Driving behavior based vehicle speed prediction method, device and equipment and storage medium

Abstract

The application discloses a driving behavior-based vehicle speed prediction method and device, equipment and a storage medium. Driving data of a driver at a current time is acquired, and the driving data at the current time includes vehicle speed, acceleration, accelerator pedal stroke, accelerator pedal stroke change slope, brake pedal stroke and brake pedal stroke change slope at the current time. According to the accelerator pedal stroke, accelerator pedal stroke change slope, brake pedal stroke and brake pedal stroke change slope at the current time, the driving behavior of the driver at the current time is determined, and a vehicle speed prediction model corresponding to the driving behavior of the driver at the current time is acquired. The vehicle speed prediction model is obtained by training a Markov model using historical driving data of the driver. The vehicle speed and acceleration at the current time are input into the vehicle speed prediction model corresponding to the driving behavior of the driver at the current time, and the corresponding vehicle speed in a set time period after the current time is output. The application can improve the vehicle speed prediction accuracy.

Description

Technical Field

[0001] This invention belongs to the field of hybrid electric vehicle energy management technology, specifically relating to a method, device, equipment, and storage medium for predicting vehicle speed based on driving behavior. Background Technology

[0002] Energy management strategies, by coordinating the distribution of power demand among various energy sources, can improve the fuel economy and emissions performance of the entire vehicle without sacrificing power demand, playing a crucial role in the control of hybrid vehicles. Model predictive control strategies, through local vehicle speed prediction and optimization control, consider future travel information and significantly shorten optimization time, facilitating the online application of energy management strategies.

[0003] Predicting future driving conditions is a key component of model predictive control strategies. In real-world driving scenarios, driver behavior changes continuously over time, and vehicle speed is closely related to these changes. Traditional model training methods rely on offline training based on overall historical driving data or categorized by driving conditions, neglecting the impact of driver behavior on vehicle speed. Consequently, the predicted speed using these methods deviates from the actual speed corresponding to the driver's actions. Summary of the Invention

[0004] In view of the problems existing in the prior art, the present invention provides a method, device, equipment and storage medium for vehicle speed prediction based on driving behavior, the purpose of which is to improve the accuracy of vehicle speed prediction.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0006] A vehicle speed prediction method based on driving behavior includes:

[0007] Acquire the driver's driving data at the current moment, which includes the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel change slope, brake pedal travel, and brake pedal travel change slope.

[0008] Based on the accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope at the current moment, the driver's driving behavior at the current moment is determined, and a vehicle speed prediction model corresponding to the driver's driving behavior at the current moment is obtained; the vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data.

[0009] The vehicle speed and acceleration at the current moment are input into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and the vehicle speed corresponding to the time period after the current moment is output.

[0010] Furthermore, the step of using the driver's historical driving data to train the Markov model and construct a vehicle speed prediction model includes:

[0011] The driver's historical driving data is obtained, including historical driving time and the corresponding vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope.

[0012] Based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope, the driver's driving behavior corresponding to the historical driving time is determined, and the driving behavior includes acceleration behavior and braking behavior.

[0013] Based on the driving behavior corresponding to the historical driving time, the historical driving time and the vehicle speed and acceleration corresponding to the historical driving time are divided into the driving behavior corresponding to the historical driving time, so as to obtain the training dataset corresponding to different driving behaviors.

[0014] The Markov model is trained using the training dataset corresponding to the different driving behaviors to obtain the vehicle speed prediction model corresponding to the different driving behaviors.

[0015] Furthermore, the Markov model includes a state space, a state transition frequency matrix, a state transition frequency matrix, and a vehicle speed prediction formula;

[0016] The state space includes the acceleration sequence a s0 and velocity sequence V s0 ; wherein, the acceleration sequence a s0 For a length of L a a min to a max Equally spaced sequences, L a Let a be the number of discrete acceleration states. min For the preset minimum acceleration threshold, a max The preset maximum acceleration threshold; the velocity sequence V s0 For a length of L v 0 to V max Equally spaced sequences, L v V represents the discrete velocity state number. max The preset maximum speed threshold;

[0017] The state transition frequency matrix uses the nearest neighbor algorithm to process the continuous variables in the training dataset and counts the number of times each state transition occurs, as shown below:

[0018]

[0019] Where V(k), a(k), and a(k+m) are continuous variable values ​​in the training dataset, V n a i and a j To represent the discrete variable values ​​in the state space corresponding to the continuous variable values ​​after applying the nearest neighbor rule, k iterates through the training dataset at time intervals Δt = 1, and L p This is the preset prediction step size;

[0020] The state transition frequency matrix is ​​obtained based on the statistical state transition frequency matrix, and is represented as follows:

[0021]

[0022] The vehicle speed prediction formula uses the expectation prediction method, expressed as follows:

[0023]

[0024] Among them, a e (m) represents the expected acceleration at the m-th prediction step, a jj and These represent the acceleration state and its corresponding probability at the m-th prediction step.

