Vehicle driver behavior intelligent analysis method and self-adaptive vehicle speed control system

Abstract

The invention relates to the technical field of intelligent driving, and provides a vehicle driver behavior intelligent analysis method, which comprises the following steps of: extracting driving preference data and environment data from historical driving data of each driver, preprocessing to obtain a data set, and taking behavior tendency data of a preset preference index as output to obtain a data set; and cutting the data set into a training set, a test set and a verification set, training the model to enable the prediction precision to reach a preset value, and outputting a trained neural network model. And acquiring real-time data in a vehicle driving process through a vehicle-mounted sensor, and inputting the real-time data into the trained neural network model to obtain behavior tendency data. The invention further discloses a self-adaptive vehicle speed control system, the method and the system can be used for generating a control instruction for vehicle aided driving and individually configuring the vehicle aided driving system by analyzing the individual behavior data of the driver and extracting the individual behavior data of the driver, so that the method and the system can adapt to the traffic environment which changes instantaneously; and the driving safety of the vehicle is further improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an adaptive vehicle speed control system using an intelligent analysis method for vehicle driver behavior. Background Art

[0002] Intelligent driving technology refers to the realization of automatic driving and intelligent assisted driving functions of vehicles through the comprehensive use of multiple technologies such as sensors, computing platforms and artificial intelligence algorithms. It aims to improve driving safety, comfort and efficiency, while reducing human errors and traffic accidents. The use of intelligent transportation system (ITS) and inter-vehicle communication technology enables vehicles to obtain information about roads and other vehicles in a timely manner and make adjustments based on real-time traffic conditions. In particular, as an important part of urban transportation, the safety and efficiency of public transportation vehicles have an important impact on the urban transportation system. Using big data and artificial intelligence technology, the driver's driving behavior is monitored and analyzed in real time, providing personalized driving suggestions and optimization solutions. Therefore, modern intelligent public transportation systems require more flexible and intelligent speed control strategies to improve safety and efficiency.

[0003] CN117698762A discloses an intelligent driving assistance system and method based on environment perception and behavior prediction. The system comprises the following parts: a data acquisition module, a driver behavior recognition module, a sensor analysis module, an obstacle recognition module, an early warning module and a dynamic path planning module; the driver behavior recognition module is used to conduct an in-depth analysis of the driver's behavior data and use the driver's behavior data and environmental data to calculate weighted features; the driver behavior recognition module also fuses the driver's behavior features with the vehicle's sensor data; the driver behavior recognition module is connected to the dynamic path planning module by means of data transmission; the sensor analysis module is used to design a ring-shaped time delay structure for each sensor data to capture the inherent pattern and change trend of the data, and the sensor analysis module is connected to the obstacle recognition module by means of data transmission; the obstacle recognition module fuses the data of multiple sensors such as radar, camera and ultrasonic wave; when an obstacle or a vehicle other than itself is detected, the obstacle recognition module transmits the information to the early warning module; the obstacle recognition module is connected to the early warning module and the dynamic path planning module by means of data transmission; the dynamic path planning module is used to provide the best driving advice according to the driver's behavior and real-time traffic information; a heuristic function is introduced to simulate the influence of traffic flow on speed, and the path is fine-tuned according to real-time traffic information.

[0004] CN113642114B discloses a modeling method for anthropomorphic random car-following driving behavior that may make mistakes, including: S1, original collection of natural driving data, using the SPMD data set as the natural driving big data; S2, extraction of car-following scenes, and generation of a car-following trajectory fragment database; S3, preprocessing of car-following data; and S4, establishment of an anthropomorphic random car-following model that may make mistakes.

[0005] CN110688729B discloses a LSTM-IDM following characteristics fusion method, storage medium and device based on adaptive Kalman filtering. It includes establishing an LSTM model for a single driver, the input of the LSTM model is the vehicle speed, relative speed and relative distance, and the output is the first vehicle acceleration; using the historical data of the single driver to train the LSTM model in batches; using the historical data of the single driver to perform parameter calibration on the IDM model based on a genetic algorithm to obtain the second vehicle acceleration; collecting the current vehicle real-time driving data and transmitting it to the LSTM model and the IDM model respectively; when the amount of collected data reaches a predetermined threshold, updating the parameters of the LSTM model and the IDM model.

