CN109033332A - Driving behavior analysis method, medium and system - Google Patents
Driving behavior analysis method, medium and system Download PDFInfo
- Publication number
- CN109033332A CN109033332A CN201810801891.9A CN201810801891A CN109033332A CN 109033332 A CN109033332 A CN 109033332A CN 201810801891 A CN201810801891 A CN 201810801891A CN 109033332 A CN109033332 A CN 109033332A
- Authority
- CN
- China
- Prior art keywords
- driving behavior
- driver
- cluster result
- feature
- vehicle
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of driving behavior analysis methods, comprising: obtains the travelling data of driver；In conjunction with vehicle travel process, to feature extraction to obtain driving behavior matrix；Screening is to obtain final feature；According to final characteristic measure characteristic similarity, and the company of foundation side, and clustering algorithm is respectively adopted based on even side and carries out driver's group clustering to obtain cluster result；Obtain the high cluster result of accuracy；It is grouped into driving behavior dimension according to the driving behavior that the high cluster result of accuracy drives a vehicle driver every time, and user's portrait is carried out using drive preference of the radar map to driver, to obtain single dimension scoring and various dimensions comprehensive score；The factor for the driving behavior for influencing driver is analyzed according to single dimension scoring and various dimensions comprehensive score；The invention also discloses a kind of medium and system, the Comprehensive Assessment that the driving behavior to each driver carries out various dimensions, the foundation to correct bad steering habit as driver can be realized.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of driving behavior analysis method, medium and system.
Background technique
In urban traffic environment, the bad steering behavior of vehicle driver is (for example, anxious accelerate, bring to a halt and change up
Vehicle), comfort level is taken in the safety and passenger for having seriously affected urban traffic environment.
In actual vehicle ride or vehicle travel process, the excessively single dimension of people's multi-pass intuitively knows driver
The mode of bad steering behavior, for example, intuitively knowing driver's by physical perception during driver brings to a halt
Bad habit, alternatively, intuitively knowing driving by the unexpected acceleration behavior of vehicle and vehicle speed value in vehicle operation
The bad habit of member.These modes are all difficult to comprehensively reflect the driving habit of driver, can not drive to each driver
The Comprehensive Assessment that behavior carries out various dimensions is sailed, to correct the foundation of bad steering habit as driver, to ensure that city is handed over
The safety of logical environment and passenger's takes comfort level.
Summary of the invention
The present invention is directed to solve one of the technical problem in above-mentioned technology at least to a certain extent.For this purpose, of the invention
One purpose is to propose a kind of driving behavior analysis method, can be realized the driving behavior to each driver and carry out various dimensions
Comprehensive Assessment, using as driver correct bad steering habit foundation, thus ensure urban traffic environment safety and
Passenger's takes comfort level.
Second object of the present invention is to propose a kind of computer readable storage medium.
Third object of the present invention is to propose a kind of driving behavior analysis system.
Fourth object of the present invention is to propose a kind of driving behavior analysis system.
In order to achieve the above objectives, first aspect present invention embodiment proposes a kind of driving behavior analysis method, including with
Lower step: the travelling data of driver is obtained；In conjunction with vehicle travel process, feature is carried out to the travelling data of the driver and is mentioned
It takes to obtain driving behavior matrix；The driving behavior matrix is screened to obtain final feature；According to institute
The driving behavior similitude that final characteristic measure driver drives a vehicle every time is stated, and according to the driving behavior similitude
The company of foundation side, and Fast Unfolding clustering algorithm and the progress of K-means clustering algorithm are respectively adopted based on the even side
Driver's group clustering is to obtain the first cluster result and the second cluster result；Obtain first cluster result and the second cluster
As a result the high cluster result of middle accuracy；The driving behavior that driver is driven a vehicle every time according to accuracy high cluster result
It is grouped into driving behavior dimension, and user's picture is carried out from drive preference of the different driving behavior dimensions to driver using radar map
Picture, to obtain driver in the single dimension scoring in each driving behavior dimension and the various dimensions in different driving behavior dimensions
Comprehensive score；The factor for the driving behavior for influencing driver is divided according to single dimension scoring and various dimensions comprehensive score
Analysis.
Driving behavior analysis method according to an embodiment of the present invention, firstly, obtaining the travelling data of driver；And combine vehicle
Driving process carries out feature extraction to the travelling data of driver to obtain driving behavior matrix；Then, it goes to driving
Matrix is characterized to be screened to obtain final feature；And it is special according to the driving behavior that final characteristic measure driver drives a vehicle every time
Similitude is levied, and even side is established according to driving behavior similitude, then, Fast is respectively adopted based on even side
Unfolding clustering algorithm and K-means clustering algorithm carry out driver's group clustering to obtain the first cluster result and second
Cluster result；Then, the cluster result that accuracy is high in the first cluster result and the second cluster result is obtained；And according to accuracy
The driving behavior that high cluster result drives a vehicle driver every time is grouped into driving behavior dimension, and using radar map from
Different driving behavior dimensions carry out user's portrait to the preference of driving of driver, to obtain driver in each driving behavior dimension
On single dimension scoring and the various dimensions comprehensive score in different driving behavior dimensions；Then according to single dimension scoring and multidimensional
Degree comprehensive score analyzes the factor for the driving behavior for influencing driver；To realize that the driving behavior to driver carries out
The Comprehensive Assessment of various dimensions, the foundation to correct bad steering habit as driver, and then ensure the peace of urban traffic environment
It is complete and passenger to take comfort level.
In addition, the driving behavior analysis method proposed according to that above embodiment of the present invention can also have following additional skill
Art feature:
Optionally, the travelling data of the driver is obtained by CAN bus vehicle-mounted instrument, wherein the driving of the driver
Data include based on driver ID, record date and time, the position of vehicle, speed, uplink and downlink, motor and engine speed,
Gear, electric brake information, parking brake information, gas pedal percentage, ignition signal, brake pedal opening information, switch state
Information.
Optionally, the driving behavior matrix is screened to obtain final feature, comprising: be based on the driving
Behavioural characteristic matrix obtains behavioural characteristic probability distribution graph to analyze driving behavior distribution situation, and is gone according to the driving
Being characterized distribution situation and deleting does not have the driving behavior of significant difference to carry out tentatively in the driving behavior matrix
Screening；Using maximal correlation minimal redundancy feature selection approach based on mutual information to the driving behavior after preliminary screening into
Row sequence, and postsearch screening is carried out to the driving behavior after preliminary screening according to ranking results；To driving after postsearch screening
It sails behavioural characteristic and carries out tax power；Feature box-shaped figure is generated according to the weight of each driving behavior after power of assigning, and according to institute
Feature box-shaped figure removal abnormal behavior is stated to obtain the final feature.
Optionally, when carrying out driver's group clustering using Fast Unfolding clustering algorithm, according to modularity algorithm
Point that modularity in network can be improved and corporations are merged, until modularity in network can not improve.
In order to achieve the above objectives, second aspect of the present invention embodiment proposes a kind of computer readable storage medium, thereon
It is stored with driving behavior analysis program, is realized when which is executed by processor such as above-mentioned driving behavior point
Analysis method.
In order to achieve the above objectives, third aspect present invention embodiment proposes a kind of driving behavior analysis system, including deposits
Reservoir, processor and it is stored in the driving behavior analysis program that can be run on the memory and on the processor, it is described
Processor realizes such as above-mentioned driving behavior analysis method when executing the driving behavior analysis program.
In order to achieve the above objectives, fourth aspect present invention embodiment proposes a kind of driving behavior analysis system, and data obtain
Modulus block, for obtaining the travelling data of driver；Characteristic extracting module, for combining vehicle travel process, to the driving
The travelling data of member carries out feature extraction to obtain driving behavior matrix；Feature Selection module, for going to the driving
Matrix is characterized to be screened to obtain final feature；Cluster module, for each according to the final characteristic measure driver
The driving behavior similitude of driving, and even side is established according to the driving behavior similitude, and be based on the company
While Fast Unfolding clustering algorithm and K-means clustering algorithm progress driver's group clustering is respectively adopted to obtain first
Cluster result and the second cluster result, and obtain the cluster knot that accuracy is high in first cluster result and the second cluster result
Fruit；Portrait generation module, the driving behavior for driver to be driven a vehicle every time according to accuracy high cluster result are grouped into
In driving behavior dimension, and user's portrait is carried out from drive preference of the different driving behavior dimensions to driver using radar map,
It is comprehensive in the single dimension scoring in each driving behavior dimension and the various dimensions in different driving behavior dimensions to obtain driver
Close scoring；Driving behavior analysis module, for being scored with various dimensions comprehensive score according to the single dimension to influence driver's
The factor of driving behavior is analyzed.
The driving behavior analysis system proposed according to embodiments of the present invention, firstly, data acquisition module obtains driver's
Travelling data；Then, characteristic extracting module combination vehicle travel process carries out feature extraction to the travelling data of driver to obtain
Obtain driving behavior matrix；Then, Feature Selection module screens driving behavior matrix to obtain final feature；
Then, the driving behavior similitude that cluster module is driven a vehicle every time according to final characteristic measure driver, and go according to driving
It is characterized similitude and establishes even side, and Fast Unfolding clustering algorithm and K-means cluster are respectively adopted based on even side
Algorithm carries out driver's group clustering to obtain the first cluster result and the second cluster result, and obtains the first cluster result and the
The high cluster result of accuracy in two cluster results；Then, portrait generation module will drive according to the high cluster result of accuracy
The driving behavior driven a vehicle every time of member is grouped into driving behavior dimension, and using radar map from different driving behavior dimensions to driving
The preference of driving for the person of sailing carries out user's portrait, is scored and with obtaining single dimension of the driver in each driving behavior dimension not
With the various dimensions comprehensive score in driving behavior dimension；Then, driving behavior analysis module is according to single dimension scoring and various dimensions
Comprehensive score analyzes the factor for the driving behavior for influencing driver；To realize that the driving behavior progress to driver is more
The Comprehensive Assessment of dimension, the foundation to correct bad steering habit as driver, and then ensure the safety of urban traffic environment
And passenger takes comfort level.
In addition, the driving behavior analysis system proposed according to that above embodiment of the present invention can also have following additional skill
Art feature:
Optionally, the data acquisition module obtains the travelling data of the driver by CAN bus vehicle-mounted instrument, wherein
The travelling data of the driver includes based on driver ID, record date and time, the position of vehicle, speed, uplink and downlink, electricity
Machine and engine speed, gear, electric brake information, parking brake information, gas pedal percentage, ignition signal, brake pedal are opened
Spend information, switching-state information.
Optionally, the Feature Selection module includes: preliminary screening unit, for being based on the driving behavior matrix
Behavioural characteristic probability distribution graph is obtained to analyze driving behavior distribution situation, and feelings are distributed according to the driving behavior
Condition, which is deleted, does not have the driving behavior of significant difference to carry out preliminary screening in the driving behavior matrix；Postsearch screening
Unit, for special to the driving behavior after preliminary screening using maximal correlation minimal redundancy feature selection approach based on mutual information
Sign is ranked up, and carries out postsearch screening to the driving behavior after preliminary screening according to ranking results；Power unit is assigned, is used for
Tax power is carried out to the driving behavior after postsearch screening；Abnormal removal unit, for according to each driving behavior after power of assigning
The weight of feature generates feature box-shaped figure, and removes abnormal behavior according to the feature box-shaped figure to obtain the final spy
Sign.
Optionally, it when the cluster module carries out driver's group clustering using Fast Unfolding clustering algorithm, presses
Lighting module degree algorithm merges the point that modularity in network can be improved and corporations, until modularity can not rise in network
Only.
Detailed description of the invention
Fig. 1 is the flow diagram according to the driving behavior analysis method of the embodiment of the present invention；
Fig. 2 is screened to driving behavior matrix to obtain the process of final feature according to another embodiment of the present invention
Schematic diagram；
Fig. 3 is the block diagram according to the driving behavior analysis system of the embodiment of the present invention；
Fig. 4 is the block diagram according to the Feature Selection module of another embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
In actual vehicle ride or vehicle travel process, the excessively single dimension of people's multi-pass intuitively knows driver
The mode of bad steering behavior, these modes are all difficult to comprehensively reflect the driving habit of driver, can not be to each driving
The driving behavior of member carries out the Comprehensive Assessment of various dimensions；A kind of driving behavior analysis method that the embodiment of the present invention proposes, first
The travelling data of driver is obtained, and vehicle travel process is combined to extract feature to generate driving behavior matrix and right
Driving behavior matrix is screened to obtain final feature；Then, it is driven a vehicle every time according to final characteristic measure driver
Driving behavior similitude, and according to similarity join, and cluster is carried out based on clustering algorithm and generates cluster result；So
Afterwards, it is drawn a portrait according to the user that cluster result establishes various dimensions, to obtain driver in the Comprehensive Assessment of various dimensions；To realization pair
The driving behavior of driver carries out the Comprehensive Assessment of various dimensions, the foundation to correct bad steering habit as driver, in turn
The safety and passenger for ensureing urban traffic environment take comfort level.
In order to better understand the above technical scheme, the exemplary reality that the present invention will be described in more detail below with reference to accompanying drawings
Apply example.Although showing exemplary embodiment of the present invention in attached drawing, it being understood, however, that may be realized in various forms this hair
It is bright and should not be limited by the embodiments set forth herein.It is to be able to thoroughly understand this on the contrary, providing these embodiments
Invention, and the scope of the present invention can be fully disclosed to those skilled in the art.
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper
Technical solution is stated to be described in detail.
Fig. 1 is a kind of flow diagram for driving behavior analysis method that the embodiment of the present invention proposes, as shown in Figure 1, should
Driving behavior analysis method the following steps are included:
S101 obtains the travelling data of driver.
Wherein, there are many modes for obtaining the travelling data of driver, for example, passing through the vehicle-mounted end for being installed on vehicle face
End obtains the travelling data of driver；Alternatively, obtaining the travelling data of driver by automobile data recorder；Or pass through driver
Acquisition for mobile terminal driver travelling data.
As an example, the travelling data of driver can be obtained by CAN bus vehicle-mounted instrument.
Wherein, the travelling data of driver include but is not limited to driver ID, record date and time, vehicle position,
Speed, uplink and downlink, motor and engine speed, gear, electric brake information, parking brake information, gas pedal percentage, igniting letter
Number, brake pedal opening information, switching-state information.
It should be noted that after the travelling data for obtaining driver by CAN bus vehicle-mounted instrument, it can be to acquisition
To the travelling data of driver arrange, and generate literary with the corresponding CSV document of driver and CSV corresponding with vehicle
Shelves, in order to which the subsequent driving behavior to driver extracts.
S102 carries out feature extraction to the travelling data of driver to obtain driving behavior spy in conjunction with vehicle travel process
Levy matrix.
That is, in conjunction with vehicle specific driving process (for example, during bus routes uplink, starting point to the end
The specific driving process of vehicle；Alternatively, specific driving process etc. of the taxi in fixed route), to the travelling data of driver
Feature extraction is carried out, to obtain driving behavior matrix.
It should be noted that can also include the pre- place to the feature of extraction before generating driving behavior matrix
Reason；Specifically, can the data of data and logic error to missing carry out nearest polishing using hot deck algorithm；Wherein,
The data of logic error can be checked by logic error detection first, and the data of logic error refer to recording due to equipment
Logical data are not obviously inconsistent caused by mistake or other reasons；For example, mistake occurs since longitude and latitude records, cause
Urban congestion section " running speed reaches 150km/h "；Alternatively, " motor speed reaches 16000r/min " etc.；Then, work as logic
It when finding the data of logic error in error detection procedure, is replaced using data of the null value to logic error, and uses hot
Deck algorithm carries out nearest polishing, to complete the pretreatment to the feature of extraction；So that raw by pretreated feature
At eigenmatrix more precisely and have more the property of can refer to.
S103 screens driving behavior matrix to obtain final feature.
That is, being screened after obtaining driving behavior matrix to the feature in eigenmatrix, to obtain
Final feature for clustering.
S104 goes according to the driving behavior similitude that final characteristic measure driver drives a vehicle every time, and according to driving
It is characterized similitude and establishes even side, and Fast Unfolding clustering algorithm and K-means cluster are respectively adopted based on even side
Algorithm carries out driver's group clustering to obtain the first cluster result and the second cluster result.
Wherein, it is referred to according to the driving behavior similitude that final characteristic measure driver drives a vehicle every time according to most
The close degree between driving behavior that whole characteristic synthetic evaluation is driven a vehicle every time；The mode of measurement can there are many, for example,
Measure the matching factor between the driving behavior driven a vehicle every time；Or it measures between the driving behavior driven a vehicle every time
Consistent degree etc..
As an example, even side is established according to driving behavior similitude, and Fast is used based on even side
When Unfolding clustering algorithm carries out driver's group clustering, modularity in network can be improved according to modularity algorithm point
It is merged with corporations, until the modularity in network can not improve.
That is, first using each driving behavior as an independent corporations, then by neighbouring corporations into
Row merges, and judges whether the modularity of the network of all corporations composition improves after consolidation, if it is judged that be it is yes, then
Merge corporations；If it is judged that be it is no, then cancel the merging of corporations；In this way, being iterated merging, Zhi Daosuo to each corporations
Until the modularity for the network being made of corporations no longer improves.
