Intelligent vehicle networking detection management system and method under mobile internet
By connecting to the vehicle and machine, obtaining control data, positioning and identifying vehicle trajectories in real time, and identifying driving behaviors, it solves the problem of driver status recognition caused by the lack of image acquisition equipment in the intelligent vehicle connection system, and realizes fatigue driving monitoring and safety of all vehicles Sex improvement.
Patent Information
- Application Number
- CN202411225016.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the intelligent vehicle connection system, vehicles lacking image acquisition equipment cannot effectively identify the driver's status, making it difficult to complete the driver's status identification operation.
By establishing data connection with the vehicle machine, obtaining steering wheel steering data and vehicle speed control data, positioning and identifying vehicle driving trajectories in real time, processing trajectories in segments to generate local driving paths, identify driving behavior based on paths and control data, and matching features to judge fatigue drive.
Fatigue driving judgments that do not rely on cameras are realized, driving safety is improved, and all vehicles can identify and monitor driver status.
Smart Images

Figure CN119095007A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of vehicle detection technology, and in particular to an intelligent vehicle connection detection management system and method under the mobile Internet. Background Art
[0002] Intelligent vehicle connectivity refers to a vehicle system that achieves high levels of interconnection between vehicles and between vehicles and infrastructure through advanced information technology and communication technology. This concept emphasizes the establishment of intelligent communication and data exchange between vehicles and between vehicles and transportation infrastructure, aiming to improve the efficiency, safety and convenience of the transportation system.
[0003] In the current intelligent vehicle networking system, vehicles generally use cameras to capture images to determine the driver's status. Vehicles that do not include image acquisition equipment do not have the above functions and it is difficult to complete the operation of identifying the driver's status. Summary of the invention
[0004] The purpose of the present invention is to provide an intelligent vehicle connection detection management method under the mobile Internet, aiming to solve the problem that for vehicles that do not include image acquisition equipment, they do not have the above-mentioned functions and it is difficult to complete the operation of identifying the driver's status.
[0005] The present invention is implemented as follows: a smart vehicle connection detection management method under mobile Internet, the method comprising:
[0006] Establishing a data connection with the vehicle computer and obtaining vehicle control data from the vehicle computer, wherein the vehicle control data includes steering wheel data and vehicle speed control data;
[0007] Real-time positioning of the vehicle, identification of the vehicle's driving trajectory, segmentation of the driving trajectory based on the vehicle's driving trajectory, and obtaining multiple groups of local driving paths;
[0008] Retrieving corresponding vehicle control data based on the local driving path, performing driving behavior recognition based on the steering wheel data and vehicle speed control data, and generating steering driving behavior data and vehicle speed control behavior data;
[0009] Behavior matching is performed based on steering driving behavior data, vehicle speed control behavior data and local driving path, and fatigue driving judgment is performed based on the matched driving behavior to generate a judgment result.
[0010] Preferably, the steps of positioning the vehicle in real time, identifying the vehicle driving trajectory, and segmenting the driving trajectory based on the vehicle driving trajectory to obtain multiple groups of local driving paths specifically include:
[0011] Acquire vehicle positioning information at preset time intervals, and generate a vehicle driving trajectory based on the vehicle positioning information;
[0012] Identify the curvature of each point in the vehicle's driving trajectory, perform segmentation processing based on the curvature of each point in the vehicle's driving trajectory, and obtain a local driving path;
[0013] The altitude of each point in the local driving path is queried to obtain the path altitude data.
[0014] Preferably, the steps of retrieving corresponding vehicle control data based on the local driving path, performing driving behavior recognition based on the steering wheel data and the vehicle speed control data, and generating steering driving behavior data and vehicle speed control behavior data specifically include:
[0015] Divide the local driving path according to the preset path division step length to obtain multiple path nodes, and retrieve the vehicle control data corresponding to each path node;
[0016] Constructing a steering angle curve for the steering wheel steering data contained in the vehicle control data, extracting steering features based on the steering angle curve, and generating steering driving behavior data;
[0017] A vehicle speed control curve is constructed for the vehicle speed control data contained in the vehicle control data, and acceleration characteristics are extracted based on the vehicle speed control curve to generate vehicle speed control behavior data.
[0018] Preferably, the steps of performing behavior matching based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path, performing fatigue driving judgment based on the matched driving behavior, and generating a judgment result specifically include:
[0019] Constructing a fatigue driving behavior database, wherein the fatigue driving behavior database contains steering characteristics, acceleration characteristics, and slope characteristics corresponding to different fatigue driving behaviors;
[0020] Extract features of steering driving behavior data, vehicle speed control behavior data and local driving paths at preset time intervals to construct node feature combinations;
[0021] A matching threshold is set, and the fatigue driving behavior database is queried based on the node feature combination for matching. If it is less than the matching threshold, it is judged as fatigue driving, and a fatigue driving instruction is generated and executed.
[0022] Preferably, in the step of establishing a data connection with the vehicle computer, the connection is made via Bluetooth or WIFI.
[0023] Another object of the present invention is to provide an intelligent vehicle connection detection and management system under mobile Internet, the system comprising:
[0024] A data acquisition module is used to establish a data connection with the vehicle computer and acquire vehicle control data from the vehicle computer, wherein the vehicle control data includes steering wheel data and vehicle speed control data;
[0025] The path division module is used to locate the vehicle in real time, identify the vehicle's driving trajectory, and segment the driving trajectory based on the vehicle's driving trajectory to obtain multiple groups of local driving paths;
[0026] A behavior recognition module is used to retrieve corresponding vehicle control data based on a local driving path, perform driving behavior recognition based on steering wheel data and vehicle speed control data, and generate steering driving behavior data and vehicle speed control behavior data;
[0027] The fatigue judgment module is used to perform behavior matching based on steering driving behavior data, vehicle speed control behavior data and local driving path, perform fatigue driving judgment based on the matched driving behavior, and generate a judgment result.
[0028] Preferably, the path division module includes:
[0029] A vehicle positioning unit, used to obtain vehicle positioning information at preset time intervals and generate a vehicle driving trajectory based on the vehicle positioning information;
[0030] A path division unit, used for identifying the curvature of each point in the vehicle's driving trajectory, performing segmentation processing based on the curvature of each point in the vehicle's driving trajectory, and obtaining a local driving path;
[0031] The altitude query unit is used to query the altitude of each point in the local driving path to obtain the path altitude data.
[0032] Preferably, the behavior recognition module includes:
[0033] A path segmentation unit is used to divide the local driving path according to a preset path segmentation step to obtain multiple path nodes and retrieve the vehicle control data corresponding to each path node;
[0034] A steering behavior recognition unit, used to construct a steering angle curve for the steering wheel steering data contained in the vehicle control data, extract steering features based on the steering angle curve, and generate steering driving behavior data;
[0035] The vehicle speed control behavior recognition unit is used to construct a vehicle speed control curve for the vehicle speed control data contained in the vehicle control data, extract acceleration features based on the vehicle speed control curve, and generate vehicle speed control behavior data.
[0036] Preferably, the fatigue determination module includes:
[0037] A database construction unit, used to construct a fatigue driving behavior database, wherein the fatigue driving behavior database contains steering characteristics, acceleration characteristics and slope characteristics corresponding to different fatigue driving behaviors;
[0038] A feature combination unit is used to extract features from the steering driving behavior data, the vehicle speed control behavior data and the local driving path at preset time intervals to construct a node feature combination;
[0039] The fatigue judgment unit is used to set a matching threshold and query the fatigue driving behavior database based on the node feature combination for matching. If it is less than the matching threshold, it is judged as fatigue driving, and a fatigue driving instruction is generated and executed.
[0040] Preferably, in the step of establishing a data connection with the vehicle computer, the connection is made via Bluetooth or WIFI.
[0041] The present invention provides an intelligent vehicle connection detection and management method under the mobile Internet. By identifying and counting the vehicle's steering behavior, speed control behavior and the position of the vehicle's path, it determines whether the driver is driving fatigued based on the combination of the above behaviors, thereby realizing a fatigue driving determination process that is independent of the camera and improving driving safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 A flowchart of a smart vehicle connection detection management method under the mobile Internet provided by an embodiment of the present invention;
[0043] Figure 2 A flowchart of the steps of real-time positioning of a vehicle, identifying a vehicle driving trajectory, segmenting the driving trajectory based on the vehicle driving trajectory, and obtaining multiple groups of local driving paths provided by an embodiment of the present invention;
[0044] Figure 3 A flowchart of the steps of retrieving corresponding vehicle control data based on a local driving path, performing driving behavior recognition based on steering wheel data and vehicle speed control data, and generating steering driving behavior data and vehicle speed control behavior data provided by an embodiment of the present invention;
[0045] Figure 4 An architecture diagram of an intelligent vehicle connection detection and management system under the mobile Internet provided by an embodiment of the present invention;
[0046] Figure 5 An architecture diagram of a path division module provided in an embodiment of the present invention;
[0047] Figure 6 An architecture diagram of a behavior recognition module provided by an embodiment of the present invention;
[0048] Figure 7An architecture diagram of a fatigue determination module provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0049] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0050] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.
[0051] like Figure 1 FIG. 1 is a flowchart of a method for intelligent vehicle connection detection and management under mobile Internet provided by an embodiment of the present invention, and the method includes:
[0052] S100, establishing a data connection with the vehicle computer, and acquiring vehicle control data from the vehicle computer, wherein the vehicle control data includes steering wheel data and vehicle speed control data.
[0053] In this step, a data connection is established between the mobile device and the vehicle computer, and the driving data of the vehicle computer can be obtained through the mobile device. The obtained driving data may include the vehicle's throttle data, brake data, steering data, speed data, and positioning data, etc. The mobile device and the vehicle computer communicate via WIFI or Bluetooth. After the mobile device and the vehicle computer complete the data connection, the mobile device can read the vehicle data. In the present invention, the vehicle control data at least includes steering wheel steering data and vehicle speed control data, wherein the steering wheel steering data is the steering wheel rotation angle of the vehicle at each moment, and the vehicle speed control data is the speed of the vehicle at each moment.
[0054] S200, real-time positioning of the vehicle, identification of the vehicle's driving trajectory, segmentation of the driving trajectory based on the vehicle's driving trajectory, and obtaining multiple groups of local driving paths.