[0006] When faced with complex and ever-changing urban traffic environments, the fixed speed control strategy adopted by vehicles does have many limitations. During peak hours or traffic congestion, the fixed speed control strategy cannot adapt to real-time traffic conditions. It cannot be adjusted according to the actual conditions of the road, resulting in vehicle accumulation and traffic congestion. Not considering the behavior of other vehicles and special conditions of the road section may cause the vehicle to be unable to respond in time. For example, in the case of sudden lane changes or braking, it is impossible to respond in time, increasing the risk of accidents. Summary of the invention

[0007] Long-term practice has found that due to individual differences in driving preferences and the diversity and complexity of driving behaviors, it is difficult to accurately, quickly and effectively extract and analyze driver behavior data for assisted driving, and the use of a unified vehicle speed control strategy is difficult to adapt to the ever-changing traffic environment and other technical issues.

[0008] In view of this, the present invention aims to propose a vehicle driver behavior intelligent analysis method, comprising:

[0009] Step S1, extracting driving preference data and environmental data from each driver's historical driving data, wherein the driving preference data includes acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D 1 , accelerator pedal travel D 2 , turning data S; the environmental data includes temperature T, road R and weather data B;

[0010] Step S2: Acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D 1 , accelerator pedal travel D 2 The steering data S, temperature T, road R and weather data B are respectively de-noised by Kalman filtering, outliers are removed by wavelet transform and normalized, and then the acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D are obtained. 1 , accelerator pedal travel D 2 , turn data S, temperature T, road R and weather data B are concatenated to form a multidimensional data set {DR};

[0011] Step S3, performing PCA analysis on the multidimensional data set {DR} to obtain a principal component set {PC}, taking {PC} as input and the behavioral tendency data {DB} of the preset preference index as output, performing supervised learning training on the neural network model, and outputting the trained neural network model when the accuracy reaches a preset value; the neural network model includes an LSTM or a Transformer model;

[0012] Step S4, obtaining real-time data during vehicle driving through on-board sensors, including driving preference data and environmental data, wherein the driving preference data includes acceleration A', speed V', braking frequency H', braking force F', brake pedal travel D' 1 , accelerator pedal travel D' 2 , turning data S '; the environmental data includes temperature T ', road R 'and weather data B ', obtained by processing the data in steps S2 and S3 {PC 1}, input the trained neural network model to obtain the behavior tendency data {DB 1}.

[0013] In one embodiment, the preset preference index is obtained from correlation statistics in traffic accident event data, and the preset preference index at least includes a driving behavior pattern index and a driving habit index.

[0014] In one embodiment, in step S1, the data of {PC} is divided into a training set, a test set, and a validation set in a ratio of 14:3:3.

[0015] In one embodiment, if acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D 1 , accelerator pedal travel D 2 , the sampling period of the steering data S is different. Based on the sampling period with the smallest period, linear interpolation or mean filling method is used to fill the missing values ​​of the time series data.

[0016] In one embodiment, in step S1 , the road data R and the weather data B are converted into numerical values.

[0017] In one embodiment, the normalization process uses minimum-maximum normalization or Z-score.

[0018] The present invention also discloses an adaptive vehicle speed control system based on the above-mentioned vehicle driver behavior intelligent analysis method, the adaptive vehicle speed control system comprises:

[0019] A sensor unit, including different types of vehicle-mounted sensors, for acquiring real-time data during vehicle driving, wherein the real-time data includes driving preference data and environmental data;

[0020] The neural network unit is used to pre-process the real-time data and input it into the neural network model established by the above-mentioned vehicle driver behavior intelligent analysis method to obtain the behavior tendency data {DB 1};

[0021] The vehicle speed control unit is used to 1}, adjust and generate vehicle speed control instructions, and send the vehicle speed control instructions to the vehicle control system for assisted driving.

[0022] In one embodiment, the adaptive vehicle speed control system further includes a communication unit, which is used for transmitting vehicle speed control instructions to the vehicle control system via the CAN protocol, as well as for vehicle-to-vehicle network communication between vehicles.

[0023] The present invention provides an electronic device, at least one processor; and

[0024] a memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned vehicle driver behavior intelligent analysis method.

[0026] The present invention provides a machine-readable storage medium on which instructions are stored, and the instructions are used to enable a machine to execute the vehicle driver behavior intelligent analysis method of the present application as described above.

[0027] The vehicle driver behavior intelligent analysis method disclosed in the present invention extracts driving preference data and environmental data from each driver's historical driving data, pre-processes the driving preference data and environmental data to obtain a data set, and uses the behavior tendency data of the preset preference index as output, cuts the data set into a training set, a test set and a validation set according to a certain ratio, trains the neural network model so that its prediction accuracy reaches a preset value, and then outputs the trained neural network model. Real-time data during vehicle driving is obtained through the on-board sensor, and the trained neural network model is input to obtain behavior tendency data. The present invention also discloses an adaptive vehicle speed control system, which, according to the real-time data obtained by the sensor unit, inputs the neural network model established by the above-mentioned vehicle driver behavior intelligent analysis method to obtain behavior tendency data, which is used to generate vehicle speed control instructions, and sends the vehicle speed control instructions to the whole vehicle control system for assisted driving. The method and system can extract the driver's personalized behavior data by analyzing the individual driver's behavior data, which is used to generate vehicle assisted driving control instructions, and personalize the vehicle assisted driving system, so as to adapt to the ever-changing traffic environment and further improve the safety of vehicle driving.

[0028] Other features and advantages of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and the description thereof are used to explain the present invention and do not constitute improper limitations on the present invention.

[0030] In the attached picture:

[0031] Figure 1 A schematic diagram of a method for intelligent analysis of vehicle driver behavior according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", "third", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] In order to solve the technical problems existing in the prior art, namely, due to individual differences in driving preferences, the diversity and complexity of driving behaviors, it is difficult to accurately, quickly and effectively extract and analyze driver behavior data for assisted driving, and the use of a unified vehicle speed control strategy is difficult to adapt to the ever-changing traffic environment. The present invention provides a vehicle driver behavior intelligent analysis method, such as Figure 1 As shown, a schematic diagram of a vehicle driver behavior intelligent analysis method according to an embodiment of the present invention, the vehicle driver behavior intelligent analysis method comprises:

[0036] Step S1, extracting driving preference data and environmental data from each driver's historical driving data, wherein the driving preference data includes acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D 1 , accelerator pedal travel D 2 , turning data S; the environmental data includes temperature T, road R and weather data B;

[0037] Step S2: Acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D 1 , accelerator pedal travel D 2 The steering data S, temperature T, road R and weather data B are respectively de-noised by Kalman filtering, outliers are removed by wavelet transform and normalized, and then the acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D are obtained. 1 , accelerator pedal travel D 2 , turn data S, temperature T, road R and weather data B are concatenated to form a multidimensional data set {DR};

[0038] Step S3, performing PCA analysis on the multidimensional data set {DR} to obtain a principal component set {PC}, taking {PC} as input and the behavioral tendency data {DB} of the preset preference index as output, performing supervised learning training on the neural network model, and outputting the trained neural network model when the accuracy reaches a preset value; the neural network model includes an LSTM or a Transformer model;

[0039] Step S4, obtaining real-time data during vehicle driving through on-board sensors, including driving preference data and environmental data, wherein the driving preference data includes acceleration A', speed V', braking frequency H', braking force F', brake pedal travel D' 1 , accelerator pedal travel D' 2 , turning data S '; the environmental data includes temperature T ', road R 'and weather data B ', obtained by processing the data in steps S2 and S3 {PC 1}, input the trained neural network model to obtain the behavior tendency data {DB 1}.

[0040] The vehicle driver behavior intelligent analysis method disclosed in the present invention extracts driving preference data and environmental data from each driver's historical driving data, pre-processes the driving preference data and environmental data to obtain a data set, and uses the behavioral tendency data of the preset preference index as output, cuts the data set into a training set, a test set and a validation set according to a certain ratio, trains the neural network model so that its prediction accuracy reaches a preset value, and then outputs the trained neural network model. Real-time data during vehicle driving is obtained through on-board sensors, and input into the trained neural network model to obtain behavioral tendency data. The method can extract personalized driver behavior data by analyzing individual driver behavior data, which is used to generate control instructions for vehicle assisted driving, and personalize the vehicle assisted driving system, so as to adapt to the ever-changing traffic environment and further improve the safety of vehicle driving.

[0041] Since the multidimensional data set spliced ​​after preprocessing driving preference data and environmental data has a high dimension, it will lead to increased computing resource consumption. The dimension reduction method is used to effectively reduce the dimension of the data and improve the computing efficiency and performance of the model. Principal Component Analysis (PCA) converts a set of variables that may be correlated into a set of linearly uncorrelated variables through orthogonal transformation. This new set of variables is called principal components {PC}. PCA projects the data into a new coordinate system through linear transformation, so that the first few principal components of the new coordinate system can retain as much variance of the original data as possible. Each principal component is a linear combination of the original variables and is arranged in descending order according to the size of the variance.

[0042] The output layer is set to a preset preference index to ensure that the output index can accurately reflect driving behavior and habits, and predict the driving behavior pattern index and driving habit index in a multi-output form. In another embodiment of the present invention, the preset preference index is obtained from the correlation statistics of the traffic accident event data, and the preset preference index at least includes a driving behavior pattern index and a driving habit index. For example, the driving behavior pattern index includes the number of frequent emergency braking, the average acceleration and deceleration rate, the steering frequency and angle, and the violation behavior detection. The driving habit index includes daily mileage, driving habits during peak and non-peak hours, weekly driving frequency, and the driver's historical accident record.

[0043] In order to effectively divide the data set into a training set, a validation set and a test set, and prepare for subsequent model training and evaluation, in another embodiment of the present invention, in step S1, the data of {PC} is divided into a training set, a test set and a validation set in a ratio of 14:3:3.

[0044] When processing time series data, especially in applications such as traffic accident analysis, it is important to handle missing values. In another embodiment of the present invention, if acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D 1 , accelerator pedal travel D 2 , steering data S have different sampling periods. Based on the smallest sampling period, linear interpolation or mean filling method is used to fill missing values ​​in time series data. Unify variables with different sampling periods, such as acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D1, accelerator pedal travel D2, and steering data S to the smallest sampling period. Assume that the minimum sampling period is Δt. In order to effectively capture trends, it is suitable for linear or approximately linearly distributed data. Linear interpolation uses the linear relationship between known data points to estimate missing values. For a given time point t, if there are known values ​​before and after it, the following formula is used for interpolation:

[0045]

[0046] Among them, the known time point t 0 and t 1 The corresponding values ​​are Y(t 0 ) and Y(t 1 ), given the time t, to determine the value of Y(t), thus completing the interpolation. Compared with acceleration A and speed V, the steering data appears to change more smoothly and the number of missing values ​​is small, so linear interpolation is a better choice.

[0047] To ensure that the same encoding mechanism is used in the training and testing phases. Road data usually includes road type, road conditions, traffic signs, etc. For ordered category data, label encoding (Label Encoding) or one-hot encoding (One-Hot Encoding) is used to convert category values ​​into integers. For example: highway = 0, urban road = 1, rural road = 2. One-hot encoding (One-Hot Encoding) highway = [1,0,0], urban road = [0,1,0], rural road = [0,0,1]. Weather data usually includes weather conditions (such as sunny, rainy, snowy), temperature, humidity, etc., and the processing method is the same. In another embodiment of the present invention, in step S1, the road R and weather data B are converted into numerical values.

[0048] In order to improve the convergence speed and accuracy of the model, if the data distribution is relatively concentrated and is not very affected by outliers, Z-score normalization is more appropriate. On the contrary, if the data contains obvious boundaries and it is desired to scale the data to a specific range, minimum-maximum normalization may be a better choice. In another embodiment of the present invention, the normalization process adopts minimum-maximum normalization or Z-score.

[0049] The present invention also discloses an adaptive vehicle speed control system based on the above-mentioned vehicle driver behavior intelligent analysis method, the adaptive vehicle speed control system comprises:

[0050] A sensor unit, including different types of vehicle-mounted sensors, for acquiring real-time data during vehicle driving, wherein the real-time data includes driving preference data and environmental data;

[0051] The neural network unit is used to pre-process the real-time data and input it into the neural network model established by the above-mentioned vehicle driver behavior intelligent analysis method to obtain the behavior tendency data {DB 1};

[0052] The vehicle speed control unit is used to 1}, adjust and generate vehicle speed control instructions, and send the vehicle speed control instructions to the vehicle control system for assisted driving.

[0053] The present invention also discloses an adaptive vehicle speed control system, which uses the real-time data acquired by the sensor unit to input the neural network model established by the above-mentioned intelligent analysis method for vehicle driver behavior to obtain behavior tendency data, which is used to generate vehicle speed control instructions, and send the vehicle speed control instructions to the vehicle control system for assisted driving. The system can analyze the individual behavior data of the driver, extract the driver's personalized behavior data, and use it to generate control instructions for vehicle assisted driving, and personalize the vehicle assisted driving system, so as to adapt to the ever-changing traffic environment and further improve the safety of vehicle driving.

[0054] In order to effectively improve the safety and driving comfort of the vehicle, on the highway, through V2V communication, the vehicle adjusts the speed in real time to adapt to the traffic flow and avoid congestion. In an urban environment, the system optimizes the driving speed according to the state of traffic lights and the behavior of surrounding vehicles to improve traffic efficiency. In another embodiment of the present invention, the adaptive speed control system also includes a communication unit, which is used to transmit the speed control command to the vehicle control system through the CAN protocol, and the vehicle-to-vehicle communication between vehicles. CAN has the advantages of strong anti-interference ability and high real-time performance. The CAN protocol (Controller Area Network) communication unit uses the CAN protocol to send the speed control command to the vehicle control system. Through the CAN bus, multiple control units share information in real time, thereby achieving more accurate vehicle speed control. The vehicle-to-vehicle communication between vehicles uses 5G or 6G for communication. Support real-time information exchange between vehicles, such as the speed, acceleration and braking status of the vehicle in front. This information is used to dynamically adjust the vehicle speed and maintain a safe distance.

[0055] The present invention provides an electronic device, at least one processor; and

[0056] a memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned vehicle driver behavior intelligent analysis method.

[0058] The present invention provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the vehicle driver behavior intelligent analysis method as described above in the present application.

[0059] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0060] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0061] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligent analysis of vehicle driver behavior, characterized in that: The vehicle driver behavior intelligent analysis method comprises: Step S1, extracting driving preference data and environmental data from each driver's historical driving data, wherein the driving preference data includes acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D1, accelerator pedal travel D2, and steering data S; and the environmental data includes temperature T, road R, and weather data B; Step S2, using Kalman filtering to remove noise from acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D1, accelerator pedal travel D2, steering data S, temperature T, road R and weather data B, using wavelet transform to remove outliers and normalize them, and then concatenating acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D1, accelerator pedal travel D2, steering data S, temperature T, road R and weather data B to form a multidimensional data set {DR}; Step S3, performing PCA analysis on the multidimensional data set {DR} to obtain a principal component set {PC}, taking {PC} as input and the behavioral tendency data {DB} of the preset preference index as output, performing supervised learning training on the neural network model, and outputting the trained neural network model when the accuracy reaches a preset value; the neural network model includes an LSTM or a Transformer model; Step S4, obtaining real-time data of the vehicle during driving through the on-board sensors, including driving preference data and environmental data. The driving preference data includes acceleration A', speed V', braking frequency H', braking force F', brake pedal travel D'1, accelerator pedal travel D'2, and steering data S'; the environmental data includes temperature T', road R' and weather data B'. {PC1} is obtained after data processing in steps S2 and S3, and is input into the trained neural network model to obtain behavioral tendency data {DB1}.

2. The vehicle driver behavior intelligent analysis method according to claim 1, characterized in that: The preset preference index is obtained from correlation statistics of traffic accident event data, and the preset preference index at least includes a driving behavior pattern index and a driving habit index.

3. The method for intelligent analysis of vehicle driver behavior according to claim 2, characterized in that: In step S1, the data of {PC} is divided into a training set, a test set, and a validation set in a ratio of 14:3:

3.

4. The vehicle driver behavior intelligent analysis method according to claim 1, characterized in that: If the sampling periods of acceleration A, speed V, braking frequency H, braking force F, brake pedal travel D1, accelerator pedal travel D2, and steering data S are different, the missing values ​​of the time series data are filled using linear interpolation or mean filling method based on the sampling period with the smallest period.

5. The vehicle driver behavior intelligent analysis method according to claim 1, characterized in that: In step S1 , the road R and weather data B are converted into numerical values.

6. The method for intelligent analysis of vehicle driver behavior according to any one of claims 1 to 5, characterized in that: The normalization process adopts minimum-maximum normalization or Z-score.

7. An adaptive vehicle speed control system based on the vehicle driver behavior intelligent analysis method according to any one of claims 1 to 6, characterized in that: The adaptive vehicle speed control system comprises: A sensor unit, including different types of vehicle-mounted sensors, for acquiring real-time data during vehicle driving, wherein the real-time data includes driving preference data and environmental data; A neural network unit, used for preprocessing the real-time data and inputting the data into a neural network model established by the vehicle driver behavior intelligent analysis method according to any one of claims 1 to 6 to obtain behavior tendency data {DB1}; The vehicle speed control unit is used to adjust and generate a vehicle speed control instruction according to the behavior tendency data {DB1}, and send the vehicle speed control instruction to the vehicle control system for auxiliary driving.

8. The adaptive vehicle speed control system according to claim 7, characterized in that: The adaptive vehicle speed control system also includes a communication unit, which is used for transmitting vehicle speed control instructions to the vehicle control system through the CAN protocol, as well as vehicle-to-vehicle network communication between vehicles.

9. An electronic device, characterized in that: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle driver behavior intelligent analysis method described in any one of claims 1-6.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute the vehicle driver behavior intelligent analysis method according to any one of claims 1 to 6 of the present invention.

Images