WO2023000762A1 - Attention analysis method, vehicle and storage medium - Google Patents

Abstract

Disclosed in the present application are an attention analysis method, a vehicle and a storage medium. The method comprises: acquiring parameter information corresponding to a road state and parameter information corresponding to at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item; calculating, according to the parameter information that has been subjected to the discretization processing, mean values and variance values corresponding to the road state and the driving item; performing calculation according to the mean values and the variance values corresponding to the parameter information, so as to obtain a prior probability corresponding to the parameter information; and respectively calculating posterior probabilities of a concentration event and an inattention event of a driver according to the prior probability and a preset naïve Bayes algorithm, and determining, according to the posterior probabilities, whether the attention of the driver is focused.

Description

Attention analysis method, vehicle and storage medium

related application

This application claims priority to a Chinese patent application with application number 202110833696.6 filed on July 22, 2021, the entire contents of which are hereby incorporated by reference.

technical field

The present application relates to the field of vehicles, in particular to an attention analysis method, a vehicle and a computer-readable storage medium.

Background technique

During the driving process of the vehicle, the more concentrated the driver's attention, the faster the reaction speed in the face of unexpected situations, and the more effective handling can be done. The existing method of judging whether the driver's attention is focused is through sensor information, such as the angle of rotation information on the steering wheel. If the angle of rotation is greater than a threshold, it is considered that the current driver is not focused. However, in the prior art, when a single sensor information judgment method is used, the data sent by the sensor will fluctuate within the threshold range, so it will frequently be judged that the driver is not paying attention at this time, which will affect the user, and there is no Fully considering the impact of lane information, when the road bends, the steering wheel angle will often lead to misjudgment, resulting in low judgment accuracy.

application content

The main purpose of the present application is to propose an attention analysis method, a vehicle and a computer-readable storage medium, aiming at solving the problem of low accuracy of existing driver attention judgment methods.

In order to achieve the above purpose, the application provides an attention analysis method, including steps:

Acquiring parameter information corresponding to the road state and parameter information corresponding to at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item;

calculating mean and variance values corresponding to the road state and the driving item according to the discretized parameter information;

calculating a priori probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information;

According to the prior probability and the preset naive Bayesian algorithm, the posterior probabilities of the driver's concentration event and the inattention event are respectively calculated, and whether the driver's concentration is determined according to the posterior probability.

In one embodiment, the parameter information corresponding to the road state includes road information corresponding to the road state; the parameter information corresponding to the driving item includes driver behavior information corresponding to driver behavior and vehicle dynamic behavior corresponding to vehicle dynamic behavior. Behavior information: the driver behavior information includes steering wheel hand torque value data and steering wheel angle value data, the vehicle dynamic behavior information includes lateral acceleration data, and the road information includes lateral deviation data.

In one embodiment, the step of obtaining parameter information corresponding to the road state and parameter information corresponding to at least one driving item, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving item includes: :

Obtain steering wheel hand torque value data, steering wheel angle value data, vehicle lateral acceleration data and lateral deviation data within a preset time period during driving according to a preset time interval, and correspond to the parameter information corresponding to the road state and the driving item Discretization processing is performed on the parameter information, and the preset time interval is less than the preset duration.

In one embodiment, the step of calculating the mean value and variance value corresponding to the road state and the driving item according to the discretized parameter information includes:

According to the discretized steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, respectively calculate the mean value and variance corresponding to each of the parameter information.

In one embodiment, the step of calculating the prior probability corresponding to the parameter information according to the mean value and variance value corresponding to the parameter information includes:

Input the mean value and variance value corresponding to the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, respectively calculated by the preset conditional probability formula A priori probability corresponding to the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data.

