CN111967415A - Behavior prediction method based on data analysis, vehicle control method and system - Google Patents

Abstract

The invention discloses a behavior prediction method, vehicle control method and system based on data analysis, which can exclude most drivers with low probability of dangerous driving from the detection of dangerous driving probability by means of data analysis. High-level drivers perform mandatory dangerous driving probability detection when operating a motor vehicle, which can not only effectively eliminate dangerous driving factors, but also take into account cost and efficiency.

Description

A behavior prediction method, vehicle control method and system based on data analysis

technical field

The present invention relates to a method for predicting the probability of a motor vehicle driver's dangerous driving behavior, and a method and system for controlling the motor vehicle based on the magnitude of the above probability.

Background technique

The prevention of dangerous driving behavior is an important topic in the current society. Whether it is drinking driving, drug driving or fatigue driving, there are different degrees of existence. Due to the lack of effective technical means to prevent the above-mentioned behaviors, at this stage, punishment is more based on post-event punishment, which often results in more serious negative results when discovered. If the probability detection of dangerous driving behaviors is performed indiscriminately on all drivers before the motor vehicle is started, it is not an optimal solution considering both efficiency and cost.

SUMMARY OF THE INVENTION

In order to overcome the defects of the prior art, the present invention proposes a behavior prediction method, vehicle control method and system based on data analysis, which can exclude most of the drivers with low probability of dangerous driving from the dangerous driving probability detection by means of data analysis. In addition, for a driver with a high probability of dangerous driving to perform mandatory dangerous driving probability detection when operating a motor vehicle, it can not only effectively eliminate the dangerous driving factor, but also take into account the cost and efficiency.

In order to realize the above-mentioned purpose of the invention, the present invention adopts the following technical solutions:

A behavior prediction method based on data analysis, characterized in that, it comprises the following steps:

Step S31, continuously collecting three-dimensional space trajectory data generated over time by at least one portable mobile device bound with the driver's identity;

Step S32, perform feature analysis on the data collected in step S31;

Step S33, according to the data analysis result of step S32, make a judgment on the probability of the driver's dangerous driving behavior.

As a preferred solution, the length of the duration does not exceed 12 hours.

As a preferred solution, when the data collection duration exceeds the set time interval, the data formed later covers the data that has already been formed in chronological order.

As a preferred solution, data collection, storage and analysis for a certain portable mobile device are all completed by the portable mobile device.

As a preferred solution, the dangerous driving behavior includes any one or more of drinking driving, drug use driving and fatigue driving.

A vehicle control method, comprising the following steps:

Step S1, driver identification and motor vehicle identification; if the driver is in the motor vehicle authorization list, go to step S3, otherwise, go to step S2;

Step S2, verifying the communication between the driver and the motor vehicle; the specific steps include,

Step S21, the driver sends a verification request to the motor vehicle; Step S22, the motor vehicle sends a verification request to the right holder; Step S23, the right holder passes the verification, and the driver's identity information is added to the authorization list; or the right holder does not do any processing; If the driver's identity information is added to the blacklist, the motor vehicle will no longer send the driver's verification request to the right holder;

Step S3, driver behavior prediction; specifically includes:

Step S31, continuously collecting three-dimensional space trajectory data generated over time by at least one portable mobile device bound with the driver's identity;

Step S32, perform feature analysis on the data collected in step S31;

Step S33, according to the data analysis result of step S32, make a judgment on the probability of the driver's dangerous driving behavior;

If the probability of any dangerous driving behavior of the driver exceeds the set threshold, go to step S4, otherwise go to step S5;

Step S4, mandatory detection of dangerous driving factors, including one or more of alcohol detection, drug use detection and fatigue driving detection; all the results of the detection of dangerous driving factors are passed, then proceed to step S5, if any one or more of dangerous driving factors are detected If the result of the factor detection fails, then enter step S6;

Step S5, open the driver's driving authority;

Step S6, cancel the driver's driving authority.

