JP7765036B2 - Information processing method, information processing device, and program - Google Patents

Description

The present invention relates to information processing technology for determining, for example, whether a user is a driver.

Technological development is progressing in telematics technology, which connects devices installed in mobile vehicles to wide-area networks such as the Internet to obtain various information about the vehicle, manage the vehicle's status and behavior, and provide services based on the obtained information. There is demand for services using telematics technology, such as delivering advertisements tailored to user behavior and calculating insurance premiums for mobile vehicles.

One type of information that should be obtained about a moving object is whether the person in question is the driver. For example, Patent Document 1 discloses a method for determining whether the user of a mobile device is the driver of a vehicle by analyzing images captured by a camera.

Japanese Patent Application Laid-Open No. 2018-166268

However, the above-mentioned conventional technology only analyzed whether the user of a mobile device was a specific person, and was unable to determine whether the user was riding in a vehicle. Furthermore, even if it was possible to determine whether the user was riding in a vehicle, it was difficult to determine whether the user was riding in the vehicle as the driver or as a non-driver.

According to one aspect of the present invention, an information processing method includes: acquiring model curvature radius information for each of at least one target curve based on position information related to a driver's seat in a plurality of moving object passing patterns when a moving object passes through the at least one target curve; acquiring user curvature radius information for each of the at least one target curve based on position information of an information processing device associated with a user riding in a user moving object passing through the at least one target curve; calculating a difference between the model curvature radius information and the user curvature radius information for each of the at least one target curve; and determining whether the user is a driver based on the difference.

The method, device, and program of the present invention can provide information related to whether a user is driving a vehicle.

FIG. 1 is a system configuration diagram of a driver discrimination system. FIG. 2 is a block diagram showing an example of the functional configuration of the mobile information processing device 10. FIG. 2 is a block diagram showing an example of the functional configuration of an on-board device 20. FIG. 2 is a block diagram showing an example of the functional configuration of a server 30. 10 is an example of a table in which target curve information and curvature radius information are linked together and stored in the storage unit 220. A flowchart showing an example of a procedure for determining whether a user is a driver of a moving object 1. FIG. 10 is a diagram showing a simplified example of the trajectory of each passenger seat when passing through a curve. A diagram showing more detailed trajectories of each passenger seat when turning left. 10A and 10B are diagrams showing examples of the trajectory of a moving object when the angle of a curve is changed.

Hereinafter, an example of an embodiment of the present invention will be described with reference to the drawings.
In the description of the drawings, the same elements are denoted by the same reference numerals, and duplicated descriptions may be omitted.
Furthermore, the components described in these embodiments are merely examples and are not intended to limit the scope of the present invention.

[Embodiment]
Hereinafter, an embodiment will be described as an example for realizing the information processing technology of the present invention.
In this embodiment, it is determined whether the user is driving a car owned by the user.
The contents described in this embodiment are applicable to any of the other embodiments, examples, and modified examples.

Figure 1 is a system configuration diagram of a driver identification system according to one aspect of this embodiment. In this system, various information such as location information is acquired by a mobile information processing device 10 carried by a user riding in a mobile object 1, and the acquired information is transmitted to a server 20 via a network NW (e.g., the Internet).

In this embodiment, mobile object 1 is a vehicle in which the user rides, but is not limited to such a vehicle. For example, it may be any mobile object, such as a rental car or a friend's vehicle.

2 is a block diagram showing the functional configuration of the mobile information processing device 10 of FIG. 1. The mobile information processing device 10 in this embodiment may be, for example, a portable electronic device such as a smartphone or a tablet, and is not limited thereto. The mobile information processing device 10 is configured to include, for example, a control unit 110, a storage unit 120, a communication unit 130, a display unit 140, an input unit 150, an audio output unit 160, a position information acquisition unit 170, a velocity information acquisition unit 180, and an angular velocity information acquisition unit 190.
The mobile information processing device 10 is held by a user, and the user is linked to the mobile information processing device 10 by logging in to an app running on the device, etc. The mobile information processing device 10 is connected to a network such as the Internet via a communication unit 130, and transmits various pieces of information acquired by, for example, a position information acquisition unit 170, a velocity information acquisition unit 180, and an angular velocity information acquisition unit 190 to a server 20.

The control unit 110 is configured by a processing and arithmetic unit including, for example, a CPU (Central Processing Unit) and an MPU (Micro-Processing Unit). The control unit 110 performs various processes on each piece of data, and by reading and executing programs stored in the memory unit 120, it controls each functional unit of the mobile information processing device 10, such as the communication unit 130, display unit 140, input unit 150, audio output unit 160, position information acquisition unit 170, velocity information acquisition unit 180, and angular velocity information acquisition unit 190.

