Usage suggestion device and vehicle

Abstract

To provide a use proposal device and a vehicle capable of promoting use of an unused driving support system.SOLUTION: The usage proposal device is capable of performing the following four operations. (1) generating a need level for a proposed use of a given actuating device based on sensor data, traffic data, and non-traffic data, (2) selecting a particular pacing model from among a plurality of pacing models in response when the generated need level is greater than or equal to a first threshold and less than or equal to a second threshold, and (3) causing the selected particular pacing model to: Obtaining, from a specific pacing model, a first suggestion with predetermined pacing processing as a suggestion to use an actuating device by inputting sensor data, traffic data, and non-traffic data (4) outputting the obtained first suggestion; and SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a usage suggestion device and a vehicle. [Background technology]

[0002] In recent years, various driving assistance systems have been researched and developed with the aim of reducing the burden on drivers, avoiding accidents, etc. Examples of driving assistance systems include leading vehicle following systems, lane keeping systems, and automated driving systems.

[0003] Because these driving assistance systems are convenient and useful for drivers, their use is suggested to drivers via a human-machine interface (HMI). Patent Documents 1 and 2 describe that driving assistance systems are suggested via an HMI. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2023-072633 [Patent Document 2] Japanese Patent Application Publication No. 2023-066938 Summary of the Invention

[0005] A usage suggestion device according to a first aspect of the present disclosure includes an acquisition unit and a processing unit. The acquisition unit is capable of acquiring sensor data, traffic data, and non-traffic data. The sensor data is data obtained from a vehicle sensor when a subject is driving the vehicle. The traffic data is traffic data around the vehicle when the subject is driving the vehicle. The non-traffic data is data including at least one of usage data, passenger data, and behavioral data. The usage data is data stored in the user terminal by the subject using the user terminal. The passenger data is data about passengers in the vehicle when the subject is driving the vehicle. The behavioral data is data about the subject's behavior when the subject is not driving the vehicle.

[0006] The processing unit is capable of processing the sensor data, traffic data, and non-traffic data acquired by the acquisition unit. The processing unit is capable of performing the following four functions: (1) generating a degree of necessity for use suggestions for a given operating device based on sensor data, traffic data, and non-traffic data; (2) selecting a specific pacing model from among a plurality of pacing models when the generated degree of necessity is equal to or greater than a first threshold and equal to or less than a second threshold; (3) inputting the sensor data, traffic data, and non-traffic data into the selected specific pacing model, and obtaining a first proposal with a predetermined pacing process as a proposal for use of the activated device from the specific pacing model; (4) Outputting the first proposed sentence obtained.

[0007] A vehicle according to a second aspect of the present disclosure includes a usage suggestion device that has a common configuration with the usage suggestion device according to the first aspect of the present disclosure. [Brief explanation of the drawings]

[0008] The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate one embodiment and, together with the description, serve to explain the principles of the disclosure.

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of functional blocks of a vehicle according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a diagram showing an example of the exterior of the area around the driver's seat in the vehicle of FIG. [Figure 3] FIG. 3 is a diagram illustrating an example of functional blocks of the usage suggestion unit of FIG. 1 and an example of data used by the usage suggestion unit of FIG. [Figure 4] FIG. 4 is a diagram illustrating an example of a procedure for promoting the use of unused driving assistance systems in the vehicle of FIG. [Figure 5] FIG. 5 is a diagram showing an example of a usage promotion procedure following FIG. [Figure 6] FIG. 6 is a diagram showing a modified example of the functional blocks of the vehicle shown in FIG. [Figure 7] FIG. 7 is a diagram illustrating an example of functional blocks of the usage suggestion unit of FIG. 6 and an example of data used by the usage suggestion unit of FIG. [Figure 8] FIG. 8 is a diagram showing a modified example of the functional blocks of the vehicle shown in FIG. [Figure 9] FIG. 9 is a diagram illustrating an example of functional blocks of the usage suggestion unit of FIG. 8 and an example of data used by the usage suggestion unit of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] In recent years, various driving assistance systems have been researched and developed with the aim of reducing the burden on drivers, avoiding accidents, etc. Examples of driving assistance systems include leading vehicle following systems, lane keeping systems, and automated driving systems.

[0011] Because these driving assistance systems are convenient and useful for drivers, their use is suggested to drivers via a human-machine interface (HMI). Patent Documents 1 and 2 describe that driving assistance systems are suggested via an HMI.

[0012] Patent Document 1 describes a method of presenting unused functions of a vehicle to a driver and allowing the driver to select whether or not to learn the unused functions. However, Patent Document 1 does not describe whether or not the rejected learning information should be presented to the driver again when the driver rejects the learning information, nor does it describe a method of re-presenting the rejected learning information.

[0013] Patent Document 2 describes proposing to the driver to implement a recommended function. However, Patent Document 2 does not describe whether, when the driver rejects the implementation of a recommended function, the implementation of the rejected recommended function is re-prompted to the driver, nor does it describe any suggestion as to a method for re-prompting the implementation of a recommended function rejected by the driver.

[0014] As described above, there has been no disclosure or suggestion of a method for encouraging drivers to use functions that have been denied by the driver in the past. It is desirable to provide a usage suggestion device and a vehicle that can promote the use of unused driving assistance systems.

[0015] Some exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that the following description illustrates one specific example of the present disclosure and should not be construed as limiting the present disclosure. For example, each element, including numerical values, shapes, materials, parts, the position of each part, and the connection method of each part, is merely an example and should not be construed as limiting the present disclosure. Furthermore, in the following exemplary embodiments, components not described in independent claims based on the highest concept of the present disclosure are optional and may be provided as needed. The drawings are schematic and are not intended to be drawn to scale. Throughout this specification and the drawings, components having substantially the same function and configuration are designated by the same reference numerals, and redundant description will be omitted. Furthermore, components not directly related to one embodiment of the present disclosure are not shown in the drawings.

[0016] The present disclosure will be described in the following order. 1. Embodiment (Figs. 1 to 5) Example of using pacing to promote the use of unused driver assistance systems 2. Modifications (Figs. 6 to 9) Variation 1: Example of changing threshold Nth1 (described later) Variation 2: Using the revised Necessity Ni (described below) Example of retraining decision model 81Ai (described below) Modification 3: When pacing, the data stored in the server device 300 (described later) Examples of using non-traffic data (Figures 6 and 7) Modification 4: Example in which the mobile terminal 200 is not used (FIGS. 8 and 9)

[0017] <1. Embodiment> [composition] FIG. 1 illustrates an example of functional blocks of a vehicle 100 according to an embodiment of the present disclosure. The vehicle 100 corresponds to a specific example of a "vehicle" according to an embodiment of the present disclosure. The driver of the vehicle 100 (hereinafter simply referred to as the "driver") corresponds to a specific example of a "subject" according to an embodiment of the present disclosure. When the vehicle 100 has multiple occupants, one or more of the multiple occupants other than the driver are passengers of the vehicle 100, and correspond to a specific example of a "passenger" according to an embodiment of the present disclosure. For example, as shown in FIG. 1, the vehicle 100 includes a sensor unit 10, a communication unit 20, an HMI (human-machine interface) 30, a data storage unit 40, a model storage unit 50, a control unit 60, and a driving device 70.

