Method and device for determining factors affecting vehicle performance prediction

Abstract

The present application provides a method for determining factors affecting vehicle performance prediction, including: obtaining multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance, inputting the multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance into a neural network model for training, and obtaining a first prediction error ranking of the impact error of the multiple influencing factors on vehicle performance prediction based on the neural network model, thereby obtaining which factors have a greater impact on the accuracy of vehicle performance prediction, so as to optimize and obtain accurate vehicle performance.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, and apparatus for determining factors that affect vehicle performance prediction. Background Art

[0002] With the widespread use of vehicles in our daily lives, users need to predict vehicle performance so that they can be reminded and make reasonable arrangements. For vehicle manufacturers, predicting vehicle performance can help with performance optimization, etc.

[0003] However, accurate prediction results are often difficult to obtain. The predicted and actual results can significantly impact user experience and hinder vehicle performance optimization. Numerous factors influence the accuracy of vehicle performance predictions. Therefore, a method is urgently needed to identify factors that influence vehicle performance prediction accuracy and enable accurate predictions. Summary of the Invention

[0004] This application provides a method for determining factors affecting vehicle performance prediction. This method analyzes multiple factors that may affect the accuracy of vehicle performance prediction, determines the impact of these factors on prediction error, and thus enables accurate vehicle performance prediction. This application also provides apparatus, devices, and computer-readable storage media corresponding to the above method.

[0005] In a first aspect, the present application provides a method for determining factors affecting vehicle performance prediction, the method comprising:

[0006] Acquire multiple influencing factors and actual effects of the multiple influencing factors on vehicle performance;

[0007] Inputting the multiple influencing factors and the actual effects of the multiple influencing factors on vehicle performance into a neural network model for training;

[0008] A first prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction is obtained based on the neural network model.

[0009] In some possible implementations, the method further includes:

[0010] Inputting the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a tree model for training;

[0011] A second prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction is obtained based on the tree model.

[0012] In some possible implementations, the method further includes:

[0013] calculating a correlation coefficient matrix of the plurality of influencing factors and predicted effects of the plurality of influencing factors on actual effects of the vehicle performance;

[0014] Obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error based on the correlation matrix;

[0015] A target influencing factor combination is determined according to the second prediction error ranking and the third prediction error ranking.

[0016] In some possible implementations, the actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining mileage of the vehicle.

[0017] In some possible implementations, the actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining time of the vehicle.

[0018] In some possible implementations, the method further includes:

[0019] An alert report is generated based on the first prediction error ranking.

[0020] In some possible implementations, the influencing factors include at least one of mileage, probe temperature, voltage, current, rest time, state of charge, and resting state of charge.

[0021] In a second aspect, the present application provides a device for determining factors affecting vehicle performance prediction, the device comprising:

[0022] an acquisition module, configured to acquire a plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance;

[0023] a training module, configured to input the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a neural network model for training;

[0024] A determination module is used to obtain a first prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction based on the neural network model.

[0025] In some possible implementations, the apparatus further includes a combining module configured to:

[0026] Inputting the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a tree model for training;

[0027] A second prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction is obtained based on the tree model.

[0028] In some possible implementations, the combination module is specifically configured to:

[0029] Calculating the plurality of influencing factors and a correlation coefficient matrix of actual effects of the plurality of influencing factors on vehicle performance;

[0030] Obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error based on the correlation matrix;

[0031] A target influencing factor combination is determined according to the second prediction error ranking and the third prediction error ranking.

[0032] In some possible implementations, the actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining mileage of the vehicle.

[0033] In some possible implementations, the actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining time of the vehicle.

[0034] In some possible implementations, the apparatus further includes a generating module configured to:

[0035] An alert report is generated based on the first prediction error ranking.

[0036] In some possible implementations, the influencing factors include at least one of mileage, probe temperature, voltage, current, rest time, state of charge, and resting state of charge.

[0037] In a third aspect, the present application provides a device comprising a processor and a memory. The processor and the memory are in communication with each other. The processor is configured to execute instructions stored in the memory to cause the device to perform the method for determining factors affecting vehicle performance prediction as described in the first aspect or any implementation of the first aspect.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and the instructions instruct a device to execute the method for determining factors affecting vehicle performance prediction as described in the above-mentioned first aspect or any implementation of the first aspect.

[0039] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods.

[0040] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0041] An embodiment of the present application provides a method for determining factors that affect vehicle performance prediction. By obtaining multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance, the multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance are input into a neural network model for training. Based on the neural network model, a first prediction error ranking of the error of vehicle performance prediction impact of the multiple influencing factors is obtained, thereby obtaining which factors have a greater impact on the accuracy of vehicle performance prediction, so as to optimize and obtain accurate vehicle performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A flowchart of a method for determining factors affecting vehicle performance prediction provided by an embodiment of the present application;

[0044] Figure 2 A flowchart of another method for determining factors affecting vehicle performance prediction provided by an embodiment of the present application;

[0045] Figure 3 A schematic diagram of the architecture of a device for determining factors affecting vehicle performance prediction provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will describe the solutions in the embodiments provided in this application in conjunction with the drawings in this application.

[0047] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate and are merely used to describe the manner in which objects with the same attributes are described in the embodiments of this application.

[0048] With the widespread use of vehicles in our daily lives, users need to predict vehicle performance so that they can be reminded and make reasonable arrangements. For vehicle manufacturers, predicting vehicle performance can help with performance optimization, etc.

[0049] However, accurate predictions are often difficult to obtain. The discrepancy between predicted and actual results can significantly impact user experience and hinder vehicle performance optimization. Numerous factors influence vehicle performance prediction accuracy, and while traditional prediction methods only detect significant errors, it's difficult to pinpoint the exact cause, making optimization difficult.

[0050] In view of this, the present application provides a method for determining factors affecting vehicle performance prediction, which can be performed by an electronic device. The electronic device refers to a device with data processing capabilities, such as a terminal device such as a smartphone, or a server.

[0051] Specifically, the electronic device obtains multiple influencing factors and the actual impacts of the multiple influencing factors on vehicle performance, and predicts the predicted impacts of the multiple influencing factors on vehicle performance. The multiple influencing factors, the actual impacts of the multiple influencing factors on vehicle performance, and the predicted impacts of the multiple influencing factors on vehicle performance are input into a neural network model for training. Based on the neural network model, a first prediction error ranking of the error of the vehicle performance prediction impact of the multiple influencing factors is obtained, thereby obtaining which factors have a greater impact on the accuracy of vehicle performance prediction, so as to optimize and obtain accurate vehicle performance.

[0052] Next, the method for determining factors affecting vehicle performance prediction provided by the embodiment of the present application will be introduced with reference to the accompanying drawings.

[0053] See also Figure 1 The flowchart of the method for determining factors affecting vehicle performance prediction is shown, and the method includes the following steps:

[0054] S102: The electronic device obtains multiple influencing factors and actual impacts of the multiple influencing factors on vehicle performance.

[0055] Among them, the influencing factors refer to factors that the user needs to determine whether the factors have an impact on the accuracy of vehicle performance prediction, for example, they may include at least one of mileage, probe temperature, voltage, current, static time, state of charge and static state of charge.

[0056] The actual impact of the influencing factors on vehicle performance can be the impact on vehicle performance obtained through actual processes, and the vehicle performance can be the remaining vehicle range or the remaining vehicle time. For example, when the influencing factors are charging current, charging voltage, and rest time, the impact of different charging currents, charging voltages, and rest times on the remaining vehicle range or the remaining vehicle time can be obtained.

[0057] S104: The electronic device inputs the multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance into the neural network model for training.

[0058] The neural network model may be an artificial neural network (ANN) model or a convolutional neural network (CNN).

[0059] Electronic devices can use a neural network model to predict the impact of multiple influencing factors on vehicle performance. For example, multiple influencing factors may include charging current, charging voltage, and rest time. The neural network model can predict the impact of charging current, charging voltage, and rest time on vehicle performance.

[0060] Specifically, multiple influencing factors can be used as inputs and actual impacts as labels. The electronic device inputs multiple influencing factors into the neural network model to obtain predicted impacts, and then obtains the gradient by comparing the predictions and the impacts.

[0061] For example, we can assume that the calculation result of the neural network model depends on each influencing factor, and the calculation result y can be expressed as y = Wx + b, then the gradient of the output y with respect to the influencing factor x is Used to directly quantify the importance of influencing factors to y.

[0062] However, if pure gradients are used directly, the highly nonlinear nature of neural networks can lead to gradient saturation. Specifically, when the calculated result differs significantly from the label, it becomes difficult to determine whether the issue lies with the objective or the algorithm itself. Therefore, the algorithm must satisfy necessary axioms to eliminate the possibility of inherent problems.

[0063] The integral gradient is an improvement on the idea of ​​model gradient to satisfy axioms such as consistency, sensitivity, collinearity, completeness and symmetry. Therefore, the integral gradient can be used to quantify the contribution of each feature (the influencing factor in this solution) to the model output, so as to explain the impact of the feature on the model. Consistency means that even if two neural networks with the same function have different structures, their importance to the final feature is the same. Sensitivity means that if a variable has no effect on the model, then its contribution value is zero. Collinearity means that if the third neural network is a linear combination of two neural networks, then the contribution value also follows the same linear combination. Completeness means that the sum of the contributions of all features is equal to the difference between the sample and the baseline. Symmetry means that for variables that meet symmetry, their contribution values ​​are determined.

[0064] The definition of the integral gradient is shown in formula (1):

[0065]

[0066] S106: Obtaining a first prediction error ranking of the influence errors of multiple influencing factors on vehicle performance prediction based on the neural network model.

[0067] In this way, the electronic device can determine the impact of multiple influencing factors on the accuracy of vehicle performance prediction based on the gradients during neural network model training. For example, a larger gradient indicates a greater impact. Alternatively, the gradient can be used to quantify the impact of the influencing factor on vehicle performance.

[0068] The impact on vehicle performance includes the impact on battery performance in the vehicle, and may also include the impact on the performance of components in the vehicle.

[0069] Furthermore, the method includes generating, by the electronic device, a reminder report of the impact of the influencing factors on the vehicle performance accuracy based on the first prediction error ranking. For example, the influencing factors may be divided into different impact levels according to different gradient values, and the user may be prompted with the influencing factors with higher impact levels.

[0070] In some possible implementations, the method can also be used to screen multiple influencing factors, determine multiple influencing factors with greater influence, and then further determine the impact of the multiple influencing factors with greater influence on prediction accuracy. Specifically, the method includes: the electronic device inputs the multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance into a tree model for training, obtains a second prediction error ranking of the multiple influencing factors on the vehicle performance prediction error based on the tree model, calculates a correlation coefficient matrix of the multiple influencing factors and the predicted impact of the actual impact of the multiple influencing factors on vehicle performance, obtains a third prediction error ranking of the multiple influencing factors on the vehicle performance prediction error based on the correlation matrix, determines a target influencing factor combination according to the second prediction error ranking and the third prediction error ranking, and obtains the impact of the multiple influencing factors in the combination on prediction accuracy.

[0071] See also Figure 2 A flow chart of another method for determining factors affecting vehicle performance prediction is shown, the method comprising the following steps:

[0072] S202: The electronic device obtains multiple influencing factors and actual impacts of the multiple influencing factors on vehicle performance.

[0073] S204: The electronic device inputs the multiple influencing factors and the actual impacts of the multiple influencing factors on vehicle performance into a tree model for training.

[0074] Tree models are a type of model in machine learning, including decision tree models, random forest models, gradient boosting tree (GBDT) models (such as the eXtreme Gradient Boosting (XGBoost) model and light gradient boosting machine (LightGBM)).

[0075] S206: Obtaining a second prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction based on the tree model.

[0076] Specifically, information gain can be used to represent the ranking of the impact of multiple factors on the battery health. That is, the importance of the factors can be judged by judging how much information the feature can bring to the model. The more information the factor brings, the more important it is. Entropy can be used to represent the amount of information. Entropy can be Conditional entropy can be the amount of information under condition X, that is, H(Y|X)=∑ X P(X)H(Y|X=x).

