CN113859247A

CN113859247A - Vehicle user identification method and device, vehicle machine and storage medium

Info

Publication number: CN113859247A
Application number: CN202010614448.8A
Authority: CN
Inventors: 曹欣; 杨冬生; 刘柯; 王欢
Original assignee: BYD Co Ltd
Current assignee: BYD Co Ltd
Priority date: 2020-06-30
Filing date: 2020-06-30
Publication date: 2021-12-31
Anticipated expiration: 2040-06-30
Also published as: CN113859247B

Abstract

The embodiment of the invention provides a vehicle user identification method, a vehicle user identification device, a vehicle machine and a storage medium, wherein the vehicle user identification method comprises the following steps: in the running process of a vehicle, under the condition that a brake pedal is detected to act, acquiring first action information of the pedal action and power information of the vehicle corresponding to the first action information; acquiring first characteristic information according to the first action information and the power information of the vehicle, wherein the first characteristic information is used for identifying the identity of a user; and identifying the user identity information of the vehicle according to the first characteristic information. According to the technical scheme of the invention, the identity of the driving user is recognized only by depending on running information such as pedal action information and power information under the condition of not relating to the privacy information of the user, so that the risk of leakage of the privacy information of the user can be reduced, and higher recognition accuracy can be obtained.

Description

Vehicle user identification method and device, vehicle machine and storage medium

Technical Field

The present invention relates to the field of motor vehicle technologies, and in particular, to a vehicle user identification method, a vehicle user identification device, a vehicle device, and a computer-readable storage medium.

Background

With the development of automobile electronic technology, the purpose of providing personalized service for a driving user, identifying whether the driving user has driving qualification or not or monitoring the driving behavior of the driving user is achieved by adding a user identity identification function on an automobile. In the related art, the identification of the user identity needs to be realized by collecting information such as face information, fingerprint information, voiceprint information and the like of the user.

Therefore, the existing user identification scheme has the risk of leaking the privacy data of the user in the application process because the biometric information of the user needs to be collected.

Disclosure of Invention

The technical problem to be solved by the embodiment of the invention is to provide a vehicle user identification method, so that the identity of a driving user can be identified only by depending on running information such as pedal action information, power information and the like under the condition of not relating to user privacy information.

Correspondingly, the embodiment of the invention also provides a vehicle user identification device, a vehicle machine and a computer readable storage medium, which are used for ensuring the realization and the application of the method.

In order to solve the above problem, an embodiment of a first aspect of the present invention provides a vehicle user identification method, including:

in the running process of a vehicle, under the condition that a brake pedal is detected to act, acquiring first action information of the pedal action and power information of the vehicle corresponding to the first action information;

acquiring first characteristic information according to the first action information and the power information of the vehicle, wherein the first characteristic information is used for identifying the identity of a user;

and identifying the user identity information of the vehicle according to the first characteristic information.

Optionally, the acquiring, during running of the vehicle, first action information of the pedal action when detecting a brake pedal action, and acquiring, when power information of the vehicle corresponding to the first action information detects a brake pedal action, first action information of the pedal action and power information of the vehicle corresponding to the first action information, include:

if the brake pedal is detected to act, recording the stroke of the brake pedal;

under the condition that the fact that the travel of the brake pedal is increased to be larger than or equal to a preset travel threshold value is detected, determining that the brake pedal meets a first preset condition so as to collect first action information of the brake pedal and power information of the vehicle;

and under the condition that the travel of the brake pedal is detected to be reduced to be less than or equal to a preset travel threshold value, stopping collecting the first action information of the brake pedal and the power information of the vehicle.

Optionally, the obtaining first feature information according to the first action information and the power information of the vehicle includes:

acquiring second action information of an accelerator pedal under the condition that the brake pedal is detected to generate action and the first preset condition is met;

respectively acquiring a first group of time-space domain characteristic information and a first group of frequency domain characteristic information in the first action information, and a second group of time-space domain characteristic information and a second group of frequency domain characteristic information in the second action information;

configuring a feature matrix according to the first set of time-space domain feature information, the first set of frequency domain feature information, the second set of time-space domain feature information, the second set of frequency domain feature information and the power information to use the feature matrix as the first feature information,

wherein the power information includes at least one of a lateral acceleration, a longitudinal acceleration, a vehicle speed, a motor rotation speed, and a vehicle torque of the vehicle.