[0025] Further, determining the driver's driving behavior corresponding to the historical driving time based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope specifically involves:

[0026] Based on fuzzy logic, the driver's driving behavior corresponding to the historical driving time is obtained according to the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel and brake pedal travel slope.

[0027] Furthermore, the acceleration behavior includes emergency acceleration behavior, general acceleration behavior, and slow acceleration behavior;

[0028] Under the premise of acceleration behavior, the behavior when the acquired acceleration is greater than the preset maximum acceleration is defined as the emergency acceleration behavior, the behavior when the acquired acceleration is less than the preset minimum acceleration is defined as the slow acceleration behavior, and the behavior when the acquired acceleration is neither greater than the preset maximum acceleration nor less than the preset minimum acceleration is defined as the normal acceleration behavior.

[0029] Furthermore, the braking behavior includes emergency braking behavior, normal braking behavior, and slow braking behavior;

[0030] Under the premise of braking behavior, the behavior when the absolute value of the acquired acceleration is greater than the absolute value of the preset maximum acceleration is defined as the emergency braking behavior, the behavior when the absolute value of the acquired acceleration is less than the absolute value of the preset minimum acceleration is defined as the slow braking behavior, and the behavior when the absolute value of the acquired acceleration is neither greater than the absolute value of the preset maximum acceleration nor less than the absolute value of the preset minimum acceleration is defined as the normal acceleration behavior.

[0031] Furthermore, determining the driver's driving behavior at the current moment based on the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change specifically involves:

[0032] Based on fuzzy logic, the driver's driving behavior at the current moment is obtained from the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change.

[0033] A vehicle speed prediction device based on driving behavior includes:

[0034] The driving data acquisition module is used to acquire the driver's driving data at the current moment. The driving data at the current moment includes the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel change slope, brake pedal travel, and brake pedal travel change slope.

[0035] The vehicle speed prediction model acquisition module is used to determine the driver's driving behavior at the current moment based on the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change, and to acquire a vehicle speed prediction model corresponding to the driver's driving behavior at the current moment; the vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data;

[0036] The vehicle speed prediction output module is used to input the vehicle speed and acceleration at the current moment into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and output the vehicle speed corresponding to a set time period after the current moment.

[0037] An apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the aforementioned vehicle speed prediction method based on driving behavior.

[0038] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the vehicle speed prediction method based on driving behavior.

[0039] Compared with the prior art, the present invention has at least the following beneficial effects:

[0040] This invention provides a vehicle speed prediction method based on driving behavior. It acquires the driver's driving data at the current moment, including vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope. Based on the accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope, the method determines the driver's driving behavior at the current moment and obtains a vehicle speed prediction model corresponding to the driver's driving behavior. The vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data. The current vehicle speed and acceleration are input into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and the output is the vehicle speed within a set time period after the current moment. In other words, by pre-classifying the driver's historical driving data according to driving behavior, and then training Markov models according to the training data corresponding to the classified driving behaviors, multiple speed prediction models corresponding to different driving behaviors are obtained. In actual use, the driving behavior is identified by the driver's current operation, and then the speed prediction model corresponding to the driving behavior is called to predict the speed. The speed predicted in the above way can be closer to the speed corresponding to the driver's actual behavior, thus achieving the goal of improving the accuracy of speed prediction.

[0041] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the specific embodiments of the present invention, the drawings used in the description of the specific embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a flowchart of a vehicle speed prediction method based on driving behavior according to the present invention;

[0044] Figure 2 This is a flowchart of a vehicle speed prediction method based on driving behavior in an implementation scheme;

[0045] Figure 3 This is a block diagram of a vehicle speed prediction device based on driving behavior according to the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] As a specific embodiment of the present invention, combined with Figure 1 and Figure 2 As shown, a vehicle speed prediction method based on driving behavior specifically includes the following steps:

[0048] S1. Obtain the driver's driving data at the current moment, including the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel change slope, brake pedal travel, and brake pedal travel change slope.

[0049] In this embodiment, the slope of the accelerator pedal travel refers to the change in the accelerator pedal travel per unit time, and the slope of the brake pedal travel refers to the change in the brake pedal travel per unit time.