[0077] The second prediction error ranking may be a ranking of multiple influencing factors in descending order of influence.

[0078] S208: The electronic device calculates a correlation coefficient matrix of the multiple influencing factors and the predicted impact of the multiple influencing factors on the actual impact of the vehicle performance, and obtains a third prediction error ranking of the predicted impact error of the multiple influencing factors on the vehicle performance based on the correlation matrix.

[0079] The Spearman correlation coefficient is used to describe the correlation between two variables. In this solution, it can be used to obtain the correlation between the influencing factors and the prediction error. For example, Represents the correlation between x and y. The prediction error can be the difference between the actual impact and the predicted impact, or the normalized value of the difference between the actual impact and the predicted impact.

[0080] It should be noted that the order in which S206 and S208 are executed is not limited in this solution. The electronic device may first obtain a second prediction error ranking of the multiple influencing factors for the prediction error based on the tree model, and then obtain a correlation coefficient matrix of the multiple influencing factors for the prediction error to obtain a third prediction error ranking. The electronic device may also first obtain a correlation coefficient matrix of the multiple influencing factors for the prediction error based on the tree model to obtain the third prediction error ranking, and then obtain the second prediction error ranking of the influencing factors for the prediction error. The electronic device may also obtain the second prediction error ranking of the multiple influencing factors for the prediction error based on the tree model while simultaneously obtaining a correlation coefficient matrix of the multiple influencing factors for the prediction error to obtain a third prediction error ranking. The third prediction error ranking may be a ranking of the multiple influencing factors in descending order of influence.

[0081] S210: The electronic device determines a target influencing factor combination according to the correlation coefficient matrix.

[0082] The electronic device comprehensively considers the first prediction error ranking and the third prediction error ranking to jointly determine a target influencing factor combination including multiple influencing factors, wherein the target influencing factors in the influencing factor combination may be all target influencing factors or some target influencing factors.

[0083] S212: The electronic device inputs the multiple influencing factors and the actual impact of the multiple influencing factors on vehicle performance into the neural network model for training.

[0084] S214: The electronic device obtains a first prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction based on the neural network model.

[0085] Specifically, the electronic device determines the influence of the target influencing factors in the target influencing factor combination on the vehicle performance prediction error based on the gradient of the neural network model.

[0086] S216: The electronic device generates a reminder report based on the first prediction error ranking.

[0087] Based on the description above, the present application provides a method for determining factors that affect vehicle performance prediction. By obtaining multiple influencing factors and the actual impact of multiple influencing factors on vehicle performance, the multiple influencing factors and the actual impact of multiple influencing factors on vehicle performance are input into a neural network model for training. Based on the neural network model, the first prediction error ranking of the error of vehicle performance prediction influence of multiple influencing factors is obtained, thereby obtaining which factors have a greater impact on the accuracy of vehicle performance prediction, so as to optimize and obtain accurate vehicle performance.

[0088] Combination of the above Figure 1The method for determining the factors affecting vehicle performance prediction provided by the embodiment of the present application is introduced in detail. Next, the device for determining the factors affecting vehicle performance prediction provided by the embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0089] See also Figure 3 The schematic structural diagram of the device for determining factors influencing vehicle performance prediction is shown, and the device 300 includes: an acquisition module 302 , a training module 304 and a determination module 306 .

[0090] an acquisition module, configured to acquire a plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance;

[0091] a training module, configured to input the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a neural network model for training;

[0092] A determination module is used to obtain a first prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction based on the neural network model.

[0093] In some possible implementations, the apparatus further includes a combining module configured to:

[0094] Inputting the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a tree model for training;

[0095] A second prediction error ranking of the influence errors of the multiple influencing factors on the vehicle performance prediction is obtained based on the tree model.

[0096] In some possible implementations, the combination module is specifically configured to:

[0097] Calculating the plurality of influencing factors and a correlation coefficient matrix of actual effects of the plurality of influencing factors on vehicle performance;

[0098] Obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error based on the correlation matrix;

[0099] A target influencing factor combination is determined according to the second prediction error ranking and the third prediction error ranking.

[0100] In some possible implementations, the actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining mileage of the vehicle.

[0101] In some possible implementations, the actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining time of the vehicle.

[0102] In some possible implementations, the apparatus further includes a generating module configured to:

[0103] An alert report is generated based on the first prediction error ranking.

[0104] In some possible implementations, the influencing factors include at least one of mileage, probe temperature, voltage, current, rest time, state of charge, and resting state of charge.

[0105] The device 300 for determining factors affecting vehicle performance prediction according to an embodiment of the present application may correspond to executing the method described in the embodiment of the present application, and the above and other operations and / or functions of each module of the device 300 for determining factors affecting vehicle performance prediction are respectively to achieve Figure 1 For the sake of brevity, the corresponding processes of each method in are not repeated here.

[0106] The present application provides a device for implementing a method for determining factors affecting vehicle performance prediction. The device includes a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory to cause the device to perform the method for determining factors affecting vehicle performance prediction.

[0107] The present application provides a computer-readable storage medium having instructions stored therein. When the computer-readable storage medium is executed on a device, the device is enabled to execute the above-mentioned method for determining factors affecting vehicle performance prediction.

[0108] The present application provides a computer program product comprising instructions, which, when executed on a device, enables the device to execute the above-mentioned method for determining factors affecting vehicle performance prediction.

[0109] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0110] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0111] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0112] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A method for determining factors affecting vehicle performance prediction, characterized in that: The method comprises: Acquire multiple influencing factors and actual effects of the multiple influencing factors on vehicle performance; Inputting the multiple influencing factors and the actual effects of the multiple influencing factors on vehicle performance into a neural network model for training; Obtaining a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error based on the neural network model; The method further comprises: Inputting the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a tree model for training; Obtaining a second prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error based on the tree model; calculating a correlation coefficient matrix of the plurality of influencing factors and predicted effects of the plurality of influencing factors on actual effects of the vehicle performance; Obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error based on the correlation matrix; wherein the correlation coefficient is used to describe the correlation between the influencing factors and the prediction error, and the prediction error is the difference between the actual impact and the predicted impact; A target influencing factor combination is determined according to the second prediction error ranking and the third prediction error ranking.

2. The method according to claim 1, characterized in that The actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining mileage of the vehicle.

3. The method according to claim 1, characterized in that The actual impact of the multiple influencing factors on vehicle performance includes the actual impact of the multiple influencing factors on the remaining time of the vehicle.

4. The method according to claim 1, wherein The method further comprises: An alert report is generated based on the first prediction error ranking.

5. The method according to claim 1, wherein The influencing factors include at least one of mileage, probe temperature, voltage, current, rest time, state of charge, and rest state of charge.

6. A device for determining factors affecting vehicle performance prediction, characterized in that: The device comprises: an acquisition module, configured to acquire a plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance; a training module, configured to input the plurality of influencing factors and actual effects of the plurality of influencing factors on vehicle performance into a neural network model for training; A determination module, configured to obtain, based on the neural network model, a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction error; A combination module is used to input the multiple influencing factors and the actual impacts of the multiple influencing factors on vehicle performance into a tree model for training; obtain a second prediction error ranking of the multiple influencing factors on the vehicle performance prediction error based on the tree model; calculate a correlation coefficient matrix of the multiple influencing factors and the predicted impacts of the actual impacts of the multiple influencing factors on vehicle performance; obtain a third prediction error ranking of the multiple influencing factors on the vehicle performance prediction error based on the correlation matrix; wherein the correlation coefficient is used to describe the correlation between the influencing factors and the prediction error, and the prediction error is the difference between the actual impact and the predicted impact; determine the target influencing factor combination according to the second prediction error ranking and the third prediction error ranking.

7. A device, characterized in that The device includes a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the device performs the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The method comprises instructions for instructing a device to execute the method according to any one of claims 1 to 5.

Images