Optionally, the identifying, according to the first feature information, user identity information of the vehicle includes:

recording the action number of the brake pedal;

under the condition that the action number of the brake pedal is larger than or equal to a preset identification number, obtaining multiple groups of first characteristic information matched with the action number;

and identifying the user identity information of the vehicle according to the plurality of groups of first characteristic information.

Optionally, the identifying the user identity information of the vehicle according to the plurality of sets of the first feature information includes:

determining the feature matrix meeting a second preset condition as the first feature information, and respectively inputting multiple groups of the first feature information into a trained classification recognition model to correspondingly output multiple recognition marks;

dividing the same identification in the plurality of identification identifications into a group to obtain at least one group of identification identifications;

and calculating the occupation ratio of each group of the identification marks in the plurality of identification marks, and determining the identification mark with the largest occupation ratio as the identification mark of the vehicle user.

Optionally, before determining the feature matrix meeting a second preset condition as the first feature information, and respectively inputting multiple groups of the first feature information into the trained classification recognition model to correspondingly output multiple recognition identifiers, the method further includes:

detecting whether the feature matrix is associated with a label;

and under the condition that the label is not associated with the feature matrix, determining the feature matrix to be the first feature information meeting the second preset condition.

Optionally, the method further comprises:

determining that the feature matrix does not meet the second preset condition under the condition that the tag is associated with the feature matrix, recording the feature matrix which does not meet the second preset condition as second feature information, wherein the second feature information is used for training the classification recognition model,

and inputting the second characteristic information and the label into a training model of the classification recognition model, and updating the classification recognition model according to a training result of the training model.

Optionally, in a case where a brake pedal generating action is detected, before collecting first action information of the pedal action and power information of the vehicle corresponding to the first action information, the method further includes:

receiving feedback information input by a user according to the identity prompt information;

determining whether the user is an identifiable user according to the feedback information;

generating the label according to the input operation of the user when the user is not the identifiable user, so as to establish the incidence relation between the label and the feature matrix when the feature matrix is taken as the second feature information;

in the case where the user is the identifiable user, directly detecting whether the brake pedal is actuated to take the feature matrix as the first feature information.

Optionally, the method further comprises:

and inputting the first characteristic information and the recognized identity into a training model, wherein the training model is used for training the classification recognition model.

An embodiment of a second aspect of the present invention provides a vehicle user identification device, including:

the system comprises an acquisition module, a judgment module and a control module, wherein the acquisition module is used for acquiring first action information of pedal action and power information of the vehicle corresponding to the first action information under the condition that the action of a brake pedal is detected in the running process of the vehicle;

the acquisition module is used for acquiring first characteristic information according to the first action information and the power information of the vehicle, wherein the first characteristic information is used for identifying the identity of a user;

and the identification module is used for identifying the user identity information of the vehicle according to the first characteristic information.

An embodiment of a third aspect of the present invention provides a vehicle machine, including: the user identification apparatus for a vehicle according to an embodiment of the second aspect of the present invention.

An embodiment of the fourth aspect of the present invention provides a computer-readable storage medium, including the method for identifying a user of a vehicle according to any one of the embodiments of the first aspect of the present invention.

According to the embodiment of the invention, the action of the brake pedal is detected, the first action information of the pedal action and the power information of the vehicle in the execution process of the pedal action are collected, and different driving habits of different users are different from each other and can be quantitatively reflected by the collected first action information and the collected vehicle power information, so that the first characteristic information for identifying the identity can be generated according to the first action information and the power information.

Through carrying out the discernment to driver's user's identity according to first characteristic information, on the one hand, only rely on travel information such as footboard action information and power information to realize driver's user's identity discernment under the condition that does not relate to user's privacy information, can reduce the risk that user's privacy information reveals, on the other hand, adopt the first characteristic information that extracts based on travel information to carry out user's identity discernment, can guarantee higher recognition accuracy, on the other hand, this identification mode does not need to gather information with the help of other sensors or terminal equipment, therefore does not need to improve on hardware device, consequently can be applicable to different motorcycle types.

Drawings

FIG. 1 is a flow chart illustrating steps of an embodiment of a method for identifying a user of a vehicle according to the present invention;

FIG. 2 is a flow chart of steps in another embodiment of a method for identifying a user of a vehicle in accordance with the present invention;

FIG. 3 is a flow chart illustrating steps of yet another embodiment of a method for identifying a user of a vehicle in accordance with the present invention;

FIG. 4 is a flow chart illustrating steps of yet another embodiment of a method for identifying a user of a vehicle in accordance with the present invention;

FIG. 5 is a block diagram of an embodiment of a vehicle user identification device according to the present invention;

FIG. 6 is a block diagram of another embodiment of a vehicle user identification device of the present invention;

fig. 7 is a block diagram of an embodiment of a vehicle machine according to the present invention.