[0018] The sensor unit 10 is configured to include various sensors mounted on the vehicle 100. The sensor unit 10 is configured to include, for example, a vehicle speed sensor, an acceleration sensor, an angular velocity sensor, a steering angular velocity sensor, and a steering torque sensor. The sensor unit 10 may include sensors other than those described above. Data obtained by the various sensors described above in the sensor unit 10 is data obtained when the driver is driving the vehicle 100, and corresponds to a specific example of "sensor data" according to an embodiment of the present disclosure.

[0019] The vehicle speed sensor is capable of detecting the speed (vehicle speed) of the vehicle 100. The vehicle speed sensor is capable of outputting time series data (vehicle speed data) about the detected vehicle speed to the control unit 60. The acceleration sensor is capable of detecting acceleration applied to the vehicle 100. The acceleration sensor is capable of outputting time series data (acceleration data) about the detected acceleration in three directions to the control unit 60. The angular velocity sensor is capable of detecting the angular velocity of the vehicle 100. The angular velocity sensor is capable of outputting time series data (angular velocity data) about the detected three angular velocities (yaw angular velocity, roll angular velocity, pitch angular velocity) to the control unit 60.

[0020] The steering angular velocity sensor is capable of detecting the rotation speed of the steering angle (steering wheel angle) of the steering wheel of the vehicle 100. The steering angular velocity sensor is capable of outputting time series data on the detected steering angular velocity to the control unit 60. The steering torque sensor is capable of detecting the steering torque generated by the driver's steering wheel operation. The steering torque sensor is capable of outputting time series data on the detected steering torque (steering torque TR) to the control unit 60.

[0021] The sensor unit 10 further includes, for example, a stereo camera 11 mounted on the vehicle 100 and a driving environment detection unit, as shown in FIG. 2. The stereo camera 11 is an autonomous sensor that senses the real space around the vehicle 100. The stereo cameras 11 are arranged, for example, at symmetrical positions on either side of the central portion in the width direction of the vehicle 100, and are capable of capturing stereo images of the area in front of the vehicle 100 from different viewpoints. The stereo camera 11 is capable of outputting image data Da (a pair of stereo image data) obtained by capturing images to the control unit 60.

[0022] The stereo camera 11 is capable of generating distance image data Db calculated from the amount of displacement between corresponding objects based on image data Da (a pair of stereo image data) obtained by capturing images. The driving environment detection unit includes, for example, a graphics processing unit (GPU) or a micro processing unit (MPU). The driving environment detection unit is capable of calculating, for example, lane markings that divide the road around the vehicle 100 based on the distance image data Db. The driving environment detection unit is further capable of calculating the road curvature of the markings that divide the left and right sides of the road (driving lane) on which the vehicle 100 is traveling, and the width between the left and right markings (vehicle width). The driving environment detection unit is also capable of performing predetermined pattern matching on the distance image data Db to detect lanes and three-dimensional objects such as structures present around the vehicle 100.

[0023] Here, when detecting a three-dimensional object in the driving environment detection unit, for example, the type of the three-dimensional object, the distance to the three-dimensional object, the speed of the three-dimensional object, and the relative speed between the three-dimensional object and the vehicle (host vehicle) are detected. Examples of three-dimensional objects to be detected include traffic lights, intersections, road signs, stop lines, other vehicles, pedestrians, bicycles, and buildings. Examples of buildings include detached houses, apartment complexes (condominiums), commercial facilities, factories, and signs. The driving environment detection unit is capable of outputting driving environment information around the vehicle 100, including the thus acquired information on the three-dimensional object, to the control unit 60.

[0024] The sensor unit 10 further includes, for example, an in-vehicle camera 12 mounted on the vehicle 100, a sound collection microphone, and an occupant detection unit, as shown in FIG. 2 . The in-vehicle camera 12 is an autonomous sensor that senses the real space inside the vehicle 100. The in-vehicle camera 12 is, for example, a monocular camera arranged at the center of the vehicle 100 in the width direction, and is capable of capturing images of the entire interior of the vehicle 100. The in-vehicle camera 12 is capable of outputting image data Dc obtained by capturing the images to the occupant detection unit and the control unit 60. The sound collection microphone is, for example, capable of collecting the voices of occupants inside the vehicle 100, and outputting the resulting voice data Dd to the occupant detection unit and the control unit 60.

[0025] The occupant detection unit includes, for example, a GPU or an MPU. The occupant detection unit is capable of detecting one or more occupants inside the vehicle 100, for example, based on image data Dc. The occupant detection unit is capable of analyzing the attributes and behavior of each detected occupant, for example, based on image data Dc and voice data Dd, generating occupant attributes, a voice history, and a behavior history for each occupant, and outputting the occupant attributes, voice history, and behavior history to the control unit 60. The attributes, voice history, and behavior history of the driver among the occupants of the vehicle 100 correspond to a specific example of driver monitoring system (DMS) data. The attributes, voice history, and behavior history of one or more passengers other than the driver among the occupants of the vehicle 100 correspond to a specific example of "passenger data" according to an embodiment of the present disclosure.

[0026] The occupant attributes may include, for example, an identifier indicating the driver, an identifier indicating that the passenger of the vehicle 100 is a family member of the driver other than the driver, or an identifier indicating that the passenger of the vehicle 100 is a family member of the driver other than the driver. The voice history may include, for example, the type of voice tone, voice pitch, speaking rate, and dialect of the occupant. The behavior history may include, for example, facial expressions, posture, movement habits, signs of drowsiness, eating and drinking habits, etc.

[0027] The communication unit 20 can acquire data to supplement data that cannot be obtained from the image data Da and the distance image data Db, for example, through vehicle-to-vehicle communication, road-to-vehicle communication, satellite communication, and short-range wireless data communication. The communication unit 20 can output the acquired data to the control unit 60.

[0028] The communication unit 20 is capable of acquiring data (e.g., vehicle position, vehicle speed) obtained by other vehicles, for example, through vehicle-to-vehicle communication. The communication unit 20 is capable of receiving positioning signals transmitted from multiple positioning satellites, for example, through satellite communication.

[0029] The communication unit 20 is capable of acquiring road map data of the surroundings of the vehicle 100, for example, through road-to-vehicle communication. The road map data consists of, for example, highly accurate road map information (dynamic map), and has static information and quasi-static information that mainly constitute road information, and quasi-dynamic information and dynamic information that mainly constitute traffic information.

[0030] Static information that makes up road information includes information that must be updated within one month, such as roads, structures on roads, structures around roads, lane information, road surface information, and permanent traffic regulations. "Roads" include, for example, road location and shape information, as well as intersection and road attribute information (e.g., national highways, prefectural roads, city roads, private roads, priority roads, non-priority roads, general roads, expressways, number of lanes, presence or absence of median strips, presence or absence of dedicated right-turn lanes, time-delayed traffic, pedestrian-vehicle separation), etc. "Structures on roads" include, for example, traffic signs, traffic lights, convex mirrors, pedestrian bridges, bus stops, garbage collection stations, etc. "Structures around roads" include, for example, various buildings, parks, etc.

[0031] The quasi-static information that constitutes road information is composed of information that needs to be updated every hour or less, such as traffic regulation information due to road construction or events, wide-area weather information, and traffic congestion forecasts.

[0032] The semi-dynamic information that makes up traffic information is composed of information that must be updated within one minute, such as the actual traffic congestion situation at the time of observation, driving restrictions, temporary driving obstructions such as fallen objects and obstacles, actual accident conditions, and narrow-area weather information.