As a preferred solution, the length of the duration does not exceed 12 hours.

As a preferred solution, when the data collection duration exceeds the set time interval, the data formed later covers the data that has already been formed in chronological order.

As a preferred solution, data collection, storage and analysis for a certain portable mobile device are all completed by the portable mobile device.

As a preferred solution, the dangerous driving behavior includes any one or more of drinking driving, drug use driving and fatigue driving.

As a preferred solution, the cancellation of the driver's driving authority in the step S6 includes prohibiting the engine and the motor from starting; or prohibiting the transmission mechanism from working.

As a preferred solution, the data collected in step S31 is only interacted between the portable mobile device that has passed the communication verification and the motor vehicle.

As a preferred solution, the data collected in step S31 is processed and analyzed by the motor vehicle.

As a preferred solution, a biometric identification device is installed on the motor vehicle, including one or more of fingerprints, finger veins, and facial biometric identification devices.

As a preferred solution, in step S1, the identity information of the driver and the motor vehicle is represented by a character string with a unique identification function.

As a preferred solution, in step S2, the administrator is given the authority to update the driver's driving license, and the specific steps include: the motor vehicle periodically sends a request for updating the driver's driving license in the authorized list to the administrator, and the administrator responds after receiving the request , and provide up-to-date information.

As a preferred solution, in step S4, the detection of dangerous driving factors is completed by a built-in detection device of the motor vehicle, and the detection device may be pre-installed in the original factory, or may be installed after the factory. .

A vehicle control system, comprising:

At least one portable mobile device bound to the driver's identity is used for identification and communication verification with the motor vehicle, and is also used to continuously collect the three-dimensional space trajectory data generated by the portable mobile device over time, and is also used for storage and analysis. the above data;

A motor vehicle with functions of storage, calculation, control, display, input and output, and detection of dangerous driving factors;

When the motor vehicle receives the dangerous driving probability judgment data made by the portable mobile device, or the dangerous driving probability judgment made by itself, it controls the driver's driving authority according to the dangerous driving probability or the detection result of the dangerous driving factor.

The beneficial effect of the present invention is that, by means of data analysis, a small number of drivers suspected of dangerous driving behaviors are screened out for compulsory detection, so as to achieve both efficiency and cost.

Description of drawings

Figure 1 is a schematic diagram of the relationship between some traffic participants.

Figure 2 is a schematic flow chart of the present invention.

Detailed ways

The present invention will be described in further detail below in conjunction with the accompanying drawings.

One of the technical solutions of the present application is to predict the probability of dangerous driving, and the dangerous driving described in the present application at least includes driving without a license, driving under the influence of alcohol, driving with drugs, and driving with fatigue. How to accurately analyze and predict whether the driver has unlicensed driving, drinking driving, drug driving and fatigue driving is one of the important steps in the technical solution.

As shown in Figure 1, we define the objects involved in the technical solution. The driver refers to the natural person who drives the motor vehicle; the motor vehicle refers to the vehicle included in the motor vehicle management according to the national policy. Cars and trucks running on the road; the manager refers to the institution and its staff who have the ability to make decisions on licensing and punishment.

We define that the manager grants a license to a qualified natural person to drive a specific type of motor vehicle, and the corresponding carrier is the natural person to obtain a driver license; Obtain a driving license for a motor vehicle; the manager issues a registration certificate to the owner of the motor vehicle to prove the ownership of the motor vehicle (Ownership registration certificate). After the manager has issued the above permission, the manager, the driver and the motor vehicle lack effective technical means to predict and control possible dangerous driving behaviors, although the manager has invested a lot of manpower and material resources in practice to prevent dangerous driving. Behaviors are punished and controlled. From the actual effect, the prevention of dangerous driving behaviors depends more on the driver's consciousness, and there is no effective technical means for the behavior prediction and control of a small number of high-risk groups of dangerous driving. That is to say, the control of dangerous driving of motor vehicles is more about punishment after the event, rather than prevention in advance.