In one embodiment, according to the prior probability and the preset naive Bayesian algorithm, respectively calculate the posterior probability of the driver's concentration event and inattention event, and judge according to the posterior probability Steps to determine whether the driver is paying attention include:

According to the prior probability and the preset naive Bayesian algorithm, calculate the posterior probability of the driver's concentration and the driver's inattention obtained according to the preset time interval in each preset duration;

Responding to the fact that the probability of the driver's inattention obtained according to the preset time interval each time within the preset duration is greater than the posterior probability of the driver's inattention, it is determined that the driver is inattention;

In response to the probability that the driver's concentration is greater than the posterior probability of the driver's inattention obtained according to the preset time interval any time within the preset duration, it is determined that the driver is in concentration.

In one embodiment, the posterior probability of the driver's inattention is calculated by the following formula:

P(y ₁ |x)＝p(x ₁ |y ₁ )*p(x ₂ |y ₁ )*p(x ₃ |y ₁ )*p(x ₄ |y ₁ )*p(y ₁ );

The posterior probability of the driver's concentration is calculated by the following formula:

P(y ₂ |x)＝p(x ₁ |y ₂ )*p(x ₂ |y ₂ )*p(x ₃ |y ₂ )*p(x ₄ |y ₂ )*p(y ₂ );

Wherein, X is a combination of the event that the steering wheel hand torque data effectively exists, the event that the steering wheel angle data effectively exists, the event that the lateral deviation data effectively exists, and the event that the lateral acceleration data effectively exists, and the _y1 is the driver's lack of attention Concentrated events, x ₁ is the event that the steering wheel hand torque data is valid, x ₂ is the event that the steering wheel angle data is valid, x ₃ is the event that the lateral deviation data is valid, x ₄ is the event that the lateral acceleration data is valid, y ₁ |x is the driver's inattention event in the combination of all events, P(y ₁ |x) is the probability of the driver's inattention event in the combination of all events, P(x ₁ |y ₁ ) is the prior probability of the event that the steering wheel hand torque data effectively exists in the event of driver inattention, P(x ₂ |y ₁ ) is the event of steering wheel inattention The prior probability of the occurrence of the event that the corner data effectively exists, P(x ₃ |y ₁ ) is the prior probability of the event that the lateral deviation data effectively exists under the event of the driver's inattention, P(x ₄ |y ₁ ) is the prior probability of occurrence of an event where the lateral acceleration data effectively exists under the event that the driver is inattentive;

y ₂ |x is the driver's attention-focused event in the combination of all events, P(y ₂ |x) is the probability of the driver's attention-focused event in the combination of all events, P(x ₁ |y ₂ ) is the prior probability of the event that the steering wheel hand torque data effectively exists under the event of driver's concentration, P(x ₂ |y ₂ ) is the effective existence of steering wheel angle data under the event of driver's concentration P(x ₃ |y ₂ ) is the prior probability of the event that the lateral deviation data effectively exists under the driver's concentration event, and P(x ₄ |y ₂ ) is the The prior probability of the occurrence of the event that the lateral acceleration data effectively exists under the event where the operator is focused.

In one embodiment, according to the prior probability and the preset naive Bayesian algorithm, respectively calculate the posterior probability of the driver's attention concentration event and the attention inattention event, and judge whether the driver's attention is concentrated The steps before include:

The preset conditional probability function of the normal distribution of the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data is obtained by processing according to the normal distribution formula.

To achieve the above object, the present application also provides a vehicle, the vehicle includes a memory, a processor, and a computer program stored in the memory and operable on the processor, the computer program being executed by the processor During execution, the steps of the attention analysis method as described above are realized.

In order to achieve the above object, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned attention analysis method are realized .