[0050] In this embodiment, the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope at the current moment are all based on data collected from the actual vehicle. Among them, the vehicle speed, accelerator pedal travel, and brake pedal travel must be collected from the actual vehicle. When the acceleration, accelerator pedal travel slope, and brake pedal travel slope cannot be obtained from the actual vehicle, they can be obtained by taking the time derivative of the vehicle speed, accelerator pedal travel, and brake pedal travel.

[0051] S2. Based on the accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope at the current moment, determine the driver's driving behavior at the current moment, and obtain a vehicle speed prediction model corresponding to the driver's driving behavior at the current moment. The vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data.

[0052] Specifically, this implementation method is based on fuzzy logic, and obtains the driver's driving behavior at the current moment based on the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change.

[0053] In this embodiment, the step of training the Markov model using the driver's historical driving data to construct a vehicle speed prediction model specifically includes the following steps:

[0054] a) Obtain the driver's historical driving data, which includes historical driving time and the corresponding vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope.

[0055] Specifically, the driver's historical driving data refers to a sufficient amount of real-world driving data collected from the driver.

[0056] b) Based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope, determine the driver's driving behavior corresponding to the historical driving time. The driving behavior refers to the driver's actions during vehicle speed fluctuations. Vehicle speed fluctuation refers to a current absolute acceleration value exceeding a preset vehicle speed fluctuation acceleration threshold; a current absolute acceleration value less than the preset vehicle speed fluctuation acceleration threshold is considered vehicle speed maintenance, which is not included in the driving behavior. The driving behavior includes two main categories: acceleration behavior and braking behavior.

[0057] Specifically, this implementation method is based on fuzzy logic. Based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel and brake pedal travel slope, the driver's driving behavior corresponding to the historical driving time is obtained.

[0058] Preferably, the acceleration behavior includes emergency acceleration behavior, normal acceleration behavior, and slow acceleration behavior. Specifically, under the premise of acceleration behavior, the behavior when the acquired acceleration is greater than a preset maximum acceleration is defined as the emergency acceleration behavior, the behavior when the acquired acceleration is less than a preset minimum acceleration is defined as the slow acceleration behavior, and the behavior when the acquired acceleration is neither greater than the preset maximum acceleration nor less than the preset minimum acceleration is defined as the normal acceleration behavior.

[0059] In this embodiment, under the premise of acceleration behavior, the preset maximum acceleration is 0.8 m / s². 2 The preset minimum acceleration is 0.2 m / s². 2 .

[0060] Preferably, the braking behavior includes emergency braking, normal braking, and slow braking. Specifically, under the premise of braking behavior, the behavior when the absolute value of the acquired acceleration is greater than the absolute value of a preset maximum acceleration is defined as the emergency braking behavior; the behavior when the absolute value of the acquired acceleration is less than the absolute value of a preset minimum acceleration is defined as the slow braking behavior; and the behavior when the absolute value of the acquired acceleration is neither greater than the absolute value of the preset maximum acceleration nor less than the absolute value of the preset minimum acceleration is defined as the normal acceleration behavior.

[0061] In this embodiment, under the premise of braking behavior, the preset maximum acceleration is -0.8 m / s². 2 The preset minimum acceleration is -0.2 m / s². 2 .

[0062] c) Based on the driving behavior corresponding to the historical driving time, the historical driving time and the vehicle speed and acceleration corresponding to the historical driving time are divided into the driving behavior corresponding to the historical driving time, so as to obtain the training dataset corresponding to different driving behaviors.

[0063] In this embodiment, the historical driving data of the driver with an acceleration greater than 0.8 m / s² is selected. 2 The historical driving time, along with the corresponding vehicle speed and acceleration, is categorized as an emergency acceleration behavior. Data from the driver's historical driving data showing acceleration less than 0.2 m / s² is also considered. 2 The historical driving time, along with the corresponding vehicle speed and acceleration, is categorized as slow acceleration behavior, with acceleration values ​​in the driver's historical driving data not exceeding 0.8 m / s². 2 And not less than 0.2 m / s 2 The historical driving time, along with the corresponding vehicle speed and acceleration, is classified as general acceleration behavior. Similarly, emergency braking, general braking, and slow braking behaviors follow the aforementioned classification principles.

[0064] d) Train the Markov model based on the training dataset corresponding to the different driving behaviors to obtain the vehicle speed prediction model corresponding to the different driving behaviors.

[0065] In other words, different driving behaviors correspond to different vehicle speed prediction models. In this embodiment, the driving behaviors include six types: emergency acceleration, normal acceleration, slow acceleration, emergency braking, normal braking, and slow braking. Each driving behavior has its own training dataset, which includes the driving time and the corresponding vehicle speed and acceleration. The Markov model is trained using the training dataset for each driving behavior to obtain the vehicle speed prediction model for each behavior. In this embodiment, a total of six vehicle speed prediction models are obtained for each of the six driving behaviors.