[0033] The dynamic information that constitutes the traffic information is composed of information that needs to be updated every second, such as information sent and exchanged between moving bodies, information on currently displayed traffic signals, information on pedestrians and bicycles at intersections, information on vehicles traveling on roads, etc. Such road map information is maintained and updated periodically until the next information is received from each vehicle, and the updated road map information is transmitted to each vehicle as appropriate via the communication unit 20.

[0034] The communication unit 20 can acquire data (usage data) stored in the driver's mobile terminal 200 by the driver using the mobile terminal 200 from the driver's mobile terminal 200 via short-range wireless data communication between digital devices, such as Bluetooth (registered trademark). The mobile terminal 200 corresponds to a specific example of a "usage terminal" according to an embodiment of the present disclosure. The usage data corresponds to a specific example of "usage data" according to an embodiment of the present disclosure. The usage data may include, for example, the driver's voice history during calls and the driver's behavior history for three days including the day on which the communication unit 20 acquired the usage data from the mobile terminal 200. The voice history that may be included in the usage data may include, for example, the driver's tone of voice, voice pitch, speaking rate, and dialect. The behavior history that may be included in the usage data may include, for example, a history of the locations the driver traveled during the three days (e.g., GPS data and map data).

[0035] 2, the HMI 30 includes a steering wheel 31, an accelerator pedal 32, a brake pedal 33, a meter panel display 34, a center panel display 35, a speaker 36, and a microphone 37. The meter panel display 34 includes, for example, a liquid crystal display panel or an organic EL display panel, and is capable of displaying information such as speed and engine RPM. The center panel display 35 includes, for example, a touch-input-enabled liquid crystal display panel or an organic EL display panel, and is capable of performing various settings for the vehicle 100.

[0036] The data storage unit 40 is configured, for example, by a non-volatile memory, such as an EEPROM (Electrically Erasable Programmable Read-Only Memory), a flash memory, a resistance change memory, etc. The data storage unit 40 stores, for example, a road map DB 41, driving data 42, non-traffic data 43, threshold data 44, and fixed phrases 45, as shown in FIG.

[0037] The road map DB 41 includes high-precision road map information (dynamic map). This high-precision road map information, like road map information acquired from the outside through road-to-vehicle communication, mainly includes static information and quasi-static information constituting road information, and quasi-dynamic information and dynamic information constituting traffic information.

[0038] The driving data 42 includes, for example, data on the surroundings of the vehicle 100 obtained by the sensor unit 10 (sensor data 42a), traffic data on the surroundings of the vehicle 100 while the driver is driving the vehicle 100 (traffic data 42b), and driver data on the driver obtained by the sensor unit 10 (DMS data 42c). The sensor data 42a corresponds to a specific example of "sensor data" according to an embodiment of the present disclosure. The traffic data 42b is data obtained by a data obtaining unit 61 (described later) that includes the road information and traffic information described above, and corresponds to a specific example of "traffic data on the surroundings of the vehicle" according to an embodiment of the present disclosure.

[0039] The non-traffic data 43 includes usage data 43a stored in the mobile terminal 200 by the driver using the mobile terminal 200, and passenger data 43b of the vehicle 100 when the driver is driving the vehicle 100. The non-traffic data 43 corresponds to a specific example of "non-traffic data" according to an embodiment of the present disclosure. The usage data 43a is usage data obtained from the mobile terminal 200 via the communication unit 20, and corresponds to a specific example of "usage data" according to an embodiment of the present disclosure. The passenger data 43b is data including the voice history and behavior history of the passenger obtained from the inside of the sensor unit 10 (the in-vehicle camera, the sound collecting microphone, and the occupant detection unit), and corresponds to a specific example of "passenger data" according to an embodiment of the present disclosure.

[0040] The threshold data 44 includes, for example, two thresholds Nth1 and Nth2. The thresholds Nth1 and Nth2 are values ​​for comparison with the output value of a determination model 81Ai (1≦i≦n; n is the number of pacing models stored in a model storage unit 50, described later). The threshold Nth1 corresponds to a specific example of a "first threshold" according to an embodiment of the present disclosure. The threshold Nth2 is a value greater than the threshold Nth1 and corresponds to a specific example of a "second threshold" according to an embodiment of the present disclosure. The threshold Nth1 has an initial value of, for example, 0.4. The threshold Nth2 has an initial value of, for example, 0.8.

[0041] The template 45 includes a plurality of template messages exchanged with the driver to encourage the use of an unused driving assistance system. The template 45 includes, for example, a plurality of suggestion messages and a plurality of response messages. The plurality of suggestion messages included in the template 45 include, for example, "Why not try using an automated driving system?", "Why not try using a leading vehicle following system?", and "Why not try using a lane keeping system?" The plurality of response messages included in the template 45 include, for example, "I understand." In this specification, the automated driving system, the leading vehicle following system, and the lane keeping system correspond to specific examples of a plurality of operating devices available in the vehicle 100.

[0042] The model storage unit 50 is configured, for example, by a nonvolatile memory, such as an EEPROM, a flash memory, or a resistive memory. The model storage unit 50 stores a plurality of pacing models. The plurality of pacing models stored in the model storage unit 50 include, for example, a mirroring model 51, a matching model 52, a backtracking model 53, a calibration model 54, a tuning model 55, and a VAK (Visual-Auditory-Kinesthetic) model 56, as shown in FIG. 1 .

[0043] Here, "pacing" refers to, when communicating with a driver, adjusting the "pace" of, for example, the pitch of voice, speaking speed, and speaking content to match the driver's psychological state. The pacing model is a learning model that, when a fixed phrase A and various data required for pacing the fixed phrase A are input, can output modified phrase B for fixed phrase A, which has been pacing-processed to correspond to the driver's characteristics contained in the various input data. Examples of data representing the driver's characteristics include the driver's facial expression, posture, movement habits, type of tone of voice, pitch of voice, speaking speed, and type of dialect.

[0044] The pacing model is a model trained using, as training data, driving data 42 and non-traffic data 43 (learning driving data and learning non-traffic data) obtained in various past situations, standard learning sentences, and modified learning sentences obtained by performing a predetermined pacing process on the standard learning sentences. The pacing model is also retrained using, as training data, data from the data storage unit 40 (driving data 42 and non-traffic data 43), a suggested sentence (standard sentence S1), a suggested sentence (standard sentence S2) obtained by performing a predetermined pacing process on the suggested sentence (standard sentence S1), and an identifier (response content) indicating whether the driver accepted or rejected the suggested sentence (standard sentence S2). When the pacing model receives the data (driving data 42 and non-traffic data 43) from the data storage unit 40 updated after relearning and a suggested sentence (standard sentence S1), it is able to output a new suggested sentence (standard sentence S2) that has undergone a predetermined pacing process for the input suggested sentence (standard sentence S1).

[0045] When the mirroring model 51 receives the driving data 42, non-traffic data 43, and text data (standard phrases), it is capable of generating voice data (sentences (modified sentences) that are modified from the standard phrases) with a speaking style and content that matches the driver's facial expressions, posture, and movement habits contained in the input driving data 42 and non-traffic data 43.

