CN114999134A - Driving behavior early warning method, device and system - Google Patents
Driving behavior early warning method, device and system Download PDFInfo
- Publication number
- CN114999134A CN114999134A CN202210586241.3A CN202210586241A CN114999134A CN 114999134 A CN114999134 A CN 114999134A CN 202210586241 A CN202210586241 A CN 202210586241A CN 114999134 A CN114999134 A CN 114999134A
- Authority
- CN
- China
- Prior art keywords
- driving
- data
- user
- driving behavior
- driving data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000006399 behavior Effects 0.000 claims description 146
- 206010039203 Road traffic accident Diseases 0.000 claims description 21
- 238000010219 correlation analysis Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000036541 health Effects 0.000 claims description 8
- 230000015654 memory Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 18
- 230000001133 acceleration Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Abstract
The application discloses a driving behavior early warning method, a driving behavior early warning device and a driving behavior early warning system, which relate to the technical field of driving safety, wherein the driving behavior early warning method comprises the following steps: acquiring current driving data of the electric automobile, wherein the driving data is related to the driving behavior of a user; predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length; according to the target prediction driving data, scoring the driving behavior of the user; and outputting early warning information under the condition that the grading result is smaller than the preset score. The scheme of this application has realized the early warning to the potential safety hazard that leads to owing to the action of driving.
Description
Technical Field
The application relates to the technical field of driving safety, in particular to a driving behavior early warning method, device and system.
Background
At present, the keeping quantity of automobiles in China is close to 3 hundred million, and due to the limitation of the current technical conditions, drivers still remain the main control bodies of the automobiles in the road running process in the past and in the future. However, due to unpredictable driving behaviors and possible abnormal driving behaviors of users, the driving behaviors may cause the service life and the use economy of the vehicle to be reduced when the driving behaviors are not predictable, and serious traffic accidents are caused when the driving behaviors are abnormal. It is estimated that automobiles have over one-third of their energy consumption and that up to 20 tens of thousands of traffic accidents per year on average cause immeasurable losses. How to early warn potential safety hazards existing in the driving process of a vehicle based on the driving behaviors of a user becomes a technical problem to be solved at present.
Disclosure of Invention
The application aims to provide a driving behavior early warning method, a driving behavior early warning device and a driving behavior early warning system, so that the problem that early warning cannot be performed on potential safety hazards caused by driving behaviors of users in the prior art is solved.
In a first aspect, to achieve the above object, an embodiment of the present application provides a driving behavior early warning method, including:
acquiring current driving data of the electric automobile, wherein the driving data is related to the driving behavior of a user;
predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length;
according to the target prediction driving data, scoring the driving behavior of the user;
and outputting early warning information under the condition that the grading result is smaller than the preset score.
Optionally, predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric vehicle within a preset time period in the future, where the method includes:
preprocessing the current driving data;
inputting the preprocessed current driving data into a user driving behavior analysis and prediction model to obtain initial predicted driving data;
and correcting the initial predicted driving data according to a pre-stored data distribution curve related to the user to obtain the target predicted driving data.
Optionally, the current driving data is preprocessed, including at least one of:
removing data lost in the data transmission process from the current driving data;
and eliminating abnormal outlier data in the current driving data by using a clustering algorithm of unsupervised learning.
Optionally, scoring the driving behavior of the user according to the target predicted driving data includes:
determining first information of the influence degree of the driving behavior of the user on a power battery of the electric automobile according to the target prediction driving data;
determining second information of the influence degree of the driving behavior of the user on the traffic accident of the electric automobile according to the target prediction driving data;
and scoring the driving behavior of the user according to the first information and the second information.
Optionally, the determining, according to the target predicted driving data, first information of the degree of influence of the driving behavior of the user on a power battery of the electric vehicle includes:
inputting the target predicted driving data into a battery life correlation analysis model to obtain the first information; wherein the first information includes power consumption of the electric vehicle and battery health of the power battery.
Optionally, the second information for determining the influence degree of the driving behavior of the user on the traffic accident of the electric vehicle according to the target predicted driving data includes:
acquiring current road condition data of the electric automobile;
and inputting the target predicted driving data and the road condition data into a traffic accident correlation analysis model to obtain second information, wherein the second information comprises an accident type and the probability of occurrence of an accident.
Optionally, scoring the driving behavior of the user according to the first information and the second information includes:
and inputting the first information and the second information into a user driving behavior evaluation feedback model to obtain a grading result.
Optionally, the current driving data includes: at least one of vehicle speed, accelerator pedal opening, and steering wheel angle.
In a second aspect, to achieve the above object, an embodiment of the present application further provides a driving behavior early warning device, including:
the first acquisition module is used for acquiring the current driving data of the electric automobile, and the driving data is related to the driving behavior of a user;
the prediction module is used for predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length;
the scoring module is used for scoring the driving behavior of the user according to the target prediction driving data;
and the output module is used for outputting the early warning information under the condition that the grading result is smaller than the preset value.
In order to achieve the above object, an embodiment of the present application further provides a driving behavior early warning system, including: a processor, a memory, and a program or instructions stored on the memory and executable on the processor; the processor, when executing the program or instructions, implements the steps of the driving behavior warning method as described above in the first aspect.
The above technical scheme of this application has following beneficial effect at least:
according to the driving behavior early warning method, firstly, current driving data of the electric automobile are obtained, and the driving data are related to driving behaviors of users; secondly, predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length; thus, the driving behavior of the user is predicted, and the driving behavior of the user is graded according to the target prediction driving data; and finally, outputting early warning information under the condition that the grading result is smaller than the preset value. Therefore, whether potential safety hazards exist in the driving process of the vehicle is judged based on the predicted driving behaviors, and the user is reminded by outputting early warning information when the potential safety hazards exist, so that safety accidents are avoided, and the driving safety of the vehicle is improved.
Drawings
Fig. 1 is a schematic flow chart of a driving behavior warning method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a driving behavior warning device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or described herein. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.
The driving behavior warning method, device and system provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.
As shown in fig. 1, a schematic flow chart of a driving behavior warning method according to an embodiment of the present application is shown, where the method includes:
here, the driving data related to the driving behavior of the user may be, for example: vehicle speed, accelerator pedal opening, steering wheel angle, etc.; therefore, the driving parameters in this step can be obtained from sensors installed on the electric vehicle, wherein each sensor is used for acquiring corresponding driving data in real time.
here, it should be noted that, depending on the rapid development of the car networking technology and the gradual maturity of the national, local and enterprise vehicle monitoring platform, especially the driving and use data of the electric car have formed a huge scale, on this basis, the step may analyze the driving habits of the user by using the big data, and on this basis, predict the target prediction driving data of the electric car within the preset time length in the future by using the current driving data.
103, scoring the driving behavior of the user according to the target prediction driving data;
in the step, the driving behaviors of the user are graded based on the target prediction driving data, so that the probability of dangerous driving operation of the user can be reduced, the accident occurrence probability and risk are reduced, the improvement of the driving technology of the user and the conversion of the driving style can be directly promoted, and the use economy of the vehicle is improved.
And 104, outputting early warning information under the condition that the grading result is smaller than the preset value.
In the step, when the scoring result is smaller than the preset score, the driving behavior of the user is predicted, so that potential safety hazards can exist in the driving process, and the user is reminded by outputting early warning information.
Specifically, this step can be through the mode that shows early warning information on the car machine screen, perhaps, through the mode at on-vehicle bee calling organ output alarm sound, remind the user.
According to the driving behavior early warning method, firstly, current driving data of the electric automobile are obtained, and the driving data are related to driving behaviors of users; secondly, predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length; therefore, the driving behavior of the user is predicted, and the driving behavior of the user is graded according to the target prediction driving data; and finally, outputting early warning information under the condition that the grading result is smaller than the preset value. Therefore, whether potential safety hazards exist in the driving process of the vehicle is judged based on the predicted driving behaviors, and the user is reminded in the mode of outputting early warning information when the potential safety hazards exist, so that safety accidents are avoided, the driving safety of the vehicle is improved, and meanwhile, the driving technology of the user is facilitated to be improved.
As an optional implementation manner, in step 102, predicting the driving behavior of the user according to the current driving data, and obtaining target predicted driving data of the electric vehicle within a preset time period in the future, the method includes:
(1) preprocessing the current driving data;
in the step, invalid data in the current driving data can be removed by preprocessing the current driving data, and only data effective to a prediction process is reserved.