[0066] Specifically, the Markov model employs a single-order multi-step model to describe the probability distribution of vehicle acceleration state transitions at each prediction time, given the vehicle's current acceleration and speed. The Markov model includes a state space, a state transition frequency matrix, a state transition frequency matrix, and a vehicle speed prediction formula, as detailed below:

[0067] The state space includes the acceleration sequence a s0 and velocity sequence V s0 ; wherein, the acceleration sequence a s0 For a length of L a a min to a max Equally spaced sequences, L a Let a be the number of discrete acceleration states. min For the preset minimum acceleration threshold, a max The preset maximum acceleration threshold; the velocity sequence V s0 For a length of L v 0 to V max Equally spaced sequences, L v V represents the discrete velocity state number. max The preset maximum speed threshold;

[0068] The state transition frequency matrix uses the nearest neighbor algorithm to process the continuous variables in the training dataset and counts the number of times each state transition occurs, as shown below:

[0069]

[0070] Where V(k), a(k), and a(k+m) are continuous variable values ​​in the training dataset, V n a i and a j To represent the discrete variable values ​​in the state space corresponding to the continuous variable values ​​after applying the nearest neighbor rule, k iterates through the training dataset at time intervals Δt = 1, and L p This is the preset prediction step size;

[0071] The state transition frequency matrix is ​​obtained based on the statistical state transition frequency matrix, and is represented as follows:

[0072]

[0073] The vehicle speed prediction formula uses the expectation prediction method, expressed as follows:

[0074]

[0075] Among them, a e (m) represents the expected acceleration at the m-th prediction step, a jj and These represent the acceleration state and its corresponding probability at the m-th prediction step.

[0076] S3. Input the current vehicle speed and acceleration into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and output the vehicle speed corresponding to the time period after the current moment.

[0077] If the vehicle speed is maintained, the vehicle speed will be maintained for a set period of time after the current time, that is, the vehicle speed will be consistent with the current time.

[0078] like Figure 3 As shown, the present invention also provides a vehicle speed prediction device based on driving behavior, used to implement a vehicle speed prediction method based on driving behavior provided by the present invention, specifically including:

[0079] The driving data acquisition module is used to acquire the driver's driving data at the current moment. The driving data at the current moment includes the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel change slope, brake pedal travel, and brake pedal travel change slope.

[0080] The vehicle speed prediction model acquisition module is used to determine the driver's driving behavior at the current moment based on the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change, and to acquire the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment; the vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data.

[0081] The vehicle speed prediction output module is used to input the vehicle speed and acceleration at the current moment into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and output the vehicle speed corresponding to a set time period after the current moment.

[0082] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used to implement a vehicle speed prediction method based on driving behavior.

[0083] In one embodiment of the present invention, a vehicle speed prediction method based on driving behavior, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data.

[0084] The computer storage medium can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs)), optical storage (e.g., CDs, DVDs, BDs, HVDs), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0085] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0087] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0089] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A vehicle speed prediction method based on driving behavior, characterized in that, include: Acquire the driver's driving data at the current moment, which includes the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel change slope, brake pedal travel, and brake pedal travel change slope. Based on the accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope at the current moment, the driver's driving behavior at the current moment is determined, and a vehicle speed prediction model corresponding to the driver's driving behavior at the current moment is obtained; the vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data. The vehicle speed and acceleration at the current moment are input into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and the vehicle speed corresponding to the time period after the current moment is output. The step of training the Markov model using the driver's historical driving data to construct a vehicle speed prediction model includes: The driver's historical driving data is obtained, including historical driving time and the corresponding vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope. Based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope, the driver's driving behavior corresponding to the historical driving time is determined, and the driving behavior includes acceleration behavior and braking behavior. Based on the driving behavior corresponding to the historical driving time, the historical driving time and the vehicle speed and acceleration corresponding to the historical driving time are divided into the driving behavior corresponding to the historical driving time, so as to obtain the training dataset corresponding to different driving behaviors. The Markov model is trained using the training dataset corresponding to the different driving behaviors to obtain the vehicle speed prediction model corresponding to the different driving behaviors.