[0046] When the driving data 42, non-traffic data 43, and text data (standard phrases) are input, the matching model 52 is capable of generating voice data (sentences (modified sentences) obtained by modifying the standard phrases) with a speaking style and content that matches the type of voice tone, voice pitch, speaking speed, and dialect of the driver contained in the input driving data 42 and non-traffic data 43.

[0047] When the backtracking model 53 receives the driving data 42, non-traffic data 43, and text data (standard phrases), it is capable of generating voice data (a modified standard phrase (modified sentence)) including sentence A, spoken in a manner that matches the type of voice tone, voice pitch, speaking speed, and dialect of the driver contained in the input driving data 42 and non-traffic data 43.

[0048] When the driving data 42, non-traffic data 43, and text data (standard phrases) are input, the calibration model 54 is capable of generating voice data (sentences (modified sentences) that are modified from the standard phrases) with a speaking style and content that takes into account the psychological state of the driver that can be read from the input driving data 42 and non-traffic data 43.

[0049] When the driving data 42, non-traffic data 43, and text data (standard phrases) are input, the tuning model 55 is capable of generating voice data (sentences (modified sentences) that are modified from the standard phrases) with a speaking style and content that is in line with the psychological state of the driver that can be read from the input driving data 42 and non-traffic data 43.

[0050] When the driving data 42, non-traffic data 43, and text data (standard phrases) are input, the VAK model 56 is capable of generating voice data (sentences (modified sentences) that are modified from the standard phrases) with a speaking style and content that matches the driver's preference (either visual, auditory, or kinesthetic) that can be read from the input driving data 42 and non-traffic data 43.

[0051] The control unit 60 is capable of controlling the entire vehicle 100. The control unit 60 is, for example, a so-called ECU (Electronic Control Unit), and is configured to include, for example, one or more processors and one or more memories. The control unit 60 may be configured to include, for example, a CPU (Central Processing Unit). In this case, the control unit 60 is capable of controlling the entire vehicle 100 by, for example, executing a program stored in a storage unit.

[0052] The control unit 60 includes, for example, a locator unit. The locator unit is capable of acquiring the position coordinates of the vehicle 100 based on the positioning signal received through the communication unit 20. The locator unit is capable of estimating the vehicle's position on a road map by map-matching the acquired position coordinates with route map information. Based on the acquired position coordinates of the vehicle 100, the locator unit acquires map information of a predetermined range including the vehicle 100 from map information stored in a road map DB (database) 41 (described later).

[0053] In an environment where it is not possible to receive valid positioning signals from positioning satellites due to reduced sensitivity, such as when driving inside a tunnel, the locator unit can switch to autonomous navigation, which estimates the vehicle's position based on the vehicle speed, angular velocity, and longitudinal acceleration detected by sensor unit 10, and estimate the vehicle's position on a road map.

[0054] As described above, the locator unit estimates the position of vehicle 100 on a road map (vehicle position) based on the positioning signal received through communication unit 20 or information detected by sensor unit 10, and is then able to determine the road type, etc. of the road on which vehicle 100 is traveling based on the estimated vehicle position on the road map.

[0055] The locator unit is capable of updating the road map information stored in the road map DB 41 to the latest version using road map information acquired through external communication (roadside-to-vehicle communication and vehicle-to-vehicle communication) via the communication unit 20. This information update is performed not only for static information but also for quasi-static information, quasi-dynamic information, and dynamic information. As a result, the road map information includes road information and traffic information acquired through communication with the outside of the vehicle, and information on moving objects such as vehicles traveling on roads is updated in approximately real time.

[0056] The locator unit verifies road map information based on the traveling environment information recognized as described above, and updates the road map information stored in the road map DB 41 to the latest version. This information update is performed not only on static information, but also on semi-static information, semi-dynamic information, and dynamic information. As a result, information on moving objects such as vehicles traveling on roads recognized as described above is updated in real time.

[0057] 1, the control unit 60 further includes a driving control unit 63. The driving control unit 63 includes, for example, an accelerator control unit, a brake control unit, and a steering control unit, and is capable of controlling the driving device 70 using these control units. The driving device 70 includes, for example, a prime mover, a brake, and an EPS motor.

[0058] The accelerator control unit is capable of controlling the torque of the prime mover included in the traveling device 70 based on the required torque corresponding to the accelerator pedal depression amount by the driver of the vehicle 100. The prime mover is configured to drive the steered wheels of the vehicle 100, and is capable of driving the steered wheels of the vehicle 100 in accordance with the required torque input from the accelerator control unit.

[0059] The brake control unit is capable of controlling the torque (braking force) of the brakes included in the traveling device 70 based on the required torque corresponding to the amount of brake pedal depression by the driver of the vehicle 100. The brakes are configured to brake the steered wheels of the vehicle 100, and are capable of braking the steered wheels of the vehicle 100 in accordance with the required torque input from the brake control unit.

[0060] The steering control unit is capable of deriving a steering assist torque that assists the steering torque generated by the driver's steering wheel operation and setting an EPS torque corresponding to the derived steering assist torque. The steering control unit is capable of outputting a control signal to the EPS motor included in the traveling device 70 so that the output torque of the EPS motor becomes the set EPS torque. The EPS motor generates an output torque based on the input control signal and is capable of controlling the steering angle of the steering wheel.

[0061] The control unit 60 further includes, for example, a data acquisition unit 61 and a usage suggestion unit 62, as shown in FIG. 1. The data acquisition unit 61 corresponds to a specific example of an "acquisition unit" in the present disclosure. The usage suggestion unit 62 corresponds to a specific example of a "control unit" in the present disclosure.

[0062] The data acquisition unit 61 is capable of periodically acquiring data on the situation or state of the vehicle 100. Specifically, the data acquisition unit 61 is capable of periodically acquiring, by monitoring, various data obtained from the sensor unit 10, various data obtained from the outside via the communication unit 20, and various control signals for various devices of the vehicle 100. The data acquisition unit 61 is further capable of acquiring map data of the surroundings of the vehicle 100 from the road map DB 41 of the data storage unit 40.

[0063] The data acquisition unit 61 is capable of acquiring driving data 42 and non-traffic data 43 based on acquired data (various data acquired from the sensor unit 10, various data acquired from the outside via the communication unit 20, various data acquired from the HMI 30, various control signals for various devices of the vehicle 100, and map data acquired from the road map DB 41). Every time the data acquisition unit 61 acquires driving data 42 and non-traffic data 43, the data acquisition unit 61 can store the acquired driving data 42 and non-traffic data 43 in the data storage unit 40. The data storage unit 40 stores, for example, three days' worth of driving data 42 and non-traffic data 43.

[0064] The usage suggestion unit 62 is capable of reading out the driving data 42 and the non-traffic data 43 from the data storage unit 40. The usage suggestion unit 62 is capable of processing the data (driving data 42 and non-traffic data 43) read out from the data storage unit 40. The usage suggestion unit 62 has, for example, a necessity determination unit 81, a model selection unit 82, and a pacing unit 83, as shown in FIG.

[0065] 3, the necessity determination unit 81 has n determination models 81Ai (1≦i≦n) and a determination unit 81B. The n determination models 81Ai are models assigned one for each pacing model stored in the model storage unit 50. When data (driving data 42 and non-traffic data 43) from the data storage unit 40 is input, each determination model 81Ai is capable of outputting the necessity Ni (for example, 0≦Ni≦1) of the assigned pacing model based on the input data.

