target sample data, the influence of abnormal sample data on model training can be avoided, thereby improving the accuracy of the target energy consumption analysis model.

[0109] In some optional implementations, see Figure 6 , Figure 6 A flow chart of another vehicle energy consumption analysis method is provided, which specifically includes the following steps:

[0110] S601, obtaining target vehicle driving data during the driving process of the target vehicle.

[0111] S602: Input the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during the driving process.

[0112] S603, when the target energy consumption data exceeds a preset threshold, obtaining at least one reference vehicle driving data in the historical vehicle driving data having the same total mass and slope as the target vehicle in the target vehicle driving data.

[0113] S604, determining the historical energy consumption data corresponding to the driving data of each reference vehicle.

[0114] S605, obtaining environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data lower than the target energy consumption data.

[0115] S606, determining a matching degree between environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data lower than the target energy consumption data.

[0116] S607: Use the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest matching degree as a driving behavior guide.

[0117] S608: Providing driving behavior guidance to the driver of the target vehicle to reduce target energy consumption data of the target vehicle.

[0118] In the embodiments of the present application, a machine learning method is used to construct an energy consumption analysis model for the Internet of Vehicles big data. From the perspective of the Internet of Vehicles big data application, an energy consumption baseline can be established according to the actual operating conditions of the vehicle, and it can adapt to the complexity and diversity of the operating conditions of commercial vehicles; and an isolation forest algorithm is used to identify and remove outliers in the data set, thereby improving the generalization ability and accuracy of the vehicle high energy consumption identification method, which can be widely used in various vehicle models.

[0119] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0120] Based on the same inventive concept, the embodiment of the present application also provides a vehicle energy consumption analysis device for implementing the vehicle energy consumption analysis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle energy consumption analysis device embodiments provided below can refer to the limitations of the vehicle energy consumption analysis method above, and will not be repeated here.

[0121] In one embodiment, Figure 7 As shown, a vehicle energy consumption analysis device is provided, comprising:

[0122] The acquisition module 10 is used to acquire the target vehicle driving data during the driving process of the target vehicle; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle;

[0123] The analysis module 20 is used to input the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving;

[0124] The guidance module 30 is used to provide driving behavior guidance to the driver of the target vehicle when the target energy consumption data exceeds a preset threshold, so as to reduce the target energy consumption data of the target vehicle.

[0125] The above-mentioned vehicle energy consumption analysis device obtains the target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle; and inputs the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving; when the target energy consumption data exceeds a preset threshold, the driver of the target vehicle is provided with driving behavior guidance to reduce the target energy consumption data of the target vehicle. In the above scheme, the target energy consumption analysis model is adopted, and the energy consumption data of the target vehicle can be analyzed in real time based on the target vehicle driving data, which improves the real-time performance of the vehicle energy consumption analysis compared with the laboratory test or field test method.

[0126] In one embodiment, the guidance module 30 specifically includes:

[0127] An acquisition unit, used for acquiring at least two reference vehicle driving data having the same total mass and slope as the target vehicle in the target vehicle driving data in the historical vehicle driving data;

[0128] A first determining unit, used to determine the historical energy consumption data corresponding to the driving data of each reference vehicle;

[0129] A second determination unit is used to use historical vehicle speed data corresponding to historical energy consumption data lower than the target energy consumption data as a driving behavior guide;

[0130] The guidance unit is used to provide driving behavior guidance to a driver driving the target vehicle.

[0131] In one of the embodiments, when there are at least two historical energy consumption data lower than the target energy consumption data, the second determining unit is specifically configured to:

[0132] Obtain environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data; determine the degree of match between the environmental data corresponding to the target vehicle driving data and the environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; and use the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest degree of match as a guide for driving behavior.

[0133] In one embodiment, the device further comprises a training module for:

[0134] Acquire candidate sample data; wherein the candidate sample data includes multi-dimensional data and energy consumption data of the sample vehicle; wherein the multi-dimensional data includes at least engine data, vehicle speed data, throttle data, slope, total mass, gravitational acceleration and vehicle resistance data; according to the correlation between each dimensional data and the energy consumption data in the candidate sample data, the total mass, slope, vehicle speed data and energy consumption data of the sample vehicle are used as target sample data; the target sample data are input into the initial energy consumption analysis model for training to obtain the target energy consumption analysis model.

[0135] In one embodiment, the device further comprises a detection module, which is used to:

[0136] The target sample data is input into the anomaly detection model to obtain the data score corresponding to the target sample data; if the data score of the target sample data is an outlier, the target sample data is discarded; if the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0137] In one of the embodiments, the target energy consumption analysis model is at least one of an extreme gradient boosting model, a support vector machine model, and a decision tree model.

[0138] Each module in the above-mentioned vehicle energy consumption analysis device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0139] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data for energy consumption analysis. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle energy consumption analysis method is implemented.

[0140] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0141] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0142] Acquire target vehicle driving data during the driving process of the target vehicle; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle;

[0143] Inputting the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving;

[0144] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to the driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] Acquire at least two reference vehicle driving data in the historical vehicle driving data that have the same total mass and slope as the target vehicle in the target vehicle driving data; determine the historical energy consumption data corresponding to each reference vehicle driving data; use the historical vehicle speed data corresponding to the historical energy consumption data that is lower than the target energy consumption data as driving behavior guidance; and provide driving behavior guidance to the driver of the target vehicle.

[0147] In one embodiment, when there are at least two historical energy consumption data lower than the target energy consumption data, the processor further implements the following steps when executing the computer program:

[0148] Obtain environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data; determine the degree of match between the environmental data corresponding to the target vehicle driving data and the environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; and use the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest degree of match as a guide for driving behavior.

[0149] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0150] Acquire candidate sample data; wherein the candidate sample data includes multi-dimensional data and energy consumption data of the sample vehicle; wherein the multi-dimensional data includes at least engine data, vehicle speed data, throttle data, slope, total mass, gravitational acceleration and vehicle resistance data;; according to the correlation between each dimensional data and the energy consumption data in the candidate sample data, the total mass, slope, vehicle speed data and energy consumption data of the sample vehicle are used as target sample data; the target sample data are input into the initial energy consumption analysis model for training to obtain the target energy consumption analysis model.

[0151] In one embodiment, before inputting the target sample data into the initial energy consumption analysis model for training, the processor further implements the following steps when executing the computer program:

[0152] The target sample data is input into the anomaly detection model to obtain the data score corresponding to the target sample data; if the data score of the target sample data is an outlier, the target sample data is discarded; if the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0153] In one embodiment, the target energy consumption analysis model is at least one of an extreme gradient boosting model, a support vector machine model, and a decision tree model.

[0154] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0155] Acquire target vehicle driving data during the driving process of the target vehicle; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle;

[0156] Inputting the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving;

[0157] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to the driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0159] Acquire at least one reference vehicle driving data in the historical vehicle driving data that has the same total mass and slope as the target vehicle in the target vehicle driving data; determine the historical energy consumption data corresponding to each reference vehicle driving data; use the historical vehicle speed data corresponding to the historical energy consumption data that is lower than the target energy consumption data as driving behavior guidance; and provide driving behavior guidance to the driver of the target vehicle.

[0160] In one embodiment, when there are at least two historical energy consumption data lower than the target energy consumption data, the computer program further implements the following steps when executed by the processor:

[0161] Obtain environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data; determine the degree of match between the environmental data corresponding to the target vehicle driving data and the environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; and use the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest degree of match as a guide for driving behavior.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0163] Acquire candidate sample data; wherein the candidate sample data includes multi-dimensional data and energy consumption data of the sample vehicle; wherein the multi-dimensional data includes at least engine data, vehicle speed data, throttle data, slope, total mass, gravitational acceleration and vehicle resistance data;; according to the correlation between each dimensional data and the energy consumption data in the candidate sample data, the total mass, slope, vehicle speed data and energy consumption data of the sample vehicle are used as target sample data; the target sample data are input into the initial energy consumption analysis model for training to obtain the target energy consumption analysis model.

[0164] In one embodiment, before inputting the target sample data into the initial energy consumption analysis model for training, the computer program further implements the following steps when executed by the processor:

[0165] The target sample data is input into the anomaly detection model to obtain the data score corresponding to the target sample data; if the data score of the target sample data is an outlier, the target sample data is discarded; if the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0166] In one embodiment, the target energy consumption analysis model is at least one of an extreme gradient boosting model, a support vector machine model, and a decision tree model.

[0167] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0168] Acquire target vehicle driving data during the driving process of the target vehicle; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle;

[0169] Inputting the target vehicle driving data into the target energy consumption analysis model to obtain the target energy consumption data of the target vehicle during driving;

[0170] When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to the driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0172] Acquire at least one reference vehicle driving data in the historical vehicle driving data that has the same total mass and slope as the target vehicle in the target vehicle driving data; determine the historical energy consumption data corresponding to each reference vehicle driving data; use the historical vehicle speed data corresponding to the historical energy consumption data that is lower than the target energy consumption data as driving behavior guidance; and provide driving behavior guidance to the driver of the target vehicle.

[0173] In one embodiment, when there are at least two historical energy consumption data lower than the target energy consumption data, the computer program further implements the following steps when executed by the processor:

[0174] Obtain environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data; determine the degree of match between the environmental data corresponding to the target vehicle driving data and the environmental data corresponding to each historical energy consumption data that is lower than the target energy consumption data; and use the historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest degree of match as a guide for driving behavior.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0176] Acquire candidate sample data; wherein the candidate sample data includes multi-dimensional data and energy consumption data of the sample vehicle; wherein the multi-dimensional data includes at least engine data, vehicle speed data, throttle data, slope, total mass, gravitational acceleration and vehicle resistance data;; according to the correlation between each dimensional data and the energy consumption data in the candidate sample data, the total mass, slope, vehicle speed data and energy consumption data of the sample vehicle are used as target sample data; the target sample data are input into the initial energy consumption analysis model for training to obtain the target energy consumption analysis model.

[0177] In one embodiment, before inputting the target sample data into the initial energy consumption analysis model for training, the computer program further implements the following steps when executed by the processor:

[0178] The target sample data is input into the anomaly detection model to obtain the data score corresponding to the target sample data; if the data score of the target sample data is an outlier, the target sample data is discarded; if the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

[0179] In one embodiment, the target energy consumption analysis model is at least one of an extreme gradient boosting model, a support vector machine model, and a decision tree model.

[0180] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0181] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0182] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0183] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle energy consumption analysis method, characterized in that: The method comprises: Acquire target vehicle driving data of the target vehicle during driving; wherein the target vehicle driving data at least includes total mass, slope and vehicle speed data of the target vehicle; Inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving; When the target energy consumption data exceeds a preset threshold, driving behavior guidance is provided to a driver of the target vehicle to reduce the target energy consumption data of the target vehicle.

2. The method according to claim 1, characterized in that: The providing driving behavior guidance to the driver of the target vehicle comprises: Acquire at least one reference vehicle driving data in the historical vehicle driving data having the same total mass and slope as the target vehicle in the target vehicle driving data; Determine the historical energy consumption data corresponding to the driving data of each reference vehicle; Using historical vehicle speed data corresponding to historical energy consumption data lower than the target energy consumption data as a driving behavior guide; Providing driving behavior guidance to a driver of the target vehicle.

3. The method according to claim 2, characterized in that In the case that there are at least two historical energy consumption data lower than the target energy consumption data, using the historical vehicle speed data corresponding to the historical energy consumption data lower than the target energy consumption data as the driving behavior guidance includes: Obtaining environmental data corresponding to the target vehicle driving data and environmental data corresponding to each historical energy consumption data lower than the target energy consumption data; wherein the environmental data includes road congestion data and weather data; Determine the matching degree between the environmental data corresponding to the target vehicle driving data and the environmental data corresponding to each historical energy consumption data lower than the target energy consumption data; The historical vehicle speed data corresponding to the historical energy consumption data associated with the greatest matching degree is used as a guide for driving behavior.

4. The method according to claim 1, characterized in that: The target energy consumption analysis model is trained in the following way: Acquire candidate sample data; wherein the candidate sample data includes multi-dimensional data and energy consumption data of the sample vehicle; wherein the multi-dimensional data includes at least engine data, vehicle speed data, throttle data, slope, total mass, gravity acceleration and vehicle resistance data; According to the correlation between each dimension data and energy consumption data in the candidate sample data, the total mass, slope, speed data and energy consumption data of the sample vehicle are used as target sample data; The target sample data is input into the initial energy consumption analysis model for training to obtain the target energy consumption analysis model.

5. The method according to claim 4, characterized in that Before inputting the target sample data into the initial energy consumption analysis model for training, the method further includes: Inputting the target sample data into an anomaly detection model to obtain a data score corresponding to the target sample data; If the data score of the target sample data is an outlier, the target sample data is discarded; If the data score of the target sample data is a normal value, the target sample data is allowed to be input into the initial energy consumption analysis model for training.

6. The method according to claim 1, characterized in that The target energy consumption analysis model is at least one of an extreme gradient boosting model, a support vector machine model and a decision tree model.

7. A vehicle energy consumption analysis device, characterized in that: The device comprises: An acquisition module, used to acquire target vehicle driving data during the driving process of the target vehicle; wherein the target vehicle driving data at least includes the total mass, slope and speed data of the target vehicle; An analysis module, used for inputting the target vehicle driving data into a target energy consumption analysis model to obtain target energy consumption data of the target vehicle during driving; The guidance module is used to provide driving behavior guidance to the driver of the target vehicle when the target energy consumption data exceeds a preset threshold value, so as to reduce the target energy consumption data of the target vehicle.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images