2. The vehicle speed prediction method based on driving behavior according to claim 1, characterized in that, The Markov model includes a state space, a state transition frequency matrix, a state transition frequency matrix, and a vehicle speed prediction formula. The state space includes acceleration sequences. and velocity sequence ; wherein, the acceleration sequence For length is of arrive Equally spaced sequences, For discrete acceleration states, The preset minimum acceleration threshold, The preset maximum acceleration threshold; the velocity sequence For length is of arrive Equally spaced sequences, For discrete velocity states, The preset maximum speed threshold; The state transition frequency matrix uses the nearest neighbor algorithm to process the continuous variables in the training dataset and counts the number of times each state transition occurs, as shown below: in, , and To train the continuous variable values ​​in the dataset, , and These are the discrete variable values ​​in the state space corresponding to the continuous variable values ​​after applying the nearest neighbor rule. By time interval Traverse the training dataset, This is the preset prediction step size; The state transition frequency matrix is ​​obtained based on the statistical state transition frequency matrix, and is represented as follows: The vehicle speed prediction formula uses the expectation prediction method, expressed as follows: in, For the predicted first Predict the expected acceleration of the step size. and The first Predict the acceleration state of the step size and the corresponding probability.

3. The vehicle speed prediction method based on driving behavior according to claim 1, characterized in that, The method of determining the driver's driving behavior corresponding to the historical driving time based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope is as follows: Based on fuzzy logic, the driver's driving behavior corresponding to the historical driving time is obtained according to the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel and brake pedal travel slope.

4. The vehicle speed prediction method based on driving behavior according to claim 1, characterized in that, The acceleration behavior includes emergency acceleration behavior, general acceleration behavior, and slow acceleration behavior; Under the premise of acceleration behavior, the behavior when the acquired acceleration is greater than the preset maximum acceleration is defined as the emergency acceleration behavior, the behavior when the acquired acceleration is less than the preset minimum acceleration is defined as the slow acceleration behavior, and the behavior when the acquired acceleration is neither greater than the preset maximum acceleration nor less than the preset minimum acceleration is defined as the normal acceleration behavior.

5. The vehicle speed prediction method based on driving behavior according to claim 1, characterized in that, The braking behavior includes emergency braking behavior, normal braking behavior, and slow braking behavior; Under the premise of braking behavior, the behavior when the absolute value of the acquired acceleration is greater than the absolute value of the preset maximum acceleration is defined as the emergency braking behavior, the behavior when the absolute value of the acquired acceleration is less than the absolute value of the preset minimum acceleration is defined as the slow braking behavior, and the behavior when the absolute value of the acquired acceleration is neither greater than the absolute value of the preset maximum acceleration nor less than the absolute value of the preset minimum acceleration is defined as the normal braking behavior.

6. The vehicle speed prediction method based on driving behavior according to claim 1, characterized in that, The step of determining the driver's driving behavior at the current moment based on the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change, specifically involves: Based on fuzzy logic, the driver's driving behavior at the current moment is obtained from the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change.

7. A vehicle speed prediction device based on driving behavior, characterized in that, include: The driving data acquisition module is used to acquire the driver's driving data at the current moment. The driving data at the current moment includes the vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel change slope, brake pedal travel, and brake pedal travel change slope. The vehicle speed prediction model acquisition module is used to determine the driver's driving behavior at the current moment based on the accelerator pedal travel, the slope of the accelerator pedal travel change, the brake pedal travel, and the slope of the brake pedal travel change, and to acquire a vehicle speed prediction model corresponding to the driver's driving behavior at the current moment; the vehicle speed prediction model is constructed by training a Markov model using the driver's historical driving data; The vehicle speed prediction output module is used to input the vehicle speed and acceleration at the current moment into the vehicle speed prediction model corresponding to the driver's driving behavior at the current moment, and output the vehicle speed corresponding to the time period after the current moment. The step of training the Markov model using the driver's historical driving data to construct a vehicle speed prediction model includes: The driver's historical driving data is obtained, including historical driving time and the corresponding vehicle speed, acceleration, accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope. Based on the historical driving time and the corresponding accelerator pedal travel, accelerator pedal travel slope, brake pedal travel, and brake pedal travel slope, the driver's driving behavior corresponding to the historical driving time is determined, and the driving behavior includes acceleration behavior and braking behavior. Based on the driving behavior corresponding to the historical driving time, the historical driving time and the vehicle speed and acceleration corresponding to the historical driving time are divided into the driving behavior corresponding to the historical driving time, so as to obtain the training dataset corresponding to different driving behaviors. The Markov model is trained using the training dataset corresponding to the different driving behaviors to obtain the vehicle speed prediction model corresponding to the different driving behaviors.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a vehicle speed prediction method based on driving behavior as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a vehicle speed prediction method based on driving behavior as described in any one of claims 1 to 6.

Images