It should be noted that the network that finally formed modularity can not improve is that Fast Unfolding is used to cluster
First cluster result of algorithm progress driver's group clustering acquisition.
Wherein, K-means clustering algorithm is a kind of typically based on the clustering algorithm of distance, is used as similitude using distance
Evaluation index, that is, think that the distance of two objects is closer, similarity is bigger.
S105 obtains the cluster result that accuracy is high in the first cluster result and the second cluster result.
That is, after getting the first cluster result and the second cluster result, by the first cluster result and second
Accuracy in cluster result compares, and chooses the high cluster result of accuracy.
Wherein, there are many modes for judging cluster result accuracy, for example, being tied according to multiple driving behaviors and cluster
Fruit judges the classification of each driving behavior, and judges whether classification is accurate according to classification results, to judge the standard of cluster result
True property.
As an example, using the driving behavior driven a vehicle every time as object of classification, it is identical to extract same driver
The multiple driving behavior of stroke driving, and according to the default average classification accuracy index of multiple driving behavior, and
The classification of each driving behavior is judged according to each driving behavior and cluster result；Then, judgement drives row every time
Whether the classification being characterized and default average classification accuracy index are consistent, if judging result is consistent, it is determined that the classification results
Accurately；Then, the accuracy of cluster result is determined according to the classification results of each driving behavior.
S106 is grouped into driving behavior according to the driving behavior that the high cluster result of accuracy drives a vehicle driver every time
In dimension, and user's portrait is carried out from drive preference of the different driving behavior dimensions to driver using radar map, to be driven
The person of sailing is in the single dimension scoring in each driving behavior dimension and the various dimensions comprehensive score in different driving behavior dimensions.
As an example, the corresponding driving behavior dimension of each classification in cluster result is set, and according to each driving
Behavior dimension is preset the corresponding score value of each driving behavior in driving behavior dimension and is then driven what driver drove a vehicle every time
It sails behavioural characteristic to be grouped into driving behavior dimension, and line is carried out to the driving behavior in each dimension using radar map, with
Form corresponding this time of driver driving user's portrait；To obtain one-dimensional of this time of the driver driving in each driving behavior dimension
Degree scoring and the various dimensions comprehensive score in different driving behavior dimensions.
S107 divides the factor for the driving behavior for influencing driver according to single dimension scoring and various dimensions comprehensive score
Analysis.
That is, according to each dimension that single dimension is gentle and various dimensions comprehensive score is to the driving behavior for influencing driver
It is analyzed, to determine the factor for the driving behavior for influencing driver.
As an example, it when the oil consumption that driver drives vehicle is higher, using oil consumption variable as dependent variable, will respectively drive
The scoring of behavioural characteristic single dimension is sailed as independent variable, building multiple linear model of coming back home is analyzed by checking fitting regression effect
The single dimension scoring of which driving behavior can significantly affect fuel consumption values, to determine that influencing driver drives vehicle generation oil
Consume higher factor.
As shown in Fig. 2, in some embodiments, in the driving behavior analysis method of the embodiment of the present invention, to driving behavior
Eigenmatrix is screened can comprise the following steps that with obtaining final feature specifically
S201 obtains behavioural characteristic probability distribution graph based on driving behavior matrix to analyze driving behavior distribution situation
And according to driving behavior distribution situation delete driving behavior matrix in do not have the driving behavior of significant difference with
Carry out preliminary screening.
That is, generating behavioural characteristic probability distribution graph according to driving behavior matrix, and general according to behavioural characteristic
Rate distribution map carries out the analysis of driving behavior distribution situation, and each driving is gone according to driving behavior distribution situation
There is no significant difference delete in being characterized, to complete the preliminary screening to driving behavior.
S202, using maximal correlation minimal redundancy feature selection approach based on mutual information to the driving row after preliminary screening
It is characterized and is ranked up, and postsearch screening is carried out to the driving behavior after preliminary screening according to ranking results.
Wherein, mutual information refers to the information content about another stochastic variable for including in a stochastic variable, or
Say be a stochastic variable due to another known stochastic variable reduced uncertainty.
As an example, it deletes in driving behavior matrix according to driving behavior distribution situation without obvious
After the driving behavior of difference is to complete preliminary screening, reduced by each driving behavior after estimation preliminary screening
Probabilistic ability of other driving behaviors in addition to itself once selects a driving behavior, using base
Feature is ranked up in the maximal correlation minimal redundancy of mutual information, and according to ranking results to the driving behavior after preliminary screening
Feature carries out postsearch screening.
Wherein, there are many modes of postsearch screening, for example, choosing sequencing numbers default according to the sequencing of sequence
Driving behavior before value.
As an example, the threshold value of Average Mutual default first is then deleted mutual information and is unexpectedly driven in threshold value
Behavioural characteristic, to complete postsearch screening.
S203 carries out tax power to the driving behavior after postsearch screening.
That is, tax power is carried out to the driving behavior after postsearch screening, to determine respectively driving after postsearch screening
Sail the weight of behavioural characteristic.
S204 generates feature box-shaped figure according to the weight of each driving behavior after power of assigning, and according to feature box-shaped
Figure removal abnormal behavior is to obtain final feature.
Wherein, box-shaped figure is a kind of statistical chart as real one group of data dispersion.
As an example, according to the sequence of each driving behavior after power of assigning, minimum value, the first quartile are carried out
The determination of number, median, third quartile and maximum value, and according to the difference of first quartile and third quartile
Limit value and outer limit value in determining, and abnormal behavior is determined according to interior limit value and outer limit value；Then, according to feature box-shaped figure
Abnormal behavior is removed to obtain final feature.
In conclusion driving behavior analysis method according to an embodiment of the present invention, is primarily based on driving behavior matrix
Behavioural characteristic probability distribution graph is obtained to analyze driving behavior distribution situation and delete according to driving behavior distribution situation
Except there is no the driving behavior of significant difference to carry out preliminary screening in driving behavior matrix, then, using based on mutual
The maximal correlation minimal redundancy feature selection approach of information is ranked up the driving behavior after preliminary screening, and according to row
Sequence result carries out postsearch screening to the driving behavior after preliminary screening, then, to the driving behavior after postsearch screening
Carry out tax power；Then, feature box-shaped figure is generated according to the weight of each driving behavior after power of assigning, and according to feature box-shaped
Figure removal abnormal behavior is to obtain final feature；To enhance the accuracy of final feature and the property of can refer to, after being conducive to
The generation of the continuous cluster result formed according to final feature.
In order to realize above-described embodiment, the embodiment of the present invention proposes a kind of computer readable storage medium, stores thereon
There is driving behavior analysis program, such as above-mentioned driving behavior analysis side is realized when which is executed by processor
Method.
In order to realize above-described embodiment, the embodiment of the present invention proposes a kind of driving behavior analysis system, including memory,
Processor and it is stored in the driving behavior analysis program that can be run on the memory and on the processor, the processor
Such as above-mentioned driving behavior analysis method is realized when executing driving behavior analysis program.
As shown in figure 3, the embodiment of the present invention proposes a kind of driving behavior analysis system, comprising: data acquisition module 10,
Characteristic extracting module 20, Feature Selection module 30, cluster module 40, portrait generation module 50, driving behavior analysis module 60.
Wherein, data acquisition module 10, for obtaining the travelling data of driver.
Characteristic extracting module 20, for combining vehicle travel process, to the travelling data of driver carry out feature extraction with
Obtain driving behavior matrix.
Feature Selection module 30, for being screened to driving behavior matrix to obtain final feature.
Cluster module 40, the driving behavior similitude for being driven a vehicle every time according to final characteristic measure driver, and
Even side is established according to driving behavior similitude, and Fast Unfolding clustering algorithm and K- are respectively adopted based on even side
Means clustering algorithm carries out driver's group clustering to obtain the first cluster result and the second cluster result, and it is poly- to obtain first
The high cluster result of accuracy in class result and the second cluster result.
Portrait generation module 50, the driving behavior for driver to be driven a vehicle every time according to accuracy high cluster result are special
Sign is grouped into driving behavior dimension, and carries out user from drive preference of the different driving behavior dimensions to driver using radar map
Portrait, to obtain driver in the single dimension scoring in each driving behavior dimension and the multidimensional in different driving behavior dimensions
Spend comprehensive score.
Driving behavior analysis module 60, for being driven according to single dimension scoring and various dimensions comprehensive score to driver is influenced
The factor for sailing behavior is analyzed.
To sum up, the driving behavior analysis system proposed according to embodiments of the present invention drives firstly, data acquisition module obtains
The travelling data of member；Then, characteristic extracting module combination vehicle travel process carries out feature extraction to the travelling data of driver
To obtain driving behavior matrix；Then, Feature Selection module screens driving behavior matrix final to obtain
Feature；Then, the driving behavior similitude that cluster module is driven a vehicle every time according to final characteristic measure driver, and according to driving
It sails behavioural characteristic similitude and establishes even side, and Fast Unfolding clustering algorithm and K-means are respectively adopted based on even side
Clustering algorithm carries out driver's group clustering to obtain the first cluster result and the second cluster result, and obtains the first cluster result
The high cluster result with accuracy in the second cluster result；Then, portrait generation module will according to the high cluster result of accuracy
The driving behavior that driver drives a vehicle every time is grouped into driving behavior dimension, and uses radar map from different driving behavior dimensions
To driver drive preference carry out user's portrait, with obtain driver in each driving behavior dimension single dimension scoring and
Various dimensions comprehensive score in different driving behavior dimensions；Then, driving behavior analysis module according to single dimension scoring and it is more
Dimension comprehensive score analyzes the factor for the driving behavior for influencing driver；To realize to the driving behavior of driver into
The Comprehensive Assessment of row various dimensions, the foundation to correct bad steering habit as driver, and then ensure urban traffic environment
Safety and passenger's takes comfort level.
In some embodiments, in the driving behavior analysis system that the embodiment of the present invention proposes, data acquisition module 10 is logical
Cross CAN bus vehicle-mounted instrument obtain driver travelling data, wherein the travelling data of driver include based on driver ID,
Record date and time, the position of vehicle, speed, uplink and downlink, motor and engine speed, gear, electric brake information, parking brake
Information, gas pedal percentage, ignition signal, brake pedal opening information, switching-state information.
As shown in figure 4, in some embodiments, in the driving behavior analysis system that the embodiment of the present invention proposes, feature sieve
Modeling block 30 includes:
Preliminary screening unit 70 drives row for obtaining behavioural characteristic probability distribution graph based on driving behavior matrix to analyze
It is characterized distribution situation, and does not have significant difference according in driving behavior distribution situation deletion driving behavior matrix
Driving behavior is to carry out preliminary screening；
Postsearch screening unit 80, for using maximal correlation minimal redundancy feature selection approach based on mutual information to preliminary screening
Driving behavior afterwards is ranked up, and carries out secondary sieve to the driving behavior after preliminary screening according to ranking results
Choosing；
Power unit 90 is assigned, for carrying out tax power to the driving behavior after postsearch screening；
Abnormal removal unit 100, for generating feature box-shaped figure, and root according to the weight of each driving behavior after power of assigning
According to feature box-shaped figure removal abnormal behavior to obtain final feature.
In some embodiments, in the driving behavior analysis system that the embodiment of the present invention proposes, cluster module 40 is used
When Fast Unfolding clustering algorithm carries out driver's group clustering, modularity in network can be improved according to modularity algorithm
Point and corporations merge, until modularity in network can not improve.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should be noted that in the claims, any reference symbol between parentheses should not be configured to power
The limitation that benefit requires.Word "comprising" does not exclude the presence of component or step not listed in the claims.Before component
Word "a" or "an" does not exclude the presence of multiple such components.The present invention can be by means of including several different components
It hardware and is realized by means of properly programmed computer.In the unit claims listing several devices, these are filled
Several in setting, which can be, to be embodied by the same item of hardware.The use of word first, second, and third is not
Indicate any sequence.These words can be construed to title.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
In the description of the present invention, it is to be understood that, term " first ", " second " are used for description purposes only, and cannot
It is interpreted as indication or suggestion relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include one or more of the features.In the description of the present invention,
The meaning of " plurality " is two or more, unless otherwise specifically defined.
In the present invention unless specifically defined or limited otherwise, term " installation ", " connected ", " connection ", " fixation " etc.
Term shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral；It can be mechanical connect
It connects, is also possible to be electrically connected；It can be directly connected, can also can be in two elements indirectly connected through an intermediary
The interaction relationship of the connection in portion or two elements.It for the ordinary skill in the art, can be according to specific feelings
Condition understands the concrete meaning of above-mentioned term in the present invention.
In the present invention unless specifically defined or limited otherwise, fisrt feature in the second feature " on " or " down " can be with
It is that the first and second features directly contact or the first and second features pass through intermediary mediate contact.Moreover, fisrt feature exists
Second feature " on ", " top " and " above " but fisrt feature be directly above or diagonally above the second feature, or be merely representative of
First feature horizontal height is higher than second feature.Fisrt feature can be under the second feature " below ", " below " and " below "
One feature is directly under or diagonally below the second feature, or is merely representative of first feature horizontal height less than second feature.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It is interpreted as that identical embodiment or example must be directed to.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of driving behavior analysis method, which comprises the following steps:
Obtain the travelling data of driver；
In conjunction with vehicle travel process, feature extraction is carried out to obtain driving behavior square to the travelling data of the driver
Battle array；
The driving behavior matrix is screened to obtain final feature；
According to the driving behavior similitude that the final characteristic measure driver drives a vehicle every time, and according to the driving behavior
Characteristic similarity establishes even side, and based on the even side Fast Unfolding clustering algorithm and K-means to be respectively adopted poly-
Class algorithm carries out driver's group clustering to obtain the first cluster result and the second cluster result；
Obtain the cluster result that accuracy is high in first cluster result and the second cluster result；
It is grouped into driving behavior dimension according to the driving behavior that the high cluster result of accuracy drives a vehicle driver every time, and
User's portrait is carried out from drive preference of the different driving behavior dimensions to driver using radar map, to obtain driver each
Single dimension scoring in driving behavior dimension and the various dimensions comprehensive score in different driving behavior dimensions；
The factor for the driving behavior for influencing driver is analyzed according to single dimension scoring and various dimensions comprehensive score.
2. driving behavior analysis method as described in claim 1, which is characterized in that obtain institute by CAN bus vehicle-mounted instrument
State the travelling data of driver, wherein the travelling data of the driver include based on driver ID, record date and time,
Position, speed, uplink and downlink, motor and engine speed, gear, electric brake information, parking brake information, the gas pedal hundred of vehicle
Divide ratio, ignition signal, brake pedal opening information, switching-state information.
3. driving behavior analysis method as described in claim 1, which is characterized in that carried out to the driving behavior matrix
Screening is to obtain final feature, comprising:
Based on driving behavior matrix acquisition behavioural characteristic probability distribution graph to analyze driving behavior distribution situation,
And it is deleted according to the driving behavior distribution situation and there is no the driving row of significant difference in the driving behavior matrix
It is characterized to carry out preliminary screening；
Using maximal correlation minimal redundancy feature selection approach based on mutual information to the driving behavior after preliminary screening into
Row sequence, and postsearch screening is carried out to the driving behavior after preliminary screening according to ranking results；
Tax power is carried out to the driving behavior after postsearch screening；
Feature box-shaped figure is generated according to the weight of each driving behavior after power of assigning, and is removed according to the feature box-shaped figure
Abnormal behavior is to obtain the final feature.
4. driving behavior analysis method as claimed in any one of claims 1-3, which is characterized in that use Fast
When Unfolding clustering algorithm carries out driver's group clustering, modularity in network can be improved according to modularity algorithm point
It is merged with corporations, until modularity in network can not improve.
5. a kind of computer readable storage medium, which is characterized in that be stored thereon with driving behavior analysis program, the driving behavior
Analysis program realizes such as driving behavior analysis method of any of claims 1-4 when being executed by processor.
6. a kind of driving behavior analysis system, which is characterized in that including memory, processor and be stored on the memory simultaneously
The driving behavior analysis program that can be run on the processor, the processor execute real when the driving behavior analysis program
Now such as driving behavior analysis method of any of claims 1-4.
7. a kind of driving behavior analysis system characterized by comprising
Data acquisition module, for obtaining the travelling data of driver；
Characteristic extracting module carries out feature extraction to the travelling data of the driver for combining vehicle travel process to obtain
Obtain driving behavior matrix；
Feature Selection module, for being screened the driving behavior matrix to obtain final feature；
Cluster module, the driving behavior similitude for being driven a vehicle every time according to the final characteristic measure driver, and root
Even side is established according to the driving behavior similitude, and Fast Unfolding cluster is respectively adopted based on the even side and is calculated
Method and K-means clustering algorithm carry out driver's group clustering to obtain the first cluster result and the second cluster result, and obtain
The high cluster result of accuracy in first cluster result and the second cluster result；
Portrait generation module, the driving behavior for driver to be driven a vehicle every time according to accuracy high cluster result are grouped into
In driving behavior dimension, and user's portrait is carried out from drive preference of the different driving behavior dimensions to driver using radar map,
It is comprehensive in the single dimension scoring in each driving behavior dimension and the various dimensions in different driving behavior dimensions to obtain driver
Close scoring；
Driving behavior analysis module, for the driving according to single dimension scoring and various dimensions comprehensive score to driver is influenced
The factor of behavior is analyzed.
8. driving behavior analysis system as claimed in claim 7, which is characterized in that the data acquisition module is total by CAN
Line vehicle-mounted instrument obtains the travelling data of the driver, wherein the travelling data of the driver include based on driver ID,
Record date and time, the position of vehicle, speed, uplink and downlink, motor and engine speed, gear, electric brake information, parking brake
Information, gas pedal percentage, ignition signal, brake pedal opening information, switching-state information.
9. driving behavior analysis system as claimed in claim 7, which is characterized in that the Feature Selection module includes:
Preliminary screening unit is driven for obtaining behavioural characteristic probability distribution graph based on the driving behavior matrix with analyzing
Behavioural characteristic distribution situation, and do not have according in the driving behavior distribution situation deletion driving behavior matrix
The driving behavior of significant difference is to carry out preliminary screening；
Postsearch screening unit, after being used for use maximal correlation minimal redundancy feature selection approach based on mutual information to preliminary screening
Driving behavior be ranked up, and according to ranking results to after preliminary screening driving behavior carry out postsearch screening；
Power unit is assigned, for carrying out tax power to the driving behavior after postsearch screening；
Abnormal removal unit, for the weight generation feature box-shaped figure according to each driving behavior after power of assigning, and according to
The feature box-shaped figure removal abnormal behavior is to obtain the final feature.
10. driving behavior analysis system as claimed in any one of claims 7-9, which is characterized in that the cluster module is adopted
When carrying out driver's group clustering with Fast Unfolding clustering algorithm, modularity in network can be mentioned according to modularity algorithm
High point and corporations merge, until modularity in network can not improve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810801891.9A CN109033332B (en) | 2018-07-20 | 2018-07-20 | Driving behavior analysis method, medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810801891.9A CN109033332B (en) | 2018-07-20 | 2018-07-20 | Driving behavior analysis method, medium and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109033332A true CN109033332A (en) | 2018-12-18 |
| CN109033332B CN109033332B (en) | 2020-12-25 |
Family
ID=64643761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810801891.9A Active CN109033332B (en) | 2018-07-20 | 2018-07-20 | Driving behavior analysis method, medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109033332B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109552338A (en) * | 2018-12-19 | 2019-04-02 | 北京理工新源信息科技有限公司 | A kind of pure electric automobile ecology driving behavior appraisal procedure and system |
| CN110097287A (en) * | 2019-05-07 | 2019-08-06 | 宏图物流股份有限公司 | A kind of group's portrait method of logistics driver |
| CN110533094A (en) * | 2019-08-26 | 2019-12-03 | 汉纳森（厦门）数据股份有限公司 | A kind of evaluation method and system for driver |
| CN111460076A (en) * | 2020-04-20 | 2020-07-28 | 广州亚美信息科技有限公司 | Driving route familiarity determination method, device, computer equipment and storage medium |
| CN112200235A (en) * | 2020-09-30 | 2021-01-08 | 蜂巢能源科技有限公司 | Method, device, medium and equipment for classifying driving behavior habits of electric vehicle |
| CN112257953A (en) * | 2020-11-03 | 2021-01-22 | 上海电力大学 | Data processing method based on polar region new energy power generation power prediction |
| CN113033651A (en) * | 2021-03-22 | 2021-06-25 | 上海仙塔智能科技有限公司 | Method and device for improving driving safety |
| CN113129473A (en) * | 2020-01-15 | 2021-07-16 | 北京京东振世信息技术有限公司 | Data acquisition method, device and system |
| CN113379945A (en) * | 2021-07-26 | 2021-09-10 | 陕西天行健车联网信息技术有限公司 | Vehicle driving behavior analysis device, method and system |
| CN113505955A (en) * | 2021-05-19 | 2021-10-15 | 辛巴网络科技(南京)有限公司 | User driving behavior scoring method based on TSP system |
| CN114842571A (en) * | 2021-02-02 | 2022-08-02 | 深圳市易流科技股份有限公司 | Method and device for determining driving behavior data |
| CN115641160A (en) * | 2022-12-26 | 2023-01-24 | 中国汽车技术研究中心有限公司 | Method, device and storage medium for improving new energy automobile |
| CN116653980A (en) * | 2023-06-28 | 2023-08-29 | 运脉云技术有限公司 | Driver driving habit analysis system and driving habit analysis method |
| CN116821805A (en) * | 2023-06-28 | 2023-09-29 | 运脉云技术有限公司 | Vehicle service platform system for monitoring driving behavior and driving behavior monitoring method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930771A (en) * | 2016-04-13 | 2016-09-07 | 乐视控股（北京）有限公司 | Driving behavior grading method and device |
| US20170255966A1 (en) * | 2014-03-28 | 2017-09-07 | Joseph Khoury | Methods and systems for collecting driving information and classifying drivers and self-driving systems |
| CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
| CN107585164A (en) * | 2017-09-04 | 2018-01-16 | 交通运输部公路科学研究所 | A kind of method and device for the driver that classifies |
-
2018
- 2018-07-20 CN CN201810801891.9A patent/CN109033332B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170255966A1 (en) * | 2014-03-28 | 2017-09-07 | Joseph Khoury | Methods and systems for collecting driving information and classifying drivers and self-driving systems |
| CN105930771A (en) * | 2016-04-13 | 2016-09-07 | 乐视控股（北京）有限公司 | Driving behavior grading method and device |
| CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
| CN107585164A (en) * | 2017-09-04 | 2018-01-16 | 交通运输部公路科学研究所 | A kind of method and device for the driver that classifies |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109552338B (en) * | 2018-12-19 | 2020-04-07 | 北京理工新源信息科技有限公司 | Evaluation method and system for ecological driving behavior of pure electric vehicle |
| CN109552338A (en) * | 2018-12-19 | 2019-04-02 | 北京理工新源信息科技有限公司 | A kind of pure electric automobile ecology driving behavior appraisal procedure and system |
| CN110097287B (en) * | 2019-05-07 | 2021-06-22 | 宏图物流股份有限公司 | Group portrait method for logistic drivers |
| CN110097287A (en) * | 2019-05-07 | 2019-08-06 | 宏图物流股份有限公司 | A kind of group's portrait method of logistics driver |
| CN110533094A (en) * | 2019-08-26 | 2019-12-03 | 汉纳森（厦门）数据股份有限公司 | A kind of evaluation method and system for driver |
| CN113129473A (en) * | 2020-01-15 | 2021-07-16 | 北京京东振世信息技术有限公司 | Data acquisition method, device and system |
| CN111460076A (en) * | 2020-04-20 | 2020-07-28 | 广州亚美信息科技有限公司 | Driving route familiarity determination method, device, computer equipment and storage medium |
| CN111460076B (en) * | 2020-04-20 | 2023-05-26 | 亚美智联数据科技有限公司 | Driving route familiarity determination method, driving route familiarity determination device, computer device, and storage medium |
| CN112200235A (en) * | 2020-09-30 | 2021-01-08 | 蜂巢能源科技有限公司 | Method, device, medium and equipment for classifying driving behavior habits of electric vehicle |
| CN112200235B (en) * | 2020-09-30 | 2022-05-27 | 蜂巢能源科技有限公司 | Method, device, medium and equipment for classifying driving behavior habits of electric vehicle |
| CN112257953A (en) * | 2020-11-03 | 2021-01-22 | 上海电力大学 | Data processing method based on polar region new energy power generation power prediction |
| CN112257953B (en) * | 2020-11-03 | 2021-09-24 | 上海电力大学 | Data processing method based on polar region new energy power generation power prediction |
| CN114842571A (en) * | 2021-02-02 | 2022-08-02 | 深圳市易流科技股份有限公司 | Method and device for determining driving behavior data |
| CN113033651A (en) * | 2021-03-22 | 2021-06-25 | 上海仙塔智能科技有限公司 | Method and device for improving driving safety |
| CN113505955A (en) * | 2021-05-19 | 2021-10-15 | 辛巴网络科技(南京)有限公司 | User driving behavior scoring method based on TSP system |
| CN113379945A (en) * | 2021-07-26 | 2021-09-10 | 陕西天行健车联网信息技术有限公司 | Vehicle driving behavior analysis device, method and system |
| CN115641160A (en) * | 2022-12-26 | 2023-01-24 | 中国汽车技术研究中心有限公司 | Method, device and storage medium for improving new energy automobile |
| CN116653980A (en) * | 2023-06-28 | 2023-08-29 | 运脉云技术有限公司 | Driver driving habit analysis system and driving habit analysis method |
| CN116821805A (en) * | 2023-06-28 | 2023-09-29 | 运脉云技术有限公司 | Vehicle service platform system for monitoring driving behavior and driving behavior monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109033332B (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033332A (en) | Driving behavior analysis method, medium and system | |
| CN109117869A (en) | User's portrait method, medium and system | |
| CN103562978B (en) | Vehicle data analysis method and vehicle data analysis system | |
| CN106536315B (en) | System for evaluating and/or optimizing the operating characteristics of a vehicle | |
| CN109017797B (en) | Driver emotion recognition method and vehicle-mounted control unit implementing same | |
| Abas et al. | Development of Malaysian urban drive cycle using vehicle and engine parameters | |
| CN111539087B (en) | Automatic driving system simulation test platform and automatic driving system evaluation method | |
| CN109635852B (en) | User portrait construction and clustering method based on multi-dimensional attributes | |
| CN111688713B (en) | Driving behavior analysis method and device | |
| CN105930771A (en) | Driving behavior grading method and device | |
| CN111242015A (en) | Method for predicting driving danger scene based on motion contour semantic graph | |
| US11619946B2 (en) | Method and apparatus for generating U-turn path in deep learning-based autonomous vehicle | |
| CN110274768A (en) | Method for executing the experiment process of test specimen | |
| CN108375378A (en) | Air navigation aid is extended in backroad | |
| CN106557663A (en) | Driving behavior methods of marking and device | |
| CN115422747A (en) | Method and device for calculating discharge amount of pollutants in tail gas of motor vehicle | |
| Mafi et al. | Developing local driving cycle for accurate vehicular CO2 monitoring: A case study of Tehran | |
| Niroomand et al. | Segment-Based CO₂ Emission Evaluations From Passenger Cars Based on Deep Learning Techniques | |
| d'Agostino et al. | Learning-based driving events classification | |
| Yardy et al. | Detecting malicious driving with machine learning | |
| CN115027497A (en) | Target vehicle cut-in intention prediction method and readable storage medium | |
| CN115520216A (en) | Driving state judging method and device, computer equipment and storage medium | |
| CN114862159A (en) | Evaluation method for automatic driving test scene | |
| CN116997890A (en) | Generating an unknown unsafe scenario, improving an automated vehicle, and a computer system | |
| CN114003582A (en) | Traffic accident foreground derivation method for automatic driving vehicle 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 | ||
| CB02 | Change of applicant information |
Address after: 361000 Innovation Building, Software Park, Xiamen Torch High-tech Zone, Xiamen City, Fujian Province Applicant after: Hanathan (Xiamen) data Limited by Share Ltd Applicant after: Shenzhen Pengcheng Electric Vehicle Rental Co., Ltd. Address before: 361000 5th Floor, 28 Guanri Road, Phase II Software Park, Siming District, Xiamen City, Fujian Province Applicant before: Hanathan (Xiamen) data Limited by Share Ltd Applicant before: Shenzhen Pengcheng Electric Vehicle Rental Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |