Method for specifying driver

Abstract

To specify a driver of a vehicle in a relatively simple manner.SOLUTION: Portable terminals 30A to 30C are portable terminals 30 owned by drivers A to C who drive a vehicle 10. The portable terminals A to C, the drivers A to C, and the vehicle 10 are linked to and stored in a storage device 120 of a server 100. When a location of any of the portable terminals 30A to 30C and a location of the vehicle 10 are within a threshold value, the server 100 specifies the driver linked to the portable terminal 30 within the threshold value as a driver of the vehicle 10. For instance, when a distance between the portable terminal 30A and the vehicle 10 is within the threshold value, the server specifies the driver A as a driver of the vehicle 10.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a method for identifying a driver, and more particularly to a method for identifying a driver of a vehicle. [Background technology]

[0002] Vehicle behavior prediction may be performed. For example, smart grids and VPPs (Virtual Power Plants) are being promoted to adjust power supply and demand, and electric vehicles equipped with power storage devices may be used as power adjustment resources. When using electric vehicles as power adjustment resources, it is desirable to predict the behavior of the electric vehicles in order to identify electric vehicles that can be connected to the power grid during power adjustment.

[0003] When multiple drivers use one vehicle, each driver behaves differently, so it is preferable to prepare behavior prediction data for each driver and predict the behavior for each driver. In this case, it is desirable to identify the driver who is driving the vehicle. JP 2023-74415 A (Patent Document 1) discloses that a feature quantity indicating the characteristics when driving a vehicle is divided for a predetermined period, and a learned model is used to identify the driver from the divided data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2023-74415 A Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, the driver is identified using machine learning. This results in a relatively large amount of data and a high computational load. In addition, when this data is exchanged using wireless communication (network), the amount of communication data becomes large.

[0006] An object of the present disclosure is to identify a driver in a relatively simple manner. [Means for solving the problem]

[0007] The method for identifying a driver of a vehicle according to the present disclosure includes acquiring vehicle position information and identifying the driver based on the position of a mobile device associated with the driver and the position of the vehicle, or based on the position of a registered point associated with the driver and the position of the vehicle.

[0008] According to this method, vehicle location information is acquired. Then, the driver is identified based on the location of the vehicle and the location of the mobile device associated with the driver. Alternatively, the driver is identified based on the location of the vehicle and the registration point associated with the driver.

[0009] For example, when the distance between the location of the mobile device linked to the driver and the location of the vehicle is within a threshold, the driver can be identified as the driver linked to the mobile device. Also, when the distance between the registered location linked to the driver and the vehicle is within a predetermined distance, the driver can be identified as the driver linked to the registered location. Since the driver is identified by comparing the location information of the vehicle with the location information of the mobile device or the registered location, the driver can be identified by a relatively simple method. Effect of the Invention

[0010] According to the present disclosure, the driver can be identified by a relatively simple method. [Brief description of the drawings]

[0011] [Figure 1] 1 is a diagram showing a schematic configuration of a vehicle behavior prediction system according to an embodiment of the present invention; [Diagram 2] 5 is a flowchart showing an example of a driver identification process executed by a server in the first embodiment. [Diagram 3]11 is a flowchart showing an example of a driver identification process executed by a server in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present disclosure will now be described in detail with reference to the accompanying drawings, in which the same or corresponding parts are designated by the same reference numerals and will not be described repeatedly.

[0013] [Embodiment 1] 1 is a diagram showing a schematic configuration of a vehicle behavior prediction system 1 according to the present embodiment. The vehicle behavior prediction system 1 includes a vehicle 10, a mobile terminal 30, and a server 100.

[0014] The vehicle 10 is, for example, a BEV (electric vehicle), and includes a power storage device 11, a control device 12, a GPS (Global Positioning System) device 13, and an HMI (Human Machine Interface) device 14. The GPS device 13 and the HMI device 14 may be a GPS device and an HMI device included in a navigation system of the vehicle 10. The vehicle 10 may be an HEV (hybrid electric vehicle), or may be a vehicle that is driven only by an internal combustion engine. The control device 12 (vehicle 10) is configured to be able to communicate with the server 100 through a network NW.

[0015] The mobile terminal 30 is owned by the driver of the vehicle 10. The mobile terminal 30 has a GPS function and a touch-up display. In this embodiment, the vehicle 10 has three drivers, and three mobile terminals 30 (30A, 30B, 30C) are capable of communicating with the server 100 via the network NW. The number of mobile terminals 30 provided is equal to the number of drivers of the vehicle 10.

[0016] The server 100 is a computer that predicts the behavior of the vehicle 10. The server 100 includes a control device 110 and a storage device 120, and is configured to be able to communicate with the vehicle 10 (control device 12) and the mobile terminal 30 via the network NW. The storage device 120 stores information on the drivers who own the mobile terminals 30. For each identification ID of the mobile terminal 30, a person (driver) who owns the mobile terminal 30 of the identification ID is linked, and the driver information is stored. For example, the driver A is linked to the identification ID of the mobile terminal 30A, and the driver B is linked to the identification ID of the mobile terminal 30B, and the driver information is stored.

[0017] Moreover, the mobile terminals 30A, 30B, and 30C are linked to the vehicle 10 and stored in the storage device 120. For example, the vehicle ID of the vehicle 10 and the identification ID of the mobile terminals 30A, 30B, and 30C are linked to each other and stored in the storage device 120. This allows the owners of the mobile terminals 30A, 30B, and 30C to be identified as being able to drive the vehicle 10. The identification ID of the mobile terminal 30 and the vehicle ID of the vehicle 10 are linked in advance. For example, the linking may be performed when the mobile terminal 30 is registered as a digital key for the vehicle 10. Furthermore, the mobile terminal 30 may be linked to the vehicle 10 using a shared car application installed in the mobile terminal 30.

[0018] 2 is a flowchart showing an example of a driver identification process executed by the server 100 in the first embodiment. This flowchart is repeatedly processed at predetermined intervals. In step (hereinafter, step is abbreviated as "S") 10, position information of the mobile terminal 30 (30A to 30C) and position information of the vehicle 10 are acquired.

[0019] In S11, it is determined whether the distance between the position of the vehicle 10 and the position of any of the mobile terminals 30 (30A to 30C) is within a threshold value. The threshold value may be, for example, 2 m. If the distance between all of the mobile terminals 30 and the vehicle 10 is not within the threshold value, a negative determination is made and the current routine is terminated. If the distance between any of the mobile terminals 30 and the vehicle 10 is within the threshold value, a positive determination is made and the process proceeds to S12.

[0020] In S12, the current driver of the vehicle 10 is identified from the identification ID of the mobile terminal 30 whose distance from the vehicle 10 is within a threshold. For example, if the distance between the mobile terminal 30A and the vehicle 10 is within the threshold, the driver A who owns the mobile terminal 30A is identified as the driver, and the current routine is terminated.

[0021] When the server 100 identifies the driver of the vehicle 10, it executes behavior prediction of the vehicle 10. A behavior prediction model for each driver is stored in the storage device 120. The server 100 executes behavior prediction of the vehicle 10 using the behavior prediction model of the driver identified in S12. For example, when driver A is identified as the driver, the server 100 executes behavior prediction of the vehicle 10 using behavior prediction model A of driver A. Parameters of the behavior prediction model may be, for example, location information, season, date, time, day of the week, weather, SOC (State of Charge) of the power storage device 11, and the like.

[0022] According to the first embodiment, when the distance between the positions of the mobile terminal 30 and the vehicle 10 is within a threshold based on the positions of the mobile terminal 30 and the vehicle 10 linked to the driver, the driver is identified as the driver linked to the mobile terminal 30. Since the driver is identified by comparing the position information of the vehicle 10 and the position information of the mobile terminal 30, the driver can be identified by a relatively simple method.

[0023] [Embodiment 2] In the second embodiment, the driver of the vehicle 10 is identified by comparing the position of a preset registration point with the position of the vehicle 10. Referring to FIG. 1, a plurality of registration points R are stored in the storage device 120 of the server 100 as the registration points of the vehicle 10. The number of registration points R is arbitrary, but it is preferable to set bases where the vehicle 10 is parked or stopped for a long time as the registration points. In this embodiment, three registration points RA, RB, and RC are preset as the registration points of the vehicle 10. Each registration point R is associated with a driver who drives the vehicle 10 at each registration point R and stored in the storage device 120. For example, if the person who gets on and drives the vehicle 10 at the registration point RA is A, the registration point RA and the driver A are associated and stored in the storage device 120. Also, if the person who gets on and drives the vehicle 10 at the registration point RB is B, the registration point RB and the driver B are associated and stored in the storage device 120.

[0024] 3 is a flowchart showing an example of a driver identification process executed by the server 100 in the second embodiment. This flowchart is executed when a driver gets into the vehicle 10. For example, when a seating switch provided in the driver's seat of the vehicle 10 is turned from OFF to ON, it may be determined that the driver gets into the vehicle 10. Also, when a power switch (ignition switch) of the vehicle 10 is operated from OFF to ON, it may be determined that the driver gets into the vehicle 10.

[0025] In S20, position information of the vehicle 10 is acquired. In the following S21, it is determined whether any of the registered points R (RA, RB, RC) is located within a predetermined distance from the vehicle 10. The predetermined distance may be, for example, 5 m. If the distance between all of the registered points R and the vehicle 10 is not within the predetermined distance, a negative determination is made and the current routine is terminated. If the distance between any of the registered points R and the vehicle 10 is within the predetermined distance, a positive determination is made and the routine proceeds to S22.

[0026] In S22, the driver of the registered point R that is within a predetermined distance from the vehicle 10 is identified as the current driver. For example, if the position of the registered point RA and the position of the vehicle 10 are within a predetermined distance, the driver A is identified as the driver, and the current routine is terminated.

[0027] When the server 100 identifies the driver of the vehicle 10 in S22, it executes behavior prediction of the vehicle 10 using a behavior prediction model of the driver identified in S22, in the same manner as in the first embodiment.

[0028] According to the second embodiment, when the distance between the registered point R and the vehicle 10 is within a predetermined distance based on the position of the registered point R linked to the driver and the position of the vehicle 10, the driver is identified as the driver linked to the registered point R. Since the driver is identified by comparing the position information of the vehicle 10 with the position information of the registered point R, the driver can be identified by a relatively simple method.

[0029] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is defined by the claims, not by the description of the embodiments described above, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0030] 1 behavior prediction system, 10 vehicles, 30 mobile terminals, 100 servers, NE network, R registration points.

Claims

[Claim 1] A method for identifying a driver who drives a vehicle, comprising: acquiring location information of the vehicle; A method for identifying a driver, comprising: identifying the driver based on the position of a mobile device linked to the driver and the position of the vehicle, or based on the position of a registered point linked to the driver and the position of the vehicle.

Images