One of the beneficial effects that can be achieved by the technical solution of the present application is that communication and control can be established between the driver, the motor vehicle and the manager, so as to prevent most of the possible dangerous driving behaviors in advance.

As shown in Figure 2, under normal circumstances, the technical solution of the present application includes the following steps:

Step S1, driver identification and vehicle identification. The driver identification and vehicle identification in this step are bidirectional, and there is a process of identity information interaction. For example, a biometric identification device is installed on the vehicle, similar to the fingerprint, finger vein, and facial biometric identification device. . When the biometric feature collected by the biometric identification device matches the preset biometric feature, and the motor vehicle controller determines that the driver is in the authorized list, it goes to step S3; otherwise, it goes to step S2.

The driver can identify the identity of the motor vehicle by observing the motor vehicle, but this identification method cannot create a technical association between the driver and the motor vehicle, and cannot form a closed loop in the sense of automatic control. A preferred solution is that the driver is bound to at least one portable mobile device identity by default, and during identification, the portable mobile device and the motor vehicle are used for identification. Portable mobile devices may be cell phones, watches, glasses, and the like. When the portable mobile device matches the identity of the motor vehicle, when the motor vehicle controller determines that the driver is in the authorized list, it goes to step S3; otherwise, it goes to step S2.

For portable mobile devices, we can understand it as a carrier of extended functions for drivers. For natural persons without physical disabilities, the natural basic functions are the same. With the development of modern technology, portable mobile devices represented by mobile phones , which extends the functional attributes of human beings, and the realization of corresponding functions needs to be carried by similar portable mobile devices. After the driver is bound with the identity of the portable mobile device, the behavior of the driver can be analyzed and predicted according to the data generated by the portable mobile device.

In the identification step, the identification information of the driver and the motor vehicle can be represented by a character string with a unique identification function, such as the ID number of the driver and the frame number of the motor vehicle.

Step S2, the driver communicates with the motor vehicle for verification. This step mainly solves the problem of how to obtain the authority to operate the motor vehicle when the driver is not in the authorized list. This step can also be understood as a step of managing the driver authorization list.

After the vehicle owner has passed the communication verification with the vehicle, he has the authority to manage the authorization list. It needs to be clearly pointed out here that the motor vehicle owner may not be in the authorized list, but adding a driver to the authorized list requires the permission of the motor vehicle owner.

The specific steps include,

Step S21, the driver sends a verification request to the motor vehicle;

Step S22, the motor vehicle sends a verification request to the right holder;

In step S23, the right holder passes the verification, and the driver's identity information is added to the authorization list; or the right holder does not do any processing; or the driver's identity information is added to the blacklist, the motor vehicle will no longer send the driver's verification request to the right holder.

For the authorization list management step, since the driver's driving license may change, the administrator needs to be given the authority to update the driver's driving license. A request for a driving permit, the administrator responds to the request and provides up-to-date information. It should be pointed out that the administrator here refers to the server authorized by the administrator. Under the premise that the update speed of the driving license information is guaranteed, driving without a license can basically be eliminated.

Step S3, driver behavior prediction. This step is one of the innovative points of this application. This step mainly analyzes and predicts three kinds of dangerous driving situations, including drinking driving, drug driving and fatigue driving.

Taking the identity binding of a driver and a portable mobile device as an example, the prediction of the driver's behavior is made based on the identity-bound portable mobile device. Specifically include the following steps:

Step S31 , collect the three-dimensional space movement trajectory data generated by the portable mobile device bound with the driver's identity as the time axis changes; the length of the time axis can be set as required, usually it does not need to exceed 12 hours, when the time exceeds 12 hours After that, the data formed after automatically overwrites the data formed 12 hours before.

How to store the data after the data collection is completed is one of the issues that needs to be considered. Considering the protection of the driver's personal privacy, the three-dimensional space movement trajectory data generated by a portable mobile device with the change of the time axis is only saved by the portable mobile device. Analysis is also done by portable mobile devices.