Detailed Description

So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments thereof which are illustrated in the appended drawings. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.

Referring to fig. 1, a flowchart illustrating steps of an embodiment of a vehicle user identification method according to the present invention is shown, which may specifically include the following steps:

step S102, in the running process of the vehicle, under the condition that the action of the brake pedal is detected, first action information of the pedal action and power information of the vehicle corresponding to the first action information are collected.

In this embodiment, the execution process corresponds to a brake pedal action interval, the first action information of the brake pedal is collected in the brake pedal action interval, and the specific collection mode can be realized by detecting a travel signal of the brake pedal.

In addition, in order to further improve the reliability of identifying the user based on the driving information of the vehicle, the power information of the vehicle can be simultaneously collected in the action interval of the brake pedal, so as to obtain first characteristic information for identifying the user according to the first action information and the power information, and the first action information and the power information can be specifically detected through corresponding sensors.

And step S104, acquiring first characteristic information according to the first action information and the power information of the vehicle, wherein the first characteristic information is used for identifying the identity of the user.

In this embodiment, because different driving users have different driving habits, the collected pedal action information and the collected power information are further processed to obtain first characteristic information capable of reflecting the driving characteristics of the driving users, so that the driving users can be identified based on the first characteristic information.

And step S106, identifying the user identity information of the vehicle according to the first characteristic information.

In this embodiment, each brake pedal action generates a group of first characteristic information correspondingly, the first characteristic information is used to identify the user identity, the user identity may be determined by detecting whether the characteristic information of the designated user matched with the first characteristic information is prestored, and the user identity may be determined based on the output result by inputting the first characteristic information into a preset identification model.

According to the vehicle user identification method provided by the embodiment, when the brake pedal is detected to act, the first action information of the pedal action and the power information of the vehicle in the pedal action execution process are collected, and different driving habits of different users are different from each other and can be quantitatively reflected through the collected first action information and the vehicle power information, so that the first characteristic information for identifying the identity can be generated according to the first action information and the power information.

In some embodiments, one possible implementation manner of step S102 is: if the brake pedal is detected to act, recording the stroke of the brake pedal; under the condition that the detected travel of the brake pedal is increased to be larger than or equal to a preset travel threshold value, determining that the brake pedal meets a first preset condition so as to acquire first action information of the brake pedal and power information of a vehicle; and under the condition that the travel of the brake pedal is detected to be reduced to be less than or equal to the preset travel threshold, stopping collecting the first action information of the brake pedal and the power information of the vehicle.

The first preset condition can be understood as that the pedal depth (i.e. pedal stroke) generated by the pedal action meets the preset condition, and the brake pedal action meets the first preset condition.

Specifically, the action of the brake pedal may be detected according to a preset detection period, for example, the travel information of the pedal collected in three adjacent detection periods is analyzed, if in a first detection period, the detected travel of the brake pedal is less than or equal to a preset threshold T (e.g., 0.0001, which may be adjusted according to the looseness of the brake pedal spring), it indicates that the travel data in the first detection period does not meet the first preset condition, and if in a second detection period, the travel of the brake pedal in the second detection period is greater than or equal to the preset travel threshold T, it is considered that the action of the brake pedal meeting the first preset condition starts in the second detection period, and thus the travel data of the brake pedal starts to be recorded; and if the stroke of the brake pedal is reduced to be smaller than the preset stroke threshold value T, the action of the brake pedal is indicated to be no longer in accordance with the first preset condition, and the recording of the stroke data of the brake pedal is finished. And dividing a single complete brake pedal action interval, if the travel of the brake pedal is continuously detected to be greater than or equal to the preset travel threshold T in the third detection period, acquiring data again, and if the travel of the brake pedal is not greater than or equal to the preset travel threshold T, not acquiring the data.

In the embodiment, the first preset condition and the preset travel threshold corresponding to the first preset condition are limited, information is collected when the pedal travel is detected to be larger than or equal to the preset travel threshold, and compared with a mode of collecting information when the pedal action is detected, the collected information can reflect the difference of the driving habits of a user, so that the identification of the identity information of the vehicle user is facilitated, and the reliability of the identification scheme is improved.

In some embodiments, one possible implementation manner of step S104 is: acquiring second action information of an accelerator pedal under the condition that the brake pedal is detected to generate action and meets a first preset condition; acquiring a first group of time-space domain characteristic information and a first group of frequency domain characteristic information in the first action information; acquiring a second group of time-space domain characteristic information and a second group of frequency domain characteristic information in the second action information; and configuring a feature matrix according to the first group of time-space domain feature information, the first group of frequency domain feature information, the second group of time-space domain feature information, the second group of frequency domain feature information and the power information so as to take the feature matrix as the first feature information.

Wherein the power information includes at least one of lateral acceleration, longitudinal acceleration, vehicle speed, motor speed, and vehicle torque of the vehicle.

In some driving environments, the action of stepping on an accelerator pedal can also occur in an action interval generated by a brake pedal, if the action of the accelerator pedal is detected, second action information of the accelerator pedal is correspondingly collected, so that a first group of time-space domain characteristic information and a first group of frequency domain characteristic information are obtained according to the first action information, a second group of time-space domain characteristic information and a second group of frequency domain characteristic information are obtained according to the second action information, and if the action of the accelerator pedal does not occur, the second action information is regarded as 0.

The first set of time-space domain feature information includes: the maximum value, the average value, the standard deviation, the duration of the travel of the brake pedal, the number of points with depth change, the quantile, the wave form factor, the peak value factor, the pulse factor and the margin factor.

The first set of frequency domain feature information includes: and carrying out frequency domain transformation on the first group of time-space domain characteristic information to obtain a maximum value, a minimum value, a mean value, a standard deviation, a kurtosis, a skewness, a wave form factor, a peak value factor, a pulse factor and a margin factor.

The second set of time-space domain feature information includes: maximum, minimum, mean, standard deviation, quantile, form factor, peak factor, pulse factor, margin factor of the travel of the accelerator pedal.

The second set of frequency domain feature information includes: and carrying out frequency domain transformation on the pedal action information second group of time-space domain characteristic information to obtain a maximum value, a minimum value, a mean value, a standard deviation, a kurtosis, a skewness, a wave form factor, a peak value factor, a pulse factor and a margin factor.

In the characteristic information, pedal action information is respectively marked by adopting a time-space domain characteristic and a frequency domain characteristic, numerical statistics of kurtosis reflecting random variable distribution characteristics are respectively adopted in the time-space domain and the frequency domain, a deviation statistical data is adopted to distribute a digital characteristic of asymmetric degree, a waveform factor is adopted to represent the ratio of a root mean square value to an average value of a signal, a peak factor is adopted to represent the ratio of a signal peak value to an effective value (RMS), a pulse factor is adopted to represent the ratio of the signal peak value to a rectified average value (average value), and a margin factor is adopted to represent the ratio of the signal peak value to the square root amplitude.

The characteristic information is acquired and calculated, pedal action information can be reflected from multiple aspects such as a time-space domain, a frequency domain, data distribution, a data mean value and a square root amplitude value, so that a characteristic matrix is generated based on the characteristic information, differential characteristics reflected in the braking process of different driving users can be effectively extracted, the characteristic matrix is used as an identification object, and a high-precision identification effect can be obtained.

In some embodiments, one possible implementation manner of step S106 is: recording the action number of the brake pedal; under the condition that the action number of the brake pedal is larger than or equal to the preset identification number, obtaining multiple groups of first characteristic information matched with the action number; and identifying the user identity information of the vehicle according to the plurality of groups of first characteristic information.

In the embodiment, a group of first characteristic information is generated corresponding to the action of each brake pedal, and because single action of the brake pedal has higher contingency, in order to ensure the accuracy of the identification result, after a plurality of groups of first characteristic information are generated, the identification operation of the user identity is executed according to the plurality of groups of first characteristic information, so that the probability of abnormal identification can be reduced, and the accuracy of the identification result is ensured.

In some embodiments, one possible implementation manner of step S106 is: determining the feature matrix meeting the second preset condition as first feature information, and respectively inputting multiple groups of first feature information into the trained classification recognition model to correspondingly output multiple recognition identifications; dividing the same identification in the plurality of identification into a group to obtain at least one group of identification; and calculating the occupation ratio of each group of identification marks in the plurality of identification marks, and determining the identification mark with the largest occupation ratio as the identification mark of the vehicle user.

In the embodiment, most of the pedal actions conform to the driving habits of the user during the driving process of the vehicle, but it is not possible to completely avoid the occurrence of pedal actions that are partially incompatible with the driving habits of the user, and if this occurs, when the part of the characteristic information is separately identified, the probability that the part of the characteristic information cannot be identified or is identified incorrectly exists, therefore, by collecting a plurality of groups of pedal actions, each group of pedal actions forms a group of first characteristic information and respectively carries out identification operation to obtain a plurality of identification marks which may be the same or different, the characteristic information corresponding to the recognition mark with the maximum value can reflect the driving habit of the user more when the recognition marks are different, therefore, the identification mark with the largest proportion is determined as the identification mark of the vehicle user, so that the accuracy of user identification and the reliability of identification operation are further improved.

In some embodiments, before determining the feature matrix meeting the second preset condition as the first feature information, and inputting the multiple sets of first feature information into the trained classification recognition model respectively to correspondingly output the multiple recognition identifiers, the method further includes: detecting whether the feature matrix is associated with a label or not; and under the condition that the feature matrix is not associated with the label, determining the feature matrix as first feature information meeting a second preset condition.

The second preset condition is specifically that the feature matrix is not associated with a label, if the feature matrix is detected to be associated with the label, it indicates that the action information and the power information corresponding to the current user are not trained, that is, if the trained classification recognition model is input for recognition, recognition abnormality is generated, and the feature information associated with the label is recorded as second feature information.

In some embodiments, when the feature matrix is associated with a tag, it is determined that the feature matrix does not meet a second preset condition, and the feature matrix that does not meet the second preset condition is recorded as second feature information used for training the classification recognition model, where the second feature information and the tag are input into a training model of the classification recognition model, and the classification recognition model is updated according to a training result of the training model, so that the updated classification recognition model can recognize the tag as a recognition identifier.

In the embodiment, the classification recognition model is obtained by training a Support Vector Machine (SVM), the obtained multiple groups of feature matrices are respectively input into the classification recognition model by setting the classification recognition model, each group of feature matrices correspondingly outputs an identity, the recognition identifier with the largest occupation ratio is determined as the identity, the recognition result corresponding to the feature matrix generated by the abnormal braking operation of the user can be deleted, and the normal recognition result is retained, so that the recognition accuracy of identity recognition is ensured.

In addition, as can be understood by those skilled in the art, the classification recognition model can also be obtained by training based on a neural network model or a bayesian classifier.

After the user identity information of the vehicle is identified according to the multiple sets of first characteristic information, the method further comprises the following steps: and inputting the first characteristic information and the recognized identity into a training model, wherein the training model is used for training a classification recognition model, and the classification recognition model is optimized according to a training result of the training model.

In this embodiment, the identity obtained by the recognition is printed on the feature matrix after the recognition and is stored in the training data set for the next training of the classification recognition model, so that the accuracy of the classification recognition model can be further improved.

Referring to fig. 2, a flow chart of steps of another embodiment of a vehicle user identification method of the present invention is shown, which may specifically include the following steps:

and step S202, receiving feedback information input by the user according to the identity prompt information.

And step S204, determining whether the user is an identifiable user according to the feedback information.

And step S206, under the condition that the user is not the recognizable user, generating a label according to the input operation of the user, taking the generated characteristic matrix as second characteristic information when the action information and the power information are acquired, and establishing an incidence relation between the label and the characteristic matrix.

If the user is not an identifiable user and the identification is not generated before, under the condition, the correspondingly generated feature matrix can be used as training data to train the classification recognition model, so that the training data can be acquired in the normal driving process, and after the training data is acquired, the training data is input into a support vector machine to be trained, so that the classification recognition model is perfected, and the recognition efficiency of the classification recognition model is improved.

And S208, inputting the second characteristic information and the label into a training model of the classification recognition model, and updating the classification recognition model according to a training result of the training model, so that the updated classification recognition model can recognize the label as a recognition identifier.

Step S210, when the user is the recognizable user, directly detecting whether the brake pedal acts or not, and using the obtained feature matrix as the first feature information.

The recognizable user can understand that the pedal action information, the power information and the like of the user are used as training data to perform model training, namely, the characteristic matrix generated by corresponding the pedal action information and the power information of the user can be recognized by the classification recognition model to output a recognition result, so that the reliability of recognition operation can be ensured.

And S212, under the condition that multiple groups of first characteristic information are obtained, identifying the user identity information of the vehicle according to the multiple groups of first characteristic information.

In this embodiment, before performing the identification operation, first prompt information may be generated, where the first prompt information is used to prompt the user to confirm whether the id has been generated, so as to use the received feedback information of the user as a confirmation result, and if the id has not been generated, then second prompt information may be generated to prompt the user to input information such as name or code, so as to generate the id according to the information such as name or code,

referring to fig. 3, a flowchart illustrating steps of another embodiment of a vehicle user identification method of the present invention is shown, which may specifically include the following steps:

step S302, receiving feedback information input by the user according to the identity prompt information.

And step S304, determining whether the user is an identifiable user according to the feedback information.

In step S306, if the user is not an identifiable user, a tag is generated according to an input operation of the user.

Step S308, when detecting that the brake pedal acts and meeting a first preset condition, acquiring first action information of the pedal action, acquiring second action information of the accelerator pedal and power information of the vehicle corresponding to the first action information, and acquiring the characteristic matrix as second characteristic information according to the action information and the power information.

Step S310, establishing an incidence relation between the label and the feature matrix.

Step S312, inputting the feature matrix and the labels into a training model of the classification recognition model, and updating the classification recognition model according to a training result of the training model, so that the updated classification recognition model can recognize the labels as recognition marks.

And step S314, when the user is an identifiable user, under the condition that the action of the brake pedal is detected and the first preset condition is met, acquiring first action information of the pedal action, acquiring second action information of the accelerator pedal and power information of the vehicle corresponding to the first action information, and acquiring the characteristic matrix as first characteristic information according to the action information and the power information.

Step S316, inputting the plurality of groups of first feature information into the trained classification recognition model, so as to output a plurality of recognition identifiers correspondingly.

Step S318, dividing the same identifier in the plurality of identifiers into a group to obtain at least one group of identifiers.

And step S320, calculating the occupation ratio of each group of identification marks in the plurality of identification marks, and determining the identification mark with the largest occupation ratio as the identification mark of the vehicle user.

Step S322, inputting the first characteristic information and the recognized identity into a training model, wherein the training model is used for training a classification recognition model, and the classification recognition model is optimized according to a training result of the training model.

In addition, after the identification of the user is identified, the application program is pushed based on the identification, so that the vehicle can provide an accurate and humanized application program for the user, and the use experience of the user is promoted.

Referring to fig. 4, a flowchart illustrating steps of another embodiment of a vehicle user identification method according to the present invention is shown, which may specifically include the following steps:

step S402, responding to the starting instruction, generating identity prompt information, prompting a driver to confirm whether the braking data is trained or not, receiving feedback information input by the user according to the identity prompt information, determining whether the user is a recognizable user or not according to the feedback information, if the determination result is yes, entering step S412, and if the determination result is no, entering step S404.

Step S404, prompting the driver to input the name/code of the driver, and generating a label according to the name/code of the driver.

Step S406, when the brake pedal is detected to act and the first preset condition is met, acquiring first action information of the pedal action, acquiring second action information of the accelerator pedal and power information of the vehicle corresponding to the first action information, and acquiring the characteristic matrix as second characteristic information according to the action information and the power information.

And step S408, establishing an incidence relation between the label and the feature matrix.

And S410, inputting the second characteristic information and the label into a training model of the classification recognition model, and updating the classification recognition model according to a training result of the training model, so that the updated classification recognition model can recognize the label as a recognition identifier.

Step S412, when the brake pedal is detected to be operated and the first preset condition is met, acquiring first action information of the pedal operation, acquiring second action information of the accelerator pedal and power information of the vehicle corresponding to the first action information.

Step S414, obtain the first set of time-space domain feature information and the first set of frequency domain feature information in the first action information.

Step S416, a second set of time-space domain feature information and a second set of frequency domain feature information in the second action information are obtained.

And step S418, configuring a feature matrix according to the first group of time-space domain feature information, the first group of frequency domain feature information, the second group of time-space domain feature information, the second group of frequency domain feature information and the power information, and taking the feature matrix as the first feature information.

Wherein the first group of time-space domain characteristic information comprises: the maximum value, the mean value, the standard deviation, the duration of the stroke of the brake pedal, the point number of the depth change, the quantile, the wave form factor, the peak value factor, the pulse factor and the margin factor, and the first group of frequency domain characteristic information comprises: the maximum value, the minimum value, the mean value, the standard deviation, the kurtosis, the skewness, the wave form factor, the peak value factor, the pulse factor and the margin factor of the travel of the brake pedal after frequency domain transformation.

The power information includes: lateral acceleration, longitudinal acceleration, vehicle speed, motor speed, vehicle torque.

The second set of time-space domain feature information includes: the maximum value, the minimum value, the mean value, the standard deviation, the quantile, the wave form factor, the peak value factor, the pulse factor and the margin factor of the travel of the accelerator pedal; the second set of frequency domain feature information includes: the maximum value, the minimum value, the mean value, the standard deviation, the kurtosis, the skewness, the wave form factor, the peak value factor, the pulse factor and the margin factor after the stroke of the accelerator pedal is subjected to frequency domain transformation.

In step S420, the number of brake pedal actuations is recorded.

In step S422, when the number of actions of the brake pedal is greater than or equal to the preset identification number, multiple sets of first feature information matched with the number of actions are obtained.

Step S424, respectively inputting the multiple groups of first feature information into the trained classification recognition model to correspondingly output multiple recognition identifiers, and determining the multiple recognition identifiers as the identity of the vehicle user.

Step S426, inputting the first characteristic information and the recognized identity into a training model, wherein the training model is used for training a classification recognition model, and the classification recognition model is optimized according to a training result of the training model.

In the embodiment, by the scheme, the identity of the driving user can be identified only by the brake data under the condition that the privacy information (such as face information, iris information, fingerprint information, voiceprint information and the like) of the driving user is not involved. Specifically, differentiation characteristics reflected in the braking action process of different driving users are effectively extracted for identity recognition of the driving users. In addition, a Support Vector Machine (SVM) is used for training the brake characteristic data with the identity marks, a classification recognition model is obtained, and the identity recognition of a driver is carried out on the brake characteristic data without the identity marks.

It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

Referring to fig. 5, a block diagram of a vehicle user identification device 500 according to an embodiment of the present invention is shown, which may specifically include the following modules:

the acquisition module 502 is configured to acquire first action information of pedal action and power information of the vehicle corresponding to the first action information when the brake pedal is detected to generate action during the running of the vehicle.

The obtaining module 504 is configured to obtain first feature information according to the first action information and the power information of the vehicle, where the first feature information is used to identify a user identity.

And the identification module 506 is used for identifying the user identity information of the vehicle according to the first characteristic information.

As shown in fig. 6, optionally, the acquisition module 502 includes:

the first recording sub-module 5022 is used for recording the stroke of the brake pedal if the brake pedal is detected to act.

The determining submodule 5024 is used for determining that the brake pedal meets a first preset condition under the condition that the fact that the travel of the brake pedal is increased to be larger than or equal to the preset travel threshold value is detected, so that first action information of the brake pedal and power information of the vehicle are collected.

The control submodule 5026 is used for stopping collecting the first action information of the brake pedal and the power information of the vehicle under the condition that the fact that the travel of the brake pedal is reduced to be smaller than or equal to the preset travel threshold value is detected.

Optionally, the obtaining module 504 includes:

and the acquisition submodule 5042 is used for acquiring second action information of the accelerator pedal under the condition that the action of the brake pedal is detected and the first preset condition is met.

The first obtaining sub-module 5044 is configured to obtain a first set of time-space domain feature information and a first set of frequency domain feature information in the first action information;

the first acquisition sub-module 5044 is further configured to: acquiring a second group of time-space domain characteristic information and a second group of frequency domain characteristic information in the second action information;

the configuration submodule 5046 is configured to configure a feature matrix according to the first set of time-space domain feature information, the first set of frequency domain feature information, the second set of time-space domain feature information, the second set of frequency domain feature information, and the power information, so as to use the feature matrix as the first feature information, where the power information includes at least one of a lateral acceleration, a longitudinal acceleration, a vehicle speed, a motor speed, and a vehicle torque of the vehicle.

Optionally, the identification module 506 comprises:

a second recording sub-module 5062 for recording the number of brake pedal actuations.

The second obtaining sub-module 5064 is configured to obtain multiple sets of first feature information that matches the number of motions of the brake pedal when the number of motions of the brake pedal is greater than or equal to a preset recognition number.

The identifying sub-module 5066 is configured to identify the user identity information of the vehicle according to the plurality of sets of first feature information.

Optionally, the identification module 506 further comprises:

the input sub-module 5068 is configured to determine the feature matrix meeting the second preset condition as first feature information, and input the multiple sets of first feature information into the trained classification recognition model respectively, so as to output multiple recognition identifiers correspondingly.

The dividing sub-module 5070 is configured to divide the same identifiers of the multiple identifiers into a group to obtain at least one group of identifiers.

And the calculating submodule 5072 is used for calculating the occupation ratio of each group of identifiers in the plurality of identifiers, and determining the identifier with the largest occupation ratio as the identity of the vehicle user.

Optionally, the vehicle user identification device 500 further includes:

a first detecting module 508, configured to detect whether the feature matrix is associated with a tag.

The determining module 510 is configured to determine the feature matrix as the first feature information meeting a second preset condition when the tag is not associated with the feature matrix.

The determination module 510 is further configured to: and under the condition that the feature matrix is associated with the label, determining the feature matrix as second feature information which is not in accordance with a second preset condition, wherein the second feature information is used for training the classification recognition model, the second feature information and the label are input into the training model of the classification recognition model, and the classification recognition model is updated according to the training result of the training model, so that the updated classification recognition model can recognize the label as the recognition identifier.

Optionally, the vehicle user identification device 500 further includes:

the receiving module 512 is configured to receive feedback information input by the user according to the identity prompting information.

The determination module 510 is further configured to: and determining whether the user is an identifiable user according to the feedback information.

A generating module 514, configured to generate a tag according to an input operation of the user if the user is not an identifiable user, so as to establish an association relationship between the tag and the feature matrix if the feature matrix is used as the second feature information.

And a second detection module 516, configured to directly detect whether the brake pedal is actuated to use the feature matrix as the first feature information if the user is an identifiable user.

Optionally, the vehicle user identification device 500 further includes:

an input module 518, configured to input the first feature information and the identified identity into a training model, where the training model is used to train a classification recognition model, and the classification recognition model is optimized according to a training result of the training model.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

As shown in fig. 7, the vehicle machine 70 according to the embodiment of the present invention includes: the above embodiment describes the user identification apparatus 500 of the vehicle.

The embodiment of the invention can be applied to a vehicle machine, a control module of other vehicles or a server with a communication link between the vehicle machine and the vehicle, wherein the vehicle machine refers to a vehicle-mounted information entertainment product which is installed in the vehicle for short, the vehicle machine can be used for information communication with the vehicle and the outside (vehicle-to-vehicle) functionally, the vehicle machine comprises a host, a display module, a microphone and a network module, a touch module can be integrated on the display module, and the vehicle machine can be electrically connected with a loudspeaker module of the vehicle.

The computer-readable storage medium according to an embodiment of the present invention includes the method for identifying a user of a vehicle according to any one of the above embodiments.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The vehicle user identification method and the vehicle user identification device provided by the invention are described in detail, specific examples are applied in the description to explain the principle and the implementation mode of the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A method for identifying a user of a vehicle, comprising:

2. The method according to claim 1, wherein the collecting of first action information of the pedal action and power information of the vehicle corresponding to the first action information in the case of detecting the action of a brake pedal during the running of the vehicle comprises:

if the brake pedal is detected to act, recording the stroke of the brake pedal;

3. The method according to claim 2, wherein the obtaining first characteristic information based on the first action information and the power information of the vehicle includes:

4. The method of claim 3, wherein identifying the user identity information of the vehicle based on the first characteristic information comprises:

recording the action number of the brake pedal;

5. The method of claim 4, wherein identifying the user identity information of the vehicle based on the plurality of sets of the first characteristic information comprises:

6. The method according to claim 5, wherein before determining the feature matrix meeting a second preset condition as the first feature information, and inputting a plurality of sets of the first feature information into the trained classification recognition model respectively to output a plurality of corresponding recognition identifiers, the method further comprises:

detecting whether the feature matrix is associated with a label;

7. The method of claim 6, further comprising:

8. The method according to claim 7, wherein in a case where a brake pedal generating action is detected, before collecting first action information of the pedal action and power information of the vehicle corresponding to the first action information, the method further comprises:

9. The method according to any one of claims 5 to 8, further comprising:

10. A user identification device for a vehicle, comprising:

11. The utility model provides a car machine, its characterized in that includes:

the user identification apparatus of a vehicle according to claim 10.

12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for user identification of a vehicle according to any one of claims 1 to 8.