An attention analysis method, a vehicle, and a computer-readable storage medium proposed by the present application, by obtaining parameter information corresponding to road state and parameter information corresponding to at least one driving item, discretize the parameter information corresponding to the driving item , it is convenient to use the parameter information for data analysis, reduce the time and space occupied by the Bayesian algorithm, and improve the classification and clustering ability and anti-noise ability of the system for road information and driving items; parameter information, calculate the mean value and variance value corresponding to the driving item, and reduce the error in the calculation of whether the driver's attention is concentrated; by calculating the mean value and variance value corresponding to the parameter information, the The prior probability corresponding to the parameter information ensures the accuracy of judging the probability of the driver's concentration and driver's inattention; by using the prior probability and the preset naive Bayesian algorithm, the driver's The posterior probability of the attention concentration event and the attention inattention event, and judge whether the driver's attention is concentrated according to the posterior probability, and realize whether the driver's attention is jointly determined according to the road state and driving items combined with the Bayesian algorithm. Concentrated and accurate judgment fully considers the impact of road conditions, eliminates misjudgments caused by lack of road information, and achieves efficient judgments on whether the driver is focused without increasing hardware costs.

Description of drawings

Fig. 1 is a schematic structural diagram of the hardware operating environment involved in the embodiment scheme of the present application;

FIG. 2 is a schematic flow chart of the first embodiment of the attention analysis method of the present application;

FIG. 3 is a schematic diagram of a detailed flowchart of step S40 in the second embodiment of the attention analysis method of the present application.

The realization, functional features and advantages of the present application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

detailed description

It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

Please refer to FIG. 1 , which is a schematic diagram of a hardware structure of a vehicle provided in various embodiments of the present application. The vehicle includes components such as a communication module 01 , a memory 02 and a processor 03 . Those skilled in the art will appreciate that the vehicle shown in FIG. 1 may also include more or fewer components than shown, or combine some components, or arrange different components. Wherein, the processor 03 is connected to the memory 02 and the communication module 01 respectively, the memory 02 stores a computer program, and the computer program is executed by the processor 03 at the same time.

The communication module 01 can be connected with external devices through the network. The communication module 01 can receive data sent by external devices, and can also send data, instructions and information to the external devices. The external devices can be electronic devices such as mobile phones, tablet computers, notebook computers, and desktop computers.

The memory 02 can be configured to store software programs and various data. The memory 02 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application required by a function, etc.; the data storage area may store data or information created according to the use of the vehicle. In addition, the memory 02 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

The processor 03 is the control center of the vehicle. It uses various interfaces and lines to connect various parts of the entire vehicle. By running or executing the software programs and/or modules stored in the memory 02, and calling the data stored in the memory 02, Execute various functions of the vehicle and process data to monitor the vehicle as a whole. The processor 03 may include one or more processing units; optionally, the processor 03 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem The tuner processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 03 .

Those skilled in the art can understand that the vehicle structure shown in FIG. 1 does not constitute a limitation to the vehicle, and may include more or less components than those shown in the illustration, or combine some components, or arrange different components.

According to the above hardware structure, various embodiments of the method of the present application are proposed.

Referring to Fig. 2, in the first embodiment of the attention analysis method of the present application, the attention analysis method includes steps:

Step S10, acquiring parameter information corresponding to the road state and parameter information corresponding to at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item;

The parameter information corresponding to the road state includes road information corresponding to the road state, for example, the road information includes lateral deviation data; the parameter information corresponding to the driving item includes driver behavior information corresponding to driver behavior and vehicle dynamic behavior Corresponding vehicle dynamic behavior information. For example, the driver behavior information includes steering wheel hand torque value data and steering wheel angle value data, the vehicle dynamic behavior information includes lateral acceleration data, and the road information includes lateral deviation data. In this embodiment, the above parameter information is discretized using a supervised learning method.

Step S20, calculating mean and variance values corresponding to the road state and the driving item according to the discretized parameter information;

In one embodiment, the step S20 includes:

According to the discretized steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, respectively calculate the mean value and variance corresponding to each of the parameter information.

In this embodiment, the mean value can be calculated by the following formula:

Among them, μ is the mean value, n is the statistical number of the parameter information, x _i is the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the Separate numerical values such as lateral deviation data.

The variance can be calculated by the following formula:

Wherein, ^σ2 is the variance value, and n is the value of the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, etc. involved in the calculation of the parameter information The respective numbers, x _i are the respective values of the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data, and the lateral deviation data in the parameter information.

Step S30, calculating a priori probability corresponding to the parameter information according to the mean value and variance value corresponding to the parameter information;

The step S30 also includes the steps of:

Input the mean value and variance value corresponding to the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, respectively calculated by the preset conditional probability formula Prior probabilities corresponding to the steering wheel hand torque value, the steering wheel angle value, the vehicle lateral acceleration and the lateral deviation.

In this embodiment, the preset conditional probability formula is specifically:

Wherein, x _i is the parameter information respectively represented by the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data; Y is inattention and attention The combination of concentrated events, X is the combination of events in which the steering wheel hand torque data effectively exists, the event in which the steering wheel angle data effectively exists, the event in which the lateral deviation data effectively exists, and the event in which the lateral acceleration data effectively exists; σ ² is the variance value , μ is the mean value; wherein, the effective existence of the data refers to the vehicle’s sensor corresponding to the acquisition of steering wheel hand torque data, steering wheel angle data, lateral deviation data, lateral acceleration data and other parameter information within the preset range. data.

Step S40, according to the prior probability and the preset naive Bayesian algorithm, respectively calculate the posterior probability of the driver's concentration event and the inattention event, and judge whether the driver's attention is concentrated;

An attention analysis method, a vehicle, and a computer-readable storage medium proposed by the present application, by obtaining parameter information corresponding to road state and parameter information corresponding to at least one driving item, discretize the parameter information corresponding to the driving item , it is convenient to use the parameter information for data analysis, reduce the time and space occupied by the Bayesian algorithm, and improve the classification and clustering ability and anti-noise ability of the system for road information and driving items; parameter information, calculate the mean value and variance value corresponding to the driving item, and reduce the error in the calculation of whether the driver's attention is concentrated; by calculating the mean value and variance value corresponding to the parameter information, the The prior probability corresponding to the parameter information ensures the accuracy of judging the probability of the driver's concentration and driver's inattention; by using the prior probability and the preset naive Bayesian algorithm, the driver's The posterior probability of the attention concentration event and the attention inattention event, and judge whether the driver's attention is concentrated according to the posterior probability, and realize whether the driver's attention is jointly determined according to the road state and driving items combined with the Bayesian algorithm. Concentrated and accurate judgment fully considers the impact of road conditions, eliminates misjudgments caused by lack of road information, and achieves efficient judgments on whether the driver is focused without increasing hardware costs.

Further, based on the attention analysis method of the present application proposed in the first embodiment of the present application, the present application proposes a second embodiment, and the step S10 includes:

Obtain steering wheel hand torque value data, steering wheel angle value data, vehicle lateral acceleration data and lateral deviation data within a preset time period during driving according to a preset time interval, and correspond to the parameter information corresponding to the road state and the driving item Discretization processing is performed on the parameter information, and the preset time interval is less than the preset duration.

In this embodiment, the preset time interval may be 1 second, 2 seconds, 3 seconds or 4 seconds, and the preset duration is longer than the preset time interval. When the preset time interval is 1 second, The preset duration can be any duration greater than 1 second, such as 3 seconds, 5 seconds, 8 seconds, etc.; when the preset time interval is 3 seconds, the preset duration can be any duration greater than 2 seconds, for example 3 seconds, 5 seconds, 8 seconds, etc.; when the preset time interval is 3 seconds or 4 seconds, and so on, it will not be repeated here. In addition, the parameter information can also be obtained according to obtaining multiple parameter information in a certain distance during the driving process.

The steering wheel hand torque value data, steering wheel angle value data, vehicle lateral acceleration data and lateral deviation data can all be obtained by corresponding sensors installed on the vehicle, and the lateral deviation is when the vehicle is driving on the road. The error between the point and the expected driving route of the vehicle system, the vehicle lateral acceleration is a physical quantity that is opposite to the centripetal acceleration direction and has the same acceleration value during the driving process of the vehicle.

In this embodiment, the parameter information within the preset duration during driving is acquired at preset time intervals, which realizes multiple acquisitions of parameter information within the preset duration, reduces errors, and ensures data and driver attention. Accurate judgment of whether the force is concentrated.

Further, referring to FIG. 3 , in the attention analysis method of the present application proposed based on the first embodiment of the present application, the present application proposes a third embodiment, and the step S40 includes:

Step S41, according to the prior probability and the preset naive Bayesian algorithm, respectively calculate the posterior probability of the driver's concentration and the driver's inattention obtained according to the preset time interval within each preset time period;

In this embodiment, the posterior probability of the driver's concentration and inattention can also be calculated according to obtaining a section of the preset travel distance that is less than the preset travel distance;

Step S42, in response to the probability that the driver's inattention is obtained according to the preset time interval each time within the preset duration is greater than the posterior probability of the driver's inattention, it is determined that the driver is inattention;

Step S43, in response to the probability that the driver's concentration is greater than the posterior probability of the driver's inattention obtained according to the preset time interval within the preset duration, it is determined that the driver's concentration;

The probability of the driver's inattention obtained according to the preset time interval each time is greater than the posterior probability of the driver's inattention, for example, within 1 minute, the probability of driver's inattention and inattention can be calculated 20 times. Probability, if the probability of inattention of the driver is greater than the probability of concentration in 20 times, it can be judged that the driver is inattention;

The probability of the driver's concentration obtained according to the preset time interval is greater than the posterior probability of the driver's inattention, that is, in 20 times, the probability of the driver's concentration is greater than that of the driver's inattention. The probability of , that is, it is judged that the driver is paying attention.

In this application, the posterior probability of the driver's inattention is calculated by the following formula:

P(y ₁ |x)＝p(x ₁ |y ₁ )*p(x ₂ |y ₁ )*p(x ₃ |y ₁ )*p(x ₄ |y ₁ )*p(y ₁ );

The posterior probability of the driver's concentration is calculated by the following formula:

P(y ₂ |x)＝p(x ₁ |y ₂ )*p(x ₂ |y ₂ )*p(x ₃ |y ₂ )*p(x ₄ |y ₂ )*p(y ₂ );

Wherein, X is a combination of the event that the steering wheel hand torque data effectively exists, the event that the steering wheel angle data effectively exists, the event that the lateral deviation data effectively exists, and the event that the lateral acceleration data effectively exists, and the _y1 is the driver's lack of attention Concentrated events, x ₁ is the event that the steering wheel hand torque data is valid, x ₂ is the event that the steering wheel angle data is valid, x ₃ is the event that the lateral deviation data is valid, x ₄ is the event that the lateral acceleration data is valid, y ₁ |x is the driver's inattention event in the combination of all events, P(y ₁ |x) is the probability of the driver's inattention event in the combination of all events, P(x ₁ |y ₁ ) is the prior probability of the event that the steering wheel hand torque data effectively exists in the event of driver inattention, P(x ₂ |y ₁ ) is the event of steering wheel inattention The prior probability of the occurrence of the event that the corner data effectively exists, P(x ₃ |y ₁ ) is the prior probability of the event that the lateral deviation data effectively exists under the event of the driver's inattention, P(x ₄ |y ₁ ) is the prior probability of occurrence of an event where the lateral acceleration data effectively exists under the event that the driver is inattentive;

y ₂ |x is the driver's attention-focused event in the combination of all events, P(y ₂ |x) is the probability of the driver's attention-focused event in the combination of all events, P(x ₁ |y ₂ ) is the prior probability of the event that the steering wheel hand torque data effectively exists under the event of driver's concentration, P(x ₂ |y ₂ ) is the effective existence of steering wheel angle data under the event of driver's concentration P(x ₃ |y ₂ ) is the prior probability of the event that the lateral deviation data effectively exists under the driver's concentration event, and P(x ₄ |y ₂ ) is the The prior probability of the occurrence of the event that the lateral acceleration data effectively exists under the event that the driver is focused

In this application, the posteriori of the driver's concentration and the driver's inattention obtained according to the preset time interval within each preset time period are respectively calculated according to the prior probability and the preset naive Bayesian algorithm probability, and judge whether the driver's attention is concentrated according to the number of times of concentration and non-concentration, which ensures the accuracy of judging whether the driver's attention is concentrated, and improves the safety during driving.

Further, based on the attention analysis method of the present application proposed in the first embodiment of the present application, the present application proposes a fourth embodiment, which includes before the step S40:

According to the normal distribution formula, the hand torque value data of the steering wheel, the steering wheel angle value data, the vehicle lateral acceleration data and the normal distribution preset conditional probability function of the lateral deviation data are obtained;

In this embodiment, the normal distribution formula is:

According to the formula of normal distribution, the conditional probability function can be obtained as:

In this embodiment, the conditional probability formula is obtained through the normal distribution formula, and the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data are smoothed , reducing frequent reactions to the driver's attention due to the use of threshold judgments.

The present application also proposes a computer-readable storage medium on which a computer program is stored. Described computer-readable storage medium can be memory 02 in the vehicle of Fig. 1, also can be as ROM (Read-Only Memory, read only memory)/RAM (Random Access Memory, random access memory), magnetic disk, optical disk At least one of them, the computer-readable storage medium includes information for enabling the vehicle to execute the methods described in the various embodiments of the present application.

It should be noted that, as used herein, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.

The serial numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.

The above are only optional embodiments of the application, and are not intended to limit the patent scope of the application. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the application, or directly or indirectly used in other related technologies fields, are all included in the scope of patent protection of this application in the same way.

Claims (10)

1. A kind of attention analysis method, comprises steps:

   Acquiring parameter information corresponding to the road state and parameter information corresponding to at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item;

   calculating mean and variance values corresponding to the road state and the driving item according to the discretized parameter information;

   calculating a priori probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information;

   According to the prior probability and the preset naive Bayesian algorithm, the posterior probabilities of the driver's concentration event and the inattention event are respectively calculated, and whether the driver's concentration is determined according to the posterior probability.
2. The attention analysis method according to claim 1, wherein the parameter information corresponding to the road state includes road information corresponding to the road state; the parameter information corresponding to the driving item includes driver behavior information corresponding to the driver behavior Vehicle dynamic behavior information corresponding to vehicle dynamic behavior; the driver behavior information includes steering wheel hand torque value data and steering wheel angle value data, the vehicle dynamic behavior information includes lateral acceleration data, and the road information includes lateral deviation data.
3. The attention analysis method according to claim 1, wherein said acquiring parameter information corresponding to the road state and parameter information corresponding to at least one driving item, the parameter information corresponding to the road state and the parameter corresponding to the driving item The steps for discretization of information include:

   Obtain steering wheel hand torque value data, steering wheel angle value data, vehicle lateral acceleration data and lateral deviation data within a preset time period during driving according to a preset time interval, and correspond to the parameter information corresponding to the road state and the driving item Discretization processing is performed on the parameter information, and the preset time interval is less than the preset duration.
4. The attention analysis method as claimed in claim 2, wherein, according to the described parameter information after the discretization process, the step of calculating the mean value and variance value corresponding to the road state and the driving item comprises:

   According to the discretized steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, respectively calculate the mean value and variance corresponding to each of the parameter information.
5. The attention analysis method according to claim 4, wherein the step of calculating the prior probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information comprises:

   Input the mean value and variance value corresponding to the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data, respectively calculated by the preset conditional probability formula A priori probability corresponding to the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data.
6. The attention analysis method as claimed in claim 3, wherein, according to the prior probability and the preset Naive Bayesian algorithm, the posterior probability of the driver's attention concentration event and the attention inattention event is calculated respectively, And the step of judging whether the driver's attention is concentrated according to the posterior probability comprises:

   According to the prior probability and the preset naive Bayesian algorithm, calculate the posterior probability of the driver's concentration and the driver's inattention obtained according to the preset time interval in each preset duration;

   Responding to the fact that the probability of the driver's inattention obtained according to the preset time interval each time within the preset duration is greater than the posterior probability of the driver's inattention, it is determined that the driver is inattention;

   In response to the probability that the driver's concentration is greater than the posterior probability of the driver's inattention obtained according to the preset time interval any time within the preset duration, it is determined that the driver is in concentration.
7. The attention analysis method according to claim 6, wherein the posterior probability of the driver's inattention is calculated by the following formula:

   P(y ₁ |x)＝p(x ₁ |y ₁ )*p(x ₂ |y ₁ )*p(x ₃ |y ₁ )*p(x ₄ |y ₁ )*p(y ₁ );

   The posterior probability of the driver's concentration is calculated by the following formula:

   P(y ₂ |x)＝p(x ₁ |y ₂ )*p(x ₂ |y ₂ )*p(x ₃ |y ₂ )*p(x ₄ |y ₂ )*p(y ₂ );

   Wherein, X is a combination of the event that the steering wheel hand torque data effectively exists, the event that the steering wheel angle data effectively exists, the event that the lateral deviation data effectively exists, and the event that the lateral acceleration data effectively exists, and the _y1 is the driver's lack of attention Concentrated events, x ₁ is the event that the steering wheel hand torque data is valid, x ₂ is the event that the steering wheel angle data is valid, x ₃ is the event that the lateral deviation data is valid, x ₄ is the event that the lateral acceleration data is valid, y ₁ |x is the driver's inattention event in the combination of all events, P(y ₁ |x) is the probability of the driver's inattention event in the combination of all events, P(x ₁ |y ₁ ) is the prior probability of the event that the steering wheel hand torque data effectively exists in the event of driver inattention, P(x ₂ |y ₁ ) is the event of steering wheel inattention The prior probability of the occurrence of the event that the corner data effectively exists, P(x ₃ |y ₁ ) is the prior probability of the event that the lateral deviation data effectively exists under the event of the driver's inattention, P(x ₄ |y ₁ ) is the prior probability of occurrence of an event where the lateral acceleration data effectively exists under the event that the driver is inattentive;

   y ₂ |x is the driver's attention-focused event in the combination of all events, P(y ₂ |x) is the probability of the driver's attention-focused event in the combination of all events, P(x ₁ |y ₂ ) is the prior probability of the event that the steering wheel hand torque data effectively exists under the event of driver's concentration, P(x ₂ |y ₂ ) is the effective existence of steering wheel angle data under the event of driver's concentration P(x ₃ |y ₂ ) is the prior probability of the event that the lateral deviation data effectively exists under the driver's concentration event, and P(x ₄ |y ₂ ) is the The prior probability of the occurrence of the event that the lateral acceleration data effectively exists under the event where the operator is focused.
8. The attention analysis method according to claim 1, wherein, according to the prior probability and the preset naive Bayesian algorithm, the posterior probability of the driver's concentration event and the inattention event are respectively calculated, And before judging whether the driver's attention is concentrated, the steps include:

   The preset conditional probability function of the normal distribution of the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data and the lateral deviation data is obtained by processing according to the normal distribution formula.
9. A vehicle, wherein the vehicle comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program implementing the method of claim 1 when executed by the processor To the step of the attention analysis method described in any one of 8.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the attention analysis method according to any one of claims 1 to 8 is realized A step of.

Images