In some embodiments, there is another solution. After the portable mobile device and the motor vehicle are authenticated and entered into the authorization list, the portable mobile device can authorize the motor vehicle to access and store the above-mentioned data. The advantage of such a scheme is that the efficiency of data processing can be significantly improved. Since the size of the portable mobile device is generally smaller than that of a motor vehicle, the processing capability of the processor it has is obviously limited. On the contrary, a high-efficiency data processing device can be configured on the motor vehicle.

Therefore, the data collected in step S31 is only interacted between the portable mobile device that has passed the communication verification and the motor vehicle; preferably, the motor vehicle performs data processing and analysis.

Step S32, carry out feature analysis on the data collected in step S31; there are various methods for feature analysis, usually the data needs to be processed according to a specific algorithm, this application does not involve specific algorithms for the time being, and is left in other applications reveal. For example, assuming that the driver's behavioral characteristics are consistent with entering and leaving bars and restaurants in a specific time period, it will affect the probability judgment of risk factors for drinking and driving.

Step S33, according to the data analysis result, make a judgment on the probability of dangerous driving by the driver, if the probability is small, go to step S5, and if the probability is high, go to step S4; Apply to adjust.

Step S4, according to the data analysis result, if the probability of dangerous driving is relatively high, the detection of dangerous driving factors, including alcohol detection, drug abuse detection and fatigue driving detection, is mandatory. The three risk factors are independent of each other and may also require testing at the same time.

The testing process is completed by the built-in testing equipment of the motor vehicle. If the results of the detection of each dangerous driving factor are all passed, the process proceeds to step S5, and if any one or more of the detection results of the dangerous driving factors fail, then the process proceeds to step S6.

Taking alcohol content detection as an example, it is generally necessary to configure an alcohol detection sensor device in the cockpit. The specific principle, structure and working method of the alcohol detection sensor device are not covered in this application for the time being and will be disclosed in other future applications. In the prior art, some alcohol detection and sensing devices have also been used in motor vehicles.

Step S5, the driver's driving authority is opened.

Step S6, cancel the driver's driving authority. The purpose of this step is to restrict the movement of the motor vehicle. There may be many situations in this process. One is to prohibit the engine and motor from starting, and the other is to prohibit the transmission mechanism from working. Even if the engine and motor work, the power cannot be transmitted to the wheels. .

In order to realize the above-mentioned vehicle control method, it is also necessary to correspond to a control system for realizing the method, which shall at least include:

At least one portable mobile device bound to the driver's identity is used for identification and communication verification with the motor vehicle, and is also used to continuously collect the three-dimensional space trajectory data generated by the portable mobile device over time, and is also used for storage and analysis. the above data;

A motor vehicle with functions of storage, calculation, control, display, input and output, and detection of dangerous driving factors;

When the motor vehicle receives the dangerous driving probability judgment data made by the portable mobile device, or the dangerous driving probability judgment made by itself, it controls the driver's driving authority according to the dangerous driving probability or the detection result of the dangerous driving factor.

Claims (18)

1. A behavior prediction method based on data analysis is characterized by comprising the following steps:

step S31, continuously acquiring three-dimensional space track data generated by the change of at least one portable mobile device bound with the identity of the driver along with time;

step S32, performing characteristic analysis on the data acquired in step S31;

and step S33, according to the data analysis result of the step S32, judging the probability of dangerous driving behaviors of the driver.

2. The method of claim 1, wherein the duration of time is no longer than 12 hours.

3. The behavior prediction method based on data analysis according to claim 2, characterized in that after the data collection duration exceeds a set time interval, the data formed later is overlaid with the data formed already according to the time sequence.

4. The method of claim 1, wherein the data collection, storage and analysis for a portable mobile device are performed by the portable mobile device.

5. The data analysis-based behavior prediction method of claim 1, wherein the dangerous driving behavior comprises any one or more of drunk driving, drug-taking driving and fatigue driving.