(2) Inputting the preprocessed current driving data into a user driving behavior analysis and prediction model to obtain initial predicted driving data;
here, it should be noted that the driving behavior analysis and prediction model of the user is an artificial intelligent learning algorithm, such as: the Long Short Term Memory Network (LSTM) is obtained by training, where data required by training may be historical data obtained based on a big data technology. The specific training process is as follows: and (3) taking a historical speed curve and an accelerator pedal opening curve with a time axis as an abscissa as learning data, importing the learning data into a long-time and short-time memory network (a user driving behavior analysis and prediction model), and learning through a neural network to obtain the longitudinal driving behaviors of different users. The whole vehicle speed curve and the accelerator pedal opening curve within a period of time in the future can be predicted through the learned user driving behavior analysis and prediction model;
(3) and correcting the initial predicted driving data according to a pre-stored data distribution curve related to the user to obtain the target predicted driving data.
Here, it should be noted that the generation process of the data distribution curve related to the user may be: aiming at each user, a numerical statistical method is applied to obtain the columnar distribution of the driving data related to the driving behaviors of the users; and then obtaining a data distribution curve of the opportunity by applying a polynomial fitting method.
In the step, the initial predicted driving data is corrected by utilizing the pre-stored data distribution curve related to the user to obtain the target predicted driving data, so that the target predicted driving data is more in line with the driving habits of the user, and the prediction accuracy is further improved.
As a specific implementation manner, the preprocessing the current driving data includes at least one of the following:
removing data lost in the data transmission process from the current driving data; namely: eliminating blank spots in the current driving data;
and rejecting abnormal outlier data in the current driving data by using a clustering algorithm of unsupervised learning.
According to the specific implementation mode, the invalid data in the current driving data are removed, so that the data used in the prediction process are all valid, and the prediction accuracy is improved.
Here, an implementation of the step of predicting the driving behavior of the user according to the current driving data to obtain the target predicted driving data of the electric vehicle within a preset time period in the future is described:
a) early preparation work:
firstly, determining quantitative analysis indexes of driving behaviors of a user, wherein the quantitative analysis indexes mainly comprise longitudinal speed, longitudinal acceleration, yaw angle, yaw rate and the like;
secondly, correlating the driving behavior quantitative analysis index obtained by analysis with the existing data of the vehicle; specifically, the longitudinal speed-related vehicle speed, the longitudinal acceleration-related accelerator pedal opening, the yaw angle, the yaw rate-related steering wheel handover, and the like; wherein the data are driving data related to driving behaviors in the application;
thirdly, aiming at each user, a numerical statistical method is applied to obtain histogram distribution of driving data related to the driving behaviors of the users, and then a polynomial fitting method is applied to obtain an actual data distribution curve;
b) and (3) prediction process:
firstly, the processing of the driving data related to the driving behavior specifically includes: removing blank spots (i.e., data lost in transmission) in the driving data related to the driving behavior of the user; screening abnormal outliers in the driving data related to the driving behaviors of the user through a clustering algorithm of unsupervised learning, and removing the driving data related to the driving behaviors of the user to be processed;
secondly, inputting the processed driving data related to the driving behavior of the user into a driving behavior analysis and prediction model of the user for prediction to obtain initial predicted driving data, wherein the initial predicted driving data can be a longitudinal driving behavior prediction curve, for example;
and thirdly, correcting the predicted longitudinal driving behavior prediction curve by using an actual data distribution curve obtained by a fitting method in the early stage to obtain a final prediction curve (target predicted driving data).
As an optional implementation manner, in step 103, scoring the driving behavior of the user according to the target predicted driving data includes:
determining first information of the influence degree of the driving behavior of the user on a power battery of the electric automobile according to the target prediction driving data;
according to the target prediction driving data, determining second information of the influence degree of the driving behavior of the user on the traffic accident of the electric automobile;
and scoring the driving behavior of the user according to the first information and the second information.
In this optional implementation, based on the influence degree of driving action to power battery and the influence degree that causes the traffic accident two aspects to grade user's driving action, can promote the use economic nature of whole car and can reduce the risk that the accident took place.
As a specific implementation manner, the first information for determining the degree of influence of the driving behavior of the user on the power battery of the electric vehicle according to the target predicted driving data includes:
inputting the target predicted driving data into a battery life correlation analysis model to obtain the first information; wherein the first information includes power consumption of the electric vehicle and battery health of the power battery.
