JP7178147B1 - Information processing device, information processing method, program - Google Patents

Abstract

A new method for estimating (reproducing) measurement data is proposed. Kind Code: A1 An information processing device is a device for measuring information about a moving object based on first measurement data measured by a first device for measuring information about the moving object, and is a second device different from the first device. A data generator that generates estimated data of the second measurement data measured by the device. [Selection drawing] Fig. 1

Description

The present invention relates to an information processing device, an information processing method, a program, and the like.

As a device (system) for measuring a certain object to be measured, for example, there is a device capable of measuring running information such as position information and acceleration information of a vehicle (for example, Patent Literature 1).

Japanese Patent Application Laid-Open No. 2022-58421

Although this is only an example, when considering developing a new service (business) using measurement data measured by a device that measures a predetermined measurement target as described above, it is possible to actually use the device for measurement. It is normal to acquire and evaluate a huge number of measurement data as data, which incurs time and money costs.

According to a first aspect of the present invention, an information processing device is a device that measures information about a moving object based on first measurement data measured by a first device that measures information about the moving object, the first A data generator that generates estimated data of second measurement data measured by a second device different from the device.
According to a second aspect of the present invention, an information processing method is a device for measuring information about a moving body based on first measurement data measured by a first device for measuring information about the moving body, Generating an estimate of second measured data measured by a second device different from the device.
According to a third aspect of the present invention, a program to be executed by a computer is a device that measures information about a mobile object based on first measurement data measured by a first device that measures information about the mobile object. causing the computer to generate estimated data of second measurement data measured by a second device that is different from the first device.
According to a fourth aspect of the present invention, an information processing device is a device that measures information about a moving object based on first measurement data measured by a first device that measures information about the moving object, the first A first determination unit that determines a measurement period of the first measurement data required for driving evaluation based on the second measurement data measured by a second device different from the device.
According to a fifth aspect of the present invention, an information processing method is a device for measuring information about a moving body based on first measurement data measured by a first device for measuring information about the moving body, Determining a measurement period of the first measured data required to evaluate driving based on a second measured data measured by a second device different from the device.
According to a sixth aspect of the present invention, a program to be executed by a computer is a device that measures information about a mobile object based on first measurement data measured by a first device that measures information about the mobile object. determining a measurement period of the first measurement data necessary for evaluating driving based on the second measurement data measured by a second device that is different from the first device.
According to a seventh aspect of the present invention, an information processing device is a device for measuring information about a mobile object based on first measurement data measured by a first device for measuring information about the mobile object, wherein the first a generation unit that simulates second measurement data measured by a second device different from the device for a predetermined period of time; an acquisition unit that acquires data loss ratio information in the generated pseudo second measurement data; and a determination unit that determines validity of the pseudo second measurement data in a predetermined period based on the loss ratio information.
According to an eighth aspect of the present invention, an information processing method is a device for measuring information about a moving body based on first measurement data measured by a first device for measuring information about the moving body, wherein the first Pseudo second measurement data measured by a second device different from the device is generated for a predetermined period of time, data loss ratio information in the generated pseudo second measurement data is obtained, and data loss ratio and determining validity of the pseudo second metrology data for the predetermined time period based on the information.
According to a ninth aspect of the present invention, a program to be executed by a computer is a device that measures information about a mobile object based on first measurement data measured by a first device that measures information about the mobile object. generating pseudo second measurement data for a predetermined period of time measured by a second device different from the first device; and obtaining data loss ratio information in the generated pseudo second measurement data. and determining the validity of the pseudo second measurement data for a predetermined period based on the data loss ratio information.

Explanatory drawing of the principle which concerns on embodiment. Explanatory drawing of the principle which concerns on embodiment. 4 is a flowchart showing an example of the flow of processing according to the embodiment; The figure which shows an example of the functional structure of the server based on 1st Example. Explanatory drawing of the principle which concerns on 1st Example. Explanatory drawing of the principle which concerns on 1st Example. Explanatory drawing of the principle which concerns on 1st Example. 4 is a flowchart showing an example of the flow of processing according to the first embodiment; The figure which shows an example of the information memorize|stored in the memory|storage part of the server based on 2nd Example. 9 is a flowchart showing an example of the flow of processing according to the second embodiment; The figure which shows an example of the histogram based on 2nd Example. The figure which shows an example of the histogram based on 2nd Example.

Hereinafter, an example of a form for carrying out the present invention will be described with reference to the drawings.
In addition, in the description of the drawings, the same elements may be denoted by the same reference numerals, and redundant description may be omitted.
However, the constituent elements described in this embodiment are merely examples, and are not intended to limit the scope of the present invention.

<Embodiment>
An example of an embodiment for realizing the present invention will be described below.

<Principle>
1.1. Principle of Data Estimation FIG. 1 is a diagram showing the flow of processing performed by an information processing apparatus according to one aspect of the present embodiment.
The information processing device, for example, based on the data obtained by measuring the measurement target by the first device (hereinafter referred to as "first device measurement data"), the measurement target is a second device different from the first device. It has, as a functional unit, a second device measurement data estimation unit 11 that generates (estimates) data for measurement. Note that the measurement may be detection or measurement. The same applies hereinafter. The data generated by the second device measurement data estimator 11 will be referred to as "estimated second device measurement data".

The first device may be, for example, a device that measures the object to be measured at predetermined time intervals (hereinafter referred to as "predetermined time intervals"). In this case, the first device measurement data is data obtained by measuring the measurement target by the first device at predetermined time intervals.

The second device may be, for example, a device that uses a sampling unit (which may be called a unit of measurement) when measuring the object to be measured, which is different from that of the first device. For example, as described above, if the first device uses time as a sampling unit and, for example, is a device that measures a measurement target at predetermined time intervals, the second device is a device that measures a measurement target using a sampling unit other than time. can be

For example, if the position (positional information) of the device is to be measured, the first device can be a device that measures the position at predetermined time intervals.
Also, in this case, the second device is, for example, a device that measures positions using a sampling unit of "distance", and a device that measures positions at predetermined distance intervals (hereinafter referred to as "predetermined distance intervals"). can be done.

In this example, if the predetermined time interval is “1 second interval” and the predetermined distance interval is “100 m”, the second device measurement data estimating unit 11 calculates, for example, 1 second included in the first device measurement data. Estimated second device measurement data can be generated by thinning (re-sampling) the measurement data at each position every "100 m" based on the position information.

When a set of a plurality of first device measurement data is defined as a "first device measurement data set", the second device measurement data estimation unit 11 performs the above process on each first device measurement data set included in the first device measurement data set. By performing on the device measurement data, estimated second device measurement data corresponding to each first device measurement data can be generated. A set of estimated second device measurement data generated in this manner may be referred to as an "estimated second device measurement data set".

Note that at least one of the first device and the second device is a device that measures a measurement target based on a plurality of sampling units (for example, distance and acceleration: the value of acceleration is a threshold value or more (or exceeds a threshold value) It may be a device that acquires a distance from a distance).
Other devices may be used.

1.2. Machine Learning Using Estimated Measurement Data FIG. 2 is a diagram for explaining the principles of learning and inference using estimated measurement data in this embodiment.

(1) At the time of learning As shown in FIG. It has as a functional part.

The first model processing unit 13 is, for example, a function unit that uses a predetermined model (existing model) as the first model, uses certain measurement data as an input to the first model, and calculates (calculates) predetermined various quantities. be able to. In addition, you may regard various quantities as a calculation object. The same applies hereinafter.
In this embodiment, the first model processing unit 13 calculates predetermined various quantities by using the above-described first device measurement data as input to the first model.

The second model generation unit 15 can be, for example, a functional unit that generates a second model capable of calculating the same quantities as the first model.
In the present embodiment, the second model generation unit 15, for example, combines the estimated second device measurement data generated by the second device measurement data estimation unit 11 and the various quantities calculated by the first model processing unit 13. A second model is generated by machine learning using a data set for learning. A second model generated in this manner is referred to as a "learned second model".
Note that the second model is not limited to the machine learning model. For example, the second model generation unit 15 may be a mathematical statistical model such as linear and nonlinear regression models, or a connectionist model such as DNN (Deep Neural Network).
Since the various quantities calculated by the first model processing unit 13 can be said to be desirable data (correct data, so to speak) that are calculated using the existing first model, here, "various quantities for teacher" (teacher data ).

(2) Inference As shown in FIG. 2B, the information processing apparatus has, for example, a trained second model processing unit 17 as a functional unit.

The learned second model processing unit 17 uses, for example, data obtained by measuring a measurement target by the second device (hereinafter referred to as “second device measurement data”) as an input to the learned second model, and performs a predetermined It can be a functional unit that calculates various quantities.
That is, the trained second model processing unit 17 receives as input the data obtained by actually measuring the measurement target by the second device, uses the trained second model to infer predetermined various quantities, and obtains the inference result (hereinafter , called “various quantity inference results”).

In addition to the above, for example, the estimated second device measurement data is used as input data to the first model, and some data held in the past corresponding to the first device measurement data accumulated from the past (for example, , data of elements that can affect various quantities, data of elements that are related to various quantities) may be used as training data to generate the second model by machine learning or the like.

<Processing>
FIG. 3 is a flowchart showing an example of the flow of processing shown in FIG.
First, the information processing device performs learning data set generation processing.
In the learning data set generation process, the information processing device targets the first device measurement data to be processed (in the example of FIG. 2, each first device measurement data included in the first device measurement data set), Processing of loop A is performed (A1 to A7).
The first apparatus measurement data to be processed may be data having the same measurement period, for example.

In the processing of loop A, the second device measurement data estimation unit 11 generates estimated second device measurement data based on the first device measurement data (A3).
In addition, the first model processing unit 13 calculates teacher variables based on the first device measurement data and the first model (A5).
Then, the information processing device shifts the processing to the next first device measurement data.

For example, if the processing of A3 and A5 is performed for all the first device measurement data to be processed, the information processing device ends the processing of loop A (A7).

After that, the information processing device performs learning processing (A9). Specifically, the second model generation unit 15 generates, for example, a supervised A trained second model is generated by learning.

Next, the information processing device performs inference processing (A11). Specifically, the learned second model processing unit 17 processes the second learned model generated in A9 and the second device measurement data to be processed (in the example of FIG. 2, the second device measurement data set is Various quantities are calculated based on each second device measurement data included). Then, the calculation result is used as the inference result of various quantities.
Then, the information processing device ends the process.

It should be noted that step A11 may be omitted and the process up to model generation may be performed.
Alternatively, only step A3 may be performed, and processing up to generating estimated second device measurement data based on the first device measurement data may be performed.

Although the principle has been described above, the measurement target can be, for example, information about a moving body.

For example, the moving object may include at least one of the following.
・Cars ・Motorcycles ・Personal mobility ・Vessels ・Railways ・Aerial vehicles (at least one of drones and aircraft)

In addition, the information about the moving object may include at least one of the following items, for example.
・Position information of moving object ・Speed information of moving object ・Acceleration information of moving object ・Azimuth information of moving object (orientation information)
・Angular velocity information of mobile object ・Time information of mobile object (time information, etc.)
Information including at least one of these pieces of information may be used as the traveling information of the moving object.

In addition, the measurement target is not limited to information (running information, etc.) related to a moving object, and may be information other than this.
For example, the measurement object may be "sound", the sampling unit of the first device may be "time", and the sampling unit of the second device may be "frequency", and the same processing as described above may be performed.
Further, for example, the same processing as described above may be performed on biological information (blood pressure, pulse, heart rate, respiratory rate, body temperature, electroencephalogram, etc.). Also in this case, for example, the sampling unit of the first device may be "time" and the sampling unit of the second device may be "frequency", and the same processing as described above may be performed.

<Example>
Next, an embodiment of a server, which is an example of the above information processing apparatus, will be described.
Below, the example in the case of applying vehicles, such as a four-wheeled vehicle, as a mobile body is described.
Note that the information processing device is not limited to a server, and may be, for example, a personal computer, a mobile phone including a smart phone, a PDA, or an electronic device (terminal) such as various tablet terminals. These devices, including servers, may also be referred to as computing devices.
However, the embodiments to which the present invention can be applied are not limited to the embodiments described below.

<First embodiment>
These days, ETC2.0 is spreading. For example, it is conceivable to develop an insurance product such as telematics insurance as a service (business) based on this ETC2.0.
However, this does not include measurement data obtained by having a driver actually drive a vehicle equipped with a device that supports ETC 2.0 (for example, an on-board device that supports ETC 2.0 or a DSRC (Dedicated Short Range Communications) device). and data such as accident data corresponding thereto are required, resulting in time cost and monetary cost.

In this case, for example, by estimating (reproducing) the data measured by a device compatible with ETC 2.0 from the data (acquired data) measured by a device different from the device compatible with ETC 2.0, It is conceivable that insurance products and the like can be developed by omitting data collection by devices compatible with ETC 2.0.

In developing insurance products for telematics insurance, for example, a model (hereinafter referred to as a "driving score model" (driving quality score model ).
Generally speaking, the driving score model should be constructed as a model in which at least one of the following elements (including elements standardized per unit time or per unit distance) affects the score value. can be done.
・Number of sharp turns (or frequency of sharp turns or distribution of degree of steering including sharp turns)
・Number of sudden decelerations (or frequency of sudden decelerations or distribution of decelerations including sudden decelerations)
・Sudden acceleration frequency (or sudden acceleration frequency or distribution of acceleration including sudden acceleration)
・Number of times of speeding (or frequency of speeding or distribution of speed including speeding)

For example, build a driving score model in which the higher the number of these elements (or the higher the frequency or the degree of sudden maneuvering/speeding), the higher the accident risk and the higher the driving score (or the lower the driving score). can do.
Then, as one of the uses (methods of utilization) of this driving score, for example, it is possible to reflect the driving score in the insurance premium of telematics insurance (determine the insurance premium based on the driving score).

In this embodiment, the above elements are not necessarily reflected strictly, but after generating estimated ETC 2.0 measurement data that reflects at least the rough driving tendency of the driver, this generated estimation A method of generating a driving score model based on ETC2.0 measurement data will be described.

It should be noted that the content described in the first embodiment can be applied to each of the other embodiments and other modifications.

<Functional configuration>
FIG. 4 is a diagram showing an example of the functional configuration of the server 100 in this embodiment.
The server 100 includes, for example, a processing unit (control unit) 110, an operation unit 120, a display unit 130, a sound output unit 140, a communication unit 150, a clock unit 160, and a storage unit 190. It can be a computer system connected by bus B.

The processing unit 110 is, for example, a processing device or a control device that comprehensively controls each unit of the server 100 according to various programs such as a system program stored in the storage unit 190 and performs various processes. Processing Unit), GPU (Graphics Processing Unit), DSP (Digital Signal Processor) and other processors, ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array) and other integrated circuits.

The operation unit 120 includes input devices, such as operation buttons and operation switches, through which the user performs various operational inputs to the server 100 . Further, the operation unit 120 may have a touch panel integrated with the display unit 130 , and this touch panel may function as an input interface between the user and the server 100 . An operation signal according to a user's operation is output from the operation unit 120 to the processing unit.

The display unit 130 is a display device including an LCD or the like, and performs various displays based on display signals output from the processing unit 110 . The display unit 130 may be integrated with a touch panel to form a touch screen.

The sound output unit 140 is a sound output device including a speaker or the like, and performs various sound outputs based on sound output signals output from the processing unit 110 .

The communication unit 150 is a communication device for transmitting and receiving information used inside the device to and from an external device. As a communication method of the communication unit 150, there is a method of connecting via a cable conforming to a predetermined communication standard, a method of connecting via an intermediate device that is also used as a charger called a cradle, and a method of connecting wirelessly using wireless communication. Various methods such as a form of connection can be applied.

The clock unit 160 is an internal clock of the server 100 and outputs time information (timekeeping information). The clock unit 160 includes, for example, a clock using a crystal oscillator.
Note that the clock unit 160 may be configured with a clock to which the NITZ (Network Identity and Time Zone) standard or the like is applied.

The storage unit 190 is a storage device including a volatile or nonvolatile memory such as a ROM, EEPROM, flash memory, and RAM, a hard disk device, and the like.

In this embodiment, the storage unit 190 includes, for example, a driving score model processing program 191, a cigar socket type device measurement database 192, an ETC 2.0 measurement database 193, an estimated ETC 2.0 measurement database 194, a first driving Score model data 195 and learned second driving score model data 196 are stored.

The driving score model processing program 191 is a program that is read by the processing unit 110 and executed as driving score model processing, which will be described later.

The cigarette lighter device measurement database 192 is, for example, a database in which cigarette lighter device measurement data including travel information measured by a cigarette lighter device mounted on a vehicle is accumulated and stored.
The cigar socket type device is a type of first device, and the cigar socket type device measurement data can be a type of first measurement data (first device measurement data).

Note that the processing unit 110 may add, for example, at least one of the following information (attribute information) in addition to the information on the vehicle (moving body) as the first device measurement data, and perform processing.
・Vehicle information (model, year, model, etc.)
・Driver information (gender, age, address, usage, etc.)

A cigar socket device is a device that can be used by inserting it into a vehicle's accessory socket. It is possible to measure travel information (information about a moving body).

Note that the first device is not limited to a cigar socket type device. Any device that is directly or indirectly provided on a mobile object that can acquire information about the mobile object may be used. For example, the first device may be at least one of the following devices.
・Drive recorder ・Digital tachograph
・Any on-vehicle device installed in or built into a vehicle (connected cars may be included)
・In-vehicle device with a communication function (for example, Bluetooth (registered trademark) communication function) that collects data in cooperation with a terminal such as a smartphone and its terminal ・Single device including a terminal such as a smartphone ・In-vehicle and Devices including terminals such as retrofitted in-vehicle equipment or smartphones

The travel information can include, for example, information such as position, speed, acceleration, and angular velocity, and any sensor or the like capable of measuring these information can be provided in the cigarette lighter device. At least any one of these information may be configured to be measurable.

The travel information measured by the cigarette lighter device can be transmitted to the server 100 or the cloud server, for example, at any time or at regular intervals.

In addition, the position is calculated using a satellite positioning unit (satellite positioning sensor), which is a unit (sensor) that detects position and speed by a satellite positioning system such as GPS (Global Positioning System), or UWB (Ultra Wide Band). A UWB positioning unit (UWB positioning sensor) or the like, which is a unit (sensor) for this purpose, may be provided in the cigar socket type device.

The satellite positioning unit includes, for example, an RF receiving circuit that converts an RF (Radio Frequency) signal including a positioning satellite signal transmitted from a positioning satellite received by an antenna (not shown) into a digital signal, and an RF receiving circuit. A baseband processing circuit that captures positioning satellite signals by performing correlation calculation processing, etc. on the output digital signal, and outputs information such as satellite orbit data and time data extracted from the positioning satellite signals as positioning information. etc. Note that information such as velocity may be detected in addition to position by Doppler positioning or the like.

The inertial measurement unit (IMU) can have, for example, inertial sensors that detect information necessary to calculate travel information by inertial navigation calculations. The inertial sensor may include, for example, a triaxial acceleration sensor or a triaxial gyro sensor, and may output acceleration detected by the acceleration sensor or angular velocity detected by the gyro sensor.

The UWB positioning unit includes, for example, an ultra-wideband RF receiving circuit that converts an ultra-wideband RF signal including an ultra-wideband pulse signal for positioning transmitted from a positioning beacon received by an antenna (not shown) into a digital signal, an ultra-wideband It is possible to have a relative position calculation processing circuit or the like for calculating the relative position between the device itself and the positioning beacon based on the digital signal output from the RF receiving circuit.
In addition, the UWB positioning unit may function as a positioning beacon by transmitting an ultra-wideband RF signal including an ultra-wideband pulse signal for positioning from an antenna (not shown). may

The cigar socket type device measurement database 192 can store, for example, measurement data of a plurality of drivers for each measurement period. That is, it is possible to store the measurement data of a plurality of drivers in association with the measurement period.
The measurement period may be, for example, a period of months (one month, two months, . . . , six months, etc.), or may be a period of other units. Further, for example, the measurement data may be stored by classifying it by road type or region.

The ETC 2.0 measurement database 193 is measured by, for example, an ETC 2.0 vehicle-mounted device (ETC 2.0-compatible vehicle-mounted device, DSRC-compatible vehicle-mounted device) or an ETC 2.0-compatible car navigation device that can be linked with this. This is a database in which ETC2.0 measurement data including travel information is accumulated and stored.
The ETC2.0 vehicle-mounted device is a type of first device, and the ETC2.0 measurement data can be a type of second measurement data (second device measurement data).

The ETC2.0 measurement data is collected from the probe information recorded in the ETC2.0 vehicle-mounted device, which is installed (deployed) on the road, such as an ITS spot and a route information collection device (hereinafter collectively referred to as "roadside device"). .) can be obtained by the server 100.

The roadside units are installed, for example, in thousands of places on expressways and national highways all over the country.
The roadside device and the ETC 2.0 on-board device are configured to be capable of two-way communication, for example, and the roadside device collects probe information from the ETC on-board device, as well as information on route guidance according to road conditions, obstacles ahead, etc. Information that supports safe driving, such as information on roads, information on accident-prone locations, etc., can be provided from the roadside device to the ETC 2.0 vehicle-mounted device.

The ETC 2.0 vehicle-mounted device also has, for example, the various sensors and units described above, and can measure and record various types of travel information.
Then, when a vehicle equipped with an ETC 2.0 vehicle-mounted device passes by the roadside device, the probe information can be transmitted to the server 100 or the probe server via the roadside device.
Various sensors and units are installed in the ETC2.0 compatible car navigation device, etc., and based on the information output (transmitted) from the ETC2.0 compatible car navigation device, various driving information is sent to the ETC2.0 in-vehicle device. It may be recorded.

Here, the probe information can include, for example, the following information.
・Basic information ・Driving history information ・Behavior history information

The basic information can include, for example, information about the ETC2.0 vehicle-mounted device, information about the ETC2.0 compatible car navigation device, information about the vehicle, and the like.

The travel history information can include, for example, time information, position information, speed information, and the like.
For example, this travel history information can be recorded (accumulated) each time it is detected that the vehicle has traveled "200 m." In addition, for example, it may be recorded when the traveling direction of the vehicle changes by "45 degrees" or more.
Although the value "200m" is based on the ETC 2.0 specification, the value is not limited to this, and may be, for example, "100m". Similarly, "45 degrees" may be set to, for example, "22.5 degrees". A distance such as "200 m" based on this ETC2.0 specification is referred to as a "unit distance" for the sake of convenience.
As will be described later, it is conceivable to change the unit distance depending on the road type and speed zone.

The behavior history information can include information such as time information, position information, azimuth information, acceleration information (information such as longitudinal acceleration and lateral acceleration), and angular velocity information (eg, yaw angular velocity information).
This behavior history information is, for example, any of the longitudinal acceleration, the lateral acceleration, and the yaw angular velocity as a threshold (for example, the longitudinal acceleration threshold "-0.25 G", the lateral acceleration threshold "±0.25 G", the yaw angular velocity threshold "±8.5 deg/sec", etc. These thresholds are examples.) can be recorded (accumulated). For example, a longitudinal acceleration of "0.25 G" or more indicates a sudden behavior, which may indicate that an action such as crisis avoidance was performed.

Note that the travel history information and the behavior history information may include road type information (highway, urban expressway, general road, other information, speed zone information, etc.).

Further, among the above information, for example, at least one of the travel history information and the behavior history information may be used as the travel information.

In addition, in ETC 2.0, from the viewpoint of personal information protection, for example, a travel start point (for example, within a range of 500 m from the travel start point) and a travel end point (for example, within a range of 500 m from the travel end point) Information (eg, at least travel history information) may not be obtained.
Note that not being acquired may be not recorded in the ETC 2.0 vehicle-mounted device, or may not be transmitted to the roadside device.

The estimated ETC2.0 measurement database 194 is a database in which estimated ETC2.0 measurement data generated based on cigarette lighter type device measurement data is stored in an accumulative manner.
The estimated ETC2.0 measurement data can be a type of estimated data (estimated second device measurement data).

The first driving score model data 195 is data of the first driving score model that is the base of the driving score used to determine the insurance premium of the vehicle.

The learned second driving score model data 196 is driving score model data generated by learning using estimated ETC 2.0 measurement data or the like.

Here, the driving score model can be, for example, a mathematical model for calculating the driving score for telematics insurance.
In telematics insurance, for example, insurance companies acquire driving information measured by devices installed in vehicles (automobiles, etc.), driving speed, braking, etc., and analyze the driver's accident risk from that information. The insurance premium can be calculated by

The driving score model is, for example, a model that can estimate the risk of a driver's accident (accident risk). It can be a calculated model. For example, a model can be used in which the greater the driving score is, the higher the accident risk is estimated to be (the smaller the driving score is, the lower the accident risk is estimated to be). In this case, the insurance company can increase the insurance premium for a higher driving score and lower the insurance premium for a lower driving score.
Conversely, a model may be used in which the higher the driving score is, the lower the accident risk is estimated to be.

Also, the input to the driving score model can be the measured data of the driving information, and the driving score can be calculated based on the measured data of the driving information.
In this embodiment, for example, based on an existing first driving score model, a learned second driving score model is generated by a technique described below.
By inputting the driver's actual ETC 2.0 measurement data into the learned second driving score model, the driver's driving score can be calculated.

Note that the cloud server may be the server 100 .
Further, when the server 100 is separate from the cloud server, the server 100 may acquire the cigar socket type device measurement data from the cloud server.
The server that performs the processing described below may acquire and store data similar to the data stored in the storage unit 190 of the server 100 .

Similarly, the probe server may be server 100 .
Also, when the server 100 is separate from the probe server, the server 100 may acquire the ETC2.0 measurement data from the probe server.
The server that performs the processing described below may acquire and store data similar to the data stored in the storage unit 190 of the server 100 .

<Principle>
FIG. 5 is a diagram for explaining the principle of learning and inference using estimated ETC2.0 measurement data in this embodiment, and corresponds to FIG.

(1) At the time of learning As shown in FIG. and a generating unit 115 as functional units.
The ETC2.0 measurement data estimation unit 111 can be a kind of the second apparatus measurement data estimation unit 11 in FIG. 2(1).
The first driving score model processing unit 113 can be a kind of the first model processing unit 13 of FIG. 2(1).
The second driving score model generator 115 can be a type of the second model generator 15 in FIG. 2(1).

6 and 7 are diagrams showing an example of a technique for generating estimated ETC2.0 measurement data.
In FIG. 6, the left side of the drawing shows the time change of the measured position of the vehicle measured by the cigarette lighter device every second (hereinafter referred to as "cigarette lighter device measured position"). In addition, it shows the time change of the measurement position contained in one certain cigar socket type device measurement data.
Moreover, the time change of the estimated ETC2.0 measurement position which is selected from the cigarette lighter type device measurement position and becomes the data element of the estimated ETC2.0 measurement data is shown on the right side of the drawing. Each hatched rectangle is an estimated ETC2.0 measurement position.
Here, as an example, a method of generating estimated ETC2.0 measurement data based on position information included in travel information is illustrated.

Further, this cigar socket type device measurement data is represented as "D1", and the cigar socket type device measurement position included in the cigar socket type device measurement data "D1" is represented as "D1 (p(t))" (t: time). .
Also, the estimated ETC2.0 measurement data is denoted as "D2", and the estimated ETC2.0 measurement position included in this estimated ETC2.0 measurement data is denoted as "D2(p(t))" (t: time).

Here, as an example, the measurement position is represented as two-dimensional position information excluding the altitude direction (height direction) (a bird's-eye view of the measurement position). It should be noted that the same can be applied to three-dimensional position information.
Also, the illustrated measurement positions are merely for convenience of explanation and are not necessarily accurate.

From the viewpoint of personal information protection of ETC 2.0 described above, the processing unit 110, for example, among the cigar socket type device measurement positions, the travel information within the range of "500 m" from the travel start point and the travel information within the range of "500 m" from the travel end point. ” is excluded from the processing targets. Alternatively, if the travel information within these ranges is included in the measurement data, it is deleted.

Next, the processing unit 110 selects, for example, the first cigar socket type device measurement position D1 (p(1)) outside the range of 500 m from the travel start point, and selects this as the first estimated ETC 2.0 measurement position D2. (p(1)). Also, for example, information such as velocity, acceleration, angular velocity, etc. of the cigar socket type device measurement data corresponding to the time is acquired.

Next, the processing unit 110 first deviates from a circle with a radius of 200 m based on the unit distance (hereinafter referred to as a “unit circle” for convenience) centered at the cigar socket type device measurement position P11. Then, the cigar socket type device measurement position D1 (p(q)) is selected, and this is set as the second estimated ETC2.0 measurement position D2 (p(2)). Also, for example, information such as velocity, acceleration, angular velocity, etc. of the cigar socket type device measurement data corresponding to the time is acquired.

Hereinafter, the processing unit 110 repeats this, and the cigar socket type device measurement position [D1 (p (1)), D1 (p (q)), D1 (p (r)), D1 (p (s)), · ] is selected, the estimated ETC2.0 measurement positions [D2(p(1)), D2(p(2)), D2(p(3)), D2(p(4)), . ] is obtained. Information such as velocity, acceleration, angular velocity, etc. can be similarly obtained.
Then, the data in which the travel information is associated with the time can be used as the estimated ETC2.0 measurement data.

Thus, basically, based on the ETC2.0 specification, it is possible to acquire the travel information as the estimated ETC2.0 measured data from the cigar socket type device measured data based on the unit distance.

Here, an example is shown in which the processing unit 110 performs processing with the unit distance set to "200m". may

Also, the processing unit 110 may perform processing by changing the unit distance depending on the road type or speed band. For example, if the road type is "highway", the unit distance may be longer than that of the road type "general road" because relatively stable driving may be performed although the vehicle is traveling at high speed. Conversely, considering the risk of high-speed driving, the unit distance may be shorter than the road type "general road".
Similarly, for speed zones, the higher the speed zone, the longer (or shorter) the unit distance.
The road type and speed zone can be specified from road type information, for example.

Also, here, the estimated ETC 2.0 measurement data is generated by selecting the travel information included in the cigarette lighter device measurement data based on the distance (unit distance), but the present invention is not limited to this.
Alternatively or additionally, the estimated ETC 2.0 measurement data may be generated by selecting travel information included in the cigarette lighter device measurement data based on time. Specifically, for example, the time required to travel a unit distance is calculated based on the speed information included in the cigar socket type device measurement data, and the travel information for the corresponding time is selected based on the calculated time. Estimated ETC 2.0 measurement data may be generated by proceeding.
Alternatively, assuming that the vehicle travels at a constant speed (eg, 60 km/h), the estimated ETC 2.0 measurement data may be similarly generated by calculating the time required to travel a unit distance. good.

Here, in ETC 2.0, as described above, there is a specification such that travel information is recorded when, for example, the traveling direction of the vehicle changes by "45 degrees" or more. Therefore, the travel information may be obtained by additionally applying at least one of the conditions exemplified below.
However, it is not absolutely necessary to apply these conditions.

FIG. 7(1) shows, as condition A, a condition relating to a change in the traveling direction (traveling azimuth) of the vehicle.
In this example, the cigar socket type device measurement position D1 (p (u)) is the most recent cigar socket type device measurement position or the average position of a plurality of cigar socket type device measurement positions that are the most recent past with respect to the threshold angle or more. (or greater than the threshold angle) indicates that the cigarette lighter device measurement position D1(p(u)) is selected as the estimated ETC2.0 measurement position. This corresponds to, for example, a case where the traveling direction of the vehicle changes significantly. A value such as "45 degrees" can be set as the threshold angle.

Here, an example in which the processing unit 110 performs processing with the threshold angle set to "45 degrees" is shown. may be performed.

FIG. 7(2) shows, as condition B, a condition based on the traveling distance of the vehicle.
In this example, the cigar socket type device measurement position D1 (p (n)) that first deviated from the unit circle is the cigar socket type device measurement position D1 (p ( m))), it indicates that the cigar socket type device measurement position D1(p(n)) is not selected when the distance is greater than or equal to the threshold distance (or more than the threshold distance). The threshold distance is based on the speed of the vehicle calculated based on the cigar socket type device measurement data and the speed of the vehicle determined in advance (e.g., 60 km/h), and the vehicle advances from the previously selected point. It is possible to set a value that is difficult to assume as the distance.

That is, a distance margin is provided, and if the distance margin is met, the travel information is selected, but if the distance margin is not met, the travel information is not selected.

In this case, for example, the measurement position D1(p(n-1)) immediately before the measurement position D1(p(n)) may be selected as the estimated ETC2.0 measurement position.
Also, for example, the next measurement position D1(p(n+1)) after the measurement position D1(p(n)) may be selected as the estimated ETC2.0 measurement position.

Further, for example, an average (which may be an arithmetic average or a weighted average) of the measured position D1(p(n)) and the measured position D1(p(m)) is calculated, and the calculated position is the estimated ETC2 0 measurement position may be used.

Further, regarding the condition of FIG. 7(2), a time margin may be provided instead of the distance margin, and similar processing may be performed.

Also, in the ETC 2.0 specification, as described above, a peak value is recorded when any of the longitudinal acceleration, lateral acceleration, and yaw angular velocity exceeds the threshold. A condition for reproducing this may be set, and the travel information may be selected based on the acceleration information and angular velocity information included in the cigar socket type device measurement data.

In the above, the method of generating estimated ETC 2.0 measurement data based on position information was exemplified. You may make it generate|occur|produce measurement data similarly.

Mathematically, it can be said that the estimated ETC 2.0 measurement data generated as described above is included in the cigarette lighter type device measurement data.
By generating a driving score model using the estimated ETC 2.0 measurement data generated in this way, a highly valid driving score model can be generated.

Returning to FIG. 5, the first driving score model processing unit 113 calculates a driving score using, for example, cigar socket type device measurement data as an input to the first driving score model.

The second driving score model generation unit 115 generates, for example, the estimated ETC2.0 measurement data estimated by the ETC2.0 measurement data estimation unit 111 and the driving score (teacher driving score) calculated by the first driving score model processing unit 113. score) and a learning data set, for example, by performing learning (for example, supervised learning) on the first driving score model, a second driving score model is generated. The one that has completed learning becomes the learned second driving score model.

(2) Inference As shown in FIG. 5(2), the processing unit 110 of the server 100 has, for example, a learned second driving score model processing unit 117 as a functional unit.
The learned second driving score model processing unit 117 can be a kind of the learned second model processing unit 17 in FIG. 2(2).

The second learned driving score model processing unit 117 calculates a driving score using, for example, the ETC2.0 measurement data stored in the ECT2.0 measurement database 194 as input to the second learned driving score model.
That is, the learned second driving score model processing unit 117 receives as input the ETC2.0 measurement data measured by the ETC2.0 vehicle-mounted device actually installed in the vehicle, and drives using the learned second driving score model. A score is inferred, and a driving score inference result, which is the inference result, is output.

The first driving score model can be, for example, an existing driving score model.
Here, the cigar socket type device measurement data input to the first driving score model processing unit 113 includes measured driving information such as vehicle position, acceleration (speed when integrated over time), and angular velocity (direction when integrated over time). contains information For this reason, the cigar socket type device measurement data reflects the driver's driving situation, and the driving score calculated by the first driving score model processing unit 113 can be a value that reflects the driver's driving situation. have a nature. This can be used for learning as teacher data.

In addition, as explained in the principle of the embodiment, in addition to this, for example, estimated ETC 2.0 measurement data is used as input data to the first driving score model, and various types of devices including cigar socket type devices accumulated from the past Some data held in the past corresponding to the first device measurement data measured by the first device may be used as training data to generate the second driving score model by machine learning or the like. .
The training data in this case is merely an example, but may be data related to vehicle accidents (data such as the presence or absence of accidents, the number of accidents (frequency, ratio), etc.).

<Processing>
FIG. 8 is a flowchart showing an example of the flow of driving score model processing executed by the processing unit 110 of the server 100 in this embodiment.
First, the processing unit 110 of the server 100 performs learning data set generation processing.
In the learning data set generation process, the processing unit 110 performs loop B processing on the cigar socket type device measurement data to be processed (S1 to S7).
The cigar socket type device measurement data to be processed is, for example, among the cigar socket type device measurement data stored in the cigar socket type device measurement database 192, under similar conditions (for example, the same measurement period, the same road type, the same measured locally, etc.). However, it is not limited to this.

In the processing of loop B, the processing unit 110 generates estimated ETC2.0 measurement data based on the cigar socket type device measurement data (S3). Then, the processing unit 110 associates the generated estimated ETC 2.0 measurement data with the cigar socket type device measurement data (for example, with the identification information (data number etc.) of the cigar socket type device measurement data), Store in estimated ETC 2.0 measurement database 194 .
Further, the processing unit 110 calculates a teacher driving score based on the cigar socket type device measurement data and the first driving score model (S5). Then, the processing unit 110 causes the storage unit 190 to store the calculated teacher driving score in association with the cigar socket type device measurement data.
Then, the processing unit 110 shifts the processing to the next cigar socket type device measurement data.

When the processing of S3 and S5 has been performed for all the cigar socket type device measurement data to be processed, the processing unit 110 ends the processing of loop B (S7).

Thereafter, the processing unit 110 performs learning processing (S9). Specifically, each estimated ETC 2.0 measurement data stored in the estimated ETC 2.0 measurement database 194 and the teacher driving score corresponding to each of them (the identification information of the cigar socket type device measurement data is the same) to generate a trained second driving score model.

Next, the processing unit 110 performs inference processing (S11). Specifically, the learned second driving score model generated in S9, the ETC2.0 measurement data to be processed (for example, each ETC2.0 measurement data stored in the ETC2.0 measurement data), and A second driving score is calculated based on. Then, the calculation result is used as the inference result of various quantities.
Then, the processing unit 110 ends the processing.

It should be noted that the step of S11 may be omitted and the processing up to the generation of the second driving score model may be performed.
Alternatively, only step S3 may be performed, and processing may be performed up to the generation of estimated ETC 2.0 measurement data based on the cigar socket type device measurement data.

In addition, the processing unit 110 may cause the display unit 130 to display the calculated value of the second driving score (inference result).
In addition to or instead of displaying the calculated second driving score value itself on the display unit 130, the processing unit 110 classifies the driver based on the calculated second driving score value. Information such as rank (information having an order relationship) may be displayed on the display unit 130 . Specifically, for example, the following rank information may be displayed on the display unit 130 .
・ In descending order of rank "5 stars, 4 stars, 3 stars, 2 stars, 1 star"
・ "◎, 〇, △, ×" in descending order of rank
・ "A (A rating), B (B rating), C (C rating)" in descending order of rank
・Gold, Silver, Bronze in descending order of rank

In addition, for example, when the insurance company that has acquired these information from the server 100 presents the calculated insurance premium to the customer, it may also present information on the value and rank of the customer's second driving score. good too.

In addition, the processing unit 110 estimates in which direction and how much G is applied by the driver's acceleration/deceleration, left and right handling operations, etc. based on the cigar socket type device measurement data, and visualizes it graphically. may be displayed on the display unit 130.

<Effect of the first embodiment>
In this embodiment, as described above, the estimated ETC2.0 measurement data is generated by selecting the travel information from the cigar socket type device measurement data based on, for example, the unit distance or the unit time.
In this case, it is conceivable that the above-described information such as rapid deceleration and sudden acceleration is not necessarily reflected accurately in the estimated ETC2.0 measurement data (so-called near-miss incidents and the like are reflected).
However, the inventor of the present application believes that if the estimated ETC 2.0 measurement data generated as described above is used, the driver's general driving tendency (such as a tendency to drive safely or a tendency to drive dangerously) is reflected. As a result, it was found that a highly valid driving score model can be generated.

In the present embodiment, the server 100 (an example of an information processing device) is a cigar socket device measurement data (first measurement data) including travel information measured by a device such as a cigarette lighter device (an example of a first device). An example) is estimated data of ETC2.0 measurement data (an example of second measurement data) measured by a device such as an ETC2.0 vehicle-mounted device (an example of a second device different from the first device) A processing unit 110 for generating ETC2.0 measurement data is provided.
As a result, based on the first measurement data measured by the first device for measuring information about the moving body, the second device that measures the information about the moving body and that is different from the first device measures the second data. 2 estimated data of the measured data can be generated.

Also, in this case, even if the sampling unit for measuring data is different between a device such as a cigar socket type device (an example of the first device) and the ETC 2.0 vehicle-mounted device (an example of the second device) good.
Thereby, the second measurement is performed by the second device that measures the information on the moving object based on the first measurement data obtained by measuring the information on the moving object by the first device out of the two devices with different sampling units. It is possible to generate estimated data for the data.

Also, in this case, even if the sampling unit of a device such as a cigar socket type device (an example of the first device) is time, and the sampling unit of the ETC 2.0 vehicle-mounted device (an example of the second device) is distance. good.
Accordingly, based on the first measurement data obtained by measuring the information on the moving body by the first device whose sampling unit is time, the second device measuring the information on the moving body measures the distance by the sampling unit. 2, it is possible to generate estimated data of measured data.

Also, in this case, a device such as a cigar socket type device (an example of the first device) measures at predetermined time intervals, and an ETC 2.0 vehicle-mounted device (an example of the second device) measures at predetermined distance intervals. good.
Thereby, based on the first measurement data measured by the first device that measures the information about the moving object at predetermined time intervals, the second measurement data that is measured by the second device that measures the information about the moving object at predetermined distance intervals is obtained. Estimated data of the measured data can be generated.

In addition, a device such as a cigar socket type device (an example of the first device) measures at predetermined time intervals, an ETC 2.0 vehicle-mounted device (an example of the second device) measures at predetermined distance intervals, and the processing unit 110 of the server 100 Estimated ETC 2.0 measurement data (an example of estimated data) based on the cigarette lighter type device measurement data (an example of the first measurement data), a predetermined distance interval measured by the ETC 2.0 on-board device, and a predetermined condition may be generated.
This makes it possible to appropriately generate estimated data based on the first measurement data, the predetermined distance interval, and the predetermined conditions.

Also, in this case, the predetermined condition may include at least a condition regarding a change in the direction of the moving object based on the position included in the cigarette lighter device measurement data (an example of the first measurement data).
This makes it possible to generate estimated data that takes into account (reflects) a change in the direction of the moving object based on the position included in the first measurement data.

Also, the processing unit 110 of the server 100 may generate a model for calculating various quantities based on estimated ETC2.0 measurement data (an example of estimated data).
Accordingly, a model for calculating various quantities can be appropriately generated based on the estimated data.

In this case, the processing unit 110 of the server 100 may generate a model such as a driving score model by machine learning using at least estimated ETC 2.0 measurement data (an example of estimated data) as learning data. .
Accordingly, a model capable of appropriately calculating various quantities can be generated based on the estimated data.

Also, in this case, the processing unit 110 of the server 100 may calculate various quantities such as the driving score based on the ETC 2.0 measurement data and the generated model such as the driving score model.
Accordingly, various quantities can be appropriately calculated based on the second measurement data and the generated model.

Also, in this case, the cigar socket type device (an example of the first device) and the ETC 2.0 vehicle-mounted device (an example of the second device) measure travel information, and various quantities are The driving score for insurance, and the model may be a second driving score model for calculating the driving score based on the ETC 2.0 measurement data.
Thereby, a model for calculating the driving score can be generated based on the second measurement data.

Also, in this case, the processing unit 110 of the server 100 generates a driving score (first measurement data The second driving score model may be generated by machine learning using (an example of information based on) as learning data.
This makes it possible to generate a model with high validity for calculating the driving score based on the second measurement data.

<Modification (1)>
In the above embodiment, the same processing may be performed by reversing the first device and the second device.

Specifically, for example,
- 1st apparatus: ETC2.0 vehicle-mounted equipment - 2nd apparatus: Cigarette-socket type device You may make it presume a cigar-socket type device measurement data based on ETC2.0 measurement data.

That is, including the above embodiment, the sampling unit of one of the first device and the second device may be time, and the sampling unit of the other may be distance. Also, one of the first device and the second device may measure at predetermined time intervals, and the other may measure at predetermined distance intervals.

<Modification (2)>
In the above embodiment, the estimated ETC2.0 measurement data is generated based on the travel information of the time-series discrete cigarette lighter device measurement data, but the present invention is not limited to this.
A continuous function approximating the running information included in the cigarette lighter type device measurement data may be calculated, and the estimated ETC2.0 measurement data may be generated based on the calculated function.

For example, based on the time-series two-dimensional position information included in the cigarette lighter type device measurement data, the two-dimensional position (X, Y) function "(X, Y) = f (t)".
Then, for example, the time required to travel a unit distance is calculated from the speed information included in the cigar socket type device measurement data, and based on the calculated time, the position information at the corresponding time “t” is converted to the function “(X , Y)=f(t)” to generate the estimated ETC2.0 measurement data.
It should be noted that the same can be applied to three-dimensional position information.

Assuming that the vehicle travels at a constant speed (for example, 60 km/h), the function "(X, Y) = f(t)" is similarly calculated by calculating the time required to travel a unit distance. may be used to generate estimated ETC 2.0 measurement data.

<Modification (3)>
In the above embodiment, the second driving score model generation unit 115 generates the driving score model by learning using at least the estimated ETC 2.0 measurement data and the ETC 2.0 measurement data as learning data. good too.

Specifically, for example, driving score for teacher and ETC2.0 measurement data are used as teacher data, and in addition to these, estimated ETC2.0 measurement data is set as learning data by performing supervised learning. A score model may be generated.

In this modification, the processing unit 110 of the server 100 uses at least estimated ETC2.0 measurement data (eg, an example of estimation data) and ETC2.0 measurement data (eg, an example of second measurement data) for learning. Generate a model by machine learning with data.
This makes it possible to generate a more accurate model.

<Modification (4)>
Validity of estimation of ETC2.0 measurement data described in the above embodiment may be verified.
Specifically, for example, under the same conditions, ETC2.0 measurement data acquired by having the driver drive a vehicle equipped with an ETC2.0 on-board device, and estimated ETC2.0 generated as in the above example Acquire measurement data. Then, the processing unit 110 of the server 100 calculates a value (correlation value) indicating the correlation of these measurement data. is determined to be present), it may be determined that the estimation of the ETC2.0 measurement data is appropriate.
In this case, by performing the above processing on a certain amount of data, the validity can be verified more appropriately.

Also, the validity of the driving score model generated as in the above embodiment may be verified.
Specifically, similarly to the above, for example, under the same conditions, the ETC 2.0 measurement data acquired by having the driver drive the vehicle equipped with the ETC 2.0 on-board device, and the ETC 2.0 measurement data generated as in the above example Obtain the estimated ETC2.0 measurement data. Then, the processing unit 110 of the server 100 calculates the driving score obtained by inputting the ETC2.0 measurement data into the driving score model and the driving score obtained by inputting the estimated ETC2.0 measurement data into the driving score model. scores, and if the difference between these driving scores is less than (or less than) a predetermined threshold, the driving score model may be determined to be valid.
In this case, by performing the above processing on a certain amount of data, the validity can be verified more appropriately.

<Modification (5)>
Although the user has made a car insurance contract with an insurance company, during the contract period, the device mounted on the car is switched from the first device (eg, cigar socket type device) to the second device (eg, cigar socket type device). ETC 2.0 in-vehicle equipment) may be changed (switched).

Therefore, the processing unit 110 of the server 100, for example, during the contract period of automobile insurance (the period from the insurance start date to the end date (maturity date)), the device mounted on the automobile (used for measuring measurement data) When the first device is changed to the second device, at least the measurement data of the first device in the first period from the start of the contract period to the device change (for example, the first device measured from the insurance start date to the device change date Estimated data based on device measurement data) and measurement data of the second device in the second period from the device change to the end of the contract period (for example, measured from the device change date to the driving score calculation date (continuation procedure date) The driving score in the case of continuing the car insurance may be calculated based on the second device measurement data).

In this case, the driving score may be calculated by any of the following methods, for example.
・Learn the first score value calculated by inputting the estimated data (e.g., estimated ETC2.0 measurement data) into the learned second driving score model and the second device measurement data (e.g., ETC2.0 measurement data) It is calculated by, for example, averaging the second score value calculated by inputting it into the second driving score model.
Input data obtained by integrating estimated data (eg, estimated ETC2.0 measurement data) and second device measurement data (eg, ETC2.0 measurement data) into the learned second driving score model for calculation.

Instead of the estimated data based on the first device measurement data in the first period from the start of the contract period to the device change, the first device measurement data in the first period from the start of the contract period to the device change will be used. may In this case, the driving score may be calculated by, for example, the following method.
・The first score value calculated by inputting the first device measurement data (for example, cigar socket type device measurement data) into the first driving score model and the second device measurement data (for example, ETC 2.0 measurement data) It is calculated by, for example, averaging the second score value calculated by inputting it into the learned second driving score model.

<Second embodiment>
In the first embodiment, for example, an embodiment related to an insurance product such as telematics insurance has been described. However, when developing a service based on ETC 2.0, including telematics insurance product services, it is important to consider how many people can use the service, the size of the market, and whether it can be provided fairly nationwide. It is necessary to evaluate whether it is a good service or not. The second example is an example related to this evaluation.
It should be noted that the content described in the second embodiment can be applied to each of the other embodiments and other modifications.

<Data structure>
FIG. 9 is a diagram showing an example of information stored in the storage unit 190 of the server 100 in this embodiment.
The storage unit 190 stores, for example, an ETC2.0 service evaluation support processing program 197 that is read by the processing unit 110 and executed as the ETC2.0 service evaluation support processing, the above-described cigar socket type device measurement database 192, A roadside unit information database 198 and a created histogram database 199 are stored.

As described above, the cigar socket type device measurement database 192 can store measurement data of a plurality of drivers for each measurement period, for example. The measurement period may be, for example, a period of months (one month, two months, . . . , six months, etc.), or may be a period of other units. Further, for example, the data may be classified and stored according to road type, region, or the like.

The roadside device information database 198 is a database that stores information including, for example, location information of roadside devices nationwide.

The created histogram database 199 is a database that stores histogram data created by the processing unit 110 in order to evaluate a service based on ETC 2.0, which will be described later.

Note that the estimated ETC 2.0 measurement database 194 and the like described above may be stored in the storage unit 190 .

<Specifications of ETC2.0 on-board device>
In ETC2.0, as described above, for example, probe information including traveling information is collected from the ETC2.0 vehicle-mounted device by the roadside device.
On the other hand, the ETC 2.0 vehicle-mounted device may only be able to record driving information for a predetermined distance, such as a maximum of "80km", and the driving information exceeding the predetermined distance will not be recorded. It may be discarded. For this reason, if a vehicle equipped with an ETC 2.0 vehicle-mounted device does not pass near the roadside device for a long time, the roadside device may not collect the travel information that has been recorded.

There is a possibility that the specification of ETC2.0 will be updated in the future.
For example, the aforementioned unit distance (for example, 200 m) may be changed, and in some cases, it may be necessary to increase the memory of the ETC 2.0 vehicle-mounted device.
However, the method of the present invention can cope with such changes in the ETC 2.0 specifications, and it is only necessary to adjust the values of various parameters.

<Processing>
FIG. 10 is a diagram showing an example of the flow of ETC2.0 service evaluation support processing performed by the processing unit 110 of the server 100 in this embodiment.
For example, the processing unit 110 performs the following processing on each cigar socket type device measurement data included in the cigar socket type device measurement database 192 .

First, the processing unit 110 performs the following processing on the travel information included in the cigar socket type device measurement data, for example, in chronological order from the oldest travel information.
The processing unit 110 determines whether or not the measured position of the vehicle included in the travel information is included in the area of the roadside device (new roadside device) (S21).

Here, the area in the vicinity of the roadside unit is called a "roadside unit area". The roadside unit area can be set, for example, as an area within a radius of 5 m or within a radius of 10 m from the position of the roadside unit.
Specifically, based on the position information of the roadside unit stored in the roadside unit information database 198, the processing unit 110 determines whether the measured position of the vehicle included in the travel information is included in the roadside unit area of the roadside unit. Determine whether or not

If it is determined to be included (S21: YES), the processing unit 110 determines whether or not the measured position of the vehicle exceeds "80 km" from the position of the previous roadside unit (S23).

If it is determined that it exceeds (S23), the processing unit 110 selects a set of traveling information within "80 km" traced back from the position of the roadside unit, among the traveling information included in the cigar socket type device measurement data. A transmission flag (collection flag) is set to "ON" (S25).

The transmission flag can be a flag that simulates transmission of travel information to the roadside device by a vehicle equipped with an ETC 2.0 vehicle-mounted device passing near the roadside device.
In this embodiment, in order to evaluate services based on ETC 2.0, using data measured by a cigar socket type device (acquired cigar socket type device measurement data), virtually ETC 2.0 in-vehicle It reproduces (simulates) the transmission of driving information (collection of driving information at the roadside unit) when a vehicle equipped with a device passes by the roadside unit.

For example, if the measured position of the vehicle included in the travel information is "100 km" away from the position of the previous roadside unit, according to the above-mentioned ETC 2.0 specifications, the position of the previous roadside unit Travel information for "20 km" exceeding "80 km" from the position will be discarded from the ETC 2.0 vehicle-mounted device. In order to reproduce this, in step S25, the transmission flag is set to "ON" for the set of travel information within "80 km" from the position of the roadside unit, excluding the portion exceeding "80 km".

On the other hand, if it is determined that it does not exceed "80 km" from the position of the previous roadside device (S23: NO), the processing unit 110 selects one A transmission flag is set to "ON" in the travel information set from the position of the previous roadside unit (S27).

After S25 or S27, the processing unit 110 determines whether or not to end the processing (S29), and if it determines to continue the processing (S29: NO), returns the processing to S1.
On the other hand, if it is determined to end the process (S29: YES), the processing unit 110 ends the ETC2.0 service evaluation support process.

<Setting the measurement period>
FIG. 11 is a diagram showing an example of a histogram for ETC2.0 service evaluation generated by the processing unit 110 of the server 100 based on the processing result of the above ETC2.0 service evaluation support processing in this embodiment. .

Based on the above processing result, for example, for each measurement period of the cigar socket type device measurement data, the processing unit 110 sets the horizontal axis (class) to the assumed collection time (h) at the roadside unit, and the vertical axis (frequency) to Create a histogram of the number of vehicles (vehicles).
The assumed collection time at the roadside unit can be derived from, for example, the traveling information (a set of traveling information) whose transmission flag is set to "ON", so that it is substantially possible to collect at the assumed roadside unit. It can be said that it is synonymous with the number of data generated. Therefore, the horizontal axis may be the assumed number of collected data.
Alternatively, the vertical axis may be the number of runs (times).

This figure shows an example of a histogram for a measurement period of "one month", and as an example, the horizontal axis shows the sections in which the estimated collection time at the roadside unit is divided by "1h" as classes. The vertical axis indicates the number of vehicles included in each section as a frequency. The sum of the number of vehicles in all sections is the total number of vehicles. Note that the values on the horizontal axis and the vertical axis are only examples, and the values are not limited to these.

FIG. 12 shows an example of a histogram similarly created for the measurement period of "2 months". The view of the figure is the same as in FIG.

For example, the processing unit 110 sets the threshold for the estimated collection time to "3 hours", and the ratio of the number of vehicles to the total number of vehicles whose estimated collection time exceeds the threshold "3 hours" (hereinafter referred to as "vehicle number ratio"). ) is calculated.
As a result of calculating the vehicle number ratio based on the histogram of the measurement period of "1 month" in FIG. 11, for example, it is calculated as "60%". is calculated as, for example, "80%".

For example, when the target value of the vehicle number ratio is set to "75%" when the threshold of the assumed collection time is "3 hours", the vehicle number ratio does not reach the target value during the measurement period of "1 month" in FIG. However, the ratio of the number of vehicles reaches the target value during the measurement period of "two months" in FIG.
Therefore, in this example, it can be determined that there is no problem even if the ETC 2.0 measurement data is reproduced by using the cigar socket type device measurement data whose measurement period is "two months".

As an actual process, the processing unit 110 of the server 100 updates the measurement period and creates a histogram in ascending order of the measurement period until the vehicle number ratio reaches the target value. Then, when the vehicle number ratio reaches the target value, the measurement period is set as the measurement period to be operated.
In this case, for example, only the set of cigar socket device measurement data for the set measurement period among the sets of cigar socket device measurement data for each measurement period stored in the cigar socket device measurement database 192 of the storage unit 190 , and sets of cigar socket type device measurement data for other measurement periods may be deleted.

Then, the processing unit 110 generates the estimated ETC 2.0 measurement data described in the first embodiment using, for example, a set of cigar socket type device measurement data for the set measurement period, and generates a driving score model. can be
By doing so, it is possible to create a telematics insurance product whose reliability is guaranteed.

Note that the following processing may be performed.
For example, when the processing unit 110 sets a period of "2 months" as the measurement period of the cigar socket type device measurement data, the driving score model is calculated using the cigar socket type device measurement data of the "2 months" measurement period. to generate Similarly, the processing unit 110 similarly generates a driving score model using the estimated ETC2.0 measurement data for this “two months” measurement period.
Then, the processing unit 110 determines whether or not similar results can be obtained when predetermined measurement data is input to these generated driving score models (for example, the difference between the models is equal to or less than a predetermined threshold (or less than the threshold) If the same result is obtained, the measurement period of ETC2.0 measurement data used for driving score calculation (used for driving evaluation) is set to "2 months" set.

On the other hand, if similar results are not obtained, the measurement period of ETC 2.0 measurement data used for driving score calculation (used for driving evaluation) may not be enough for "two months", so processing The unit 110 sets the measurement period of the ETC 2.0 measurement data used for calculating the driving score to a measurement period longer than "2 months" (for example, any period of "3 months" to "6 months"). may be set to

This is because, in the method of the present invention, the estimated ETC2.0 measurement data is generated by thinning out (resampling) the travel information of the cigarette lighter device measurement data. This is because it may not always be appropriate to apply the measurement period of the measurement data as it is.
Therefore, as described above, two driving score models are compared and verified, and based on the result of the comparison and verification, the measurement period of the ETC 2.0 measurement data used for calculating the driving score may be set (determined). good.

<Evaluation of insurance product business>
Using the histogram created by the server 100 as described above, it is also possible to evaluate the success or failure of an insurance product based on ETC 2.0 as a business.

When considering making an insurance product based on the driving information of ETC2.0, it is necessary to have a user actually drive a vehicle equipped with an ETC2.0 vehicle-mounted device and collect the measurement data. This has the problem of cost, as mentioned above, and if it turns out that it is not possible to collect sufficient driving information with the mechanism of ETC 2.0 in the first place, it will not be viable as an insurance product business in the first place. There is In other words, as described above, it is assumed that data loss occurs when a vehicle equipped with an ETC 2.0 vehicle-mounted device travels, for example, 80 km or more without passing near the roadside device. This cannot be known unless a demonstration experiment is conducted using a vehicle equipped with an ETC 2.0 vehicle-mounted device.

Therefore, for example, data collected by other means not based on ETC 2.0 (e.g. cigar socket type device measurement data) and roadside equipment included in the area covered by telematics insurance (e.g. metropolitan area etc.) Based on the location information, the estimated collection time is calculated for each vehicle. Then, for all target vehicles, how much travel information is virtually collected by the roadside unit (or conversely, how much travel information is discarded) is calculated using the above-mentioned histogram or the like. can be evaluated.

Specifically, the processing unit 110 of the server 100, for example, based on the cigar socket type device measurement data in a predetermined measurement period, for example, a histogram showing how much traveling information is collected per month, as shown in FIG. 11 and FIG. 12 are prepared.
Then, the processing unit 110 of the server 100 sets a threshold (for example, 7 hours or 10 hours) for the estimated collection time of the roadside unit, and determines the number of vehicles whose estimated collection time is equal to or greater than the threshold (or exceeds the threshold). ratio) is equal to or greater than a set value (or exceeds the set value), it can be determined that a general insurance product business is established.

In this case, for example, processing may be performed with a period of "one month" as the predetermined measurement period, or processing may be performed with a period of "two months" or "three months" as the predetermined measurement period. may In this case, the estimated collection time in a predetermined measurement period may be used as it is, or the estimated collection time per month may be used.
Alternatively, a histogram may be created from cigar socket type device measurement data in a plurality of different measurement periods, and the time calculated by averaging the assumed collection times in each measurement period may be used.

Also, instead of the estimated collection time, the estimated number of collected data items described above may be used.
Further, similar processing may be performed based on the number of data (assumed number of discarded data) and time (assumed discard time) indicating how much travel information has been virtually discarded without being collected by the roadside unit. This is the ratio (degree ) (data loss ratio information (data loss degree information)).

In addition, judging the success or failure of the above insurance product as a business is based on the above data loss ratio information, estimated ETC 2.0 measurement data (cigarette socket type device It can also be said to determine the effectiveness of pseudo ETC 2.0 measurement data generated based on the measurement data.

In this case, the server 100 may or may not actually generate the estimated ETC2.0 measurement data. That is, after generating the estimated ETC2.0 measurement data based on the cigar socket type device measurement data, the validity of the generated estimated ETC2.0 measurement data may be determined by the above method, or the estimated ETC2 0 measurement data is not generated, and the estimated ETC 2.0 measurement data is generated based on the cigarette lighter device measurement data, the effectiveness of the generated estimated ETC 2.0 measurement data is determined by the above method. You may do so.

Note that when it is determined that a general insurance product business is established, the processing unit 110 of the server 100 sets the measurement period based on the method described in <Setting the measurement period> above, and then sets the set measurement period. A set of cigar socket type device measurement data for a period may be used to generate the estimated ETC 2.0 measurement data described in the first embodiment to generate a driving score model.

Conversely, when the processing unit 110 of the server 100 determines that the general insurance product business is not viable, the processing unit 110 may perform any of the following.
・Do not generate estimated ETC2.0 measurement data ・Generate estimated ETC2.0 measurement data but do not use

In addition, in the above <setting of measurement period> and <evaluation of insurance product business>, the processing unit 110 of the server 100 uses the estimated ETC 2.0 measurement data instead of the cigar socket type device measurement data. may be evaluated.

<Effect of Second Embodiment>
In this embodiment, the server 100 transmits the ETC2.0 measurement data (an example of the second measurement data) to the roadside device (an example of the third device) installed at a predetermined position, and the ETC2.0 vehicle-mounted device (an example of the second device). example), and based on the cigar socket type device measurement data (an example of the first measurement data) and the position information of the roadside unit, it is determined whether or not to generate the estimated ETC 2.0 measurement data.
Accordingly, it is possible to appropriately determine whether or not to generate the estimated data of the second measurement data based on the first measurement data and the position information of the third device installed at the predetermined position.

In addition, in this embodiment, the server 100 transmits the ETC 2.0 measurement data (an example of the second measurement data) to the roadside device (an example of the third device) installed at a predetermined position, the ETC 2.0 vehicle-mounted device (the second device) and generated based on the cigarette lighter type device measurement data (an example of the first measurement data) and the location information of the roadside unit, whether to use the estimated ETC 2.0 measurement data judge.
Accordingly, it is possible to appropriately determine whether or not to use the estimated data of the second measurement data based on the first measurement data and the position information of the third device installed at the predetermined position.

In addition, in this embodiment, the server 100 transmits the ETC 2.0 measurement data (an example of the second measurement data) to the roadside device (an example of the third device) installed at a predetermined position, the ETC 2.0 vehicle-mounted device (the second device), based on the cigar socket type device measurement data (an example of the first measurement data) and the position information of the roadside unit, the cigarette lighter type device measurement data used to generate the ETC 2.0 measurement data Determine the measurement period.
Accordingly, the measurement period of the first measurement data used to generate the estimated data of the second measurement data can be appropriately determined based on the first measurement data and the position information of the third device installed at the predetermined position. can be done.

Further, in this embodiment, the server 100 is required for driving evaluation based on the ETC2.0 measurement data measured by the ETC2.0 vehicle-mounted device based on the cigarette lighter device measurement data measured by the cigarette lighter device. and a processing unit 110 for determining the measurement period of the cigar socket type device measurement data.
As a result, based on the first measurement data measured by the first device for measuring information about the moving body, the second device that measures the information about the moving body and that is different from the first device measures the second data. It is possible to appropriately determine the measurement period of the first measurement data necessary for evaluating driving based on the second measurement data.

Further, in this case, the server 100 measures ETC 2.0 measurement data necessary for evaluation of driving based on the ETC 2.0 measurement data based on the cigar socket type device measurement data for the measurement period determined as described above. determine the duration.
Thus, based on the first measurement data of the measurement period determined as described above, it is possible to appropriately determine the measurement period of the second measurement data, which is necessary for evaluating driving based on the second measurement data. can.

The server 100 also generates pseudo ETC 2.0 measurement data for a predetermined period based on the cigar socket type device measurement data, and acquires data loss ratio information in this pseudo ETC 2.0 measurement data. Then, the server 100 determines the validity of this pseudo ETC2.0 measurement data based on the acquired data loss ratio information.
Accordingly, the effectiveness of the pseudo second measurement data generated based on the first measurement data in the predetermined period can be appropriately determined based on the data loss ratio information.

<Modification>
In the above embodiment, the server 100 converts the cigar socket type device data and estimated ETC 2.0 measurement data measured with a leisure area etc. as a destination (for example, when it is located within the leisure area range for a predetermined time) Based on this, it may be determined whether or not the business of insurance products for leisure (leisure use) will be established by the same method as described in the above embodiment. Then, when it is determined to be established, the insurance company may provide a special insurance product for leisure.

Also, in this case, as described in the above embodiment, the server 100 determines that the product is established as a general insurance product by evaluation based on cigar socket type device measurement data and estimated ETC 2.0 measurement data in the metropolitan area and the like. If so, the insurance company will uniformly offer general insurance products determined to hold regardless of whether they are for leisure use or not.

On the other hand, when the server 100 determines that it is not established as a general insurance product by evaluation based on the measured data of the cigar socket type device such as the metropolitan area and the estimated ETC 2.0 measured data, the server 100 In this way, it may be determined whether or not the leisure insurance product business is viable. Then, when it is determined to be established, the insurance company may provide a special insurance product for leisure.

<Others>
The server 100 in the above embodiment is configured as a plurality of physically separated servers, a part of the processing described in the above embodiment is performed by the first server, and the other processing is performed by the second server. It is also possible to make it perform. It may be considered that a server system is composed of a plurality of servers.

Further, the mobile body is not limited to four-wheeled vehicles, and may be two-wheeled vehicles, personal mobility vehicles, ships, railroads, aircraft, etc., as described above. In this case, the same processing as in the above embodiment can be performed by using various measuring devices as the first device and the second device mounted on or built into the moving object.

Further, as described above, for example, the measurement target is set to "sound", the sampling unit of the first device is set to "time", and the sampling unit of the second device is set to "frequency", and the same processing as above is performed. may be performed.
Further, for example, the same processing as described above may be performed on biological information (blood pressure, pulse, heart rate, respiratory rate, body temperature, electroencephalogram, etc.). Also in this case, for example, the sampling unit of the first device may be "time" and the sampling unit of the second device may be "frequency", and the same processing as described above may be performed.

As an example of this application, while the insured user is driving a vehicle, the first device measures information about the user's biometrics. Then, the server 100, based on the first device measurement data obtained by measuring the information on the living body by the first device, estimates the second device measurement data when the information on the user's living body is measured by the second device. may be generated.
In this case, the running information of the vehicle driven by the user may be measured by a cigar socket type device or the like, and the server 100 may generate the above-described estimated ETC 2.0 measurement data. In other words, the insured user and the vehicle may be linked, and the server 100 may generate the estimated data of the biometric information together with the generation of the estimated ETC 2.0 measurement data. Then, the health condition of the user may be evaluated together with the evaluation of the user's driving (driving quality).
It should be noted that the estimated data of the user's biometric information may be generated not only at the time of driving but also at times other than driving.

In addition, the cigar socket type device measurement data and the ETC 2.0 measurement data are acquired from the vehicle equipped with the cigar socket type device measurement data and the ETC 2.0 vehicle-mounted device. Then, in the estimated ETC 2.0 measurement data generated based on the cigar socket type device measurement data, the ratio of how much data is lost to the actual ETC 2.0 measurement data is calculated. good too.
In addition, the score calculated by inputting the estimated ETC2.0 measurement data into the second driving score model and the score calculated by inputting the actual ETC2.0 measurement data into the second driving score model are compared. However, if the difference is equal to or less than the threshold (or less than the threshold), it may be determined that the estimated ETC2.0 measurement data is valid.

Further, in the above embodiments, various programs and data related to various processes are stored in the storage unit, and the processing unit reads and executes these programs, thereby performing the processing in each of the above embodiments. Realized. In this case, the storage unit of each device includes internal storage devices such as ROM, EEPROM, flash memory, hard disk, and RAM, as well as memory cards (SD cards), compact flash (registered trademark) cards, memory sticks, USB memories, and CDs. - You may have a recording medium (recording medium, external storage device, storage medium) such as RW (optical disk) or MO (magneto-optical disk), and store the above various programs and data in these recording media You can do it.

100 server 110 processing unit 120 operation unit 130 display unit 140 sound output unit 150 communication unit 160 clock unit 190 storage unit

Claims (20)

An information processing device,
A second measurement that is measured by a second device that measures information about a moving object and that is different from the first device, based on first measurement data that is measured by a first device that measures information about the moving object. a data generation unit that generates data estimation data;
a model generation unit that generates a model for calculating various quantities related to the moving object in driving evaluation using the second device, based on the estimated data;
with
The data generation unit generates at least part of the estimated data of the second measurement data based on the following formula,
D2(1)=D1(1)
D2(k)=D1(g(D2(k-1)))
here,
k is a natural number of 2 or more,
D1 and D2 indicate the position information of the data in the argument that is the order value from the reference data when the estimated data of the first measurement data and the second measurement data are arranged based on time series, respectively,
The function g is the order value of data located near the end of a predetermined range defined based on the data whose order value is the argument value, or the predetermined traveling direction amount after the data whose order value is the argument value. Output the order value of the data located near the position where there was a change in
Information processing equipment. An information processing device,
a function generator that generates a function that approximates travel information included in the first measurement data based on the first measurement data that is measured by a first device that measures information about a moving body;
a calculation unit that sequentially calculates time information at which either a predetermined distance condition or a predetermined traveling direction condition is satisfied based on the first measurement data;
Based on the generated function and the calculated time information, generate estimated data of second measurement data measured by a second device that measures information about a moving object and is different from the first device. a data generator that
a model generation unit that generates a model for calculating various quantities related to the moving object in driving evaluation using the second device, based on the estimated data;
Information processing device. An information processing device,
A second measurement that is measured by a second device that measures information about a moving object and that is different from the first device, based on first measurement data that is measured by a first device that measures information about the moving object. a data generation unit that generates data estimation data;
a model generation unit that generates a model for calculating various quantities related to the mobile object in telematics insurance using the second device, based on the estimated data;
with
The data generation unit generates at least part of the estimated data of the second measurement data based on the following formula,
D2(1)=D1(1)
D2(k)=D1(g(D2(k-1)))
here,
k is a natural number of 2 or more,
D1 and D2 indicate the position information of the data in the argument that is the order value from the reference data when the estimated data of the first measurement data and the second measurement data are arranged based on time series, respectively,
The function g is the order value of data located near the end of a predetermined range defined based on the data whose order value is the argument value, or the predetermined traveling direction amount after the data whose order value is the argument value. Output the order value of the data located near the position where there was a change in
Information processing equipment. An information processing device,
a function generator that generates a function that approximates travel information included in the first measurement data based on the first measurement data that is measured by a first device that measures information about a moving body;
a calculation unit that sequentially calculates time information at which either a predetermined distance condition or a predetermined traveling direction condition is satisfied based on the first measurement data;
Based on the generated function and the calculated time information, generate estimated data of second measurement data measured by a second device that measures information about a moving object and is different from the first device. a data generator that
a model generation unit that generates a model for calculating various quantities related to the mobile object in telematics insurance using the second device, based on the estimated data;
Information processing device. The information processing device according to any one of claims 1 to 4 ,
The model generation unit generates the model by machine learning using at least the estimated data as learning data.
Information processing equipment. The information processing device according to claim 5 ,
The model generation unit generates the model by machine learning using at least the estimated data and the second measurement data as learning data.
Information processing equipment. The information processing device according to any one of claims 1 to 4 ,
a calculation unit that calculates the various quantities based on the second measurement data and the generated model;
Information processing device. The information processing device according to any one of claims 1 to 4 ,
The first device and the second device measure travel information,
The various quantities are driving scores related to driving of the mobile object for which the driving information is measured,
The model is a model for calculating the driving score based on the second measurement data,
Information processing equipment. The information processing device according to claim 8 ,
The model generation unit generates a model for calculating the driving score by machine learning using the estimated data and information based on the first measurement data as learning data.
Information processing equipment. The information processing device according to any one of claims 1 to 4 ,
The second measurement data is transmitted from the second device to a roadside device installed at a predetermined position,
a determination unit that determines whether to generate the estimated data based on the first measurement data and the position information of the roadside unit;
Information processing device. The information processing device according to any one of claims 1 to 4 ,
The second measurement data is transmitted from the second device to a roadside device installed at a predetermined position,
a determination unit that determines whether or not to use the generated estimated data based on the first measurement data and the position information of the roadside unit;
Information processing device. The information processing device according to any one of claims 1 to 4 ,
The second measurement data is transmitted from the second device to a roadside device installed at a predetermined position,
a determination unit that determines a measurement period of the first measurement data used to generate the estimated data based on the first measurement data and the position information of the roadside unit;
Information processing device. An information processing method,
A second measurement that is measured by a second device that measures information about a moving object and that is different from the first device, based on first measurement data that is measured by a first device that measures information about the moving object. generating estimates of the data;
generating a model for calculating various quantities related to the mobile object in telematics insurance using the second device based on the estimated data;
including
At least part of the estimated data is generated based on the following formula,
D2(1)=D1(1)
D2(k)=D1(g(D2(k-1)))
here,
k is a natural number of 2 or more,
D1 and D2 indicate the position information of the data in the argument that is the order value from the reference data when the estimated data of the first measurement data and the second measurement data are arranged based on time series, respectively,
The function g is the order value of data located near the end of a predetermined range defined based on the data whose order value is the argument value, or the predetermined traveling direction amount after the data whose order value is the argument value. Output the order value of the data located near the position where there was a change in
Information processing methods. An information processing method,
generating a function approximating travel information included in the first measurement data based on first measurement data measured by a first device that measures information about a moving object;
Sequentially calculating time information at which either a predetermined distance condition or a predetermined traveling direction condition is satisfied based on the first measurement data;
Based on the generated function and the calculated time information, generate estimated data of second measurement data measured by a second device that measures information about a moving object and is different from the first device. and
generating a model for calculating various quantities related to the moving object in driving evaluation using the second device, based on the estimated data;
Information processing method including. An information processing method,
A second measurement that is measured by a second device that measures information about a moving object and that is different from the first device, based on first measurement data that is measured by a first device that measures information about the moving object. generating estimates of the data;
generating a model for calculating various quantities related to the moving object in driving evaluation using the second device, based on the estimated data;
including
At least part of the estimated data is generated based on the following formula,
D2(1)=D1(1)
D2(k)=D1(g(D2(k-1)))
here,
k is a natural number of 2 or more,
D1 and D2 indicate the position information of the data in the argument that is the order value from the reference data when the estimated data of the first measurement data and the second measurement data are arranged based on time series, respectively,
The function g is the order value of data located near the end of a predetermined range defined based on the data whose order value is the argument value, or the predetermined traveling direction amount after the data whose order value is the argument value. Output the order value of the data located near the position where there was a change in
Information processing methods. An information processing method,
generating a function approximating travel information included in the first measurement data based on first measurement data measured by a first device that measures information about a moving object;
Sequentially calculating time information at which either a predetermined distance condition or a predetermined traveling direction condition is satisfied based on the first measurement data;
Based on the generated function and the calculated time information, generate estimated data of second measurement data measured by a second device that measures information about a moving object and is different from the first device. and
generating a model for calculating various quantities related to the mobile object in telematics insurance using the second device based on the estimated data;
Information processing method including. to the computer,
A second measurement that is measured by a second device that measures information about a moving object and that is different from the first device, based on first measurement data that is measured by a first device that measures information about the moving object. generating estimates of the data;
generating a model for calculating various quantities related to the moving object in driving evaluation using the second device, based on the estimated data;
A program for executing
At least part of the estimated data is generated based on the following formula,
D2(1)=D1(1)
D2(k)=D1(g(D2(k-1)))
here,
k is a natural number of 2 or more,
D1 and D2 indicate the position information of the data in the argument that is the order value from the reference data when the estimated data of the first measurement data and the second measurement data are arranged based on time series, respectively,
The function g is the order value of data located near the end of a predetermined range defined based on the data whose order value is the argument value, or the predetermined traveling direction amount after the data whose order value is the argument value. Output the order value of the data located near the position where there was a change in
program. to the computer,
generating a function approximating travel information included in the first measurement data based on first measurement data measured by a first device that measures information about a moving object;
Sequentially calculating time information at which either a predetermined distance condition or a predetermined traveling direction condition is satisfied based on the first measurement data;
Based on the generated function and the calculated time information, generate estimated data of second measurement data measured by a second device that measures information about a moving object and is different from the first device. and
generating a model for calculating various quantities related to the moving object in driving evaluation using the second device, based on the estimated data;
program to run the to the computer,
A second measurement that is measured by a second device that measures information about a moving object and that is different from the first device, based on first measurement data that is measured by a first device that measures information about the moving object. generating estimates of the data;
generating a model for calculating various quantities related to the mobile object in telematics insurance using the second device based on the estimated data;
A program for executing
At least part of the estimated data is generated based on the following formula,
D2(1)=D1(1)
D2(k)=D1(g(D2(k-1)))
here,
k is a natural number of 2 or more,
D1 and D2 indicate the position information of the data in the argument that is the order value from the reference data when the estimated data of the first measurement data and the second measurement data are arranged based on time series, respectively,
The function g is the order value of data located near the end of a predetermined range defined based on the data whose order value is the argument value, or the predetermined traveling direction amount after the data whose order value is the argument value. Output the order value of the data located near the position where there was a change in
program. to the computer,
generating a function approximating travel information included in the first measurement data based on first measurement data measured by a first device that measures information about a moving object;
Sequentially calculating time information at which either a predetermined distance condition or a predetermined traveling direction condition is satisfied based on the first measurement data;
Based on the generated function and the calculated time information, generate estimated data of second measurement data measured by a second device that measures information about a moving object and is different from the first device. and
generating a model for calculating various quantities related to the mobile object in telematics insurance using the second device based on the estimated data;
program to run the

Images