6. A vehicle control method characterized by comprising the steps of:

step S1, identifying the identity of the driver and the identity of the motor vehicle; if the driver is in the motor vehicle authorization list, the step S3 is carried out, otherwise, the step S2 is carried out;

step S2, verifying the communication between the driver and the motor vehicle; the specific steps comprise that,

step S21, the driver sends a verification request to the motor vehicle; step S22, the motor vehicle sends a verification request to the obligee; step S23, the authorized person passes the verification, and the driver identity information is added into the authorization list; or the obligee does not do any treatment; or adding the identity information of the driver into a blacklist, and then the motor vehicle does not send the verification request of the driver to the obligee any more;

step S3, predicting the behavior of the driver; the method specifically comprises the following steps:

step S31, continuously acquiring three-dimensional space track data generated by the change of at least one portable mobile device bound with the identity of the driver along with time;

step S32, performing characteristic analysis on the data acquired in step S31;

step S33, according to the data analysis result of step S32, making judgment aiming at the probability of dangerous driving behavior of the driver;

if the probability of any dangerous driving behavior of the driver exceeds the set threshold value, the step S4 is executed, otherwise, the step S5 is executed;

step S4, forcibly detecting dangerous driving factors, including one or more of alcohol detection, drug absorption detection and fatigue driving detection; if the results of the dangerous driving factor detections pass, the step S5 is performed, and if any one or more dangerous driving factor detections fail, the step S6 is performed;

step S5, opening the driving authority of the driver;

and step S6, canceling the driving authority of the driver.

7. A vehicle control method according to claim 6, characterised in that the duration is no longer than 12 hours in length.

8. A vehicle control method according to claim 7, characterized in that after the data acquisition duration exceeds the set time interval, the data formed later is overlaid with the data already formed in chronological order.

9. The vehicle control method according to claim 6, wherein the data collection, storage and analysis for a portable mobile device are all performed by the portable mobile device.

10. A vehicle control method as claimed in claim 6, wherein the dangerous driving behaviour comprises any one or more of drunk driving, drug-absorbed driving and fatigue driving.

11. The vehicle control method according to claim 6, wherein said cancellation of the driver' S driving authority of step S6 includes prohibiting an engine, a motor from starting; or to disable the transmission.

12. The vehicle control method according to claim 6, wherein the data collected in step S31 only interacts with the vehicle through the communication verification of the portable mobile device.

13. The vehicle control method according to claim 6, wherein the data collected in step S31 is processed and analyzed by the vehicle.

14. The vehicle control method according to claim 6, wherein a biometric recognition device is provided on the motor vehicle, and comprises one or more of fingerprints, finger veins and facial biometric acquisition recognition devices.

15. The vehicle control method according to claim 6, wherein in step S1, the identification information of the driver and the vehicle is represented by a character string having a unique identification function.

16. The vehicle control method according to claim 6, wherein in step S2, the step of giving the manager the authority to update the driver' S driving permission comprises: the motor vehicle regularly sends a request for updating the driving permission of the driver in the authorization list to the manager, and the manager responds after receiving the request and provides the latest information.

17. The vehicle control method according to claim 6, wherein in step S4, the dangerous driving factor detection is performed by a detection device built in the vehicle, and the detection device may be pre-installed in a factory or installed after shipment. .

18. A vehicle control system, characterized by comprising:

the portable mobile equipment is bound with the identity of the driver and is used for identifying the identity of the motor vehicle, verifying communication, continuously acquiring three-dimensional space track data generated by the portable mobile equipment along with the change of time and storing and analyzing the data;

the motor vehicle has the functions of storage, calculation, control, display, input and output, and also has the function of detecting dangerous driving factors;

and when the motor vehicle receives dangerous driving probability judgment data made by the portable mobile equipment or dangerous driving probability judgment made by the motor vehicle, controlling the driving authority of the driver according to the dangerous driving probability or the dangerous driving factor detection result.

Images