JP2019016238A - Estimation apparatus, vehicle terminal, program, and method for estimating road section from which personal characteristic can be easily specified from driving vehicle signal - Google Patents

Abstract

To provide an apparatus and the like for estimating a road section which is easy to identify a personal characteristic from a driving vehicle signal.SOLUTION: An estimation apparatus comprises: driving data selection means for storing driving data correlated with a "driving position" and a "driving vehicle signal" acquired during driving of a vehicle in a "personal characteristic" for each driver, and for selecting a plurality of pieces of driving data including a traveling position within a position range of a road section with respect to the road section; correlation degree acquiring means for acquiring a degree of correlation between the personal characteristic and the driving vehicle signal; and road segment estimating means for estimating a road section according to the degree of correlation. It is possible to further comprise estimation model generating means for generating an estimation model from the personal characteristic of the driving data and the driving vehicle signal by using a predetermined algorithm and for calculating a correlation degree by using the estimation model.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a technique for collecting operation data as big data.

Conventionally, there is a technique for estimating a driver using a driving vehicle signal measured by a vehicle terminal mounted on the vehicle (see, for example, Non-Patent Documents 1 and 2). The driving vehicle signal is, for example, a “driving signal” such as the steering angle of the steering wheel or the accelerator / brake pedal, and a “vehicle signal” such as the engine speed, the vehicle speed, and the acceleration / angular velocity.
According to this technique, it consists of a learning phase and an evaluation phase. In the “learning phase”, driving vehicle signals from a plurality of drivers are collected in advance from the vehicle terminal in a state where the driver can be specified, and an estimated model in which the driver and the driving vehicle signal are associated with each other is generated. In the “evaluation phase”, the driver can be estimated from the driving vehicle signal in which the driver cannot be identified using the estimation model.

  There is also a technique for estimating an “emotional empathy measure” as a driver's personal characteristic from a driving vehicle signal (see, for example, Non-Patent Documents 3 and 4). The emotional empathy scale is a scale for measuring empathy for the emotions and feelings of others. According to this technique, it is possible to generate a model in which a driving vehicle signal collected in advance and a driver's emotional empathy measure are associated with each other, and to estimate the emotional empathy measure from the driving vehicle signal.

“Automobile Driver Fingerprinting” Proceedings on Privacy Enhancing Technologies; 2016 (1): 34-51, [online], [Search June 13, 2017], Internet <URL: http://www.autosec.org/pubs /fingerprint.pdf> “Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification” Proceedings of the IEEE (Volume: 95, Issue: 2, Feb. 2007), [online], [Search June 13, 2017], Internet <URL : https: //pdfs.semanticscholar.org/b14c/dccfc712cd16e240e13b30be07b75fd0900b.pdf> “Estimation of driver's personal characteristics using vehicle signals”, Proceedings of National Convention of Information Processing Society Volume ： 78th Issue ： 3 Page ： 3.147-3.148 “Automatic estimation of driver behavior and personal characteristics using driving signals”, Proceedings. JSAE Annual Congress Issue ： 128-13 Page ： 11-16

  Any of the above-described techniques requires that the driving vehicle signals be collected frequently and for a long time in both the learning phase and the evaluation phase. It is also assumed that driving vehicle signals are collected over the entire section being driven. Therefore, there is a problem that the network cost for the vehicle terminal to transmit the driving vehicle signal to the server and the server cost for processing the driving vehicle signal become enormous.

  In contrast, the inventors of the present application considered that there might be road sections where the degree of correlation between the driver's personal characteristics and the driving vehicle signal is high, and road sections where this is not the case. We thought that network costs and server costs could be reduced if the driving vehicle signals could be collected and analyzed only for road sections with a high degree of correlation.

  Therefore, an object of the present invention is to provide an estimation device, a vehicle terminal, a program, and a method for estimating a road section in which personal characteristics can be easily identified from a driving vehicle signal.

According to the present invention, the “personal characteristic” is an estimation device that accumulates driving data in association with “traveling position” and “driving vehicle signal” acquired during driving of the vehicle,
Driving data selection means for selecting a plurality of driving data for which a traveling position is included in the position range of the road section for a predetermined road section;
Correlation degree acquisition means for acquiring the degree of correlation between the personal characteristics and the driving vehicle signal for the road section;
The road section has road section estimation means for estimating a road section according to the degree of correlation.

According to another embodiment of the estimation device of the present invention,
A road section storage means for storing the position range on the map where the vehicle can travel in a plurality of “road sections”;
It is also preferable to cause the driving data selection means, the correlation degree acquisition means, and the road section estimation means to function for each road section.

According to another embodiment of the estimation device of the present invention,
The road section estimation means preferably outputs one or more road sections in descending order of the degree of correlation among the plurality of road sections.

According to another embodiment of the estimation device of the present invention,
The road section further includes an estimation model generation means for generating an estimation model from a personal characteristic of driving data and a driving vehicle signal using a predetermined algorithm.
It is also preferable that the correlation degree acquisition unit acquires the correlation degree using the estimation model.

According to another embodiment of the estimation device of the present invention,
The estimation model generation means generates an estimation model by machine learning using a statistical classification algorithm,
The degree of correlation is also preferably the likelihood (determination probability) of personal characteristics based on machine learning.

According to another embodiment of the estimation device of the present invention,
A teacher evaluation data classification unit that arbitrarily classifies a plurality of driving data selected by the driving data selection unit into a driving data for a teacher and an evaluation driving data for a road section,
The estimation model generation means generates an estimation model for the road section from the personal characteristics of the driving data for teachers and the driving vehicle signal using a predetermined algorithm,
It is also preferable that the correlation degree acquisition means acquires the degree of correlation between the personal characteristics and the driving vehicle signal in the evaluation driving data for the road section using the estimation model.

According to another embodiment of the estimation device of the present invention,
Correlation degree acquisition means
Input the "driving vehicle signal" of the driving data for evaluation into the estimation model, compare the "personal characteristic" that is the output with the "personal characteristic" of the correct answer of the driving data for evaluation, determine whether it is correct, The ratio of the number of positive judgments to the predetermined number of evaluation operation data is used as the correlation degree.
It is also preferable that the “driving vehicle signal” of the evaluation driving data is input to the estimation model, and the likelihood based on the “individual characteristics” that is the output is used as the correlation.

According to another embodiment of the estimation device of the present invention,
In the same road section, the teacher evaluation data classification means, the estimation model generation means, and the correlation degree acquisition means are repeated,
The teacher evaluation data classification means classifies the same road section into a plurality of data sets having different combinations of teacher driving data and evaluation driving data,
The estimation model generation means generates an estimation model from the teacher driving data for each data set,
When there are a plurality of data sets for the same road section, the correlation degree acquisition means preferably outputs the average value of the correlation degrees for each data set as the correlation degree.

According to another embodiment of the estimation device of the present invention,
It is also preferable that any one of “time zone”, “weather condition information”, “traffic condition information”, “vehicle attribute information” or a combination thereof is associated with the driving data.

According to another embodiment of the estimation device of the present invention,
"Personal characteristics" of driving data is
Driver ID (IDentifier)
Personal attributes DSQ (Driving Style Questionnaire),
WSQ (Workload Sensitivity Questionnaire),
DBQ (Driving Behavior Questionnaire),
DBI (Driving Behavior Inventory),
DAS (Driving Anger Scale),
Emotional empathy scale,
EAEQ (Everyday Attentional Experiences Questionnaire),
SSS (Sensation Seeking Scale),
FFM (Five Factor Model)
Or any combination thereof is also preferred.

According to the present invention, a vehicle terminal that communicates with the estimation device described above via a network,
Road section receiving means for receiving the position range of the road section estimated from the estimation device to have a high degree of correlation between the driver's personal characteristics and the driving vehicle signal;
When the positioning position acquired by the positioning function is included in the position range of the road section, it has driving data transmission means for transmitting driving data measured by itself to the estimation device.

According to the present invention, the “personal characteristic” for each driver is associated with the “running position” and “driving vehicle signal” acquired during driving of the vehicle, and is installed in the estimation device that accumulates driving data. A program that causes a computer to function,
Driving data selection means for selecting a plurality of driving data for which a traveling position is included in the position range of the road section for a predetermined road section;
Correlation degree acquisition means for acquiring the degree of correlation between personal characteristics and driving vehicle signals for road sections;
For road sections, the computer functions as road section estimation means for estimating road sections according to the degree of correlation.

According to the present invention, there is provided an estimation method for an apparatus for accumulating driving data in which “traveling position” and “driving vehicle signal” acquired during driving of a vehicle are associated with “personal characteristics” for each driver. And
The device
A first step of selecting, for a predetermined road section, a plurality of driving data whose travel position is included in the position range of the road section;
A second step of obtaining a correlation between the personal characteristics and the driving vehicle signal for the road section;
For the road section, a third step of estimating the road section according to the degree of correlation is executed.

  According to the estimation apparatus, the vehicle terminal, the program, and the method of the present invention, a road section where personal characteristics can be easily specified is estimated from a driving vehicle signal. Only the estimated driving data of the road section can be collected from the vehicle terminal to the estimation device.

It is a system block diagram which collects operation data. It is a functional block diagram of the estimation apparatus in this invention. It is a table which an operation data storage part memorizes. It is a table which a road section storage part memorizes. It is the map which divided the road section. It is explanatory drawing showing the learning function of this invention with respect to driving | operation data. It is explanatory drawing showing the classification | category of the driving | running | working data in the same road area. It is explanatory drawing which calculates a correlation degree from the some driving | operation data for evaluation in the same road area. It is the table which matched external factor information with driving data.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a system configuration diagram for collecting operation data.

  According to FIG. 1, the estimation apparatus 1 as a server and the vehicle terminal 2 mounted in the vehicle are connected via a network.

<Estimation device 1>
The estimation apparatus 1 of FIG. 1 has a learning function and an operation function.
The learning function instructs the operation function of a “road section” having a high degree of correlation between the driver's personal characteristics and the driving vehicle signal. Here, “individual characteristics” include a driver ID (IDentifier) and / or psychological characteristics. A driving vehicle signal collected from a road section having a high degree of correlation means that personal characteristics can be estimated with relatively high accuracy compared to other road sections.

The operation function transmits the road section instructed from the learning function to the vehicle terminal 2 via the network. On the other hand, the vehicle terminal 2 transmits only the received driving data (traveling position information + driving vehicle signal) in the road section to the estimation device 1. That is, the estimation device 1 only needs to collect driving data for the specified road section, and does not need to collect driving data from all road sections.
If the personal characteristics of the driver can be estimated from the service point of view, the information corresponding to the personal characteristics of the driver can be distributed to the terminal possessed by the driver.

<Vehicle terminal 2>
The vehicle terminal 2 acquires a “driving vehicle signal” including a driving signal and a vehicle signal via a CAN (Controller Area Network). Examples of driving signals and vehicle signals include the following.

[Operation signal]
・ Degree of brake / accel pedal depression ・ Handle steering angle ・ Operation status of various devices such as winker, wiper, power window ・ Distance between the vehicle and the front vehicle measured by the front monitoring camera or front monitoring sensor ・ Front / back / side Distance to obstacles in the lane ・ Frequency of lane change (detected from direction indicator operation information and steering information)
-Lane departure frequency (detected from the front monitoring camera, turn signal operation information, or steering information)
・ Speed excess frequency / degree (comparison of road speed limit and vehicle speed on the map based on driving position)
・ Detour selection frequency (comparison of driving route with the shortest route on the map)
・ Number of turnovers during parking (total steering angle during a certain period of time until the engine stops)

[Vehicle signal]
-Engine speed-Tire speed-Vehicle speed-Steering angular velocity (front, rear, lateral acceleration, front wheel turning angle)
-Travel distance, total travel distance-Elapsed time since the last engine start-Engine coolant temperature-Engine oil temperature-Battery temperature / charge rate-Braking distance / time (travel distance or travel time until stop)

  In addition, the vehicle terminal 2 has a positioning unit, and can acquire current traveling position information by receiving positioning radio waves such as GPS (Global Positioning System). Of course, the traveling position information may be acquired via the CAN.

  The vehicle terminal 2 includes a road section reception unit 21 and an operation data transmission unit 22 with respect to the estimation device 1.

  The road section receiving unit 21 receives from the estimation device 1 a position range of a road section that is estimated to have a high degree of correlation between the driver's personal characteristics and the driving vehicle signal. The road section is output to the driving data transmission unit 22.

  The driving data transmission unit 22 transmits driving data measured by itself to the estimation device 1 when the positioning position acquired by the positioning function is included in the position range of the road section. It is determined whether or not the latitude and longitude of the positioning position are included in the position range (latitude range and longitude range) of the road section. When it is determined to be true, the vehicle terminal 2 can transmit only the driving data of the road section to the estimation device 1.

  Note that, as another embodiment, the vehicle terminal 2 transmits, for example, VICS (registered trademark, Vehicle Information and Communication System) information and traffic status information such as ITS Connect (congestion, traffic regulation, etc.) to the estimation device 1. It may be a thing. The estimation apparatus 1 can also estimate the correlation tendency between the personal characteristics and the driving vehicle signal in the road section according to the traffic situation information.

  FIG. 2 is a functional configuration diagram of the estimation apparatus according to the present invention.

  2 includes a driving data storage unit 101, a road section storage unit 102, a driving data selection unit 11, a teacher evaluation data classification unit 12, an estimation model generation unit 13, and a correlation degree acquisition unit 14. And a road section estimation unit 15. These functional components are realized by executing a program that causes a computer installed in the apparatus to function. The processing flow of these functional components can also be understood as an estimation method.

  The essential functions of the present invention are the driving data selection unit 11, the correlation degree acquisition unit 14, and the road segment estimation unit 15, which are the road segment storage unit 102, the teacher evaluation data classification unit 12, and the estimation. The model generation unit 13 may function as an option.

[Operation data storage unit 101]
The driving data accumulating unit 101 accumulates “driving data” in which “traveling position” and “driving vehicle signal” acquired during driving of the vehicle are associated with “personal characteristics” for each driver.

The “personal characteristic” of the driving data is, for example, one of the following or a combination thereof.
・ Driver ID (IDentifier)
・ Personal attributes ・ DSQ (Driving Style Questionnaire),
・ WSQ (Workload Sensitivity Questionnaire),
・ DBQ (Driving Behavior Questionnaire),
-DBI (Driving Behavior Inventory),
・ DAS (Driving Anger Scale),
・ Emotional empathy scale,
・ EAEQ (Everyday Attentional Experiences Questionnaire),
・ SSS (Sensation Seeking Scale),
・ FFM (Five Factor Model)
Here, the psychological characteristics other than the driver ID may be acquired in advance by, for example, a questionnaire response, or may be acquired by other methods.

The personal attribute is driver profile information such as gender, age, and life zone.
DSQ and WSQ are indexes mainly used in Japan to quantify the personal characteristics of a driver.
DSQ is an index of attitude, orientation, and way of thinking about driving, and is quantified with a score of 5 out of 5 points based on questionnaire results for items such as “confidence in driving skills”, “reluctance”, and “impact”.
WSQ is an indicator of what kind of driving burden you feel strongly, with a score of 5 out of 5 based on the questionnaire results for items such as "Traffic information grasping", "Road environment grasping", and "Driving concentration inhibition" Quantified.
DBQ, DBI, and DAS are indexes used to quantify the personal characteristics of the driver, which are mainly used in Europe and the United States.
Furthermore, the emotional empathy scale, EAEQ, SSS, and FFM are indicators based on general personal characteristics that are not limited to driving behavior.

The driving vehicle signal that is different for each driver is often influenced by individual characteristics such as the personality and customs of each driver.
For example, a driver who repeatedly starts, stops, and changes lanes is confident in driving skills and impatient, but often has low awareness of safe driving. In addition, although grasping the traffic situation information is high, there is a high possibility that it is not concentrated on driving.
On the other hand, for example, a driver who drives relatively slowly has a high awareness of safe driving and often makes sufficient preparations. In addition, it has a high grasp of traffic condition information and is likely to concentrate on driving.

  FIG. 3 is a table stored in the operation data storage unit.

  According to FIG. 3, the driving data storage unit 101 includes “personal characteristics” (including driver ID and / or psychological characteristics) answered in advance by a questionnaire, “traveling position information” and “ The “driving vehicle signal” is associated.

  In addition, it is also preferable that driving | operation data is the performance data based on an unspecified many third party. In addition, a new road segment tendency can be estimated by updating the driving data every predetermined period (for example, every three months or every year) or at the time of change of traffic flow.

[Road section storage unit 102]
The road section storage unit 102 stores the position range on the map where the vehicle can travel by dividing it into a plurality of “road sections”. Based on a predetermined section division rule, the road section is divided from the map and output to the driving data selection unit 11.

FIG. 4 is a table stored in the road section storage unit.
According to FIG. 4, a position range is associated with each road section ID. The position range is represented by a latitude range and a longitude range.

FIG. 5 is a map in which road sections are segmented.
According to Fig.5 (a), a map area | region is divided | segmented into mesh shape and the road contained in a mesh is made into each area.
According to FIG.5 (b), the range which connects between the arbitrary points on a road is made into each area.

As another embodiment, the road sections may be further limitedly distinguished not only by the position range of the road sections but also by road types and / or road conditions on the map.
Examples of the “road type” include road width, number of lanes, high speed, national road, prefectural road, and city road.
“Road conditions” include crossroads, T-shaped roads, three-way crossings, pedestrian crossings, railroad crossings, bridges, tunnels, road gradients, overlap with school roads, and the like.
The road section does not necessarily need to cover all roads included in the map area, and may be only a part of the map area.

  The driving data selection unit 11, the teacher evaluation data classification unit 12, the estimation model generation unit 13, the correlation degree acquisition unit 14, and the road section estimation unit 15 that function in the following are executed for each road section. Is done.

[Operation data selection unit 11]
The driving data selection unit 11 selects, for a predetermined road section, a plurality of driving data whose travel positions are included in the position range of the road section.
In addition, when a plurality of road sections are stored in the road section storage unit 102, the driving data selection unit 11 selects driving data for each position range of the road section.
The driving data selected for each road section is output to the teacher evaluation data classification unit 12. In the simplest case, the operation data may be output directly to the correlation degree acquisition unit 14.

  FIG. 6 is an explanatory diagram showing the learning function of the present invention for driving data.

  According to FIG. 6, the driving data selection unit 11 selects driving data including the travel position information for each road section position range (road section ID) stored in the road section storage unit 102. For one road section ID, a set of personal characteristics and driving vehicle signals based on a plurality of drivers is selected.

[Teacher evaluation data classification unit 12]
The teacher evaluation data classification unit 12 arbitrarily classifies a plurality of driving data into “teacher driving data” and “evaluation driving data” for the road section. Classification is performed so that at least the number of teacher driving data groups is larger than the number of evaluation driving data groups.
The driving data for teacher is output to the estimation model generation unit 13, and the driving data for evaluation is output to the correlation degree acquisition unit 14.

  FIG. 7 is an explanatory diagram showing classification of driving data in the same road section.

The teacher evaluation data classification unit 12 classifies the same road section into a plurality of data sets having different combinations of the teacher driving data and the evaluation driving data.
In the simplest case, in order to evaluate the learning level of the estimation model by the three-way intersection verification, when three driving data exist in the same road section, the classification is performed as follows. According to FIG. 7, the combinations of the driving data for teachers and the driving data for evaluation are arbitrarily classified so as to be different each time.
First data set
Driving data for teachers-> 1st driving data, 2nd driving data
Electricity data for evaluation-> Third operation data Second data set
Driving data for teachers-> 1st driving data, 3rd driving data
Power data for evaluation-> 2nd operation data 3rd data set
Driving data for teachers-> 2nd driving data, 3rd driving data
Evaluation Electricity Data-> First Operation Data In this way, three data sets are created and input to the estimated model generation unit 13 and the correlation degree acquisition unit 14 for each data set.
That is, the teacher evaluation data classification unit 12, the estimated model generation unit 13, and the correlation degree acquisition unit 14 are repeated a plurality of times.

[Estimated model generation unit 13]
The estimation model generation unit 13 generates an estimation model for the road section from the personal characteristics of the driving data for teachers and the driving vehicle signal using a predetermined algorithm. That is, an estimation model is created for each road section.

The estimation model generation unit 13 generates an estimation model by machine learning using a statistical classification algorithm.
Here, an estimation model based on the degree of correlation between the “personal characteristics” and the “driving vehicle signal” is constructed. As the statistical classification algorithm, for example, a general machine learning algorithm used for the identification problem such as Random Forest, Support Vector Machine, Naive Bayes, and K-nearest neighbor may be used.

  By inputting the “driving vehicle signal” into the generated estimation model, “personal characteristics” can be output. When the estimation model is a machine learning engine, the likelihood (correlation degree to be described later) of “personal characteristics” output to the input “driving vehicle signal” may be further output.

  As another embodiment, an estimation model may be generated for each teacher data group (data set) output from the teacher evaluation data classification unit 12 even in the same road section. In this case, a plurality of estimation models are generated even in the same road section.

[Correlation degree acquisition unit 14]
The correlation degree acquisition unit 14 acquires the degree of correlation between the personal characteristics and the driving vehicle signal for the road section. Here, the driving data group output from the driving data selection unit 11 may be directly processed to derive the degree of correlation between the personal characteristics and the driving vehicle signal. The degree of correlation may be calculated by a statistical analysis algorithm, for example.

  Further, as another embodiment, the correlation degree acquisition unit 14 uses the estimation model generated by the estimation model generation unit 13 for the road section, and calculates the correlation between the individual characteristics in the evaluation driving data and the driving vehicle signal. You may acquire. For example, there are two embodiments as follows.

<First embodiment: Correlation degree based on correctness of operation data for evaluation>
The correlation degree acquisition unit 14 inputs the “driving vehicle signal” of the evaluation driving data to the estimation model, and compares the “personal characteristic” as the output with the “personal characteristic” of the correct answer of the evaluation driving data. The correctness is determined. Then, the ratio of the number of positive determinations with respect to the total number of operation data for evaluation is defined as the degree of correlation.
Correlation degree = number of positive determinations of evaluation operation data / total number of evaluation operation data Note that a predetermined number may be used instead of the total number of evaluation operation data.

  Further, when there are a plurality of data sets for the same road section, the correlation degree acquisition unit 14 may output an average value of the correlation degrees of each data set as the correlation degree in the road section. .

FIG. 8 is an explanatory diagram for calculating the degree of correlation from a plurality of evaluation driving data in the same road section.
According to FIG. 8, the correlation degree based on the plurality of data sets in the road section 1 is compared with the correlation degree based on the plurality of data sets in the road section 2, and the correlation degree is higher in the road section 1. Can be recognized.

Second Embodiment: Correlation Based on Likelihood Output from Machine Learning Estimation Model
The correlation degree acquisition unit 14 may input the “driving vehicle signal” of the evaluation driving data to the estimation model and output the likelihood based on the “personal characteristic” as the output as the correlation degree.

  The correlation degree acquisition unit 14 outputs both the first correlation degree of the first embodiment described above and the second correlation degree of the second embodiment to the road section estimation unit 15. There may be.

[Road section estimation unit 15]
The road section estimation unit 15 estimates a road section according to the degree of correlation. Specifically, the road section where the correlation degree is equal to or greater than a predetermined threshold may be estimated, or the road section is estimated according to the relative height of the correlation degree in an arbitrary distribution. Also good.
In addition, the road section estimation unit 15 selects one or more road sections (for example, the top 10 sections) in descending order of the degree of correlation among the plurality of road sections, and the degree of correlation between the driver's personal characteristics and the driving vehicle signal is It may be estimated as a high road section.

Furthermore, when the correlation level acquisition unit 14 outputs both the first correlation level and the second correlation level described above, it can be estimated by the following combinations, for example.
First correlation degree is greater than or equal to a predetermined threshold + second correlation degree is greater than or equal to a predetermined threshold-> correlation tendency: high first correlation degree is greater than or equal to a predetermined threshold + second correlation degree is less than a predetermined threshold-> correlation tendency: medium First correlation degree is less than a predetermined threshold + second correlation degree is a predetermined threshold or more-> correlation tendency: medium first correlation degree is less than a predetermined threshold + second correlation degree is less than a predetermined threshold-> correlation tendency: low

  As another embodiment, the road section may be estimated based on the total distance of the road section. For example, when two road sections have the same degree of correlation, road sections with a short total distance are estimated in a high order. The shorter the total distance, the more personal characteristics can be estimated with a smaller number of driving data that can be collected.

  The degree of correlation for estimating the road section is calculated from personal characteristics and driving vehicle information. For this reason, depending on the “personal characteristics” as a target, the degree of correlation changes, so that the estimated road sections also differ. Of course, the degree of correlation also changes depending on the target “driving vehicle information”, and the estimated road sections also differ.

<Expansion of operation data components>
As another embodiment, it is also preferable to associate the driving data with any one of “time zone”, “weather condition information”, “traffic condition information”, “vehicle attribute information” or a combination thereof as the external cause information.

  FIG. 9 is a table in which external data is associated with operation data.

  Even on the same road section, depending on the time zone (early morning, night, etc.), weather conditions (rainfall, snowfall, etc.), traffic situation information (eg, during traffic jams), and vehicle attribute information, the driver's personal characteristics The degree of correlation with the signal may increase.

The traffic situation information may be VICS information received from the vehicle terminal 2. Further, for example, when the vehicle is traveling at a speed of 20 km / h or less for a predetermined time, it may be simply determined as a traffic jam.
Also, as vehicle attribute information, information such as vehicle drive system (for example, 2WD (FR, FF, MR, RR) / 4WD, etc.), steering wheel position, vehicle type (for example, minivan / coupe / sedan / one box) It is.

The estimation model generation unit 13 adds “time zone, weather condition information, traffic condition information, and vehicle attribute information” to the driving vehicle signal, and generates an estimation model based on personal characteristics. That is, even in the same road section, different estimation models are generated for each combination of time zone / weather condition / traffic condition information / vehicle attribute information.
The correlation degree acquisition unit 14 also uses the estimation model to calculate the degree of correlation between the “driving vehicle signal, time zone, weather situation information, traffic situation information, and vehicle attribute information” based on the evaluation driving data, and the personal characteristics. Can be acquired. That is, even in the same road section, different correlations are acquired for each combination of time zone / weather condition / traffic condition information / vehicle attribute information.

  As described above in detail, according to the estimation apparatus, the vehicle terminal, the program, and the method of the present invention, a road section in which personal characteristics can be easily identified from a driving vehicle signal is estimated. Only the estimated driving data of the road section can be collected from the vehicle terminal to the estimation device.

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Estimation apparatus 101 Driving data storage part 102 Road section memory | storage part 11 Driving data selection part 12 Teacher evaluation data classification | category part 13 Estimation model production | generation part 14 Correlation degree acquisition part 15 Road section estimation part 2 Vehicle terminal 21 Road section receiving part 22 Driving data Transmitter

Claims (13)

An estimation device that accumulates driving data in which “personal characteristics” are associated with “traveling position” and “driving vehicle signal” acquired during driving of the vehicle,
Driving data selection means for selecting a plurality of driving data for which a traveling position is included in the position range of the road section for a predetermined road section;
Correlation degree acquisition means for acquiring the degree of correlation between the personal characteristics and the driving vehicle signal for the road section;
An estimation apparatus comprising road segment estimation means for estimating a road segment according to the degree of correlation for the road segment. A road section storage means for storing the position range on the map where the vehicle can travel in a plurality of “road sections”;
The estimation apparatus according to claim 1, wherein the driving data selection unit, the correlation degree acquisition unit, and the road segment estimation unit function for each road segment. The estimation apparatus according to claim 2, wherein the road section estimation unit outputs one or more road sections in descending order of correlation among a plurality of road sections. The road section further includes an estimated model generating means for generating an estimated model from a personal characteristic of driving data and a driving vehicle signal using a predetermined algorithm,
The estimation apparatus according to claim 1, wherein the correlation degree acquisition unit acquires the correlation degree using the estimation model. The estimation model generation means generates the estimation model by machine learning using a statistical classification algorithm,
The estimation apparatus according to claim 4, wherein the correlation degree is a likelihood (determination probability) of personal characteristics based on the machine learning. A teacher evaluation data classification means for arbitrarily classifying the plurality of driving data selected by the driving data selection means into the driving data for teacher and the driving data for evaluation for the road section,
The estimated model generation means generates an estimated model using a predetermined algorithm from the personal characteristics of the driving data for teachers and the driving vehicle signal for the road section,
The said correlation degree acquisition means acquires the correlation degree of the individual characteristic in the driving data for evaluation, and a driving vehicle signal using the said estimation model about the said road section, The Claim 4 or 5 characterized by the above-mentioned. Estimating device. The correlation degree acquisition means includes
Input the "driving vehicle signal" of the driving data for evaluation into the estimation model, compare the "personal characteristic" that is the output with the "personal characteristic" of the correct answer of the driving data for evaluation, determine whether it is correct, The ratio of the number of positive judgments to the predetermined number of evaluation operation data is used as the correlation degree.
The estimation apparatus according to claim 6, wherein the “driving vehicle signal” of the evaluation driving data is input to the estimation model, and the likelihood based on the “individual characteristic” that is an output thereof is used as the correlation. In the same road section, the teacher evaluation data classification means, the estimation model generation means, and the correlation degree acquisition means are repeated,
The teacher evaluation data classification means classifies the same road section into a plurality of data sets having different combinations of the driving data for teacher and the driving data for evaluation,
The estimated model generation means generates an estimated model from teacher driving data for each data set,
The correlation degree acquisition unit outputs an average value of correlation degrees for each data set as a correlation degree when a plurality of data sets exist for the same road section. Estimating device. 2. The driving data is further associated with any one of “time zone”, “weather condition information”, “traffic condition information”, “vehicle attribute information”, or a combination thereof. The estimation apparatus according to any one of 1 to 8. “Personal characteristics” of the driving data are:
Driver ID (IDentifier)
Personal attributes DSQ (Driving Style Questionnaire),
WSQ (Workload Sensitivity Questionnaire),
DBQ (Driving Behavior Questionnaire),
DBI (Driving Behavior Inventory),
DAS (Driving Anger Scale),
Emotional empathy scale,
EAEQ (Everyday Attentional Experiences Questionnaire),
SSS (Sensation Seeking Scale),
FFM (Five Factor Model)
The estimation device according to any one of claims 1 to 9, wherein the estimation device is any one of or a combination thereof. A vehicle terminal that communicates with the estimation device according to any one of claims 1 to 10 via a network,
Road section receiving means for receiving a position range of a road section estimated to have a high degree of correlation between the driver's personal characteristics and the driving vehicle signal from the estimation device;
A vehicle terminal comprising: driving data transmitting means for transmitting driving data measured by itself to the estimating device when the positioning position acquired by the positioning function is included in the position range of the road section. A program that causes a computer installed in an estimation device that accumulates driving data to function by associating “traveling position” and “driving vehicle signal” acquired during driving of the vehicle with “personal characteristics” for each driver. There,
Driving data selection means for selecting a plurality of driving data for which a traveling position is included in the position range of the road section for a predetermined road section;
Correlation degree acquisition means for acquiring the degree of correlation between the personal characteristics and the driving vehicle signal for the road section;
A program for causing a computer to function as road section estimation means for estimating a road section according to the degree of correlation for the road section. An estimation method for an apparatus for accumulating driving data, in which "driving position" and "driving vehicle signal" acquired during driving of a vehicle are associated with "personal characteristics" for each driver,
The device is
A first step of selecting, for a predetermined road section, a plurality of driving data whose travel position is included in the position range of the road section;
A second step of obtaining a correlation between the personal characteristics and the driving vehicle signal for the road section;
An estimation method for an apparatus, comprising: performing a third step of estimating a road section according to the degree of correlation for the road section.

Images