[0066] The determination model 81Ai is a model trained using, as training data, the driving data 42 and non-traffic data 43 (learning driving data and learning non-traffic data) obtained in various past situations and the degree of necessity Ni (learning degree of necessity) set corresponding to the learning driving data and learning non-traffic data. The determination model 81Ai is also re-trained using, as training data, the data (driving data 42 and non-traffic data 43) in the data storage unit 40 and the degree of necessity Ni obtained by inputting the data (driving data 42 and non-traffic data 43) in the data storage unit 40 into the determination model 81Ai. When the data (driving data 42 and non-traffic data 43) in the data storage unit 40 updated after the re-learning is input, the determination model 81Ai is capable of generating and outputting a new degree of necessity Ni for the assigned pacing model based on the input data.

[0067] The necessity determination unit 81 is capable of generating a degree of necessity Ni for a use suggestion of a predetermined operating device based on the driving data 42 and non-traffic data 43 read from the data storage unit 40. The necessity determination unit 81 is capable of selecting an appropriate operating device from among a plurality of operating devices based on the driving data 42 and non-traffic data 43. The necessity determination unit 81 inputs the driving data 42 and the non-traffic data 43 to a determination model 81Ai (hereinafter referred to as the "selected determination model 81Ai") corresponding to the selected operating device (predetermined operating device), thereby obtaining a degree of necessity Ni for a use suggestion of the predetermined operating device from the selected determination model 81Ai in response to the input data.

[0068] The determination unit 81B is capable of comparing the degree of necessity Ni with two thresholds Nth1 and Nth2. When the degree of necessity Ni is higher than the threshold Nth2, the determination unit 81B is capable of reading one fixed phrase S1 included in the fixed phrases 45 from the data storage unit 40 and outputting the read fixed phrase S1 to the HMI 30. When the degree of necessity Ni is lower than the threshold Nth1, the determination unit 81B is capable of canceling the output of the fixed phrase S1 (i.e., not outputting anything). When the degree of necessity Ni is equal to or greater than the threshold Nth1 and equal to or less than the threshold Nth2, that is, when the degree of necessity Ni is within the pacing target range, the determination unit 81B is capable of outputting a flag FLG indicating that the degree of necessity Ni is within the pacing target range to the model selection unit 82. When the degree of necessity Ni is within the pacing target range, the judgment unit 81B is capable of reading out one standard phrase S1 included in the standard phrases 45 from the data storage unit 40 and outputting the read standard phrase S1 to the pacing unit 83.

[0069] 3, the model selection unit 82 has a selection model 82A. When data (driving data 42 and non-traffic data 43) from the data storage unit 40 is input, the selection model 82A is capable of selecting an appropriate pacing model (hereinafter referred to as "pacing model 83A") from among the multiple pacing models stored in the model storage unit 50 based on the input data, and outputting an identifier Sx of the selected pacing model 83A to the pacing unit 83.

[0070] When flag FLG is input from determination unit 81B, model selection unit 82 is able to select a specific pacing model 83A from among the multiple pacing models stored in model storage unit 50, based on driving data 42 and non-traffic data 43. When flag FLG is input from determination unit 81B, model selection unit 82 is able to input driving data 42 and non-traffic data 43 to selection model 82A, and thereby acquire, from selection model 82A, an identifier Sx of pacing model 83A appropriate for the input data, as a response to the input data.

[0071] When the identifier Sx is input from the model selection unit 82, the pacing unit 83 is capable of reading out the pacing model Mx (pacing model 83A) corresponding to the identifier Sx from the model storage unit 50. By inputting the driving data 42, non-traffic data 43, and the standard text S1 to the read (selected) pacing model 83A, the pacing unit 83 is capable of acquiring, from the pacing model 83A, a modified text Sa in which a predetermined pacing process has been performed on the standard text S1 as a suggested text for using the operating device. The pacing unit 83 is capable of outputting the acquired modified text Sa (suggested text) to the HMI 30.

[0072] The use suggestion unit 62 is capable of acquiring an answer sentence Ans from the HMI 30 as a response to the modified sentence Sa from the driver. If the acquired answer sentence Ans indicates approval of use of the operating device, the use suggestion unit 62 is capable of reading a fixed phrase S2 indicating understanding, which is included in the fixed phrases 45, from the data storage unit 40, and outputting the read fixed phrase S2 to the HMI 30. If the acquired answer sentence Ans indicates refusal of use of the operating device, the use suggestion unit 62 is capable of reading a fixed phrase S2 indicating understanding, which is included in the fixed phrases 45, from the data storage unit 40, and outputting the read fixed phrase S2 to the pacing unit 83.

[0073] When the fixed sentence S2 is input, the pacing unit 83 inputs the driving data 42, the non-traffic data 43, and the fixed sentence S2 to the pacing model 83A, and is thereby able to acquire from the pacing model 83A a modified sentence Sb, which is a sentence of understanding for the refusal to use the operating device, in which a predetermined pacing process has been performed on the fixed sentence S2. The pacing unit 83 is able to output the acquired modified sentence Sb (understanding sentence) to the HMI 30.

[0074] When a fixed phrase S1 is input from the usage suggestion unit 62, the HMI 30 (speaker 36) is capable of outputting the input fixed phrase S1 as a voice message. When an altered sentence Sa is input from the usage suggestion unit 62, the HMI 30 (speaker 36) is capable of outputting the input altered sentence Sa as a voice message. When an altered sentence Sb is input from the usage suggestion unit 62, the HMI 30 (speaker 36) is capable of outputting the input altered sentence Sb as a voice message. When the HMI 30 (microphone 37) collects an answer sentence Ans from the driver as a voice message in response to the altered sentence Sa, the HMI 30 (microphone 37) is capable of outputting the collected answer sentence Ans to the usage suggestion unit 62.

[0075] [Operation] Next, the operation of the control unit 60 of the vehicle 100 will be described with reference to Fig. 4. Fig. 4 is a diagram for explaining an example of a procedure for promoting the use of unused driving assistance systems in the vehicle 100.

[0076] The data acquisition unit 61 periodically acquires data from the sensor unit 10, the communication unit 20, and various devices of the vehicle 100. This data may include various data acquired from the sensor unit 10, various data acquired from the outside via the communication unit 20, various data acquired from the HMI 30, and various control signals for various devices of the vehicle 100. The data acquisition unit 61 also acquires map data of the surroundings of the vehicle 100 from the road map DB 41 in the data storage unit 40. The data acquisition unit 61 further acquires driving data 42 and non-traffic data 43 based on the acquired data. Every time the data acquisition unit 61 acquires the driving data 42 and non-traffic data 43, it stores the acquired driving data 42 and non-traffic data 43 in the data storage unit 40.

[0077] The control unit 60 reads out the driving data 42 and the non-traffic data 43 from the data storage unit 40 (step S101). The control unit 60 selects an appropriate operating device from among a plurality of operating devices based on the read driving data 42 and non-traffic data 43. The control unit 60 inputs data from the data storage unit 40 into the determination model 81Ai corresponding to the selected operating device (predetermined operating device), and thereby acquires the degree of necessity Ni of a usage suggestion for the predetermined operating device from the determination model 81Ai as a response to the input data (step S102).

[0078] The control unit 60 determines whether the degree of necessity Ni is higher than a threshold value Nth1 (step S103). If the degree of necessity Ni is higher than the threshold value Nth1 (step S103; Y), the control unit 60 determines whether the degree of necessity Ni is higher than a threshold value Nth2 (step S104). If the degree of necessity Ni is higher than the threshold value Nth2 (step S104; Y), the control unit 60 outputs a fixed phrase S1 suggesting the use of a predetermined operating device to the HMI 30 (step S105). When the fixed phrase S1 is input from the control unit 60, the HMI 30 outputs the input fixed phrase S1 as a voice message.

[0079] When the degree of necessity Ni is equal to or greater than threshold value Nth1 and equal to or less than threshold value Nth2 (step S104; N), control unit 60 selects an appropriate pacing model 83A from among the multiple pacing models stored in model storage unit 50 based on driving data 42 and non-traffic data 43 (step S106). Control unit 60 selects pacing model 83A using, for example, selection model 82A.

[0080] The control unit 60 inputs the driving data 42, non-traffic data 43, and the standard text S1 to the pacing model 83A, and acquires from the pacing model 83A an altered text Sa, which is a text suggesting use of the operating device, obtained by performing a predetermined pacing process on the standard text S1 (step S107). The control unit 60 outputs the altered text Sa, which has been subjected to the predetermined pacing process, to the HMI 30 (step S108). When the altered text Sa is input from the control unit 60, the HMI 30 outputs the input altered text Sa as a voice message.

[0081] The control unit 60 determines whether or not a response (answer sentence Ans) to the modified sentence Sa has been received from the HMI 30 from the driver (step S109). If the control unit 60 has received the answer sentence Ans from the HMI 30 (step S109; Y), the control unit 60 determines whether or not the answer sentence Ans indicates a refusal to use the operating device (step S110). If the answer sentence Ans indicates approval to use the operating device (step S110; N), the control unit 60 outputs a fixed sentence S2 indicating approval to the HMI 30 (step S111).

[0082] If the answer sentence Ans indicates a denial of use of the operating device (step S110; Y), the control unit 60 inputs the driving data 42, non-traffic data 43, and the standard sentence S2 to the pacing model 83A, thereby acquiring from the pacing model 83A a modified sentence Sb obtained by performing a predetermined pacing process on the standard sentence S2 as an understanding sentence for the denial of use of the operating device (step S112). The control unit 60 outputs the modified sentence Sb obtained by performing a predetermined pacing process to the HMI 30 (step S113). When the modified sentence Sb is input from the control unit 60, the HMI 30 outputs the input modified sentence Sb as a voice message. In this way, the use of unused driving assistance systems in the vehicle 100 is promoted.

[0083] [effect] Next, the effects of vehicle 100 according to this embodiment will be described.

[0084] In this embodiment, a degree of necessity Ni for a suggestion to use a predetermined operating device is generated based on the driving data 42 and the non-traffic data 43. When the generated degree of necessity Ni is equal to or greater than the threshold Nth1 and equal to or less than the threshold Nth2, the driving data 42 and the non-traffic data 43 are input to a specific pacing model 82A selected based on the driving data 42 and the non-traffic data 43, and a suggested sentence (modified sentence Sa) that has undergone a predetermined pacing process is obtained from the specific pacing model 82A as a suggestion sentence for using the operating device. This increases the likelihood that a driver who hears the suggested sentence (modified sentence Sa) that has undergone a predetermined pacing process will readily accept the suggestion without feeling annoyed. As a result, the use of unused driving assistance systems can be promoted.

[0085] In this embodiment, the determination model 81Ai is a learning model that is re-trained using the driving data 42, the non-traffic data 43, and the degree of necessity Ni as teaching data. New driving data 42 and non-traffic data 43 are input to the determination model 81Ai, and a new degree of necessity Ni is obtained from the determination model 81Ai. This makes it possible to obtain the degree of necessity Ni corresponding to various driving data 42 and non-traffic data 43, and therefore it is possible to provide a suggested sentence (modified sentence Sa) that is likely to make the driver accept the suggestion willingly without feeling uncomfortable. As a result, it is possible to promote the use of unused driving assistance systems.

[0086] In this embodiment, the pacing model 83A is a learning model that is re-trained using, as teaching data, the driving data 42, the non-traffic data 43, the proposed sentence (standard sentence S1), the proposed sentence (modified sentence Sa), and an identifier (response content) indicating whether the driver accepted or rejected the proposed sentence (standard sentence S2). Then, new driving data 42, the non-traffic data 43, and the proposed sentence (standard sentence S1) are input to the pacing model 83A, thereby obtaining a new proposed sentence (standard sentence S1). This makes it possible to obtain a proposed sentence (modified sentence Sa) that reflects the driver's preferences, thereby providing a proposed sentence (modified sentence Sa) that is likely to make the driver accept the proposal willingly without feeling uncomfortable. As a result, it is possible to promote the use of unused driving assistance systems.

[0087] In this embodiment, the multiple pacing models stored in the model storage unit 50 include at least one of a mirroring model, a matching model, a backtracking model, a calibration model, a tuning model, and a VAK model. This makes it possible to obtain a suggested sentence (modified sentence Sa) that reflects the driver's preferences, and therefore to provide a suggested sentence (modified sentence Sa) that is likely to make the driver accept the suggestion willingly without feeling uncomfortable. As a result, it is possible to promote the use of unused driving assistance systems.

[0088] In this embodiment, when the necessity level Ni is smaller than the threshold value Nth1, the output of the suggested text (fixed text S1) is stopped. As a result, when the driver has no intention of using the driving assistance system, the use of the driving assistance system is not suggested, so that the driver can be prevented from feeling uncomfortable.

[0089] In this embodiment, when the necessity level Ni is greater than the threshold value Nth2, a standard suggestion sentence is output as a suggestion sentence for using the activated device. In other words, pacing is not performed when the driver intends to use the driving assistance system. This makes it possible to promote the use of unused driving assistance systems without performing processing for pacing.

[0090] In this embodiment, the usage data 43a obtained from the mobile terminal 200 via the communication unit 20 includes the driver's voice history during calls. This makes it possible to perform pacing according to, for example, the driver's tone of voice, voice pitch, speaking speed, dialect, etc. As a result, it is possible to increase the likelihood that a driver who hears a proposed sentence (modified sentence Sa) that has been subjected to a predetermined pacing process will accept the proposal without feeling annoyed. This can therefore promote the use of unused driving assistance systems.

[0091] In this embodiment, the passenger data 43b obtained from the in-vehicle camera 12 includes attributes of one or more passengers who are riding in the vehicle 100 when the driver is driving the vehicle 100. This makes it possible to obtain a suggested sentence (modified sentence Sa) that reflects the psychological state of the driver when, for example, one or more passengers are family members. As a result, it is possible to increase the likelihood that a driver who hears a suggested sentence (modified sentence Sa) that reflects such a psychological state will readily accept the suggestion without feeling uncomfortable. As a result, it is possible to promote the use of unused driving assistance systems.

[0092] <2. Modifications> [Variation 1] In the above embodiment, when the degree of necessity Ni is equal to or greater than the threshold Nth1 and equal to or less than the threshold Nth2, and the driver's response to the output of the proposed sentence (modified sentence Sa) indicates a refusal to use a predetermined operating device, the necessity determination unit 81 may be able to change the threshold Nth1 in the threshold data 44 stored in the data storage unit 40 to a value smaller than the initial threshold Nth1. In this case, the pacing target range is widened, and it is possible to promote the use of unused driving assistance systems while reducing the possibility of using pacing to make the driver feel uncomfortable.

[0093] [Variation 2] In the above embodiment and the first modified example, when the degree of necessity Ni is equal to or greater than the threshold value Nth1 and equal to or less than the threshold value Nth2, and the driver's response to the output of the proposed sentence (modified sentence Sa) indicates a refusal to use a predetermined operating device, the necessity determination unit 81 may be capable of re-training the determination model 81Ai using, as teaching data, the data (the driving data 42 and the non-traffic data 43) of the data storage unit 40 and a value that is smaller by a predetermined magnitude than the degree of necessity Ni obtained by inputting the data (the driving data 42 and the non-traffic data 43) of the data storage unit 40 into the determination model 81Ai. In this case, the possibility that the degree of necessity Ni falls outside the pacing target range can be increased, and therefore the possibility of presenting the driver with a proposed sentence (modified sentence Sa) that makes the driver feel uncomfortable can be reduced.

[0094] [Variation 3] In the above embodiment and the first and second modifications, the data storage unit 40 may store non-traffic data 46 instead of the non-traffic data 43, for example, as shown in FIG. 6. In this case, the non-traffic data 46 is data including usage data 43a, passenger data 43b, and behavior data 43c, for example, as shown in FIG. 7. The behavior data 43c is behavior data of the driver when the driver is not driving the vehicle 100, for example, behavior data of the driver for three days when the driver is not driving the vehicle 100. The behavior data 43c includes, for example, at least one of data obtained when the driver is a passenger in the vehicle 100, data obtained when the driver is a passenger in another vehicle other than the vehicle 100, and data obtained when the driver is not in the vehicle 100 or another vehicle.

[0095] 6, the behavior data 43c may be stored in a server device 300 that can communicate with the vehicle 100 via a network 400. When the behavior data 43c is stored in the server device 300, the control unit 60 can acquire the behavior data 43c from the server device 300 via the communication unit 20 and the network 400, and store the acquired behavior data 43c in the data storage unit 40.

[0096] Here, "data obtained when the driver is riding as a passenger in vehicle 100" may include, for example, the driver's voice history and behavioral history. "data obtained when the driver is riding as a passenger in a vehicle other than vehicle 100" may include, for example, the driver's voice history and behavioral history. The driver's voice history may include, for example, the driver's tone of voice, voice pitch, speaking rate, and dialect. The driver's behavioral history may include, for example, facial expressions, posture, movement habits, signs of drowsiness, and eating and drinking habits.

[0097] The "data obtained when the driver is not in vehicle 100 or another vehicle" may include, for example, the driver's behavior history. The driver's behavior history may include, for example, a history of the locations where the driver has traveled over a three-day period (for example, GPS data and map data).

[0098] In this modification, the usage suggestion unit 62 uses the non-traffic data 46 instead of the non-traffic data 43. This allows the driver's characteristics to be captured in more detail, increasing the likelihood that the driver will accept the suggestion without feeling annoyed when hearing the suggested sentence (modified sentence Sa) that has been subjected to a predetermined pacing process. As a result, the use of unused driving assistance systems can be promoted.

[0099] [Variation 4] In the above-described embodiment and the first and second modifications, the data storage unit 40 may store non-traffic data 47 instead of the non-traffic data 43, as shown in FIG. 8, for example. In this case, the non-traffic data 47 includes passenger data 43b and behavioral data 43c, as shown in FIG. 9, for example. In other words, the non-traffic data 47 does not include usage data 43a obtained from the mobile terminal 200, and the mobile terminal 200 is not connected to the communication unit 20, as shown in FIG. 8, for example. In this way, even if usage data 43a cannot be obtained from the mobile terminal 200, behavioral data 43c can be used instead of usage data 43a. This increases the likelihood that a driver who hears a suggested sentence (modified sentence Sa) that has undergone a predetermined pacing process will readily accept the suggestion without feeling annoyed. As a result, the use of unused driving assistance systems can be promoted.

[0100] Although the present disclosure has been described above using embodiments, the present disclosure is not limited to these embodiments and various modifications are possible. The effects described in this specification are merely examples, and the effects of the present disclosure are not limited to the effects described in this specification. Therefore, other effects may be obtained with respect to the present disclosure.

[0101] Furthermore, the present disclosure may take the following aspects. (1) an acquisition unit capable of acquiring non-traffic data which is at least one of sensor data obtained from a sensor of a vehicle when the subject is driving the vehicle, traffic data around the vehicle when the subject is driving the vehicle, usage data stored in the user terminal of the subject when the subject uses the user terminal of the subject, passenger data of the vehicle when the subject is driving the vehicle, and behavior data of the subject when the subject is not driving the vehicle; a processing unit capable of processing the sensor data, the traffic data, and the non-traffic data acquired by the acquisition unit; Equipped with The processing unit generating a necessity for a usage suggestion for a predetermined operating device based on the sensor data, the traffic data, and the non-traffic data; When the generated degree of necessity is equal to or greater than a first threshold and equal to or less than a second threshold, selecting a specific pacing model from among a plurality of pacing models based on the sensor data, the traffic data, and the non-traffic data; inputting the sensor data, the traffic data, and the non-traffic data into the selected specific pacing model, and obtaining a first suggestion sentence with a predetermined pacing process as a suggestion sentence for use of the operating device from the specific pacing model; outputting the acquired first proposal sentence; It is possible to carry out Usage proposal device. (2) The processing unit has a first learning model that is re-learned using the sensor data, the traffic data, the non-traffic data, and the degree of necessity as teaching data, and by inputting newly acquired sensor data, the traffic data, and the non-traffic data into the first learning model, it is possible to acquire a new degree of necessity from the learning model. (1) A usage suggestion device according to the present invention. (3) the acquisition unit is capable of acquiring a response from the subject to the output of the first proposal sentence, The specific pacing model is a learning model that is re-trained using the sensor data, the traffic data, and the non-traffic data, the first proposal sentence, a standard proposal sentence before a predetermined pacing process is performed on the first proposal sentence, and the content of the response as teaching data, and is capable of outputting a new first proposal sentence by inputting the newly acquired sensor data, the traffic data, and the non-traffic data, and the standard proposal sentence. A usage suggestion device according to (1) or (2). (4) further comprising a storage unit that stores the first threshold value and the second threshold value; When the response of the subject to the output of the first suggestion sentence indicates a refusal to use the predetermined operating device, the processing unit is capable of changing the first threshold value stored in the storage unit to a value smaller than the first threshold value. A usage suggestion device according to any one of (1) to (3). (5) The plurality of pacing models includes at least one of a mirroring model, a matching model, a backtracking model, a calibration model, a tuning model, and a VAK model. A usage suggestion device according to any one of (1) to (4). (6) The processing unit is capable of stopping output of the suggested sentence when the generated degree of necessity is smaller than the first threshold value. A usage suggestion device according to any one of (1) to (5). (7) When the generated degree of necessity is greater than the second threshold, the processing unit is capable of outputting a standard suggestion sentence as a suggestion sentence for using the operating device. A usage suggestion device according to any one of (1) to (6). (8) The usage data includes the subject's voice history during a call. A usage suggestion device according to any one of (1) to (7). (9) The passenger data includes attributes of one or more passengers who are in the vehicle when the subject is driving the vehicle. A usage suggestion device according to any one of (1) to (8). (10) The behavioral data includes at least one of data obtained when the subject is riding as a passenger in the vehicle, data obtained when the subject is riding as a passenger in another vehicle different from the vehicle, and data obtained when the subject is not riding in the vehicle or the other vehicle. A usage suggestion device according to any one of (1) to (9). (11) Equipped with a usage suggestion device, The usage suggestion device an acquisition unit capable of acquiring non-traffic data which is at least one of sensor data obtained from a sensor of a vehicle when the subject is driving the vehicle, traffic data around the vehicle when the subject is driving the vehicle, usage data stored in the user terminal of the subject when the subject uses the user terminal of the subject, passenger data of the vehicle when the subject is driving the vehicle, and behavior data of the subject when the subject is not driving the vehicle; a processing unit capable of processing the sensor data, the traffic data, and the non-traffic data acquired by the acquisition unit; and The processing unit generating a necessity for a usage suggestion for a predetermined operating device based on the sensor data, the traffic data, and the non-traffic data; When the generated degree of necessity is equal to or greater than a first threshold and equal to or less than a second threshold, selecting a specific pacing model from among a plurality of pacing models based on the sensor data, the traffic data, and the non-traffic data; inputting the sensor data, the traffic data, and the non-traffic data into the selected specific pacing model, and obtaining a first suggestion sentence with a predetermined pacing process as a suggestion sentence for use of the operating device from the specific pacing model; outputting the acquired first proposal sentence; It is possible to carry out vehicle.

[0102] The control unit 60 shown in FIGS. 1, 6, and 8 can be implemented by circuitry including at least one semiconductor integrated circuit, such as at least one processor (e.g., a central processing unit (CPU)), at least one application-specific integrated circuit (ASIC), and / or at least one field-programmable gate array (FPGA). The at least one processor can be configured to perform all or a portion of the various functions of the control unit 60 shown in FIGS. 1, 6, and 8 by reading instructions from at least one non-transitory, tangible computer-readable medium. Such media can take various forms, including, but not limited to, various magnetic media such as hard disks, various optical media such as CDs or DVDs, and various semiconductor memories (i.e., semiconductor circuits) such as volatile or non-volatile memories. Volatile memories can include DRAM and SRAM. Non-volatile memories can include ROM and NVRAM. An ASIC is an integrated circuit (IC) specialized to perform all or a portion of the various functions of the control unit 60 shown in FIGS. 1, 6, and 8. An FPGA is an integrated circuit designed to be configurable after manufacture to perform all or part of the various functions of the control unit 60 shown in FIGS. [Explanation of symbols]

[0103] 10...sensor unit, 11...stereo camera, 20...communication unit, 30...HMI, 31...steering wheel, 32...accelerator pedal, 33...brake pedal, 34...meter panel display, 35...center panel display, 36...speaker, 37...microphone, 40...data storage unit, 41...road map DB, 42...driving data, 42a...sensor data, 42b...traffic data, 42c...DMS data, 43, 45, 46...non-traffic data, 43a...usage data, 43b...passenger data, 43c...behavior data, 44...threshold data, 50...model storage unit, 51...mirroring model, 52...matching model, 53... Backtracking model, 54...calibration model, 55...tuning model, 56...VAK model, 60...control unit, 61...data acquisition unit, 62...usage suggestion unit, 63...driving control unit, 70...driving device, 81...necessity determination unit, 81Ai...determination model, 82...model selection unit, 82A...selection model, 83...pacing unit, 83A...pacing model, 100...vehicle, 200...mobile terminal, 300...server device, 400...network, Ans...answer, FLG...flag, Mx...pacing model, Ni...necessity, Nth1, Nth2...threshold, S1, S2...standard text, Sa, Sb...modified text, Sx...identifier.

Claims

1. an acquisition unit capable of acquiring non-traffic data which is at least one of sensor data obtained from a sensor of a vehicle when the subject is driving the vehicle, traffic data around the vehicle when the subject is driving the vehicle, usage data stored in the subject's usage terminal when the subject uses the subject's usage terminal, passenger data of the vehicle when the subject is driving the vehicle, and behavior data of the subject when the subject is not driving the vehicle; a processing unit capable of processing the sensor data, the traffic data, and the non-traffic data acquired by the acquisition unit; Equipped with The processing unit generating a necessity for a usage suggestion for a predetermined operating device based on the sensor data, the traffic data, and the non-traffic data; selecting a specific pacing model from among a plurality of pacing models based on the sensor data, the traffic data, and the non-traffic data when the generated degree of necessity is equal to or greater than a first threshold and equal to or less than a second threshold; inputting the sensor data, the traffic data, and the non-traffic data into the selected specific pacing model, and obtaining a first suggestion sentence, in which a predetermined pacing process is performed, from the specific pacing model as a suggestion sentence for use of the operating device; outputting the acquired first suggested sentence; It is possible to carry out Usage proposal device.

2. The processing unit has a learning model that is re-trained using the sensor data, the traffic data, the non-traffic data, and the degree of necessity as teaching data, and by inputting newly acquired sensor data, the traffic data, and the non-traffic data into the learning model, it is possible to acquire a new degree of necessity from the learning model. The usage suggestion device according to claim 1 .

3. the acquisition unit is capable of acquiring a response from the subject to the output of the first proposal sentence, The specific pacing model is a learning model that is re-trained using the sensor data, the traffic data, and the non-traffic data, the first proposal sentence, a standard proposal sentence before a predetermined pacing process is performed on the first proposal sentence, and the content of the response as teaching data, and is capable of outputting a new first proposal sentence by inputting the newly acquired sensor data, the traffic data, and the non-traffic data, and the standard proposal sentence. The usage suggestion device according to claim 1 .

4. a storage unit that stores the first threshold value and the second threshold value; When the response of the subject to the output of the first suggestion sentence indicates a refusal to use the predetermined operating device, the processing unit is capable of changing the first threshold value stored in the storage unit to a value smaller than the first threshold value. The usage suggestion device according to claim 1 .

5. Equipped with a usage suggestion device, The usage suggestion device an acquisition unit capable of acquiring non-traffic data which is at least one of sensor data obtained from a sensor of a vehicle when the subject is driving the vehicle, traffic data around the vehicle when the subject is driving the vehicle, usage data stored in the subject's usage terminal when the subject uses the subject's usage terminal, passenger data of the vehicle when the subject is driving the vehicle, and behavior data of the subject when the subject is not driving the vehicle; a processing unit capable of processing the sensor data, the traffic data, and the non-traffic data acquired by the acquisition unit; and The processing unit generating a necessity for a usage suggestion for a predetermined operating device based on the sensor data, the traffic data, and the non-traffic data; selecting a specific pacing model from among a plurality of pacing models based on the sensor data, the traffic data, and the non-traffic data when the generated degree of necessity is equal to or greater than a first threshold and equal to or less than a second threshold; inputting the sensor data, the traffic data, and the non-traffic data into the selected specific pacing model, and obtaining a first suggestion sentence, in which a predetermined pacing process is performed, from the specific pacing model as a suggestion sentence for use of the operating device; outputting the acquired first suggested sentence; It is possible to carry out vehicle.

Images