The storage unit 120 includes, for example, a hard disk drive (HDD), a solid state drive (SSD), an electrically erasable programmable read-only memory (EEPROM), a read-only memory (ROM), a random access memory (RAM), etc., and stores the control programs processed by the control unit 110 and various data, such as acquired location information. Note that the storage unit 120 is not limited to being built into the mobile information processing device 10, but may also be an external storage device connected via a digital input/output port such as a universal serial bus (USB).

The communication unit 130 is a module that can connect to a public network such as the Internet using, for example, mobile communications such as LTE (Long Term Evolution), 3G, 4G, or 5G, or narrowband communications such as DSRC (Dedicated Short Range Communication), and can communicate data with various devices such as the server 20 connected to the network.
For example, the mobile information processing device 10 exchanges data with the server 20 via the communication unit 130 .

The display unit 140 is a display means for displaying various information, and is configured by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display.
The display unit 140 displays, for example, various information acquired through the communication unit 130 and processing results by the control unit 110 .

The input unit 150 is an input means for the user to input various information to the mobile information processing device 10. For example, the input unit 150 is configured with buttons, a touch panel, switches, etc. The input unit 150 may also be configured as a touch screen integrated with the display unit 140.
When a user performs an input operation on the input unit 150, a control signal corresponding to the input is generated and output to the control unit 110. Then, the control unit 110 performs arithmetic processing and control corresponding to the control signal.

The audio output unit 160 is, for example, an audio output terminal, and transmits an audio signal to output audio from a connected earphone, speaker, etc. Alternatively, it may be a speaker that outputs audio related to the audio signal.
The audio output unit 160 outputs, for example, music data distributed via the Internet or the like and stored in the storage unit 120, which has been processed by the control unit 110 as an audio signal.

The location information acquisition unit 170 acquires location information (e.g., latitude and longitude information) of the mobile information processing device 10 at predetermined intervals, for example, based on radio waves arriving from GNSS satellites (e.g., GPS satellites). That is, it is possible to acquire location information of the user carrying the mobile information processing device 10. In other words, when the user carrying the mobile information processing device 10 uses the mobile object 1, it is possible to essentially acquire location information of the mobile object 1. The acquired location information is linked to the time (current time) at which the location information was acquired and stored in the storage unit 120.
Here, the location information acquisition unit 170 may acquire location information and also acquire an accuracy value (e.g., DOP value) indicating the accuracy of the location information. In this case, the acquired location information and accuracy value are linked to the current time and stored in the storage unit 120.

Note that the method for acquiring location information by the location information acquisition unit 170 is not limited to the above, and any location information acquisition method may be applied. For example, the location information of the information processing device 10 may be acquired by the location information acquisition unit 170 receiving radio waves containing location information specific to a roadside device installed on the side of the road when a mobile object 1 carrying a user of the mobile information processing device 10 approaches the mobile object 1.

The speed acquisition unit 180 periodically acquires the traveling speed of the mobile object 1 and supplies this traveling speed to the control unit 110. The speed acquisition unit 180 may have any configuration, but may, for example, calculate speed information based on position information acquired by the position information acquisition unit 170. Alternatively, the speed acquisition unit 180 may acquire vehicle speed pulse information acquired by a vehicle speed pulse acquisition unit mounted on the mobile object 1 via the communication unit 130, and calculate the speed of the mobile object 1 based on this vehicle speed pulse information.

The angular velocity acquisition unit 190 is configured to be able to detect angular velocities around three axes in the portable information processing device 10. Specifically, the angular velocity acquisition unit 190 can detect a roll angular velocity, which is the rate of change of the angle (roll angle) around the longitudinal axis of the portable information processing device 10, a pitch angular velocity, which is the rate of change of the angle (pitch angle) around the lateral axis of the vehicle body, and a yaw angular velocity, which is the rate of change of the angle (yaw angle) around the vertical axis of the vehicle body. Note that, since the only angular velocity information required for calculating the radius of curvature is the yaw angle, it is possible to acquire only the yaw angle without acquiring information on the roll angle and pitch angle. Furthermore, the configuration of the angular velocity acquisition unit 190 is not limited thereto, and for example, the yaw angle may be calculated based on position information acquired by the position information acquisition unit 170.
The angular velocity acquisition section 190 may have any configuration, and may calculate angular velocity information based on the position information acquired by the position information acquisition section 170, for example.

Fig. 3 is a block diagram showing the functional configuration of the server 20 in Fig. 1. The server 20 in this embodiment is configured to include a control unit 210, a storage unit 220, and a communication unit 230.
The server 20 is connected to the mobile information processing device 10 and the like via a network such as the Internet, receives various information such as location information from the mobile information processing device 10 and the like, and stores it in the storage unit 220. The server 20 also processes the stored information as appropriate, and performs processes such as determining whether the user of the mobile information processing device 10 is the driver of the mobile object 1.

Like the control unit 110 of the mobile information processing device 10, the control unit 210 is configured with a processing and arithmetic unit including, for example, a CPU (Central Processing Unit) and an MPU (Micro-Processing Unit). The control unit 210 performs various processes on each piece of data and also reads and executes programs stored in the memory unit 220. In addition,

Like the storage unit 120 of the mobile information processing device 10, the storage unit 220 includes, for example, a hard disk drive (HDD), a solid state drive (SSD), an electrically erasable programmable read-only memory (EEPROM), a read-only memory (ROM), a random access memory (RAM), etc., and stores the control programs processed by the control unit 210 and various data, such as an on-board device table in which device identification information is registered. Note that the storage unit 220 is not limited to being built into the server 20, but may also be an external storage device connected via a digital input/output port such as a universal serial bus (USB).

The communication unit 340 is a module that can connect to a network such as the Internet using a wired communication interface, or, like the communication unit 130 of the mobile information processing device 10, using mobile communications such as LTE (Long Term Evolution) or 3G, or narrowband communications such as DSRC (Dedicated Short Range Communication), and can communicate data with devices such as the mobile information processing device 10 connected to the network.

[Information processing procedure: Obtaining the model curvature radius of the target curve]
FIG. 4 is a flowchart showing an example of processing in this embodiment for obtaining, as a model, curvature radius information based on a group of driver trajectories when multiple moving bodies pass a curve (hereinafter referred to as a target curve) that serves as a reference for determining whether a user is riding in a moving body as a driver.
The processing in the flowcharts of FIG. 4 and other figures is realized, for example, by the control unit 210 of the server 20 reading out the code of the information processing program stored in the storage unit 220 into a RAM (not shown) and executing it.

Each symbol S in the flowcharts of FIG. 4 and other figures denotes a step.
Furthermore, the flowchart described below merely shows an example of the procedure for information processing in this embodiment, and other steps may be added or some steps may be deleted.

First, the server 20 identifies a curve (hereinafter referred to as a target curve) for which model curvature radius information is to be acquired (S1001). Here, it is assumed that model curvature radius information is associated with each of a plurality of curves as data, and the server 20 identifies the target curve from among the plurality of curves based on some selection condition. The selection condition will be described later.
Here, when storing the target curve as data, for example, the position information of the intersection where the curve is located is identified and stored. However, the method of storing the target curve is not limited to this. For example, the curve may be identified by the position information of buildings near the curve, or any other information that can identify the curve is sufficient.
It is preferable that the information about the identified target curve also includes information about the approach direction to the curve. That is, the information is stored in association with the direction of approach to the curve. For example, the storage unit 220 stores information about the identified target curve in a format as shown in FIG. 5. As shown in FIG. 5, in this storage method, position information (x1, y1) about the target curve is associated with azimuth angle information (α) indicating the approach direction to the curve. The azimuth angle information means, for example, the magnitude of the horizontal angle measured clockwise from due north. However, the definition of the azimuth angle is not limited thereto, and it may be based on any other direction (e.g., due south) or may be the magnitude of the horizontal angle measured counterclockwise.

Next, the server 20 acquires multiple patterns of information on the radius of curvature when the mobile object passes through the target curve through a device or the like provided near the driver's seat in the mobile object (S1003). In acquiring this information on the radius of curvature, for example, the following processing is performed.
First, the server 20 acquires speed information of the moving object when it passes through the target curve based on position information acquired from the moving object that passed through the target curve. Similarly, it acquires angular velocity (yaw angle) information of the moving object when it passed through the target curve. Then, it calculates radius of curvature information for each pattern based on the following equation 1.

The calculated curvature radius information may be composed of multiple curvature radius values. For example, it may be composed of curvature radius values calculated for each piece of position information of the moving object when passing through the curve (e.g., for each piece of position information obtained every second).

Furthermore, the period during which the vehicle is passing through a curve may be defined, for example, by setting the time when the acquired angular velocity becomes equal to or greater than a predetermined threshold as the curve passing start time, and the time when the acquired angular velocity becomes equal to or less than the predetermined threshold as the curve passing end time, but is not limited to this. For example, a range for passing through a curve may be registered in advance, and if the position information of the vehicle is within that range, it may be determined that the vehicle is passing through a curve.
The method for identifying the range recognized as a curve is not particularly limited, as long as the method can identify the start and end of the curve in a form that includes a certain range from the center of the curve, preferably in a form that includes a range four times the length of the moving body.

Preferably, the area through which the curve is traversed may be divided into multiple regions and curvature radius information acquired. For example, two pieces of curvature radius information are acquired: one for the first half of the curve traversal and one for the second half of the curve traversal. The curvature radius information for the second half of the curve traversal is particularly useful for determining whether the user is sitting in the front or back seat of the mobile object 1, as described below in the driver identification process. The boundary between the first half of the curve and the second half of the curve may be set based on any criteria. For example, the boundary may be set based on half the time from when the mobile object enters the curve to when it leaves it, or the point at which the angular acceleration value of the mobile object changes from positive to negative. It may also be set as a fixed boundary for the curve, regardless of how the mobile object traverses the curve, such as by using a position that physically divides the size of the curve in half.

Then, the server 20 processes the acquired curvature radius information (S1005). Processing the curvature radius information means making the acquired multiple curvature radius values easier to handle in subsequent processing. For example, in this embodiment, these multiple curvature radius values are treated as a set, and the expected value and variance of this set are calculated.

Note that step S1005 does not have to be performed. In other words, the acquired multiple curvature radius values may be stored as is and used for subsequent processing without processing.

Thereafter, the server 20 associates the processed curvature radius information with the target curve information and stores them in the storage unit 220 (S1007). As shown in Fig. 5, as the curvature radius information associated with the target curve information, for example, an expected value Ea1 and a variance Va1 of the set in the first half, and an expected value Ea2 and a variance Va2 of the set in the second half are stored in correspondence with the position information (x1, y1) regarding the target curve.
Then, the process of acquiring the model curvature radius information for the target curve ends.

The method for obtaining model curvature radius information is not limited to the above, and any method can be applied. For example, a set of points plotted on a two-dimensional plane based on position information obtained when passing through the target curve can be fitted with a model of the curve trajectory for each curvature radius, and the information on the model that fits best (e.g., the value of the curvature radius in the model) can be used as the model curvature radius information.

Furthermore, the velocity information and angular velocity information used in the above-described method for obtaining the radius of curvature do not necessarily have to be calculated from position information, but may instead be values (observed values) obtained by the velocity information obtaining unit 180 and angular velocity information obtaining unit 190 provided in the moving body, or, taking into account that these values may contain noise, etc., values obtained by applying processing to remove noise, etc. as appropriate may be used.

Furthermore, model curvature radius information does not have to be acquired for the entire period of passing through the curve, but may be acquired for only a portion of the period of passing through the curve. For example, any portion, such as only the latter half of the period of passing through the curve, may be acquired. Alternatively, curvature radius information for the entire period of passing through the curve may be acquired, and only the necessary portion may be cut out and processed in the processing process in step S1005.

[Information processing procedure: Determining whether the user is a driver]
FIG. 6 is a flowchart showing an example of a procedure for determining whether or not the user is the driver of the moving object 1 in this embodiment.

First, based on the position information acquired from the mobile information processing device 10, the server 20 identifies the position information when the mobile information processing device 10 passed through the target curve (S2001). For example, if the acquired position information is within a predetermined distance (e.g., within 5 m) from the target curve position information for a predetermined period of time (e.g., 3 seconds) or more, and the acquired position information is entered from the same direction as the entry direction in the target curve information, the server 20 determines that the mobile information processing device 10 has passed through the target curve and identifies the corresponding position information. Of course, the method for determining whether the target curve has been passed is not limited to this method, and any method based on the acquired position information can be applied.

Next, the server 20 acquires the radius of curvature information when the mobile information processing device 10 passes through the target curve (S2003). As in S1003, the method of acquiring the radius of curvature information may be to calculate the velocity and angular velocity based on the position information acquired by the position information acquisition unit 170 and acquire the radius of curvature information based on these, or to acquire the radius of curvature information based on the velocity information and angular velocity information acquired by the velocity acquisition unit 180 and the angular velocity acquisition unit 190, respectively, and is not particularly limited.
In this embodiment, the curvature radius information is acquired separately for the first half of the curve and the second half of the curve.

The server 20 then compares the already acquired model curvature radius information with the curvature radius information acquired in S2003 for the first half of the curve and the second half of the curve, and determines whether the differences are equal to or less than a predetermined threshold (S2005). If both differences are equal to or less than the predetermined threshold (S2005; Y), it determines that the user linked to the mobile information processing device 10 is the driver of the mobile object 1 (S2007). Conversely, if at least one difference exceeds the predetermined threshold (S2005; N), it determines that the user linked to the mobile information processing device 10 is not the driver of the mobile object 1 (is a non-driver) (S2009).

In this embodiment, for each of the first half and second half of the curve, the determination is based on the difference between the acquired curvature radius value and the expected value in the model curvature radius, and a predetermined threshold value (which may be the same for the first half and second half). That is, for the first half of the curve, the difference between the expected value in the model curvature radius information and the acquired curvature radius value is calculated, and further, for the second half of the curve, the difference between the expected value in the model curvature radius information and the acquired curvature radius value is calculated, and these difference values are compared with the predetermined threshold value.
In addition, if one of the first and second half of the curve is below a predetermined threshold and the other exceeds the predetermined threshold, it is determined that the person is not the driver, but this determination is not limited to this, and for example, it is also possible to withhold determination as to whether the person is the driver.

Figure 7 shows an example of the trajectory taken by each passenger seat when going through a curve. Figure 7 (1) shows the case of a left turn, and Figure 7 (2) shows the case of a right turn. As shown in Figure 7 (1), when turning left, the driver's seat in the front right has the largest radius of curvature. Conversely, as shown in Figure 7 (2), when turning right, the driver's seat (similar) has a larger radius of curvature than the rear right seat, but a smaller radius of curvature than the front left seat.

For this reason, it is preferable that the curve with the model curvature radius is a left turn, as this simplifies the calculation process. Also, in the case of a left turn, if the difference between the model curvature radius information and the acquired curvature radius information exceeds a predetermined threshold and the acquired curvature radius information is larger than the model curvature radius information, it is preferable to suspend the determination of whether or not the driver is the driver, assuming that the curve was not traversed in a manner normally expected (for example, the curvature radius was larger than normal due to detouring an obstacle, etc.).
Furthermore, in consideration of such cases where judgment may be withheld, it is also possible to detect the passage of multiple target curves and determine whether or not the driver is the driver based on comprehensive information combining judgments at each target curve.

8 shows a more detailed trajectory of each passenger seat when turning left. As shown in FIG. 8, when comparing the first half of the curve and the second half of the curve, the radius of curvature in the front seat of the moving body is larger in the second half than in the first half (r2>r1). On the other hand, there is no significant difference in the radius of curvature between the first half and the second half of the curve in the rear seat of the moving body.
Therefore, by making a comparison in both the first half of the curve and the second half of the curve, it is possible to more appropriately determine whether the user is in the front seat or the back seat of the vehicle.

Note that when the driver's seat is located at the front left of the vehicle, the relationship is symmetrical to when it is located at the front right, and it can be said that, for example, it is preferable that the curve with the model curvature radius be a right turn.

Furthermore, when the model curvature radius information is stored in the storage unit 220 using an expected value and a variance value, as in this embodiment, the expected value is compared with the acquired curvature radius value based on a predetermined threshold value, but this predetermined threshold value may be changed depending on the variance value. For example, if the variance is small, the threshold value may be set small, and conversely, if the variance is large, the threshold value may be set large.

After step S2007, the server 20 identifies a range of the same driver that includes the time when the target curve was passed, and registers that the user was driving the mobile unit 1 within this range of the same driver (S2011). Here, the range of the same driver is a range of time during which the same driver is assumed to be driving the mobile unit 1. The range of the same driver may be determined, for example, based on location information acquired from the mobile information processing device 10. A period during which changes in the location information continue to occur is considered to be the range of the same driver. For example, if the speed value (e.g., calculated from the location information) observed over a certain period (e.g., 5 minutes) does not exceed a predetermined speed (e.g., 10 km/h), the mobile unit 1 is considered to be not in operation or not being driven. At that point, the range of the same driver may be deemed to have ended, and the corresponding end time may be identified and recorded. Furthermore, the same can be applied to information regarding past driving. The start time of the range of the same driver may be identified and recorded based on a similar process, going back to the time when the target curve was passed.
Alternatively, for example, the mobile body 1 may be equipped with an operation information acquisition unit (not shown), which is configured to generate operation information of the mobile body 1 (information regarding whether the engine is on or off), and the server 20 may acquire such operation information, and the server 20 may identify the same driver range based on the operation information and the time at which the target curve was passed when the determination was made that the person is the driver; the method for identifying the same driver range is not particularly limited.
In this way, it is possible to determine when the user was driving the mobile body 1, which has the effect of making it possible to appropriately apply, for example, insurance linked to actual driving distance, in which the insurance premium is set according to the distance traveled, or insurance linked to driving behavior, in which the insurance premium is set according to driving behavior.

Here, whether or not the person is the driver is immediately determined based on the result in step S2005, but this method is not limited to this. For example, similar processing may be performed for multiple target curves, and in step S2005, a score may be calculated based on the magnitude of the difference, and the scores calculated for all of the multiple target curves may be compiled (e.g., summed), and based on the results of comparing the compiled result with a predetermined threshold (e.g., whether the sum is equal to or less than the threshold), whether or not the person is the driver may be determined.

[Modification]
In the above-described embodiment, whether the user is the driver of the moving body 1 is determined based on model curvature radius information calculated from curvature radius information in multiple passing patterns for the target curve, but this is not limited to this.
For example, it is preferable to use model curvature radius information calculated from curvature radius information of a group of moving objects corresponding to the vertical length (which means the length from front to back, hereinafter referred to as vehicle length) of the moving object 1. This is because the difference in curvature radius between the first half of the curve and the second half of the curve varies depending on the vehicle length of the moving object. For example, if the moving object 1 is a light vehicle, it is preferable to calculate the model curvature radius information from curvature radius information of multiple patterns at the target curve for the light vehicle.

Furthermore, in the above-described embodiment, the location information acquisition unit 170 acquires location information and also acquires an accuracy value (e.g., DOP value) indicating the accuracy of that location information. However, this accuracy value may be used to determine whether the user is the driver if the accuracy value is lower than a predetermined threshold, or may not be used as a basis for the determination (when the scores at multiple target curves are judged together).

In the above embodiment, the model curvature radius information is defined by an expected value and a variance value, but the present invention is not limited to this. The model curvature radius information may be any information that can express the acquired multiple pieces of curvature radius information in some form.
Furthermore, if the variance value in the model curvature radius information is greater than a predetermined value, the reliability of the model may be deemed low, and the corresponding curve may not be adopted as the target curve.

Furthermore, in the above-described embodiment, the server 20 makes the determination in step S2007 or step S2009, but this is not limited to this. For example, a device other than the server 20, including the mobile information processing device 10, may make these determinations by referencing model curvature radius information stored in the server 20. Alternatively, all steps may be performed by the mobile information processing device 10.

In addition, in the above-described embodiment, the curvature radius information of the moving body 1 obtained for each of the first half and second half of the curve was compared with the model curvature radius information. However, the method of using the curvature radius information to determine whether or not a user is the driver is not limited to this method, and any method can be applied. For example, in light of the fact that the curvature radius is larger in the second half of the curve than in the first half of the curve for passengers in the front seats, the difference between the curvature radius information of the second half of the curve and the curvature radius information of the first half of the curve for each of the curvature radius information of the moving body 1 and the model curvature radius information can be obtained, and whether or not the user is the driver of the moving body 1 can be determined based on this difference. In this case as well, it is preferable to make the determination based on, for example, whether the comparison result (difference) is equal to or less than a predetermined threshold.

In addition, in the above-described embodiment, curvature radius information, i.e., the curvature radius value, is obtained for an arbitrary range within the target curve, but this value may be the value of multiple curvature radii obtained within this range, or the value obtained by combining these multiple curvature radius values (e.g., the average value) may be used as the curvature radius information.

Furthermore, in the above-described embodiment, the nature of the target curve is not particularly limited, but a curve with a smaller angle is preferable. Figures 9 (1), (2), and (3) show examples of trajectories of a moving object when the curve angles are 120 degrees, 90 degrees, and 60 degrees, respectively. As shown in Figure 9, the smaller the angle, the greater the difference in curvature radius between the front and rear parts of the curve from the front passenger seat of the moving object. Therefore, the smaller the curve angle, the easier it is to clearly determine whether the user is the driver.
Here, the "curve angle" refers to, for example, the magnitude of the yaw angle that a moving object changes from when it enters a curve from a straight line to when it leaves the curve and returns to the straight line. In other words, it is not something that can be determined by focusing on one point on the curve, but rather indicates the amount of change in angle that occurs when the curve is viewed as a whole.

Therefore, for example, when making a comprehensive judgment based on the difference between the curvature radius when passing through multiple target curves and the model curvature radius, the judgment may be made by assigning a greater weight to the comparison results for target curves with smaller angles.
Furthermore, when selecting a target curve, if the angle of the curve is not equal to or greater than a predetermined threshold, the curve may not be selected as the target curve.

Furthermore, the characteristics of the road on the approaching side of the target curve and the road on the exiting side of the curve that must be satisfied for the target curve are not particularly limited, but it is preferable that both the former and the latter have small widths. The term "width" here does not necessarily refer to the width of the entire road. For example, if the road on the approaching side of the target curve is a multi-lane road consisting of an approaching direction, a forward direction, and a reverse direction, it may refer to the width of only the forward direction lane. Similarly, if the road on the exiting side of the target curve is a multi-lane road consisting of an exiting direction, a forward direction, and a reverse direction, it may refer to the width of only the forward direction lane.
It should be noted that information relating to road width (hereinafter referred to as "road width information") may be acquired from, for example, map information that includes road width information.

In other words, the smaller the width of the road that a moving object can use when passing through the target curve, the smaller the dispersion of the moving object's trajectory when passing through the curve is expected to be, and this property is utilized.

Furthermore, in the above-described embodiment, no particular mention was made of how the user's moving body passed through the target curve, but it is preferable that the characteristics when passing through the target curve satisfy, for example, the following conditions.
- The speed when entering the curve is within a specified range. - The speed while passing through the curve is within a specified range. - The speed when leaving the curve is within a specified range. - The acceleration when entering the curve is within a specified range. - The acceleration while passing through the curve is within a specified range. - The acceleration when leaving the curve is within a specified range. In other words, if the speed is too small or too large when entering, passing through, or leaving the curve, and if the acceleration does not behave as would normally be expected, it is likely that the curve was not passed in the way that would normally be expected (for example, there was an obstacle, the vehicle was in a hurry more than usual, or a sudden event caused the vehicle to steer or slow down suddenly), and the trajectory in such cases will be excluded from processing.

The server 20 may also determine a target curve from among a plurality of target curve candidates based on some selection condition.
For example, in light of the above explanation, it is preferable that the target curve candidate satisfies at least one of the following conditions.
A large amount of information about past moving object trajectories has been accumulated (greater than a predetermined amount), and more preferably, a large amount of information about trajectories of moving objects corresponding to the user's moving object has been accumulated. The variance value of the curvature radius information of the target curve candidate is small (smaller than a predetermined value).
・Left turn ・Angle is small (smaller than the specified angle)
・The width of the road when entering the curve is small (shorter than the specified length)
・The width of the road when exiting the curve is small (shorter than the specified length)

Similarly, for example, based on the above explanation, it is preferable that information about the user's moving body when the user's moving body passes through the target curve candidate satisfies at least one of the following conditions.
The accuracy of the position information acquired when passing through the target curve candidate is high (the accuracy value is higher than a predetermined value).
- The speed when entering the target curve is within a specified range. - The speed while passing through the target curve is within a specified range. - The speed when leaving the target curve is within a specified range. - The acceleration when entering the target curve is within a specified range. - The acceleration while passing through the target curve is within a specified range. - The acceleration when leaving the target curve is within a specified range.

In addition, in the above-described embodiment, whether or not the user is a driver is determined by processing based on the radius of curvature, but by combining this with other processing, it may be possible to comprehensively determine whether or not the user is a driver.
For example, the mobile information processing device 10 may include an operation detection unit (not shown) that determines a period during which the user is likely to be driving based on information acquired from the position information acquisition unit 170, the speed information acquisition unit 180, or the angular velocity information acquisition unit 190, and the operation detection unit may determine whether any input has been made to the input unit 150 during that period, or whether input has been made with a frequency greater than a predetermined value, and the determination result may be used as one of the criteria for determining whether the user is a driver. This utilizes the background that if the user is operating the mobile information processing device 10 via the input unit 150 while driving, it is highly likely that the user is not a driver.
Similarly, when a user of the portable information processing device 10 gets into the stopped moving body 1, the result of which side the user gets into the moving body 1 may be used as one of the factors for determining whether the user is the driver. This utilizes the fact that, since the driver's seat is usually on the right side, if the user gets into the moving body 1 from the right side, it can be said that there is a high possibility that the user will sit in the driver's seat, but conversely, if the user gets into the moving body 1 from the left side, it can be said that there is a high possibility that the user is not the driver.

Although the embodiments and variations of the present invention have been described in detail above, the scope of the present invention is not limited to the above embodiments and variations. Furthermore, the above embodiments and variations can be improved or modified in various ways without departing from the spirit of the present invention. Furthermore, the above embodiments and variations can be combined.

REFERENCE SIGNS LIST 1 Mobile object 10 Portable information processing device 110 Control unit 120 Storage unit 130 Communication unit 140 Display unit 150 Input unit 160 Audio output unit 170 Position information acquisition unit 180 Speed information acquisition unit 190 Angular velocity information acquisition unit 20 Server 210 Control unit 220 Storage unit 230 Communication unit

Claims (9)

acquiring model curvature radius information for each of the at least one target curve based on position information related to a driver's seat in a plurality of moving object passing patterns when the moving object passes through the at least one target curve;
acquiring user curvature radius information for each of the at least one target curve based on position information of an information processing device associated with a user who is riding in a user moving body passing through the at least one target curve;
calculating a difference between the model curvature radius information and the user curvature radius information for each of the at least one target curve;
determining whether the user is a driver based on the difference;
An information processing method, including: determining the at least one target curve from a plurality of target curve candidates based on a first condition;
Further comprising:
The first condition is at least one of the following: the amount of information about past moving body trajectories at the target curve candidate is greater than a predetermined amount; the amount of information about trajectories by a moving body corresponding to the user moving body at the target curve candidate is greater than a predetermined amount; the variance value of the curvature radius information of the target curve candidate is smaller than a predetermined value; the target curve candidate is a left turn; the angle of the target curve candidate is smaller than a predetermined angle; the width of the road on the side entering the target curve candidate is smaller than a predetermined length; and the width of the road on the side leaving the target curve candidate is smaller than a predetermined length.
The information processing method according to claim 1 . determining the at least one target curve from a plurality of target curve candidates based on a second condition;
Further comprising:
The second condition is at least one of the following: the accuracy of the position information acquired when the user moving body passes the target curve candidate is higher than a predetermined value; the speed of the user moving body when entering the target curve candidate is within a predetermined range; the speed of the user moving body while passing the target curve candidate is within a predetermined range; the speed of the user moving body when leaving the target curve candidate is within a predetermined range; the acceleration of the user moving body when entering the target curve candidate is within a predetermined range; the acceleration of the user moving body while passing the target curve candidate is within a predetermined range; and the acceleration of the user moving body when leaving the target curve candidate is within a predetermined range.
The information processing method according to claim 1 . In determining whether the user is a driver, if it is determined that the user is a driver, determining that the user was a driver in the same driving range, which is a time range from when the operation of the user moving body starts to when it ends and includes the time when it was determined that the user was a driver;
Calculating insurance premiums based on the same driving range determined to be the driver;
The information processing method according to claim 1 , further comprising: The same operation range is determined based on a variation in the position information of the information processing device.
The information processing method according to claim 4 . When the at least one target curve is a plurality of target curves, the determining is performed by giving a higher priority to a result due to a difference in the first target curve than to a result due to a difference in the second target curve when an angle of the first target curve is smaller than an angle of the second target curve in a first target curve and a second target curve included in the plurality of target curves.
6. The information processing method according to claim 1 . setting a threshold value based on a variance value of the model curvature radius information;
Further comprising:
The determining is performed based on the threshold value.
7. The information processing method according to claim 1 . An information processing device associated with a user who is riding in a user moving body passing through at least one target curve,
a model curvature radius information acquisition unit that acquires model curvature radius information for each of the at least one target curve based on position information related to a driver's seat in a plurality of moving object passing patterns when a moving object passes through the at least one target curve;
a location information acquisition unit that acquires location information;
a user curvature radius information acquisition unit that acquires user curvature radius information for each of the at least one target curve based on the acquired position information;
a calculation unit that calculates a difference between the model curvature radius information and the user curvature radius information for each of the at least one target curve;
a determination unit that determines whether the user is a driver based on the difference;
An information processing device comprising: On the computer,
acquiring model curvature radius information for each of the at least one target curve based on position information related to a driver's seat in a plurality of moving object passing patterns when the moving object passes through the at least one target curve;
acquiring user curvature radius information for each of the at least one target curve based on position information of an information processing device associated with a user who is riding in a user moving body passing through the at least one target curve;
calculating a difference between the model curvature radius information and the user curvature radius information for each of the at least one target curve;
determining whether the user is a driver based on the difference;
A program that executes.