In this specific implementation manner, the power consumption is the power consumption of the electric vehicle, for example: the power consumption of the electric vehicle per hour; the battery health may include: the remaining driving mileage of the battery, the number of charge and discharge times of the battery, and the like; the relation between the driving data and the power consumption/battery health degree of the battery can be obtained through self-learning of the neural network; the following describes the process of establishing and training a battery life correlation analysis model:
firstly, establishing theoretical and formula definitions of the power consumption of the whole vehicle and the service life of a battery;
secondly, calculating the power consumption curve and the service life curve of the conventional whole vehicle according to the historical driving data and the battery state data of each user;
thirdly, by applying a correlation analysis and principal component analysis method and combining the knowledge in the field of pure electric vehicles, driving behavior influence factors (including strong positive correlation and strong negative correlation) which are strongly related to the power consumption and the service life of the whole vehicle are extracted from the driving behavior related data, and the factors such as the running speed, the acceleration, the running temperature and the charging and discharging power of the battery of the whole vehicle are analyzed to be related main influence factors; wherein, the running speed and the acceleration of the whole vehicle are related to the driving behavior of a user;
and finally, establishing a prediction model of the influence factors, the vehicle power consumption and the battery life through a deep circulation neural network method.
As another specific implementation manner, the second information for determining the degree of influence of the driving behavior of the user on the occurrence of the traffic accident on the electric vehicle according to the target predicted driving data includes:
(1) acquiring current road condition data of the electric automobile;
in this step, the road condition information may be the road conditions around the electric vehicle detected by the vehicle-mounted detection device (e.g., a vehicle-mounted camera, a radar, etc.), such as the environmental information around the electric vehicle (e.g., static obstacles), road participants (e.g., surrounding vehicles, pedestrians), traffic information (traffic lights, road guide signs, lane lines);
(2) and inputting the target predicted driving data and the road condition data into a traffic accident correlation analysis model to obtain second information, wherein the second information comprises an accident type and the probability of occurrence of an accident.
The following describes the process of building and training a traffic accident correlation analysis model:
firstly, acquiring vehicle accident related data, wherein the data acquisition modes are divided into two modes, namely vehicle data reproduction after an accident occurs and vehicle data uploading during the accident;
secondly, automatically classifying the accident types according to the acquired data, screening out accidents related to the driving behaviors of the user, and classifying the accidents into high (the safety airbag is completely opened), medium (the safety airbag is partially opened) and low (light scratch and emergency brake) according to severity levels;
thirdly, counting the distribution of the corresponding driving behavior related data aiming at the accidents with different severity, so as to obtain the correlation of the accidents caused by the acceleration and steering behaviors of different users;
then, for the vehicle with radar, camera and driving recorder, the video stream and radar information data are recorded at the same time, wherein the lane lines, pedestrians, traffic lights, traffic signs and road obstacles and the like in the video stream are identified by CNN and semantic segmentation technology. Acquiring whether other vehicles exist around the vehicle and relative distance and relative speed information of the vehicles through radar data;
then, the real scene when the accident happens can be directly reproduced by fusing the information acquired from the video stream and the radar data, so that a complete correlation database of the accident scene and the driving behavior of the user can be obtained.
And finally, training a traffic accident correlation analysis model based on the data in the established accident scene and the correlation database of the driving behaviors of the user.
Here, another implementation of obtaining the second information is described again: firstly, determining the speed/acceleration in target prediction driving data and the type of traffic accidents possibly caused by road condition information around the electric automobile in a table look-up mode; secondly, extracting the pre-stored nominal speed/acceleration when the traffic accident occurs, and nominal road condition information and nominal probability; thirdly, calculating the ratio of the vehicle speed to the nominal vehicle speed in the target prediction driving data, the ratio of the acceleration to the nominal acceleration in the target prediction driving data, and the ratio of the road condition information to the nominal road condition information; and finally, calculating the probability of the accident according to the ratios and the nominal probability.
As another specific implementation, the scoring the driving behavior of the user according to the first information and the second information includes:
and inputting the first information and the second information into a user driving behavior evaluation feedback model to obtain a grading result.
Here, it should be noted that the user driving behavior evaluation feedback model may be specifically scored by a weighted sum or the like. The weights of the first information and the second information may be preset or dynamically adjusted, wherein if the weights are dynamically adjusted, the weights may be adjusted according to the degree of emergency, and if the probability of a traffic accident is high, the weight occupied by the second information is high.
Further, this application embodiment can also further upload the result of grading to the cloud server to realize the ranking to different users' driving technique, increase the interest of driving.
In short, the driving behavior early warning method of the embodiment of the application is realized by the following steps:
firstly, acquiring driving parameters related to the driving behavior of the user, which are detected by an on-board detection device, such as: vehicle speed, accelerator pedal opening, steering wheel angle, etc.;
secondly, preprocessing the acquired driving parameters related to the driving behaviors of the user to remove invalid data, such as: eliminating data lost in the transmission process; rejecting abnormal outlier data, and the like;
thirdly, inputting the preprocessed data into a user driving behavior analysis and prediction model to predict initial predicted driving data of the electric automobile in a future preset time period;
fourthly, correcting the initial predicted driving data by utilizing a pre-stored data distribution curve to obtain target predicted driving data;
fifthly, inputting the target prediction driving data into a battery life correlation analysis model to obtain power consumption and battery health degree;
sixthly, inputting the target predicted driving data and the acquired road condition information into a traffic accident correlation analysis model to obtain the accident type and the accident occurrence probability;
seventhly, inputting the power consumption, the battery health degree, the accident type and the accident occurrence probability into a user driving behavior evaluation feedback model, and grading the driving behavior of the user to obtain a grading result;
eighthly, outputting early warning information through a locomotive screen or a buzzer when the scoring result is smaller than a preset score;
and ninthly, uploading the scoring results to a cloud server, and ranking according to the advantages and disadvantages of the driving behaviors.
It should be noted that, in the driving behavior early warning method provided in the embodiment of the present application, the execution subject may be a driving behavior early warning device, or a control module in the driving behavior early warning device, which is used for executing the loaded driving behavior early warning method. The driving behavior early warning method provided by the embodiment of the application is described by taking the driving behavior early warning method executed by the driving behavior early warning device as an example.
According to the driving behavior early warning method, the predicted driving parameters of the electric automobile within a period of time in the future are predicted based on the driving parameters related to the driving behaviors of the user, so that the driving behaviors of the user are graded from two aspects of influence on a battery and possibility of traffic accidents based on the predicted driving parameters, and early warning information is output when the grading is low, so that the probability of dangerous driving operation of the user can be reduced, and further the accident occurrence probability and risk are reduced; the driving technique of the user and the conversion of the driving style can be directly promoted, and the use economy and the service life of the battery of the vehicle are further improved.
As shown in fig. 2, an embodiment of the present application further provides a driving behavior early warning device, including:
the first obtaining module 201 is configured to obtain current driving data of the electric vehicle, where the driving data is related to a driving behavior of a user;
the prediction module 202 is configured to predict the driving behavior of the user according to the current driving data, and obtain target predicted driving data of the electric vehicle within a preset time length in the future;
the scoring module 203 is used for scoring the driving behavior of the user according to the target prediction driving data;
and the output module 204 is configured to output the early warning information when the scoring result is smaller than the preset score.
In the driving behavior early warning device according to the embodiment of the application, first, a first obtaining module 201 obtains current driving data of an electric vehicle, where the driving data is related to a driving behavior of a user; secondly, the prediction module 202 predicts the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric vehicle within a preset time length in the future; thus, the driving behavior of the user is predicted, and the scoring module 203 scores the driving behavior of the user according to the target prediction driving data; finally, the output module 204 outputs the early warning information when the scoring result is smaller than the preset score. Therefore, whether potential safety hazards exist in the driving process of the vehicle is judged based on the predicted driving behaviors, and the user is reminded in the mode of outputting early warning information when the potential safety hazards exist, so that safety accidents are avoided, the driving safety of the vehicle is improved, and meanwhile, the driving technology of the user is facilitated to be improved.
Optionally, the prediction module 202 comprises:
the processing submodule is used for preprocessing the current driving data;
the prediction submodule is used for inputting the preprocessed current driving data into a user driving behavior analysis prediction model to obtain initial prediction driving data;
and the correction submodule is used for correcting the initial predicted driving data according to a pre-stored data distribution curve related to the user to obtain the target predicted driving data.
Optionally, the processing sub-module is specifically configured to perform at least one of the following:
in the current driving data, removing data lost in the data transmission process;
and eliminating abnormal outlier data in the current driving data by using a clustering algorithm of unsupervised learning.
Optionally, the scoring module 203 comprises:
the first determining submodule is used for determining first information of the influence degree of the driving behavior of the user on a power battery of the electric automobile according to the target prediction driving data;
the second determining submodule is used for determining second information of the influence degree of the driving behavior of the user on the traffic accident of the electric automobile according to the target prediction driving data;
and the scoring submodule is used for scoring the driving behavior of the user according to the first information and the second information.
Optionally, the first determining submodule is specifically configured to:
inputting the target predicted driving data into a battery life correlation analysis model to obtain the first information; wherein the first information includes power consumption of the electric vehicle and battery health of the power battery.
Optionally, the second determining sub-module includes:
the first acquisition unit is used for acquiring the current road condition data of the electric automobile;
and the second obtaining unit is used for inputting the target predicted driving data and the road condition data into a traffic accident correlation analysis model to obtain second information, wherein the second information comprises an accident type and the probability of occurrence of an accident.
Optionally, the scoring sub-module is specifically configured to: and inputting the first information and the second information into a user driving behavior evaluation feedback model to obtain a grading result.
Optionally, the current driving data includes: at least one of a vehicle speed, an accelerator pedal opening, and a steering wheel angle.
The embodiment of the present application further provides a driving behavior early warning system, including: a processor, a memory, and a program or instructions stored on the memory and executable on the processor; when the processor executes the program or the instruction, the processes of the driving behavior early warning method embodiment can be realized, and the same technical effect can be achieved.
The embodiment of the present application further provides a readable storage medium, where a program is stored on the readable storage medium, and when the program is executed by a processor, the program implements each process of the driving behavior early warning method embodiment described above, and can achieve the same technical effect, and in order to avoid repetition, the detailed description is omitted here. The readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
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 apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing is a preferred embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and refinements can be made without departing from the principle described in the present application, and these modifications and refinements should be regarded as the protection scope of the present application.
Claims (10)
1. A driving behavior early warning method is characterized by comprising the following steps:
acquiring current driving data of the electric automobile, wherein the driving data is related to the driving behavior of a user;
predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length;
according to the target prediction driving data, scoring the driving behavior of the user;
and outputting early warning information under the condition that the grading result is smaller than the preset score.
2. The method according to claim 1, wherein predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric vehicle within a preset time period in the future comprises:
preprocessing the current driving data;
inputting the preprocessed current driving data into a user driving behavior analysis and prediction model to obtain initial prediction driving data;
and correcting the initial predicted driving data according to a pre-stored data distribution curve related to the user to obtain the target predicted driving data.
3. The method of claim 2, wherein preprocessing the current driving data comprises at least one of:
removing data lost in the data transmission process from the current driving data;
and rejecting abnormal outlier data in the current driving data by using a clustering algorithm of unsupervised learning.
4. The method of claim 1, wherein scoring the driving behavior of the user based on the target predicted travel data comprises:
determining first information of the influence degree of the driving behavior of the user on a power battery of the electric automobile according to the target prediction driving data;
determining second information of the influence degree of the driving behavior of the user on the traffic accident of the electric automobile according to the target prediction driving data;
and scoring the driving behavior of the user according to the first information and the second information.
5. The method according to claim 4, wherein determining first information of the degree of influence of the driving behavior of the user on the power battery of the electric vehicle based on the target predicted travel data includes:
inputting the target predicted driving data into a battery life correlation analysis model to obtain the first information; wherein the first information comprises the power consumption of the electric automobile and the battery health degree of the power battery.
6. The method according to claim 4, wherein the second information for determining the degree of influence of the driving behavior of the user on the traffic accident of the electric vehicle according to the target predicted driving data comprises:
acquiring current road condition data of the electric automobile;
and inputting the target predicted driving data and the road condition data into a traffic accident correlation analysis model to obtain second information, wherein the second information comprises an accident type and the probability of occurrence of an accident.
7. The method of claim 4, wherein scoring the driving behavior of the user based on the first information and the second information comprises:
and inputting the first information and the second information into a user driving behavior evaluation feedback model to obtain a grading result.
8. The method according to any one of claims 1 to 7, characterized in that the current driving data comprises: at least one of a vehicle speed, an accelerator pedal opening, and a steering wheel angle.
9. A driving behavior warning device, comprising:
the first acquisition module is used for acquiring the current driving data of the electric automobile, and the driving data is related to the driving behavior of a user;
the prediction module is used for predicting the driving behavior of the user according to the current driving data to obtain target predicted driving data of the electric automobile in a future preset time length;
the scoring module is used for scoring the driving behavior of the user according to the target prediction driving data;
and the output module is used for outputting the early warning information under the condition that the grading result is smaller than the preset value.
10. A driving behavior early warning system, comprising: a processor, a memory, and a program or instructions stored on the memory and executable on the processor; characterized in that the processor, when executing the program or instructions, carries out the steps of the driving behavior warning method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210586241.3A CN114999134A (en) | 2022-05-26 | 2022-05-26 | Driving behavior early warning method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210586241.3A CN114999134A (en) | 2022-05-26 | 2022-05-26 | Driving behavior early warning method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114999134A true CN114999134A (en) | 2022-09-02 |
Family
ID=83029825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210586241.3A Pending CN114999134A (en) | 2022-05-26 | 2022-05-26 | Driving behavior early warning method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114999134A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106740864A (en) * | 2017-01-12 | 2017-05-31 | 北京交通大学 | A kind of driving behavior is intended to judge and Forecasting Methodology |
| CN111341106A (en) * | 2020-03-11 | 2020-06-26 | 北京汽车集团有限公司 | Traffic early warning method, device and equipment |
| CN112009486A (en) * | 2019-05-30 | 2020-12-01 | 北京新能源汽车股份有限公司 | Driving control method, system and device and automobile |
| CN113158947A (en) * | 2021-04-29 | 2021-07-23 | 重庆长安新能源汽车科技有限公司 | Power battery health scoring method, system and storage medium |
| WO2021244632A1 (en) * | 2020-06-05 | 2021-12-09 | 北京理工大学 | Electric automobile energy consumption prediction method and system |
-
2022
- 2022-05-26 CN CN202210586241.3A patent/CN114999134A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106740864A (en) * | 2017-01-12 | 2017-05-31 | 北京交通大学 | A kind of driving behavior is intended to judge and Forecasting Methodology |
| CN112009486A (en) * | 2019-05-30 | 2020-12-01 | 北京新能源汽车股份有限公司 | Driving control method, system and device and automobile |
| CN111341106A (en) * | 2020-03-11 | 2020-06-26 | 北京汽车集团有限公司 | Traffic early warning method, device and equipment |
| WO2021244632A1 (en) * | 2020-06-05 | 2021-12-09 | 北京理工大学 | Electric automobile energy consumption prediction method and system |
| CN113158947A (en) * | 2021-04-29 | 2021-07-23 | 重庆长安新能源汽车科技有限公司 | Power battery health scoring method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| CN110615001B (en) | Driving safety reminding method, device and medium based on CAN data | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| CN108319909B (en) | Driving behavior analysis method and system | |
| CN110400478A (en) | A kind of road condition notification method and device | |
| CN108944939B (en) | Method and system for providing driving directions | |
| CN113609016B (en) | Method, device, equipment and medium for constructing automatic driving test scene of vehicle | |
| US20200234578A1 (en) | Prioritized vehicle messaging | |
| CN110858312A (en) | Driver driving style classification method based on fuzzy C-means clustering algorithm | |
| CN115731695A (en) | Scene security level determination method, device, equipment and storage medium | |
| CN116753938A (en) | Vehicle test scene generation method, device, storage medium and equipment | |
| CN115376115B (en) | Reckimic driving behavior marking method, vehicle, cloud server and storage medium | |
| CN116461546A (en) | Vehicle early warning method, device, storage medium and processor | |
| CN114999134A (en) | Driving behavior early warning method, device and system | |
| CN114822044B (en) | Driving safety early warning method and device based on tunnel | |
| CN112990563B (en) | Real-time prediction method for rear-end collision accident risk of expressway | |
| CN114802264A (en) | Vehicle control method and device and electronic equipment | |
| CN113657716B (en) | Comprehensive evaluation method for driving behavior safety of driver based on entropy weight method | |
| CN114638429A (en) | Accident occurrence probability prediction method and device, vehicle and storage medium | |
| Peng et al. | A Method for Vehicle Collision Risk Assessment through Inferring Driver's Braking Actions in Near-Crash Situations | |
| Ali et al. | Employment of instrumented vehicles to identify real-time snowy weather conditions on freeways using supervised machine learning techniques–A naturalistic driving study | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| CN112686127A (en) | GM-HMM-based driver overtaking intention identification method | |
| CN115966100B (en) | Driving safety control method and system | |
| CN116343484B (en) | Traffic accident identification method, terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |