CN114971068A - Method and device for determining factors influencing vehicle performance prediction - Google Patents

Method and device for determining factors influencing vehicle performance prediction Download PDF

Info

Publication number
CN114971068A
CN114971068A CN202210699680.5A CN202210699680A CN114971068A CN 114971068 A CN114971068 A CN 114971068A CN 202210699680 A CN202210699680 A CN 202210699680A CN 114971068 A CN114971068 A CN 114971068A
Authority
CN
China
Prior art keywords
factors
influence
vehicle performance
influencing
prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210699680.5A
Other languages
Chinese (zh)
Inventor
马瑞峰
曹斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Neusoft Reach Automotive Technology Shenyang Co Ltd
Original Assignee
Neusoft Reach Automotive Technology Shenyang Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Neusoft Reach Automotive Technology Shenyang Co Ltd filed Critical Neusoft Reach Automotive Technology Shenyang Co Ltd
Priority to CN202210699680.5A priority Critical patent/CN114971068A/en
Publication of CN114971068A publication Critical patent/CN114971068A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Educational Administration (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method for determining factors influencing vehicle performance prediction, which comprises the following steps: the method comprises the steps of obtaining a plurality of influence factors and actual influences of the plurality of influence factors on vehicle performance, inputting the plurality of influence factors and the actual influences of the plurality of influence factors on the vehicle performance to a neural network model together for training, obtaining a first prediction error ranking of the plurality of influence factors on vehicle performance prediction influence errors based on the neural network model, and accordingly obtaining which factors have large influences on the accuracy of vehicle performance prediction so as to optimize and obtain accurate vehicle performance.

Description

Method and device for determining factors influencing vehicle performance prediction
Technical Field
The application relates to the technical field of vehicles, in particular to a method, a device and equipment for determining factors influencing vehicle performance prediction.
Background
With the wide application of vehicles in life, users need to predict the performance of vehicles so as to remind the users, and the users can conveniently arrange reasonably. For the manufacturer of the vehicle, prediction of the vehicle performance can help performance optimization and the like.
However, it is difficult to obtain an accurate prediction result in many cases, and the predicted result and the actual result have a large influence, influence the use of the user, and influence the performance optimization of the vehicle. In the process of predicting the vehicle performance, many factors influence the accuracy of prediction, so a method for determining factors influencing the vehicle performance prediction is urgently needed, and the factors influencing the vehicle performance prediction accuracy are determined, so that accurate prediction is performed.
Disclosure of Invention
The method can analyze a plurality of factors possibly influencing the vehicle performance prediction accuracy, and obtain the influence of the plurality of factors on the prediction error, so that the vehicle performance can be accurately predicted. The application also provides a device, equipment and a computer readable storage medium corresponding to the method.
In a first aspect, the present application provides a method of determining factors that influence vehicle performance predictions, the method comprising:
acquiring a plurality of influence factors and actual influence of the influence factors on vehicle performance;
inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a neural network model for training;
a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the neural network model.
In some possible implementations, the method further includes:
inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a tree model for training;
a second prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the tree model.
In some possible implementations, the method further includes:
calculating a matrix of correlation coefficients for the plurality of influencing factors and a predicted influence of the plurality of influencing factors on the actual influence of the vehicle performance;
obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the correlation matrix;
and determining a target influence factor combination according to the second prediction error ranking and the third prediction error ranking.
In some possible implementations, the actual impact of the plurality of influencing factors on the vehicle performance includes an actual impact of the plurality of influencing factors on a remaining range of the vehicle.
In some possible implementations, the actual impact of the plurality of influencing factors on the vehicle performance includes an actual impact of the plurality of influencing factors on a remaining time of the vehicle.
In some possible implementations, the method further includes:
generating a reminder report based on the first prediction error ranking.
In some possible implementations, the influencing factor includes at least one of mileage, probe temperature, voltage, current, length of rest time, state of charge, and rest state of charge.
In a second aspect, the present application provides an apparatus for determining factors that influence vehicle performance prediction, the apparatus comprising:
the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring a plurality of influence factors and actual influences of the plurality of influence factors on the vehicle performance;
the training module is used for inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a neural network model together for training;
a determination module to obtain a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the neural network model.
In some possible implementations, the apparatus further includes a combining module to:
inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a tree model for training;
a second prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the tree model.
In some possible implementations, the combining module is specifically configured to:
calculating a correlation coefficient matrix of the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance;
obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the correlation matrix;
and determining a target influence factor combination according to the second prediction error ranking and the third prediction error ranking.
In some possible implementations, the actual impact of the plurality of influencing factors on the vehicle performance includes an actual impact of the plurality of influencing factors on a remaining range of the vehicle.
In some possible implementations, the actual impact of the plurality of influencing factors on the vehicle performance includes an actual impact of the plurality of influencing factors on a remaining time of the vehicle.
In some possible implementations, the apparatus further includes a generating module configured to:
generating a reminder report based on the first prediction error ranking.
In some possible implementations, the influencing factor includes at least one of mileage, probe temperature, voltage, current, length of rest time, state of charge, and rest state of charge.
In a third aspect, the present application provides an apparatus comprising a processor and a memory. The processor and the memory are in communication with each other. The processor is configured to execute the instructions stored in the memory to cause the apparatus to perform the method of determining factors that affect vehicle performance prediction as in the first aspect or any one of the implementations of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored therein, where the instructions instruct an apparatus to execute the method for determining the factors that affect the vehicle performance prediction according to the first aspect or any implementation manner of the first aspect.
The present application can further combine to provide more implementations on the basis of the implementations provided by the above aspects.
According to the technical scheme, the embodiment of the application has the following advantages:
the embodiment of the application provides a method for determining factors influencing vehicle performance prediction, which includes the steps of obtaining actual influences of a plurality of influence factors and the plurality of influence factors on vehicle performance, inputting the actual influences of the plurality of influence factors and the plurality of influence factors on the vehicle performance into a neural network model together for training, obtaining a first prediction error ranking of the plurality of influence factors on vehicle performance prediction influence errors based on the neural network model, and accordingly obtaining which factors have greater influence on accuracy of vehicle performance prediction so as to optimize and obtain accurate vehicle performance.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating a method for determining factors influencing vehicle performance prediction according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating another method for determining factors that affect vehicle performance prediction according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a device for determining factors affecting vehicle performance prediction according to an embodiment of the present application.
Detailed Description
The scheme in the embodiments provided in the present application will be described below with reference to the drawings in the present application.
The terms "first," "second," and the like in the description and in the claims of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely descriptive of the various embodiments of the application and how objects of the same nature can be distinguished.
With the wide application of vehicles in life, users need to predict the performance of vehicles so as to remind the users, and the users can conveniently arrange reasonably. For the manufacturer of the vehicle, prediction of the vehicle performance can help performance optimization and the like.
However, it is difficult to obtain an accurate prediction result in many cases, and the predicted result and the actual result have a large influence, influence the use of the user, and influence the performance optimization of the vehicle. In the process of predicting the vehicle performance, many factors influence the accuracy of prediction, and the traditional prediction method only knows that the error is large, but is difficult to know which factor causes the error and is difficult to optimize.
In view of the above, the present application provides a method for determining factors affecting vehicle performance prediction, which may be performed by an electronic device. The electronic device refers to a device with data processing capability, and may be a terminal device such as a smart phone, or a server, for example.
Specifically, the electronic device obtains actual influences of a plurality of influence factors and the plurality of influence factors on vehicle performance respectively, predicts the predicted influences of the plurality of influence factors on the vehicle performance respectively, inputs the actual influences of the plurality of influence factors, the plurality of influence factors on the vehicle performance respectively, and the predicted influences of the plurality of influence factors on the vehicle performance respectively into the neural network model for training, and obtains a first prediction error ranking of the plurality of influence factors on vehicle performance prediction influence errors based on the neural network model, so that the accuracy influence of the plurality of influence factors on vehicle performance prediction is obtained, and accurate vehicle performance is obtained through optimization.
Next, a method for determining factors that affect vehicle performance prediction according to an embodiment of the present application will be described with reference to the drawings.
Referring to the flowchart of the method for determining factors that affect vehicle performance prediction shown in FIG. 1, the method includes the steps of:
s102: the electronic device obtains a plurality of influencing factors and the actual influence of the plurality of influencing factors on the vehicle performance.
The influence factor refers to a factor that a user needs to determine whether the factor has influence on the accuracy of the vehicle performance prediction, and may include at least one of driving distance, probe temperature, voltage, current, standing time, state of charge, and standing state of charge, for example.
The actual influence of the influencing factor on the vehicle performance may be the influence on the vehicle performance acquired through an actual process, and the vehicle performance may be the remaining mileage of the vehicle or the remaining time of the vehicle. For example, when the influencing factors are the charging current, the charging voltage, and the standing time length, the influence of different charging currents, charging voltages, and standing time lengths on the remaining mileage of the vehicle or the remaining time of the vehicle may be obtained.
S104: the electronic device inputs the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into the neural network model for training.
The Neural Network model may be an Artificial Neural Network (ANN) model or a Convolutional Neural Network (CNN).
The electronic device may predict a predicted impact of the plurality of influencing factors on the vehicle performance via a neural network model. For example, the plurality of influencing factors may include a charging current, a charging voltage, and a rest duration, with the predicted influence of the charging current, the charging voltage, and the rest duration on the vehicle performance being predicted by the neural network model.
Specifically, the plurality of influencing factors can be used as input, the actual influence can be used as a label, the electronic device inputs the plurality of influencing factors into the neural network model to obtain predicted influence, and then the gradient is obtained through comparison of the prediction and the influence.
For example, it may be assumed that the calculation result of the neural network model depends on each influence factor, and the calculation result y may be expressed as y ═ Wx + b, so that the gradient of the output y with respect to the influence factor x is
Figure BDA0003703926180000062
To directly quantify how important the influencing factors are for y.
However, if the gradient is expressed directly by pure gradient, there is a problem of gradient saturation due to the high nonlinearity of the neural network. That is, when the difference between the calculation result and the label is too large, it is difficult to determine whether the calculation result is an objective problem or a problem of the algorithm itself, so the algorithm needs to satisfy a necessary axiom to eliminate the possibility of the problem of the algorithm itself.
The integral gradient is improved on the basis of the idea of the model gradient so as to satisfy the axioms of consistency, sensitivity, collinearity, completeness, symmetry and the like, so that the integral gradient can be used for quantifying the contribution of each feature (influencing factor in the scheme) to the output of the model so as to explain the influence of the feature on the model. Consistency means that two neural networks that function the same are of equal importance to the final feature, even if they are structurally different. Sensitivity means that if a variable has no effect on the model, its contribution is zero. Co-linearity means that if the third neural network is a linear combination of two neural networks, the contribution values follow the same linear combination. Completeness refers to the sum of all feature contributions being equal to the difference between the sample and baseline. Symmetry refers to the determination of their contribution to variables that satisfy symmetry.
The integral gradient is defined as shown in equation (1):
Figure BDA0003703926180000061
s106: a first prediction error ranking of a plurality of influencing factors on vehicle performance prediction influencing errors is obtained based on the neural network model.
In this manner, the electronic device may determine the impact of the plurality of influencing factors on the accuracy of the vehicle performance prediction based on the gradient during the neural network model training process, for example, a larger gradient indicates a larger impact. Alternatively, the influence of the influencing factor on the vehicle performance may be represented by gradient quantization.
The influence on the performance of the vehicle includes the influence on the performance of a battery in the vehicle, and may also include the influence on the performance of parts in the vehicle.
Further, the method also includes the electronic device generating a reminder report of the impact of the influencing factor on the accuracy of the vehicle performance based on the first prediction error ranking. For example, the plurality of influence factors may be divided into different influence levels according to different gradient values, and the influence factors with higher influence degree may be prompted to the user.
In some possible implementation manners, the method may further be used to screen multiple influence factors, determine multiple influence factors with larger influence degrees, and then further determine the influence of the multiple influence factors with larger influence degrees on the prediction accuracy. The method specifically comprises the following steps: the electronic equipment jointly inputs the multiple influence factors and the actual influences of the multiple influence factors on the vehicle performance to a tree model for training, obtains a second prediction error ranking of the multiple influence factors on the vehicle performance prediction influence errors based on the tree model, calculates a correlation coefficient matrix of the multiple influence factors and the prediction influences of the multiple influence factors on the actual influences of the vehicle performance, obtains a third prediction error ranking of the multiple influence factors on the vehicle performance prediction influence errors based on the correlation matrix, determines a target influence factor combination according to the second prediction error ranking and the third prediction error ranking, and obtains the influences of the multiple influence factors on the prediction accuracy in the combination.
Referring to FIG. 2, another method for determining factors that affect vehicle performance prediction is shown, which includes the steps of:
s202: the electronic device obtains a plurality of influencing factors and the actual influence of the plurality of influencing factors on the vehicle performance.
S204: the electronic equipment inputs the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into the tree model for training.
The Tree model is a type of model in Machine learning, and includes a Decision Tree model, a random forest model, a Gradient Boosting Decision Tree (GBDT) model (e.g., an eXtreme Gradient Boosting (XGBoost) model, a Light Gradient Boosting Machine (LightGBM)), and the like.
S206: a second prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the tree model.
In particular, information gain may be employed to represent a ranking of the impact of a plurality of influencing factors on the health of the battery. That is, the importance of the influence factor is determined by determining how much information the features can bring to the model, and the more information the influence factor brings, the more important the influence factor is. The amount of information can be represented using entropy, which can be
Figure BDA0003703926180000081
The conditional entropy may be the amount of information under the condition X, i.e., H (Y | X) ═ Σ X P(X)H(Y|X＝x)。
Wherein the second prediction error ranking may be a plurality of influencing factors ranked from high to low in influence.
S208: the electronic device calculates a correlation coefficient matrix of the plurality of influence factors and the predicted influence of the plurality of influence factors on the actual influence of the vehicle performance, and obtains a third prediction error ranking of the plurality of influence factors on the vehicle performance prediction influence error based on the correlation matrix.
The spearman correlation coefficient is used to describe the correlation between two variables and can be used in the present scheme to obtain the correlation between the influencing factor and the prediction error, for example, by
Figure BDA0003703926180000082
Representing the correlation between x and y. The prediction error may be a difference between the actual influence and the predicted influence, or a normalized value of the difference between the actual influence and the predicted influence.
It should be noted that the sequence of execution of S206 and S208 is not limited in this scheme, and the electronic device may obtain a second prediction error rank of the multiple influence factors for the prediction error based on the tree model, and then obtain a correlation coefficient matrix of the multiple influence factors for the prediction error, and obtain a third prediction error rank. The electronic device may also obtain a correlation coefficient matrix of the plurality of influence factors to the prediction error based on the tree model, obtain a third prediction error rank, and obtain a second prediction error rank of the influence factors to the prediction error. The electronic device may further obtain a second prediction error rank of the plurality of influence factors for the prediction error based on the tree model, and obtain a correlation coefficient matrix of the plurality of influence factors for the prediction error at the same time, to obtain a third prediction error rank. Wherein the third prediction error ranking may be a plurality of influence factors ranked from high to low in influence.
S210: and the electronic equipment determines a target influence factor combination according to the correlation coefficient matrix.
The electronic device synthesizes the first prediction error ranking and the third prediction error ranking to jointly determine a target influence factor combination comprising a plurality of influence factors. The target influence factors in the influence factor combination may be all target influence factors or part of the target influence factors.
S212: the electronic device jointly inputs the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a neural network model for training.
S214: the electronic device obtains a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the neural network model.
Specifically, the electronic device determines an effect of a target influence factor of the combination of target influence factors on a vehicle performance prediction error based on a gradient of the neural network model.
S216: the electronic device generates a reminder report based on the first prediction error ranking.
Based on the description of the above content, the application provides a method for determining factors affecting vehicle performance prediction, by obtaining actual influences of a plurality of influencing factors and the plurality of influencing factors on vehicle performance, the actual influences of the plurality of influencing factors and the plurality of influencing factors on vehicle performance are jointly input into a neural network model for training, and a first prediction error ranking of the plurality of influencing factors on vehicle performance prediction influence errors is obtained based on the neural network model, so that which factors have a greater influence on the accuracy of vehicle performance prediction is obtained, and accurate vehicle performance is obtained through optimization.
The method for determining the factors affecting the vehicle performance prediction provided by the embodiment of the present application is described in detail with reference to fig. 1, and the device for determining the factors affecting the vehicle performance prediction provided by the embodiment of the present application is described with reference to the accompanying drawings.
Referring to fig. 3, a schematic diagram of a device for determining factors that influence vehicle performance prediction is shown, where the device 300 includes: an acquisition module 302, a training module 304, and a determination module 306.
The system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring a plurality of influence factors and actual influences of the influence factors on vehicle performance;
the training module is used for inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a neural network model together for training;
a determination module to obtain a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the neural network model.
In some possible implementations, the apparatus further includes a combining module to:
inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a tree model for training;
a second prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the tree model.
In some possible implementations, the combining module is specifically configured to:
calculating a matrix of correlation coefficients for the plurality of influencing factors and the actual influence of the plurality of influencing factors on the vehicle performance;
obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the correlation matrix;
and determining a target influence factor combination according to the second prediction error ranking and the third prediction error ranking.
In some possible implementations, the actual impact of the plurality of influencing factors on the vehicle performance includes an actual impact of the plurality of influencing factors on a remaining range of the vehicle.
In some possible implementations, the actual impact of the plurality of influencing factors on the vehicle performance includes an actual impact of the plurality of influencing factors on a remaining time of the vehicle.
In some possible implementations, the apparatus further includes a generating module configured to:
generating a reminder report based on the first prediction error ranking.
In some possible implementations, the influencing factor includes at least one of mileage, probe temperature, voltage, current, length of rest time, state of charge, and rest state of charge.
The determining apparatus 300 for influencing vehicle performance prediction factors according to the embodiment of the present application may correspond to performing the method described in the embodiment of the present application, and the above and other operations and/or functions of the modules of the determining apparatus 300 for influencing vehicle performance prediction factors are respectively for implementing the corresponding processes of the methods in fig. 1, and are not described herein again for brevity.
The present application provides an apparatus for implementing a method of determining factors that affect vehicle performance predictions. The apparatus includes a processor and a memory. The processor and the memory are in communication with each other. The processor is configured to execute the instructions stored in the memory to cause the device to perform a method of determining factors that affect a vehicle performance prediction.
The present application provides a computer-readable storage medium having stored therein instructions that, when run on an apparatus, cause the apparatus to perform the above-described method of determining factors that affect vehicle performance predictions.
The present application provides a computer program product comprising instructions which, when run on an apparatus, cause the apparatus to perform the above-described method of determining factors that influence vehicle performance prediction.
It should be noted that the above-described embodiments of the apparatus are merely schematic, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiments of the apparatus provided in the present application, the connection relationship between the modules indicates that there is a communication connection therebetween, and may be implemented as one or more communication buses or signal lines.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus necessary general-purpose hardware, and certainly can also be implemented by special-purpose hardware including special-purpose integrated circuits, special-purpose CPUs, special-purpose memories, special-purpose components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions may be various, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, the implementation of a software program is more preferable. Based on such understanding, the technical solutions of the present application may be substantially embodied in the form of a software product, which is stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, an exercise device, or a network device) to execute the method according to the embodiments of the present application.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, training device, or data center to another website site, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). 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 incorporates one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

Claims (10)

1. A method of determining factors that influence vehicle performance predictions, the method comprising:
acquiring a plurality of influence factors and actual influence of the influence factors on vehicle performance;
inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a neural network model for training;
a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the neural network model.
2. The method of claim 1, further comprising:
inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a tree model for training;
a second prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error is obtained based on the tree model.
3. The method of claim 2, further comprising:
calculating a matrix of correlation coefficients for the plurality of influencing factors and a predicted influence of the plurality of influencing factors on the actual influence of the vehicle performance;
obtaining a third prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the correlation matrix;
and determining a target influence factor combination according to the second prediction error ranking and the third prediction error ranking.
4. The method of claim 1, wherein the actual impact of the plurality of impact factors on vehicle performance comprises an actual impact of the plurality of impact factors on a remaining range of the vehicle.
5. The method of claim 1, wherein the actual impact of the plurality of impact factors on vehicle performance comprises an actual impact of the plurality of impact factors on a vehicle time remaining.
6. The method of claim 1, further comprising:
generating a reminder report based on the first prediction error ranking.
7. The method of claim 1, wherein the influencing factors comprise at least one of mileage, probe temperature, voltage, current, length of rest time, state of charge, and rest state of charge.
8. An apparatus for determining factors that influence vehicle performance predictions, the apparatus comprising:
the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring a plurality of influence factors and actual influences of the influence factors on vehicle performance;
the training module is used for inputting the plurality of influence factors and the actual influence of the plurality of influence factors on the vehicle performance into a neural network model together for training;
a determination module to obtain a first prediction error ranking of the plurality of influencing factors on the vehicle performance prediction influencing error based on the neural network model.
9. An apparatus, comprising a processor and a memory;
the processor is to execute instructions stored in the memory to cause the device to perform the method of any of claims 1-7.
10. A computer-readable storage medium comprising instructions that direct a device to perform the method of any of claims 1-7.
CN202210699680.5A 2022-06-20 2022-06-20 Method and device for determining factors influencing vehicle performance prediction Pending CN114971068A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210699680.5A CN114971068A (en) 2022-06-20 2022-06-20 Method and device for determining factors influencing vehicle performance prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210699680.5A CN114971068A (en) 2022-06-20 2022-06-20 Method and device for determining factors influencing vehicle performance prediction

Publications (1)

Publication Number Publication Date
CN114971068A true CN114971068A (en) 2022-08-30

Family

ID=82962943

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210699680.5A Pending CN114971068A (en) 2022-06-20 2022-06-20 Method and device for determining factors influencing vehicle performance prediction

Country Status (1)

Country Link
CN (1) CN114971068A (en)

Similar Documents

Publication Publication Date Title
CN110276446B (en) Method and device for training model and selecting recommendation information
CN108229667A (en) Trimming based on artificial neural network classification
CN112889042A (en) Identification and application of hyper-parameters in machine learning
US20180157965A1 (en) Device and method for determining convolutional neural network model for database
CN107357764B (en) Data analysis method, electronic device, and computer storage medium
CN111159563A (en) Method, device and equipment for determining user interest point information and storage medium
CN114780338A (en) Host information processing method and device, electronic equipment and computer readable medium
CN112612887A (en) Log processing method, device, equipment and storage medium
CN111178537A (en) Feature extraction model training method and device
CN114325454A (en) Method, device, equipment and medium for determining influence of multiple characteristics on battery health degree
CN112420125A (en) Molecular attribute prediction method and device, intelligent equipment and terminal
CN114168318A (en) Training method of storage release model, storage release method and equipment
CN116166967B (en) Data processing method, equipment and storage medium based on meta learning and residual error network
KR102192461B1 (en) Apparatus and method for learning neural network capable of modeling uncerrainty
CN114971068A (en) Method and device for determining factors influencing vehicle performance prediction
CN115730152A (en) Big data processing method and big data processing system based on user portrait analysis
CN113780666B (en) Missing value prediction method and device and readable storage medium
CN115795928A (en) Accelerated degradation test data processing method and device based on gamma process
CN114971375A (en) Examination data processing method, device, equipment and medium based on artificial intelligence
CN115203556A (en) Score prediction model training method and device, electronic equipment and storage medium
CN115061042A (en) Method, device, equipment and medium for determining influence of multiple characteristics on battery health degree
CN116501993B (en) House source data recommendation method and device
CN116663989B (en) Method and device for measuring terrain complexity of linear engineering
CN114048392B (en) Multimedia resource pushing method and device, electronic equipment and storage medium
CN113344056B (en) Training method and device of personnel mobility prediction model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination