CN113157817A - Method and device for distinguishing drivers and computer equipment - Google Patents
Method and device for distinguishing drivers and computer equipment Download PDFInfo
- Publication number
- CN113157817A CN113157817A CN202110276146.9A CN202110276146A CN113157817A CN 113157817 A CN113157817 A CN 113157817A CN 202110276146 A CN202110276146 A CN 202110276146A CN 113157817 A CN113157817 A CN 113157817A
- Authority
- CN
- China
- Prior art keywords
- data
- track
- map
- driving
- historical
- 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 44
- 238000003491 array Methods 0.000 claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims abstract description 30
- 239000013598 vector Substances 0.000 claims description 58
- 230000006870 function Effects 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The application relates to the field of artificial intelligence, and discloses a method for distinguishing drivers, which comprises the following steps: acquiring historical driving track data corresponding to a specified vehicle; matching historical driving track data into a map grid to form a track map; forming characteristic data arrays corresponding to the historical driving track data according to the track map; inputting each feature data array into a twin neural network model, and calculating classification weights between the feature data arrays pairwise; and distinguishing corresponding appointed running tracks of the historical running track data when the same driver drives according to the classification weight and a preset threshold value. The historical driving track data and the map grids are overlapped to form a track map, the characteristic data arrays are calculated and labeled with the historical driving track data, the similarity between the characteristic data arrays of the historical driving track data is calculated according to the twin neural network model, the driving behaviors of different drivers are distinguished, and the distinguishing and the classification of the drivers are realized.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method, an apparatus, and a computer device for distinguishing drivers.
Background
The insurance premium of the designated driver is different from that of the non-designated driver, and the insurance claim settlement cost is also different. The driver's familiarity degree with the vehicle directly influences the driving behavior, the insurance premium is far lower than other temporary drivers in the probability of leaving risk of the designated driver, and the premium is much discounted. However, in the car insurance, after the car is lent to other people for driving insurance by the insurance applicant, the phenomenon that the insurance applicant pretends to be the own driving insurance and forms insurance fraud claims is easy to occur, and how to effectively judge whether the car insurance is the insurance applicant in the insurance becomes a difficult problem for checking the insurance company.
Disclosure of Invention
The main purpose of the present application is to provide a method for distinguishing drivers, aiming to solve the technical problem that the drivers cannot be distinguished according to the characteristics of the driving track.
The application provides a method for distinguishing drivers, which comprises the following steps:
acquiring historical driving track data corresponding to a specified vehicle;
matching the historical driving track data into a map grid to form a track map;
forming a characteristic data array corresponding to each historical driving track data according to the track map;
inputting each feature data array into a twin neural network model, and calculating classification weights between feature data arrays pairwise;
and distinguishing corresponding appointed running tracks of the historical running track data when the same driver drives according to the classification weight and a preset threshold value.
Preferably, the step of matching the historical travel track data into a map grid to form a track map includes:
dividing a map into map grids according to a preset dividing mode;
acquiring longitude and latitude information corresponding to each track point in appointed historical driving track data, wherein the appointed historical driving track data belongs to any one of all historical driving track data;
superposing the specified historical driving track data to the map grid according to the longitude and latitude information;
and according to the mode that the appointed historical driving track data are superposed into the map grid, superposing all the historical driving track data into the map grid in a one-to-one correspondence mode to form the track map.
Preferably, the feature data array includes trajectory feature data, and the step of forming a feature data array corresponding to each of the historical travel trajectory data according to the trajectory map includes:
acquiring map grid sections occupied by the appointed historical driving track data and speed limit labels respectively corresponding to the map grid sections;
according to the speed limit labels respectively corresponding to each map grid region, calculating the track characteristic data corresponding to the appointed historical driving track data, wherein the track characteristic data comprises a slow driving region ratio and an overspeed driving region ratio;
and according to the statistical mode of the track characteristic data corresponding to the appointed historical driving track data, counting the track characteristic data respectively corresponding to all the historical driving track data.
Preferably, the feature data array includes driver driving feature data, and the step of forming a feature data array corresponding to each of the historical driving trajectory data according to the trajectory map includes:
acquiring time data respectively corresponding to each track point corresponding to the specified historical driving track data;
calculating driver driving characteristic data corresponding to the appointed historical driving track data according to the time data, wherein the driver driving characteristic data comprise preset time interval driving data, driving smoothness and fatigue driving data;
and calculating the driving characteristic data of the driver corresponding to all the historical driving track data according to the calculation mode of the driving characteristic data of the driver corresponding to the specified historical driving track data.
Preferably, the step of inputting each feature data array into the twin neural network model and calculating the classification weight between the feature data arrays pairwise is preceded by:
inputting training samples into a twin neural network model, and mapping to a high-dimensional space through a specified function to obtain a space vector corresponding to each training sample, wherein the specified function is Gw (X), w represents a parameter, and X represents a training sample;
calculating a first space vector distance corresponding to a first sample and a second sample with the same class label and a second space vector distance corresponding to a third sample and a fourth sample with different class labels according to a first calculation formula, wherein the first calculation formula is Ew (X)1,X2)＝||Gw(X1)-Gw(X2)||，X1,X2Represents a training sample, Ew (X)1,X2) Representing a space vector distance;
adjusting parameters of the designated function to enable the first space vector distance to be smaller and the second space vector distance to be larger;
judging whether the second space vector distance is simultaneously maximum when the first space vector distance is minimum;
and if so, determining the parameters of the specified function as fixed parameters.
Preferably, the step of distinguishing a corresponding designated travel track in each of the historical travel track data when the same driver drives according to the classification weight and a preset threshold includes:
dividing the historical travel track data with the classification weight larger than or equal to the preset threshold into a first set and a second set corresponding to two drivers respectively, and merging the historical travel track data with the classification weight smaller than the preset threshold into sets corresponding to the same driver;
and respectively associating the set type and the travel track data volume respectively corresponding to each set type in each map grid.
Preferably, after the step of distinguishing the corresponding designated driving track in each of the historical driving track data when the same driver drives according to the classification weight and the preset threshold, the method includes:
screening a designated set with the maximum data volume in a designated map grid, wherein the designated map grid is a grid where a vehicle insurance place is located;
taking the appointed set as a running track set corresponding to the applicant;
judging whether the current driving track for taking out the insurance is contained in the driving track set corresponding to the applicant;
if so, determining that the danger type of the designated driver is available, otherwise, not.
The present application further provides a device for differentiating drivers, comprising:
the first acquisition module is used for acquiring historical driving track data corresponding to the specified vehicle;
the first forming module is used for matching the historical driving track data into a map grid to form a track map;
the second forming module is used for forming a characteristic data array corresponding to each historical driving track data according to the track map;
the first calculation module is used for inputting each feature data array into the twin neural network model, and calculating the classification weight between the feature data arrays pairwise;
and the distinguishing module is used for distinguishing the corresponding specified driving track of the historical driving track data when the same driver drives according to the classification weight and a preset threshold value.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method as described above.
According to the method, the historical driving track data and the map grids are overlapped to form the track map, the characteristic data arrays are calculated according to the track map, each piece of historical driving track data is marked, the similarity between the characteristic data arrays of each piece of historical driving track data is calculated according to the twin neural network model, the driving behaviors of different drivers are distinguished, the drivers are distinguished and classified, and the driving track data and the drivers are associated in a one-to-one correspondence mode.
Drawings
FIG. 1 is a flow chart illustrating a method for distinguishing drivers according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a system for driver differentiation according to an embodiment of the present application;
fig. 3 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, a method for distinguishing drivers according to an embodiment of the present application includes:
s1: acquiring historical driving track data corresponding to a specified vehicle;
s2: matching the historical driving track data into a map grid to form a track map;
s3: forming a characteristic data array corresponding to each historical driving track data according to the track map;
s4: inputting each feature data array into a twin neural network model, and calculating classification weights between feature data arrays pairwise;
s5: and distinguishing corresponding appointed running tracks of the historical running track data when the same driver drives according to the classification weight and a preset threshold value.
In the embodiment of the application, historical driving track data corresponding to the appointed vehicle is obtained through an insurance APP account number registered by an owner of the appointed vehicle, and the navigation track of each insurance driver is collected as the historical driving track data by the insurance APP through setting rewards or setting insurance conditions. The navigation track is a vector cluster with the unit of second, and comprises: time, longitude and latitude, altitude, direction, speed and other driving data. The map grid is obtained by applying a division algorithm on the existing open-source map data, and the open-source map data comprises road longitude and latitude, road types, road speed limit and the like. The division algorithm includes an algorithm for dividing the map grid at specified intervals, for example, dividing the map grid at intervals of 10 km or 20 km to form a map grid of 10 × 10 square km or 20 × 20 square km; or a partitioning algorithm for partitioning the map grid according to each administrative region in the map, such as a Shenzhen Futian region grid, a Shenzhen Nanshan region grid, and the like. By overlapping the historical travel track data with the map grid, data samples of analyzed travel track characteristics are formed and used for calculating characteristic data arrays corresponding to the historical travel track data respectively, such as night travel data, peak travel data, driving smoothness and the like.
The method comprises the steps of inputting characteristic data arrays corresponding to two pieces of historical driving track data into a twin neural network model, calculating the similarity of the two pieces of historical driving track data through functions contained in the twin neural network model, further judging the probability that the two pieces of historical driving track data accord with the driving characteristics of the same driver, and further determining whether a specified vehicle is driven by the same driver with insurance registration.
According to the method, the historical driving track data and the map grids are overlapped to form the track map, the characteristic data arrays are calculated according to the track map, each piece of historical driving track data is marked, the similarity between the characteristic data arrays of each piece of historical driving track data is calculated according to the twin neural network model, the driving behaviors of different drivers are distinguished, the drivers are distinguished and classified, and the driving track data and the drivers are associated in a one-to-one correspondence mode.
Further, the step S2 of matching the historical driving trace data into a map grid to form a trace map includes:
s21: dividing a map into map grids according to a preset dividing mode;
s22: acquiring longitude and latitude information corresponding to each track point in appointed historical driving track data, wherein the appointed historical driving track data belongs to any one of all historical driving track data;
s23: superposing the specified historical driving track data to the map grid according to the longitude and latitude information;
s24: and according to the mode that the appointed historical driving track data are superposed into the map grid, superposing all the historical driving track data into the map grid in a one-to-one correspondence mode to form the track map.
In the embodiment of the application, the appointed historical driving track data are superposed into the corresponding grids according to the longitude and latitude data to form the track map with one-to-one correspondence between the historical driving track data and the map grids, and the track map is displayed as the composition of the map grids and the track lines respectively corresponding to the historical driving track data. Background data of the track map is represented by merging a data table corresponding to the historical travel track data and a data table corresponding to the map grid.
Further, the step S3 of forming a feature data array corresponding to each of the historical driving trajectory data according to the trajectory map includes:
s31, acquiring map grid sections occupied by the appointed historical driving track data and speed limit labels respectively corresponding to the map grid sections;
s32: according to the speed limit labels respectively corresponding to each map grid region, calculating the track characteristic data corresponding to the appointed historical driving track data, wherein the track characteristic data comprises a slow driving region ratio and an overspeed driving region ratio;
s33: and according to the statistical mode of the track characteristic data corresponding to the appointed historical driving track data, counting the track characteristic data respectively corresponding to all the historical driving track data.
In the embodiment of the application, the track characteristic data takes each map grid as a calculation interval, and the interval value corresponds to the driving mileage of the driving track in the interval. The track characteristic data comprises a slow driving section ratio and an overspeed driving section ratio, and the overspeed driving section ratio is subdivided into a highest speed limit section ratio, a road type speed limit section ratio and an extreme overspeed driving section ratio. The slow driving interval ratio and the overspeed driving interval ratio are equal to the total interval quantity ratio corresponding to the whole driving track, wherein the driving record interval quantity is less than 60 kph; the highest speed limit interval ratio is equal to the proportion of the number of overspeed recording intervals with the vehicle speed exceeding 120kph to the total number of the intervals; the ratio of the road type speed limit intervals is equal to the ratio of the number of the recording intervals with the speed exceeding the road type speed limit to the total number of the intervals; the extreme overspeed driving interval ratio is equal to the ratio of the number of recorded intervals of extreme overspeed driving to the total number of intervals, and exceeds the definition extreme overspeed of 20 percent of the speed limit.
Further, the step S3 of forming a characteristic data array corresponding to each of the historical driving trajectory data according to the trajectory map includes:
s301: acquiring time data respectively corresponding to each track point corresponding to the specified historical driving track data;
s302: calculating driver driving characteristic data corresponding to the appointed historical driving track data according to the time data, wherein the driver driving characteristic data comprise preset time interval driving data, driving smoothness and fatigue driving data;
s303: and calculating the driving characteristic data of the driver corresponding to all the historical driving track data according to the calculation mode of the driving characteristic data of the driver corresponding to the specified historical driving track data.
In the embodiment of the application, in order to increase the accuracy of distinguishing different drivers according to the driving data characteristics corresponding to the drivers, the characteristic data array not only comprises the track characteristic data, but also comprises the driving characteristic data of the drivers, and the characteristic data array is a group of 8-dimensional data. The driving characteristic data is obtained by analyzing the driving habits of the driver, and comprises night driving data, peak driving data, driving smoothness, fatigue driving data and the like. And acquiring the driving characteristic data by acquiring the time data of the driving track data. For example, when the vehicle drives from 11 pm to 5 am, the record is marked as 1 to indicate night, the record is marked as 0 to indicate non-night, and the number of the sections with night driving in the driving track is counted to account for the total number of the sections of the current driving track and serve as night driving data; counting the number of intervals of driving in peak periods, wherein the number of the intervals accounts for the total number of the intervals of the current driving track, the counted number is used as peak period driving data, a record mark is 1 to indicate that the peak period driving exists, otherwise, the record mark is 0 to indicate that the off-peak period driving exists, and the peak periods comprise the peak periods in the morning and evening of a working day; the driving smoothness is calculated by counting the times of rapid acceleration and rapid deceleration in the current driving track, and the speed change exceeds 100kph/10S, namely a rapid acceleration or rapid deceleration event; the fatigue driving data is obtained by counting the number of intervals with fatigue driving marks, and the number of the intervals accounts for the total number of the current counted running tracks, and the fatigue driving data is marked as fatigue driving when a journey of more than 2.5 hours is continuously driven.
Further, before the step S4 of inputting each of the feature data arrays into the twin neural network model and calculating the classification weight between the feature data arrays two by two, the method includes:
s41: inputting training samples into a twin neural network model, and mapping to a high-dimensional space through a specified function to obtain a space vector corresponding to each training sample, wherein the specified function is Gw (X), w represents a parameter, and X represents a training sample;
s42: calculating the first space vector distance corresponding to the first sample and the second sample with the same class label and having non-phase according to a first calculation formulaA second space vector distance corresponding to a third sample and a fourth sample of the same class label, wherein the first calculation formula is Ew (X)1,X2)＝||Gw(X1)-Gw(X2)||，X1,X2Represents a training sample, Ew (X)1,X2) Representing a space vector distance;
s43: adjusting parameters of the designated function to enable the first space vector distance to be smaller and the second space vector distance to be larger;
s44: judging whether the second space vector distance is simultaneously maximum when the first space vector distance is minimum;
s45: and if so, determining the parameters of the specified function as fixed parameters.
In the embodiment of the application, parameters of a designated function in a twin neural network are trained by taking the historical driving tracks corresponding to different drivers in an insurance APP as training samples and taking characteristic data arrays corresponding to the training samples as input data. The designated function is used for distinguishing the types of different characteristic data arrays, and further distinguishing different drivers corresponding to the types of the different characteristic data arrays. The twin neural network comprises two inputs and two parallel-designed networks, and can be divided into true and false twin networks according to whether the two networks share parameter weight, wherein the parameters in the two parallel-designed networks are the same. The twin neural network learns a similarity metric relationship from the input data and then uses the learned similarity metric relationship to compare and match new unknown classes of samples.
According to the method and the device, the input data are mapped to the high-dimensional space through the designated function in the twin neural network, space vectors corresponding to the input data are formed, and then the similarity of the two input data is judged by calculating the distance between the space vectors. According to the method, parameters in the designated function are determined by minimizing the loss function values of a pair of samples from the same category on training samples and maximizing the loss function values of a stack of samples from different categories, and then after the parameters in the designated function are determined, classification information of input data is obtained by receiving the similarity of input data of which category labels are not expressed.
Further, the step S5 of distinguishing the designated driving trajectory corresponding to the same driver when driving in each of the historical driving trajectory data according to the classification weight and the preset threshold includes:
s51: dividing the historical travel track data with the classification weight larger than or equal to the preset threshold into a first set and a second set corresponding to two drivers respectively, and merging the historical travel track data with the classification weight smaller than the preset threshold into sets corresponding to the same driver;
s52: and respectively associating the set type and the travel track data volume respectively corresponding to each set type in each map grid.
In the embodiment of the application, historical travel track data corresponding to a specified vehicle is classified through classification, each class is stored in a set, corresponding set types, set type quantity and travel track quantity respectively corresponding to each set type are associated in a map grid, and the set type with the maximum travel track quantity corresponds to a specified driver for insurance registration. The output value interval of the twin neural network model is a value between [ -1 and 1], the absolute value of the output value is used as a classification weight, the preset threshold value is 0.8, and if the absolute value is less than 0.8, the twin neural network model is regarded as that the same driver drives the appointed vehicle, otherwise, the twin neural network model is not in the form of track data that the same driver drives the appointed vehicle. On the basis that the classification weight is less than 0.8, the smaller the value is, the higher the accurate probability of being presumed to be the same driver is.
The feature data array input in the embodiment of the present application is a group of 8-dimensional vectors, and a formula for calculating the similarity between two input data is as follows:
wherein the content of the first and second substances,
is a value of the degree of similarity,
a first vector is represented by a first vector,
a second vector is represented that represents the second vector,
representing the ith dimension of the first vector,
representing the ith dimension of the second vector.
Further, after the step S5 of distinguishing the corresponding designated driving trajectory when the same driver drives in each of the historical driving trajectory data according to the classification weight and the preset threshold, the method includes:
s501: screening a designated set with the maximum data volume in a designated map grid, wherein the designated map grid is a grid where a vehicle insurance place is located;
s502: taking the appointed set as a running track set corresponding to the applicant;
s503: judging whether the current driving track for taking out the insurance is contained in the driving track set corresponding to the applicant;
s504: if so, determining that the danger type of the designated driver is available, otherwise, not.
In the embodiment of the application, the set type containing the maximum number of the running tracks is corresponding to the designated driver registered for insurance, then the designated map grids corresponding to the insurance places are determined, the designated set corresponding to the designated map grids is used as a judgment standard, whether the running tracks at the current insurance are contained in the running track set corresponding to the applicant is judged by comparing the relation between the classification weight of the running tracks at the current insurance and the characteristic data arrays in the designated set and the preset threshold value, if the classification weight of the characteristic data arrays of the running tracks at the current insurance and the characteristic data arrays in the designated set is less than the preset threshold value, the running tracks at the current insurance are contained in the running track set corresponding to the applicant, and the running tracks at the current insurance are the driving behavior of the designated driver registered for insurance and belong to the insurance type of the designated driver, otherwise, the vehicle does not belong to the danger type of the designated driver, and is the danger fraud.
Referring to fig. 2, an apparatus for distinguishing drivers according to an embodiment of the present application includes:
the system comprises a first acquisition module 1, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring historical driving track data corresponding to a specified vehicle;
the first forming module 2 is used for matching the historical driving track data into a map grid to form a track map;
a second forming module 3, configured to form, according to the trajectory map, feature data arrays corresponding to the historical travel trajectory data, respectively;
the first calculation module 4 is used for inputting each feature data array into the twin neural network model, and calculating the classification weight between the feature data arrays pairwise;
and the distinguishing module 5 is used for distinguishing the corresponding specified driving track of the same driver in the historical driving track data according to the classification weight and a preset threshold value.
The explanation of the corresponding method part is applicable to the explanation of the embodiment of the present application, which is not described in detail.
Further, the first forming module 2 comprises:
the dividing unit is used for dividing the map into map grids according to a preset dividing mode;
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring longitude and latitude information corresponding to each track point in appointed historical driving track data, and the appointed historical driving track data belongs to any one of all historical driving track data;
the first superposition unit is used for superposing the specified historical driving track data into the map grid according to the longitude and latitude information;
and the second superposition unit is used for superposing all the historical driving track data into the map grid in a one-to-one correspondence mode according to the mode that the specified historical driving track data are superposed into the map grid to form the track map.
Further, the feature data array includes trajectory feature data, and the second forming module 3 includes:
the second acquisition unit is used for acquiring map grid sections occupied by the specified historical driving track data and speed limit labels respectively corresponding to the map grid sections;
the first statistical unit is used for counting the track characteristic data corresponding to the appointed historical driving track data according to the speed limit labels respectively corresponding to the map grid sections, wherein the track characteristic data comprise a slow driving section ratio and an overspeed driving section ratio;
and the second statistical unit is used for counting the track characteristic data corresponding to all the historical driving track data according to the statistical mode of the track characteristic data corresponding to the specified historical driving track data.
Further, the characteristic data array includes driver driving characteristic data, and the second forming module 3 includes:
a third obtaining unit, configured to obtain time data corresponding to each track point corresponding to the specified historical travel track data;
the first calculation unit is used for calculating driver driving characteristic data corresponding to the specified historical driving track data according to the time data, wherein the driver driving characteristic data comprises preset time interval driving data, driving smoothness and fatigue driving data;
and the second calculation unit is used for calculating the driving characteristic data of the driver corresponding to all the historical driving track data according to the calculation mode of the driving characteristic data of the driver corresponding to the specified historical driving track data.
Further, an apparatus for differentiating drivers, comprising:
the input module is used for inputting the training samples into the twin neural network model and mapping the training samples to a high-dimensional space through a specified function to obtain a space vector corresponding to each training sample, wherein the specified function is Gw (X), w represents a parameter, and X represents a training sample;
second computing moduleAnd the distance calculation module is used for calculating a first space vector distance corresponding to a first sample and a second sample with the same class label and a second space vector distance corresponding to a third sample and a fourth sample with different class labels according to a first calculation formula, wherein the first calculation formula is Ew (X)1,X2)＝||Gw(X1)-Gw(X2)||，X1,X2Represents a training sample, Ew (X)1,X2) Representing a space vector distance;
the adjusting module is used for adjusting the parameters of the specified function to enable the first space vector distance to be smaller and enable the second space vector distance to be larger;
the first judgment module is used for judging whether the second space vector distance is simultaneously maximum when the first space vector distance is minimum;
and the determining module is used for determining the parameters of the specified functions as fixed parameters if the parameters are maximum at the same time.
Further, the distinguishing module 5 includes:
the distinguishing unit is used for distinguishing the historical travel track data of which the classification weight is greater than or equal to the preset threshold value into a first set and a second set corresponding to two drivers respectively, and merging the historical travel track data of which the classification weight is less than the preset threshold value into a set corresponding to the same driver;
and the association unit is used for associating the set types and the travel track data volumes respectively corresponding to the set types in the map grids.
Further, an apparatus for differentiating drivers, comprising:
the screening module is used for screening a specified set with the maximum data volume in a specified map grid, wherein the specified map grid is a grid where the vehicle insurance place is located;
the acting module is used for taking the designated set as a running track set corresponding to the applicant;
the second judgment module is used for judging whether the current insurance driving track is contained in the driving track set corresponding to the applicant;
and the judging module is used for judging that the insurance type of the designated driver is the insurance type if the insurance type is contained in the driving track set corresponding to the applicant, otherwise, judging that the insurance type is not the insurance type.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all the data required for the process of differentiating the driver. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of differentiating drivers.
The processor executes the method for distinguishing drivers, and comprises the following steps: acquiring historical driving track data corresponding to a specified vehicle; matching the historical driving track data into a map grid to form a track map; forming a characteristic data array corresponding to each historical driving track data according to the track map; inputting each feature data array into a twin neural network model, and calculating classification weights between feature data arrays pairwise; and distinguishing corresponding appointed running tracks of the historical running track data when the same driver drives according to the classification weight and a preset threshold value.
According to the computer equipment, the historical driving track data and the map grids are overlapped to form a track map, the characteristic data arrays are calculated according to the track map to mark each piece of historical driving track data, the similarity between the characteristic data arrays of each piece of historical driving track data is calculated according to the twin neural network model, the driving behaviors of different drivers are distinguished, the drivers are distinguished and classified, and the driving track data and the drivers are correspondingly associated one by one.
In one embodiment, the step of matching the historical driving track data into a map grid by the processor to form a track map includes: dividing a map into map grids according to a preset dividing mode; acquiring longitude and latitude information corresponding to each track point in appointed historical driving track data, wherein the appointed historical driving track data belongs to any one of all historical driving track data; superposing the specified historical driving track data to the map grid according to the longitude and latitude information; and according to the mode that the appointed historical driving track data are superposed into the map grid, superposing all the historical driving track data into the map grid in a one-to-one correspondence mode to form the track map.
In one embodiment, the feature data array includes track feature data, and the step of forming, by the processor, a feature data array corresponding to each of the historical driving track data according to the track map includes: acquiring map grid sections occupied by the appointed historical driving track data and speed limit labels respectively corresponding to the map grid sections; according to the speed limit labels respectively corresponding to each map grid region, calculating the track characteristic data corresponding to the appointed historical driving track data, wherein the track characteristic data comprises a slow driving region ratio and an overspeed driving region ratio; and according to the statistical mode of the track characteristic data corresponding to the appointed historical driving track data, counting the track characteristic data respectively corresponding to all the historical driving track data.
In one embodiment, the feature data array includes driver driving feature data, and the step of forming, by the processor, a feature data array corresponding to each of the historical driving trajectory data according to the trajectory map includes: acquiring time data respectively corresponding to each track point corresponding to the specified historical driving track data; calculating driver driving characteristic data corresponding to the appointed historical driving track data according to the time data, wherein the driver driving characteristic data comprise preset time interval driving data, driving smoothness and fatigue driving data; and calculating the driving characteristic data of the driver corresponding to all the historical driving track data according to the calculation mode of the driving characteristic data of the driver corresponding to the specified historical driving track data.
In one embodiment, the step of inputting each of the feature data arrays into the twin neural network model, and calculating the classification weight between the feature data arrays two by two, by the processor, includes: inputting training samples into a twin neural network model, and mapping to a high-dimensional space through a specified function to obtain a space vector corresponding to each training sample, wherein the specified function is Gw (X), w represents a parameter, and X represents a training sample; calculating a first space vector distance corresponding to a first sample and a second sample with the same class label and a second space vector distance corresponding to a third sample and a fourth sample with different class labels according to a first calculation formula, wherein the first calculation formula is Ew (X)1,X2)＝||Gw(X1)-Gw(X2)||，X1,X2Represents a training sample, Ew (X)1,X2) Representing a space vector distance; adjusting parameters of the designated function to enable the first space vector distance to be smaller and the second space vector distance to be larger; judging whether the second space vector distance is simultaneously maximum when the first space vector distance is minimum; and if so, determining the parameters of the specified function as fixed parameters.
In one embodiment, the step of distinguishing, by the processor, a corresponding designated travel track for the same driver when driving in each of the historical travel track data according to the classification weight and a preset threshold includes: dividing the historical travel track data with the classification weight larger than or equal to the preset threshold into a first set and a second set corresponding to two drivers respectively, and merging the historical travel track data with the classification weight smaller than the preset threshold into sets corresponding to the same driver; and respectively associating the set type and the travel track data volume respectively corresponding to each set type in each map grid.
In one embodiment, after the step of distinguishing the corresponding designated driving track of each historical driving track data when the same driver drives according to the classification weight and the preset threshold value, the processor includes: screening a designated set with the maximum data volume in a designated map grid, wherein the designated map grid is a grid where a vehicle insurance place is located; taking the appointed set as a running track set corresponding to the applicant; judging whether the current driving track for taking out the insurance is contained in the driving track set corresponding to the applicant; if so, determining that the danger type of the designated driver is available, otherwise, not.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing a method of distinguishing drivers, comprising: acquiring historical driving track data corresponding to a specified vehicle; matching the historical driving track data into a map grid to form a track map; forming a characteristic data array corresponding to each historical driving track data according to the track map; inputting each feature data array into a twin neural network model, and calculating classification weights between feature data arrays pairwise; and distinguishing corresponding appointed running tracks of the historical running track data when the same driver drives according to the classification weight and a preset threshold value.
The computer-readable storage medium forms a track map by overlapping historical driving track data and a map grid, marks each piece of historical driving track data according to a feature data array calculated by the track map, then calculates the similarity between the feature data arrays of each piece of historical driving track data according to a twin neural network model, distinguishes driving behaviors of different drivers, realizes distinguishing and classifying the drivers, and realizes one-to-one corresponding association of the driving track data and the drivers.
In one embodiment, the step of matching the historical driving track data into a map grid by the processor to form a track map includes: dividing a map into map grids according to a preset dividing mode; acquiring longitude and latitude information corresponding to each track point in appointed historical driving track data, wherein the appointed historical driving track data belongs to any one of all historical driving track data; superposing the specified historical driving track data to the map grid according to the longitude and latitude information; and according to the mode that the appointed historical driving track data are superposed into the map grid, superposing all the historical driving track data into the map grid in a one-to-one correspondence mode to form the track map.
In one embodiment, the feature data array includes track feature data, and the step of forming, by the processor, a feature data array corresponding to each of the historical driving track data according to the track map includes: acquiring map grid sections occupied by the appointed historical driving track data and speed limit labels respectively corresponding to the map grid sections; according to the speed limit labels respectively corresponding to each map grid region, calculating the track characteristic data corresponding to the appointed historical driving track data, wherein the track characteristic data comprises a slow driving region ratio and an overspeed driving region ratio; and according to the statistical mode of the track characteristic data corresponding to the appointed historical driving track data, counting the track characteristic data respectively corresponding to all the historical driving track data.
In one embodiment, the feature data array includes driver driving feature data, and the step of forming, by the processor, a feature data array corresponding to each of the historical driving trajectory data according to the trajectory map includes: acquiring time data respectively corresponding to each track point corresponding to the specified historical driving track data; calculating driver driving characteristic data corresponding to the appointed historical driving track data according to the time data, wherein the driver driving characteristic data comprise preset time interval driving data, driving smoothness and fatigue driving data; and calculating the driving characteristic data of the driver corresponding to all the historical driving track data according to the calculation mode of the driving characteristic data of the driver corresponding to the specified historical driving track data.
In one embodiment, the step of inputting each of the feature data arrays into the twin neural network model, and calculating the classification weight between the feature data arrays two by two, by the processor, includes: inputting training samples into a twin neural network model, and mapping to a high-dimensional space through a specified function to obtain a space vector corresponding to each training sample, wherein the specified function is Gw (X), w represents a parameter, and X represents a training sample; calculating a first space vector distance corresponding to a first sample and a second sample with the same class label and a second space vector distance corresponding to a third sample and a fourth sample with different class labels according to a first calculation formula, wherein the first calculation formula is Ew (X)1,X2)＝||Gw(X1)-Gw(X2)||，X1,X2Represents a training sample, Ew (X)1,X2) Representing a space vector distance; adjusting parameters of the designated function to enable the first space vector distance to be smaller and the second space vector distance to be larger; judging whether the second space vector distance is simultaneously maximum when the first space vector distance is minimum; and if so, determining the parameters of the specified function as fixed parameters.
In one embodiment, the step of distinguishing, by the processor, a corresponding designated travel track for the same driver when driving in each of the historical travel track data according to the classification weight and a preset threshold includes: dividing the historical travel track data with the classification weight larger than or equal to the preset threshold into a first set and a second set corresponding to two drivers respectively, and merging the historical travel track data with the classification weight smaller than the preset threshold into sets corresponding to the same driver; and respectively associating the set type and the travel track data volume respectively corresponding to each set type in each map grid.
In one embodiment, after the step of distinguishing the corresponding designated driving track of each historical driving track data when the same driver drives according to the classification weight and the preset threshold value, the processor includes: screening a designated set with the maximum data volume in a designated map grid, wherein the designated map grid is a grid where a vehicle insurance place is located; taking the appointed set as a running track set corresponding to the applicant; judging whether the current driving track for taking out the insurance is contained in the driving track set corresponding to the applicant; if so, determining that the danger type of the designated driver is available, otherwise, not.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A method of differentiating drivers, comprising:
acquiring historical driving track data corresponding to a specified vehicle;
matching the historical driving track data into a map grid to form a track map;
forming a characteristic data array corresponding to each historical driving track data according to the track map;
inputting each feature data array into a twin neural network model, and calculating classification weights between feature data arrays pairwise;
and distinguishing corresponding appointed running tracks of the historical running track data when the same driver drives according to the classification weight and a preset threshold value.
2. The method for differentiating drivers according to claim 1, wherein the step of matching the historical travel track data into a map grid to form a track map comprises:
dividing a map into map grids according to a preset dividing mode;
acquiring longitude and latitude information corresponding to each track point in appointed historical driving track data, wherein the appointed historical driving track data belongs to any one of all historical driving track data;
superposing the specified historical driving track data to the map grid according to the longitude and latitude information;
and according to the mode that the appointed historical driving track data are superposed into the map grid, superposing all the historical driving track data into the map grid in a one-to-one correspondence mode to form the track map.
3. The method for distinguishing drivers according to claim 1, wherein the feature data array includes trajectory feature data, and the step of forming a feature data array corresponding to each of the historical travel trajectory data from the trajectory map includes:
acquiring map grid sections occupied by the appointed historical driving track data and speed limit labels respectively corresponding to the map grid sections;
according to the speed limit labels respectively corresponding to each map grid region, calculating the track characteristic data corresponding to the appointed historical driving track data, wherein the track characteristic data comprises a slow driving region ratio and an overspeed driving region ratio;
and according to the statistical mode of the track characteristic data corresponding to the appointed historical driving track data, counting the track characteristic data respectively corresponding to all the historical driving track data.
4. The method for distinguishing the driver according to claim 1, wherein the feature data array includes driver driving feature data, and the step of forming a feature data array corresponding to each of the historical driving trajectory data from the trajectory map includes:
acquiring time data respectively corresponding to each track point corresponding to the specified historical driving track data;
calculating driver driving characteristic data corresponding to the appointed historical driving track data according to the time data, wherein the driver driving characteristic data comprise preset time interval driving data, driving smoothness and fatigue driving data;
and calculating the driving characteristic data of the driver corresponding to all the historical driving track data according to the calculation mode of the driving characteristic data of the driver corresponding to the specified historical driving track data.
5. The method of differentiating drivers of claim 1, wherein said step of inputting each of said feature data arrays into a twin neural network model, pairwise calculating classification weights between feature data arrays, is preceded by the step of:
inputting training samples into a twin neural network model, and mapping to a high-dimensional space through a specified function to obtain a space vector corresponding to each training sample, wherein the specified function is Gw (X), w represents a parameter, and X represents a training sample;
calculating a first space vector distance corresponding to a first sample and a second sample with the same class label and a second space vector distance corresponding to a third sample and a fourth sample with different class labels according to a first calculation formula, wherein the first calculation formula is Ew (X)1,X2)＝||Gw(X1)-Gw(X2)||，X1,X2Represents a training sample, Ew (X)1,X2) Representing a space vector distance;
adjusting parameters of the designated function to enable the first space vector distance to be smaller and the second space vector distance to be larger;
judging whether the second space vector distance is simultaneously maximum when the first space vector distance is minimum;
and if so, determining the parameters of the specified function as fixed parameters.
6. The method for distinguishing drivers according to claim 1, wherein the step of distinguishing the corresponding designated driving track of each historical driving track data when the same driver drives according to the classification weight and the preset threshold value comprises:
dividing the historical travel track data with the classification weight larger than or equal to the preset threshold into a first set and a second set corresponding to two drivers respectively, and merging the historical travel track data with the classification weight smaller than the preset threshold into sets corresponding to the same driver;
and respectively associating the set type and the travel track data volume respectively corresponding to each set type in each map grid.
7. The method for distinguishing drivers according to claim 1, wherein the step of distinguishing designated driving trajectories corresponding to the same driver in the historical driving trajectory data according to the classification weight and the preset threshold value is followed by the step of distinguishing the designated driving trajectories corresponding to the same driver in the historical driving trajectory data, and the method comprises the following steps:
screening a designated set with the maximum data volume in a designated map grid, wherein the designated map grid is a grid where a vehicle insurance place is located;
taking the appointed set as a running track set corresponding to the applicant;
judging whether the current driving track for taking out the insurance is contained in the driving track set corresponding to the applicant;
if so, determining that the danger type of the designated driver is available, otherwise, not.
8. An apparatus for differentiating a driver, comprising:
the first acquisition module is used for acquiring historical driving track data corresponding to the specified vehicle;
the first forming module is used for matching the historical driving track data into a map grid to form a track map;
the second forming module is used for forming a characteristic data array corresponding to each historical driving track data according to the track map;
the first calculation module is used for inputting each feature data array into the twin neural network model, and calculating the classification weight between the feature data arrays pairwise;
and the distinguishing module is used for distinguishing the corresponding specified driving track of the historical driving track data when the same driver drives according to the classification weight and a preset threshold value.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110276146.9A CN113157817A (en) | 2021-03-15 | 2021-03-15 | Method and device for distinguishing drivers and computer equipment |
| PCT/CN2021/091711 WO2022193416A1 (en) | 2021-03-15 | 2021-04-30 | Method and apparatus for distinguishing driver, and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110276146.9A CN113157817A (en) | 2021-03-15 | 2021-03-15 | Method and device for distinguishing drivers and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113157817A true CN113157817A (en) | 2021-07-23 |
Family
ID=76887126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110276146.9A Pending CN113157817A (en) | 2021-03-15 | 2021-03-15 | Method and device for distinguishing drivers and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113157817A (en) |
| WO (1) | WO2022193416A1 (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106314438A (en) * | 2016-08-15 | 2017-01-11 | 西北工业大学 | Method and system for detecting abnormal track in driver driving track |
| US20170255966A1 (en) * | 2014-03-28 | 2017-09-07 | Joseph Khoury | Methods and systems for collecting driving information and classifying drivers and self-driving systems |
| CN109145982A (en) * | 2018-08-17 | 2019-01-04 | 上海汽车集团股份有限公司 | The personal identification method and device of driver, storage medium, terminal |
| CN110443185A (en) * | 2019-07-31 | 2019-11-12 | 京东城市(北京)数字科技有限公司 | Driver's recognition methods, driver identification device, electronic equipment and storage medium |
| US20200198645A1 (en) * | 2018-12-20 | 2020-06-25 | Nauto, Inc. | System and method for analysis of driver behavior |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11244254B2 (en) * | 2014-12-31 | 2022-02-08 | The City And County Of San Francisco | Application-based commercial ground transportation clearinghouse system |
| DE102016210029A1 (en) * | 2016-06-07 | 2017-12-07 | Robert Bosch Gmbh | Method Device and system for wrong driver identification |
| CN107784046B (en) * | 2016-11-14 | 2021-05-04 | 平安科技（深圳）有限公司 | POI information processing method and device |
| US11106969B2 (en) * | 2017-01-19 | 2021-08-31 | International Business Machines Corporation | Method and apparatus for driver identification leveraging telematics data |
| WO2019048034A1 (en) * | 2017-09-06 | 2019-03-14 | Swiss Reinsurance Company Ltd. | Electronic logging and track identification system for mobile telematics devices, and corresponding method thereof |
| US10820166B1 (en) * | 2019-12-04 | 2020-10-27 | Toyota Connected North America, Inc. | Systems and methods for obtaining location intelligence |
| CN112417273B (en) * | 2020-11-17 | 2022-04-19 | 平安科技（深圳）有限公司 | Region portrait image generation method, region portrait image generation device, computer equipment and storage medium |
-
2021
- 2021-03-15 CN CN202110276146.9A patent/CN113157817A/en active Pending
- 2021-04-30 WO PCT/CN2021/091711 patent/WO2022193416A1/en unknown
Patent Citations (5)
| 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 |
| CN106314438A (en) * | 2016-08-15 | 2017-01-11 | 西北工业大学 | Method and system for detecting abnormal track in driver driving track |
| CN109145982A (en) * | 2018-08-17 | 2019-01-04 | 上海汽车集团股份有限公司 | The personal identification method and device of driver, storage medium, terminal |
| US20200198645A1 (en) * | 2018-12-20 | 2020-06-25 | Nauto, Inc. | System and method for analysis of driver behavior |
| CN110443185A (en) * | 2019-07-31 | 2019-11-12 | 京东城市(北京)数字科技有限公司 | Driver's recognition methods, driver identification device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| GALINA MALYKHINA ET AL: "Application of Siamese Neural Networks for the Type of Emergency Determination", 《CSIS\'2019: PROCEEDINGS OF THE XI INTERNATIONAL SCIENTIFIC CONFERENCE COMMUNICATIVE STRATEGIES OF THE INFORMATION SOCIETY》, pages 1 - 5 * |
| SARA HERNÁNDEZ SÁNCHEZ ET AL: "Driver Identification and Verification From Smartphone Accelerometers Using Deep Neural Networks", 《IEEE》, pages 97 - 108 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022193416A1 (en) | 2022-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6961012B2 (en) | Customized safe speed determination for the vehicle | |
| Panwai et al. | Neural agent car-following models | |
| US20190308619A1 (en) | Method and system for estimating an accident risk of an autonomous vehicle | |
| CN107784587A (en) | A kind of driving behavior evaluation system | |
| CN108877213B (en) | Traffic accident identification method and system | |
| CN109544351A (en) | Vehicle risk appraisal procedure, device, computer equipment and storage medium | |
| WO2021050152A1 (en) | Systems and methods for predicting fuel consumption efficiency | |
| CN108492023A (en) | A kind of vehicle loan air control method based on trajectory analysis | |
| DE102019114595B4 (en) | Method for controlling the operation of a motor vehicle and for deriving road segment speed limits | |
| EP3578433A1 (en) | Method for estimating an accident risk of an autonomous vehicle | |
| Wang et al. | Vehicle reidentification with self-adaptive time windows for real-time travel time estimation | |
| CN112860782A (en) | Pure electric vehicle driving range estimation method based on big data analysis | |
| CN113157817A (en) | Method and device for distinguishing drivers and computer equipment | |
| CN115774942A (en) | Driving style identification model modeling and statistical method based on Internet of vehicles real vehicle data and SVM | |
| CN116434523A (en) | Vehicle active safety control method and device based on constraint degree in information perception scene | |
| Ziegmann et al. | Stochastic driver velocity prediction with environmental features on naturalistic driving data | |
| CN114043948A (en) | Vehicle energy consumption measuring and calculating method and device, electronic equipment and storage medium | |
| CN108268678A (en) | Driving behavior analysis method, apparatus and system | |
| CN113888302A (en) | Risk early warning method and system for automobile financial vehicle loan | |
| CN112559968A (en) | Driving style representation learning method based on multi-situation data | |
| CN114493191B (en) | Driving behavior modeling analysis method based on network about vehicle data | |
| CN113723529B (en) | Traffic information credible identification method based on speed prediction algorithm | |
| CN115472040B (en) | Personalized anti-collision early warning method for networked vehicle based on collision probability field | |
| Wickramanayake et al. | Real-Time Monitoring and Driver Feedback to Promote Fuel Efficient Driving | |
| CN112613225B (en) | Intersection traffic state prediction method based on neural network cell transmission model |
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 |