[0055] In this step, the vehicle is positioned in real time. During the driving process of the vehicle, the positioning module built into the vehicle body is used to continuously position the vehicle to obtain the real-time position of the vehicle. The real-time positions are connected in series according to the positioning order to obtain the vehicle's driving trajectory. The positioning information of the above-mentioned vehicle can also be obtained through a mobile device. The positioning data of the two are overlapping. The vehicle will have different driving behaviors under different driving conditions. For example, the throttle opening will be increased in an uphill position, and conversely, the throttle opening may be reduced in a downhill position. The entire vehicle driving trajectory is divided into multiple local driving paths based on the curvature of the road.
[0056] S300, retrieve corresponding vehicle control data based on the local driving path, perform driving behavior recognition based on steering wheel data and vehicle speed control data, and generate steering driving behavior data and vehicle speed control behavior data.
[0057] In this step, the corresponding vehicle control data is retrieved based on the local driving path. Both the vehicle control data and the local driving path are data based on time series, and both have the same time series. The vehicle control data is segmented according to the time interval corresponding to the local driving path to obtain vehicle control data whose time interval matches the local driving path. According to the changes in the steering wheel steering data and the vehicle speed in the vehicle control data, the steering behavior and the vehicle speed control behavior are determined to obtain the steering driving behavior data and the vehicle speed control behavior data.
[0058] S400, performing behavior matching based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path, performing fatigue driving judgment based on the matched driving behavior, and generating a judgment result.
[0059] In this step, behavior matching is performed based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path. The steering behavior and the vehicle speed control behavior are divided into multiple intervals, such as left turning behavior and right turning behavior, and further divided into N-level left turning behavior and N-level right turning behavior. The higher the level of the steering behavior, the faster the angle changes. Similarly, the vehicle speed control behavior includes acceleration control behavior and deceleration control behavior, which is further subdivided into N-level acceleration control behavior and N-level deceleration control behavior. The road is also divided into multiple road conditions, such as straight lanes, left turn lanes and right turn lanes. The lane levels are divided according to the turning radius, such as N-level left turn lanes and N-level right turn lanes. Based on the combination of steering behavior, vehicle speed control behavior and road level, it is determined whether the user is in fatigue driving. If so, a judgment result is generated and the user is prompted according to the judgment result.
[0060] like Figure 2As shown, as a preferred embodiment of the present invention, the steps of real-time positioning of the vehicle, identifying the vehicle driving trajectory, segmenting the driving trajectory based on the vehicle driving trajectory, and obtaining multiple groups of local driving paths specifically include:
[0061] S201, obtaining vehicle positioning information at preset time intervals, and generating a vehicle driving trajectory based on the vehicle positioning information.
[0062] In this step, the vehicle positioning information is obtained at preset time intervals. Specifically, the GPS positioning data can be obtained every 500ms. The GPS data should include the longitude and latitude data of the vehicle. The vehicle's driving trajectory is determined based on the map and positioning data. The vehicle's driving trajectory should coincide with the road in the map.
[0063] S202, identifying the curvature of each point in the vehicle driving trajectory, performing segmentation processing based on the curvature of each point in the vehicle driving trajectory, and obtaining a local driving path. The process of identifying the curvature of each point in the vehicle driving trajectory has the following relationship:
[0064]
[0065] Among them, k i represents the curvature of the ith position point, x′, y′ represent the first-order derivatives of the longitude and latitude of the position point with respect to time t, i.e., the velocity component; x″, y″ represent the second-order derivatives of the longitude and latitude of the position point with respect to time t, i.e., the acceleration component; γ represents the weight coefficient used to adjust the comprehensive effect of velocity change on curvature, t represents time, v represents velocity, dv represents the change in velocity, dt represents the change in time, It represents the derivative of velocity v with respect to time t, that is, the rate at which velocity changes with time.
[0066] Curvature is a measure of how a track is curved. The present invention can analyze the shape of a track by calculating the curvature of each point on the track. In the process of calculating the curvature, by considering the velocity and acceleration components of the track points, the curvature of the track can be more accurately reflected. In addition, the weight coefficient γ is introduced so that the curvature calculation can flexibly adjust the sensitivity to speed changes and adapt to different road conditions. This allows the present invention to better adapt to changes in speed and acceleration during actual driving and improve the accuracy of the analysis.
[0067] In this step, the curvature of each point in the vehicle's driving trajectory is identified. For different road conditions, the driver needs to adopt different driving strategies. The curvature of each point in the vehicle's driving trajectory is calculated according to a preset calculation formula. The larger the curvature, the larger the arc of the point. When segmenting, when the change value of the curvature within the preset path length is greater than the preset value, segmentation is performed at this location. If the curvature change still fails to reach the preset value, segmentation is performed at the preset length position to obtain a local driving path.
[0068] S203, querying the altitude of each point in the local driving path to obtain path altitude data, and the corresponding process has the following relationship:
[0069]
[0070] Among them, h i represents the altitude of the i-th position point, H0 represents the altitude of the initial position, β represents the weight coefficient used to adjust the effect of acceleration on altitude change, and a j represents the acceleration of the jth position, Δh j Indicates the change in altitude from the j-1th position to the jth position. The calculation formula for the change in altitude is as follows:
[0071] Δh j =H j -H j-1 ;
[0072] Among them, H j , H j-1 They represent the altitudes of the j-th and j-1-th points respectively.
[0073] The present invention can accurately determine the actual altitude of the vehicle in the path by considering the altitude change of each point. And according to the change of altitude data, it can effectively identify whether the vehicle is going uphill or downhill, which is helpful to analyze the driver's operating behavior. It improves the adaptability to actual driving conditions and makes the calculation results more accurate.
[0074] By combining the changes in curvature and altitude, driving behavior can be analyzed from multiple angles to more comprehensively evaluate the driver's operating behavior and route selection. This can better reflect the dynamic changes in real driving scenarios and improve the analysis quality and credibility of driving data.
[0075] In this step, the altitude of each point in the local driving path is queried, and the altitude data corresponding to the point is queried based on the positioning data. According to the change of the altitude data, it can be determined whether the point is uphill or downhill, so that the driver's operating behavior can be identified from multiple angles.
[0076] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of retrieving corresponding vehicle control data based on the local driving path, performing driving behavior recognition based on the steering wheel data and the vehicle speed control data, and generating steering driving behavior data and vehicle speed control behavior data specifically include:
[0077] S301, dividing the local driving path according to a preset path division step to obtain a plurality of path nodes, and retrieving vehicle control data corresponding to each path node.
[0078] In this step, the local driving path is divided according to the preset path division step. Specifically, 50m can be used as a path division step. Then the corresponding vehicle control data can be extracted, including steering behavior data and vehicle speed control data, and the altitude data, that is, the road parameter data, can be obtained synchronously.
[0079] S302, calculating the steering wheel data at each time point, the corresponding process has the following relationship:
[0080]
[0081] Among them, θ(t) represents the steering wheel angle at time t, θ0 represents the initial steering wheel angle, ω(t′) represents the steering wheel steering rate at time t′, which directly affects the steering angle; α′ represents the weight coefficient used to adjust the influence of vehicle speed change on the steering angle, represents the acceleration at time t′, represents the influence of the vehicle speed change rate on the steering angle, and its weight is adjusted by the coefficient α′; β′ represents the weight coefficient used to adjust the influence of altitude change on the steering angle, h(t′) represents the altitude at time t′, β′h(t′) represents the influence of altitude on the steering angle, and its weight is adjusted by the coefficient β′;
[0082] A steering angle curve is constructed for the steering wheel steering data contained in the vehicle control data. Steering features are extracted based on the steering angle curve to generate steering driving behavior data. The steering features have the following relationship:
[0083] θ 特征 =[max(θ),min(θ),f(θ),k(θ),σ(θ)];
[0084] Among them, θ 特征 represents the steering feature, max(θ) represents the maximum value of the steering wheel steering angle, min(θ) represents the minimum value of the steering wheel steering angle, f(θ) represents the frequency feature of the steering wheel steering angle, σ(θ) represents the standard deviation of the steering wheel steering angle, and k(θ) represents the curvature of the steering angle curve;
[0085] The calculation process of the curvature of the steering angle curve has the following relationship:
[0086]
[0087] Wherein, θ′, θ″ represent the first and second order derivatives of the steering angle, respectively.
[0088] The calculation process of the standard deviation of the steering wheel angle has the following relationship:
[0089]
[0090] Among them, θ n represents the steering wheel angle at each time point, represents the average steering wheel angle, and N represents the number of data points.
[0091] In this step, a steering angle curve is constructed for the steering wheel steering data contained in the vehicle control data. By constructing the curve, curve features contained in the curve, such as peaks, troughs, frequency, curvature, etc., can be extracted. The above features are used as steering features, and the driving behavior is determined based on the above steering features to obtain steering driving behavior data.
[0092] S303, calculating the vehicle speed control data at each time point, the corresponding process has the following relationship:
[0093]
[0094] Where v(t) represents the vehicle speed at time t, v0 represents the initial vehicle speed, γ represents the weight coefficient used to adjust the influence of steering angle and altitude change on vehicle speed, θ(t′) represents the steering angle at time t′, δ represents the coefficient used to adjust the influence of altitude change on acceleration, h(t′) represents the altitude at time T′, and a(t′) represents the acceleration at time t′, which is the direct factor of vehicle speed change.
[0095] A speed control curve is constructed for the speed control data contained in the vehicle control data, and acceleration characteristics are extracted based on the speed control curve to generate speed control behavior data. The acceleration characteristics are in the following relationship:
[0096] v 特征 =[max(v),min(v),f(v),k(v),σ(v)];
[0097] Among them, v feature represents the acceleration feature, maX(v) represents the maximum value of the vehicle speed, min(v) represents the minimum value of the vehicle speed, f(v) represents the frequency feature of the vehicle speed, σ(v) represents the standard deviation of the vehicle speed, and k(v) represents the curvature of the vehicle speed curve;
[0098] The calculation process of the curvature of the speed curve has the following relationship:
[0099]
[0100] Where v′, v″ represent the first and second order derivatives of vehicle speed respectively;
[0101] The calculation process of the standard deviation of vehicle speed has the following relationship:
[0102]
[0103] Among them, v n represents the vehicle speed at each time point, Indicates average vehicle speed.
[0104] In this step, a speed control curve is constructed for the speed control data contained in the vehicle operation data. In the same way, curve features contained in the curve, such as peaks, troughs, frequency, curvature, etc., are extracted. The above features are used as acceleration features, and the speed control behavior is determined according to the speed change rate to generate speed control behavior data.
[0105] The present invention constructs a steering angle curve and a vehicle speed control curve, and extracts multiple features based on the angle curve and the vehicle speed control curve, so as to comprehensively and accurately describe the driver's steering behavior. Therefore, it can not only capture the driver's immediate reaction, but also reveal the signs of fatigue caused by long-term driving, and improve the accuracy and robustness of fatigue driving detection.
[0106] As a preferred embodiment of the present invention, the steps of performing behavior matching based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path, performing fatigue driving judgment based on the matched driving behavior, and generating a judgment result specifically include:
[0107] S401, constructing a fatigue driving behavior database, wherein the fatigue driving behavior database contains steering characteristics, acceleration characteristics, and slope characteristics corresponding to different fatigue driving behaviors.
[0108] In this step, a fatigue driving behavior database is constructed. By performing data labeling, the curve characteristics corresponding to fatigue driving are determined and stored in the driving fatigue database. The fatigue driving behavior database contains steering characteristics, acceleration characteristics and slope characteristics corresponding to different fatigue driving behaviors.
[0109] S402: extracting features from the steering driving behavior data, the vehicle speed control behavior data and the local driving path at preset time intervals to construct a node feature combination.
[0110] S403, setting a matching threshold, querying the fatigue driving behavior database based on the node feature combination for matching, if it is less than the matching threshold, it is determined to be fatigue driving, generating a fatigue driving instruction, and executing it. The process of querying the fatigue driving behavior database based on the node feature combination has the following relationship:
[0111]
[0112] Where d(·) represents the Euclidean distance calculation. The smaller the distance, the more similar it is. D(t, l) represents the similarity between the current feature combination and the feature in the database. θ 特征 (t) represents the turning characteristics at time t, represents the lth steering sample, v 特征 (t) represents the acceleration characteristic at time t, represents the lth acceleration sample, γ 特征 (t) represents the slope characteristics at time t, represents the lth slope sample, w θ , w v , w γ They represent the weights of steering feature, vehicle speed feature and slope feature respectively.
[0113] In this step, feature extraction is performed on the steering driving behavior data, vehicle speed control behavior data and local driving path at preset time intervals. Since the driving data in each time step, including steering features, acceleration features and slope features, has been determined in a segmented manner, the driving data in each time step is comprehensively compared with the data in the fatigue driving behavior database to determine whether the driver is in a fatigue driving state. Therefore, multiple features can be effectively considered comprehensively to improve the accuracy of fatigue driving judgment.
[0114] like Figure 4 As shown, an intelligent vehicle connection detection and management system under the mobile Internet provided by an embodiment of the present invention, the system includes:
[0115] The data acquisition module 100 is used to establish a data connection with the vehicle computer and acquire vehicle control data from the vehicle computer. The vehicle control data includes steering wheel data and vehicle speed control data.
[0116] In this system, the data acquisition module 100 establishes a data connection with the vehicle computer through a mobile device, and the driving data of the vehicle computer can be acquired through the mobile device. The acquired driving data may include the vehicle's throttle data, brake data, steering data, speed data, and positioning data, etc. The mobile device and the vehicle computer communicate via WIFI or Bluetooth. After the mobile device and the vehicle computer complete the data connection, the mobile device can read the vehicle data. In the present invention, the vehicle control data at least includes steering wheel steering data and vehicle speed control data, wherein the steering wheel steering data is the steering wheel rotation angle of the vehicle at each moment, and the vehicle speed control data is the speed of the vehicle at each moment.
[0117] The path division module 200 is used to locate the vehicle in real time, identify the vehicle's driving trajectory, and segment the driving trajectory based on the vehicle's driving trajectory to obtain multiple groups of local driving paths.
[0118] In this system, the path division module 200 performs real-time positioning of the vehicle. During the driving process of the vehicle, the positioning module on the vehicle body is used to continuously perform positioning to obtain the real-time position of the vehicle. The real-time positions are connected in series according to the positioning order to obtain the vehicle's driving trajectory. The positioning information of the above-mentioned vehicle can also be obtained through a mobile device. The positioning data of the two are overlapping. The vehicle will have different driving behaviors under different driving conditions. For example, the throttle opening will be increased in an uphill position, and conversely, the throttle opening may be reduced in a downhill position. The entire vehicle driving trajectory is divided into multiple local driving paths based on the curvature of the road.
[0119] The behavior recognition module 300 is used to retrieve corresponding vehicle control data based on the local driving path, perform driving behavior recognition based on the steering wheel data and the vehicle speed control data, and generate steering driving behavior data and vehicle speed control behavior data.
[0120] In this system, the behavior recognition module 300 retrieves the corresponding vehicle control data based on the local driving path. Both the vehicle control data and the local driving path are time series data, and both have the same time series. The vehicle control data is segmented according to the time interval corresponding to the local driving path to obtain vehicle control data whose time interval matches the local driving path. According to the steering wheel steering data and vehicle speed changes in the vehicle control data, the steering behavior and vehicle speed control behavior are determined to obtain the steering driving behavior data and vehicle speed control behavior data.
[0121] The fatigue determination module 400 is used to perform behavior matching based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path, perform fatigue driving judgment based on the matched driving behavior, and generate a judgment result.
[0122] In this system, the fatigue judgment module 400 performs behavior matching based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path. The steering behavior and the vehicle speed control behavior are divided into multiple intervals, such as left turning behavior and right turning behavior, and further divided into N-level left turning behavior and N-level right turning behavior. The higher the level of the steering behavior, the faster the angle changes. Similarly, the vehicle speed control behavior includes acceleration control behavior and deceleration control behavior, which is further subdivided into N-level acceleration control behavior and N-level deceleration control behavior. The road is also divided into multiple road conditions, such as straight lanes, left turn lanes and right turn lanes. The lane levels are divided according to the turning radius, such as N-level left turn lanes and N-level right turn lanes. Based on the combination of steering behavior, vehicle speed control behavior and road level, it is determined whether the user is in fatigue driving. If so, a judgment result is generated and the user is prompted according to the judgment result.
[0123] like Figure 5 As shown, as a preferred embodiment of the present invention, the path division module 200 includes:
[0124] The vehicle positioning unit 201 is used to obtain vehicle positioning information at preset time intervals and generate a vehicle driving trajectory based on the vehicle positioning information.
[0125] In this module, the vehicle positioning unit 201 obtains the vehicle positioning information at a preset time interval. Specifically, the GPS positioning data can be obtained every 500ms. The GPS data should include the longitude data and latitude data of the vehicle. The vehicle driving trajectory is determined according to the map and positioning data. The vehicle driving trajectory should coincide with the road in the map.
[0126] The path division unit 202 is used to identify the curvature of each point in the vehicle driving trajectory, and perform segmentation processing based on the curvature of each point in the vehicle driving trajectory to obtain a local driving path.
[0127] In this module, the path division unit 202 identifies the curvature of each point in the vehicle's driving trajectory. For different road conditions, the driver needs to adopt different driving strategies. The curvature of each point in the vehicle's driving trajectory is calculated according to a preset calculation formula. The larger the curvature, the larger the arc of the point. When segmenting, when the change value of the curvature within the preset path length is greater than the preset value, segmentation is performed at this location. If the curvature change still fails to reach the preset value, segmentation is performed at the preset length position to obtain a local driving path.
[0128] The altitude query unit 203 is used to query the altitude of each point in the local driving path to obtain path altitude data.
[0129] In this module, the altitude query unit 203 queries the altitude of each point in the local driving path, queries the altitude data corresponding to the point according to the positioning data, and determines whether the point is uphill or downhill according to the change of the altitude data, thereby being able to identify the driver's operating behavior from multiple angles.
[0130] like Figure 6 As shown, as a preferred embodiment of the present invention, the behavior recognition module 300 includes:
[0131] The path segmentation unit 301 is used to divide the local driving path according to a preset path segmentation step to obtain multiple path nodes and retrieve the vehicle control data corresponding to each path node.
[0132] In this module, the path segmentation unit 301 divides the local driving path according to the preset path division step. Specifically, 50m can be used as a path division step. Then, the corresponding vehicle control data can be extracted, including steering behavior data and vehicle speed control data, and the altitude data, that is, the road parameter data, can be obtained synchronously.
[0133] The steering behavior recognition unit 302 is used to construct a steering angle curve for the steering wheel steering data included in the vehicle control data, extract steering features based on the steering angle curve, and generate steering driving behavior data.
[0134] In this module, the steering behavior recognition unit 302 constructs a steering angle curve for the steering wheel steering data contained in the vehicle control data. By constructing the curve, the curve features contained in the curve, such as peaks, troughs, frequency, curvature, etc., can be extracted. The above features are used as steering features, and the driving behavior is determined according to the above steering features to obtain steering driving behavior data.
[0135] The vehicle speed control behavior recognition unit 303 is used to construct a vehicle speed control curve for the vehicle speed control data included in the vehicle control data, extract acceleration features based on the vehicle speed control curve, and generate vehicle speed control behavior data.
[0136] In this module, the vehicle speed control behavior identification unit 303 constructs a vehicle speed control curve for the vehicle speed control data contained in the vehicle operation data, and in the same way, extracts curve features contained in the curve, such as peaks, troughs, frequency, curvature, etc., and uses the above features as acceleration features. The vehicle speed control behavior is determined according to the vehicle speed change rate to generate vehicle speed control behavior data.
[0137] like Figure 7 As shown, as a preferred embodiment of the present invention, the fatigue determination module 400 includes:
[0138] The database construction unit 401 is used to construct a fatigue driving behavior database, wherein the fatigue driving behavior database contains steering characteristics, acceleration characteristics and slope characteristics corresponding to different fatigue driving behaviors.
[0139] In this module, the database construction unit 401 constructs a fatigue driving behavior database, determines the curve characteristics corresponding to fatigue driving by performing data labeling, and stores them in the driving fatigue database. The fatigue driving behavior database contains steering characteristics, acceleration characteristics and slope characteristics corresponding to different fatigue driving behaviors.
[0140] The feature combination unit 402 is used to extract features from the steering driving behavior data, the vehicle speed control behavior data and the local driving path at preset time intervals to construct a node feature combination.
[0141] The fatigue determination unit 403 is used to set a matching threshold, query the fatigue driving behavior database based on the node feature combination for matching, and if it is less than the matching threshold, it is determined as fatigue driving, and a fatigue driving instruction is generated and executed.
[0142] In this module, feature extraction is performed on the steering driving behavior data, vehicle speed control behavior data and local driving path at preset time intervals. Since the driving data in each time step, including steering features, acceleration features and slope features, has been determined in a segmented manner, the driving data in each time step is comprehensively compared with the data in the fatigue driving behavior database to determine whether the driver is in a fatigue driving state.
[0143] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.
[0144] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0145] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0146] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
[0147] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A smart vehicle connection detection management method under mobile Internet, characterized in that: The method comprises the following steps: Establishing a data connection with the vehicle computer and obtaining vehicle control data from the vehicle computer, wherein the vehicle control data includes steering wheel data and vehicle speed control data; Real-time positioning of the vehicle, identification of the vehicle's driving trajectory, segmentation of the driving trajectory based on the vehicle's driving trajectory, and obtaining multiple groups of local driving paths; Retrieving corresponding vehicle control data based on the local driving path, performing driving behavior recognition based on the steering wheel data and vehicle speed control data, and generating steering driving behavior data and vehicle speed control behavior data; Behavior matching is performed based on steering driving behavior data, vehicle speed control behavior data and local driving path, and fatigue driving judgment is performed based on the matched driving behavior to generate a judgment result.
2. The intelligent vehicle connection detection management method under the mobile Internet according to claim 1 is characterized in that: The steps of positioning the vehicle in real time, identifying the vehicle's driving trajectory, and segmenting the driving trajectory based on the vehicle's driving trajectory to obtain multiple groups of local driving paths specifically include: Acquire vehicle positioning information at preset time intervals, and generate a vehicle driving trajectory based on the vehicle positioning information; Identify the curvature of each point in the vehicle's driving trajectory, perform segmentation processing based on the curvature of each point in the vehicle's driving trajectory, and obtain a local driving path. The process of identifying the curvature of each point in the vehicle's driving trajectory has the following relationship: Among them, k i represents the curvature of the ith position point, x′(t), y′(t) represent the first-order derivatives of the longitude and latitude of the position point with respect to time t, i.e., the velocity component; x″(T), y″(t) represent the second-order derivatives of the longitude and latitude of the position point with respect to time t, i.e., the acceleration component; γ represents the weight coefficient used to adjust the comprehensive effect of velocity change on curvature, t represents time, v represents velocity, dv represents the change in velocity, and dt represents the change in time; It represents the derivative of velocity v with respect to time t, that is, the rate at which velocity changes with time; The altitude of each point in the local driving path is queried to obtain the path altitude data. The corresponding process has the following relationship: Among them, h i represents the altitude of the i-th position point, i and j represent two adjacent position points in the local driving path, H0 represents the altitude of the initial position, β represents the weight coefficient used to adjust the influence of acceleration on altitude change, and a j represents the acceleration of the jth position, Δh j Indicates the change in altitude from the j-1th position to the jth position. The calculation formula for the change in altitude is as follows: Δh j =H j -H j-1 ; Among them, H j , H j-1 They represent the altitudes of the j-th and j-1-th locations respectively.
3. The intelligent vehicle connection detection management method under the mobile Internet according to claim 2 is characterized in that: The steps of retrieving corresponding vehicle control data based on the local driving path, performing driving behavior recognition based on the steering wheel data and the vehicle speed control data, and generating steering driving behavior data and vehicle speed control behavior data specifically include: Divide the local driving path according to the preset path division step length to obtain multiple path nodes, and retrieve the vehicle control data corresponding to each path node; Calculate the steering wheel data at each time point. The corresponding process has the following relationship: Among them, θ(t) represents the steering wheel angle at time t, θ0 represents the initial steering wheel angle, ω(t′) represents the steering wheel steering rate at time t′, which directly affects the steering angle; α′ represents the weight coefficient used to adjust the influence of vehicle speed change on the steering angle, represents the acceleration at time t′, represents the influence of the vehicle speed change rate on the steering angle, and its weight is adjusted by the coefficient α′; β′ represents the weight coefficient used to adjust the influence of altitude change on the steering angle, h(t′) represents the altitude at time t′, β′h(t′) represents the influence of altitude on the steering angle, and its weight is adjusted by the coefficient β′; A steering angle curve is constructed for the steering wheel steering data contained in the vehicle control data. Steering features are extracted based on the steering angle curve to generate steering driving behavior data. The steering features have the following relationship: i 特征 = [max(θ), min(θ), f(θ), k(θ), σ(θ)]; Among them, θ 特征 represents the steering feature, max(θ) represents the maximum value of the steering wheel steering angle, min(θ) represents the minimum value of the steering wheel steering angle, f(θ) represents the frequency feature of the steering wheel steering angle, σ(θ) represents the standard deviation of the steering wheel steering angle, and k(θ) represents the curvature of the steering angle curve; The calculation process of the curvature of the steering angle curve has the following relationship: Where θ′, θ″ represent the first and second order derivatives of the steering angle, respectively; The calculation process of the standard deviation of the steering wheel angle has the following relationship: Among them, θ n represents the steering wheel angle at each time point, represents the average steering wheel steering angle, and N represents the number of data points; Calculate the vehicle speed control data at each time point, and the corresponding process has the following relationship: Where v(t) represents the vehicle speed at time t, v0 represents the initial vehicle speed, γ represents the weight coefficient used to adjust the influence of steering angle and altitude change on vehicle speed, θ(t′) represents the steering angle at time t′, δ represents the coefficient used to adjust the influence of altitude change on acceleration, h(t′) represents the altitude at time t′, a(t′) represents the acceleration at time t′, which is the direct factor of vehicle speed change, where A speed control curve is constructed for the speed control data contained in the vehicle control data, and acceleration characteristics are extracted based on the speed control curve to generate speed control behavior data. The acceleration characteristics are in the following relationship: v 特征 = [max(v), min(v), f(v), k(v), σ(v)]; Among them, v 特征 represents the acceleration characteristic, max(v) represents the maximum value of the vehicle speed, min(v) represents the minimum value of the vehicle speed, f(v) represents the frequency characteristic of the vehicle speed, σ(v) represents the standard deviation of the vehicle speed, and k(v) represents the curvature of the vehicle speed curve; The calculation process of the curvature of the speed curve has the following relationship: Where, v′, v" represent the first and second order derivatives of vehicle speed respectively; The calculation process of the standard deviation of vehicle speed has the following relationship: Among them, v n represents the vehicle speed at each time point, Indicates average vehicle speed.
4. The intelligent vehicle connection detection management method under the mobile Internet according to claim 3 is characterized in that: The steps of performing behavior matching based on the steering driving behavior data, the vehicle speed control behavior data and the local driving path, performing fatigue driving judgment based on the matched driving behavior, and generating a judgment result specifically include: Constructing a fatigue driving behavior database, wherein the fatigue driving behavior database contains steering characteristics, acceleration characteristics, and slope characteristics corresponding to different fatigue driving behaviors; Extract features of steering driving behavior data, vehicle speed control behavior data and local driving paths at preset time intervals to construct node feature combinations; A matching threshold is set, and the fatigue driving behavior database is queried based on the node feature combination for matching. If it is less than the matching threshold, it is determined to be fatigue driving, and a fatigue driving instruction is generated and executed. The process of querying the fatigue driving behavior database based on the node feature combination has the following relationship: Where d(·) represents the Euclidean distance calculation operation, D(t, l) represents the similarity value between the current feature combination and the feature in the database, and θ 特征 (t) represents the turning characteristics at time t, represents the,th steering sample, V 特征 (t) represents the acceleration characteristic at time t, represents the lth acceleration sample, γ 特征 (t) represents the slope characteristics at time t, represents the lth slope sample, w θ , w v , w γ They represent the weights of steering feature, vehicle speed feature and slope feature respectively.
5. The intelligent vehicle connection detection management method under the mobile Internet according to claim 4 is characterized in that: In the step of establishing a data connection with the vehicle computer, connect via Bluetooth or WIFI.
6. An intelligent vehicle connection detection and management system under mobile Internet, characterized in that: The intelligent vehicle connection detection management method under the mobile Internet as claimed in any one of claims 1 to 5 is applied, and the system includes: A data acquisition module is used to establish a data connection with the vehicle computer and acquire vehicle control data from the vehicle computer, wherein the vehicle control data includes steering wheel data and vehicle speed control data; The path division module is used to locate the vehicle in real time, identify the vehicle's driving trajectory, and segment the driving trajectory based on the vehicle's driving trajectory to obtain multiple groups of local driving paths; A behavior recognition module is used to retrieve corresponding vehicle control data based on a local driving path, perform driving behavior recognition based on steering wheel data and vehicle speed control data, and generate steering driving behavior data and vehicle speed control behavior data; The fatigue judgment module is used to perform behavior matching based on steering driving behavior data, vehicle speed control behavior data and local driving path, perform fatigue driving judgment based on the matched driving behavior, and generate a judgment result.
7. The intelligent vehicle connection detection and management system under the mobile Internet according to claim 6 is characterized in that: The path division module comprises: A vehicle positioning unit, used to obtain vehicle positioning information at preset time intervals and generate a vehicle driving trajectory based on the vehicle positioning information; A path division unit, used for identifying the curvature of each point in the vehicle's driving trajectory, performing segmentation processing based on the curvature of each point in the vehicle's driving trajectory, and obtaining a local driving path; The altitude query unit is used to query the altitude of each point in the local driving path to obtain the path altitude data.
8. The intelligent vehicle connection detection and management system under the mobile Internet according to claim 7 is characterized in that: The behavior recognition module includes: A path segmentation unit is used to divide the local driving path according to a preset path segmentation step to obtain multiple path nodes and retrieve the vehicle control data corresponding to each path node; A steering behavior recognition unit, used to construct a steering angle curve for the steering wheel steering data contained in the vehicle control data, extract steering features based on the steering angle curve, and generate steering driving behavior data; The vehicle speed control behavior recognition unit is used to construct a vehicle speed control curve for the vehicle speed control data contained in the vehicle control data, extract acceleration features based on the vehicle speed control curve, and generate vehicle speed control behavior data.
9. The intelligent vehicle connection detection and management system under the mobile Internet according to claim 8, characterized in that: The fatigue determination module comprises: A database construction unit, used to construct a fatigue driving behavior database, wherein the fatigue driving behavior database contains steering characteristics, acceleration characteristics and slope characteristics corresponding to different fatigue driving behaviors; A feature combination unit is used to extract features from the steering driving behavior data, the vehicle speed control behavior data and the local driving path at preset time intervals to construct a node feature combination; The fatigue judgment unit is used to set a matching threshold and query the fatigue driving behavior database based on the node feature combination for matching. If it is less than the matching threshold, it is judged as fatigue driving, and a fatigue driving instruction is generated and executed.
10. The intelligent vehicle connection detection and management system under the mobile Internet according to claim 9, characterized in that: In the step of establishing a data connection with the vehicle computer, connect via Bluetooth or WIFI.
