JP2018180983A - Information processing device, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve safety of driving a moving body.SOLUTION: An information processing device includes a diagnosis part that performs diagnosis of suitability for driving of a user before and during driving based on a state of the user driving a moving body. This technology is applicable to, for example, an information processing system, an information processing device, or a moving body supporting a user driving a moving body such as a vehicle, a motorcycle, a bicycle, personal mobility, an airplane, a ship, a construction machine, an agricultural machine.SELECTED DRAWING: Figure 4

Description

  The present technology relates to an information processing apparatus, an information processing method, and a program, and more particularly to an information processing apparatus, an information processing method, and a program that are suitably used when performing driving support of a moving object.

  Conventionally, in order to detect the driver's driving condition, the driver's biometric information is used.

  For example, the correction value of the skin impedance of the driver is corrected based on the correction value based on the correction value based on the measurement value of the skin impedance of the driver when the eye is at rest and the average value of the measurement during normal activity. It has been proposed to determine the awakening degree of the driver (see, for example, Patent Document 1).

  For example, the biometric data measured by the biometric sensor of the vehicle is transmitted to the data processing apparatus via the portable terminal installed in the charger in the vehicle and the public network line, and the data processing apparatus receives the biometric data received by the driver. It has been proposed to transmit to a mobile terminal of (see, for example, Patent Document 2).

Japanese Patent Application Laid-Open No. 10-80405 JP, 2016-140377, A

  By the way, the safety of driving of a mobile body such as a vehicle is influenced by various factors other than the driver's driving condition. Then, it is desirable to improve the safety of the operation of the mobile body by considering the influence as much as possible.

  The present technology has been made in view of such a situation, and is intended to improve the safety of operation of a mobile.

  The information processing apparatus according to one aspect of the present technology is directed to the driving of the user based on the pre-driving state of the user driving the moving body and the state of the driving user acquired during driving. And a presentation control unit configured to generate feedback information based on the diagnosis obtained by the diagnosis unit.

  There is further provided a driving behavior detection unit for detecting a driving behavior that is the behavior of the user or the moving body during driving, and the level of dangerous driving to be detected by the driving behavior detection unit is changed based on the result of the diagnosis. It can be done.

  The diagnosis unit can further cause the diagnosis to be performed based on the detection result of the driving behavior.

  The diagnosis unit causes the user's suitability for driving before driving to be diagnosed based on the state of the user before driving, and driving is based on the state of the user while driving and the detection result of the driving behavior. It is possible to diagnose the aptitude for driving of the user.

  It is possible to further provide a risk prediction unit that predicts a risk relating to the driving of the mobile object by the user based on at least one of the diagnosis result and the detection result of the driving behavior.

  The feedback information may include the content of the risk and the basis on which the risk is predicted.

  The basis for which the risk is predicted can be based on the result of the diagnosis.

  The feedback information may include the risk avoidance plan.

  The lower the driving suitability of the user based on the diagnosis, the lower the level of dangerous driving to be detected by the driving behavior detection unit.

  A learning unit may be further provided to learn a model for performing the diagnosis based on the result of the diagnosis and the detection result of the driving behavior.

  The diagnosis unit may perform the diagnosis based on a difference between the latest state of the user and the standard state of the user.

  The diagnosis unit may further cause the diagnosis to be performed based on a difference between the latest state of the user and the average state of the user in a user group including a plurality of users.

  A state estimation unit may be provided to estimate the state of the user before and during driving, and the diagnosis unit may make the diagnosis based on the estimation result of the user's state.

  The state of the user may include at least one of a biological state, an action, and an emotion of the user.

  The diagnosis unit may perform the diagnosis based on data indicating the state of the user acquired before and during the operation of the user.

  The information processing method according to one aspect of the present technology is, based on a predicted risk, a presentation control step of generating a risk avoidance plan for the user, and the user's reaction based on the user's reaction to the risk avoidance plan. The evaluation step which evaluates compliance and the risk prediction step which adjusts the prediction parameter of risk based on the evaluated compliance.

  The program according to one aspect of the present technology includes a presentation control step of generating a risk avoidance plan for the user based on the predicted risk, and the user's compliance based on the user's reaction to the risk avoidance plan. To cause the computer to execute processing including an evaluation step of evaluating and a risk prediction step of adjusting a prediction parameter of risk based on the evaluated degree of compliance.

  In one aspect of the present technology, a risk avoidance plan for the user is generated based on the predicted risk, and the user's compliance is evaluated and evaluated based on the user's reaction to the risk avoidance plan. Risk prediction parameters are adjusted based on the degree of compliance.

  According to one aspect of the present technology, diagnosis accuracy of aptitude for driving a mobile object of a user is improved. As a result, the safety of operation of the mobile unit is improved.

  In addition, the effect described here is not necessarily limited, and may be any effect described in the present disclosure.

1 is a block diagram illustrating an embodiment of an information processing system to which the present technology is applied. It is a block diagram which shows the structural example of a user terminal part. It is a block diagram showing an example of composition of vehicles. It is a block diagram showing an example of composition of a server. It is a flowchart for demonstrating the driving | operation assistance processing performed by a server. It is a flowchart for demonstrating the driving | operation assistance processing performed by a server. It is a figure for demonstrating the estimation process of a user's state. It is a figure for demonstrating the learning method of a user's standard state pattern. It is a figure for demonstrating the learning method of a user group state pattern. It is a figure for demonstrating the example of the method of driving | operation diagnosis. It is a figure showing an example of composition of a computer.

Hereinafter, modes for carrying out the present technology will be described. The description will be made in the following order.
1. Embodiment 2. Modified example 3. Other

<< 1. Embodiment >>
<Configuration Example of Information Processing System>
FIG. 1 is a block diagram showing an embodiment of an information processing system to which the present technology is applied.

  The information processing system 10 is a system that provides services such as vehicle driving support and automobile insurance using, for example, telematics technology.

  The information processing system 10 includes a user terminal unit 11, a vehicle 12, and a server 13. The user terminal unit 11 and the vehicle 12 communicate directly or via the network 14. The server 13 communicates with the user terminal unit 11 and the vehicle 12 via the network 14.

  The user terminal unit 11 includes one or more information processing terminals owned by a user who uses the information processing system 10. For example, the user terminal unit 11 may include a mobile terminal and a wearable terminal.

  The vehicle 12 is a vehicle driven by a user who uses the information processing system 10.

  The server 13 communicates with the user terminal unit 11 and the vehicle 12 via the network 14 to provide the user using the information processing system 10 with services such as driving assistance and automobile insurance.

  Although one user terminal unit 11, one vehicle 12, and one server 13 are illustrated in FIG. 1 in order to make the drawing easy to understand, two or more user terminals may be provided. For example, the user terminal units 11 and the vehicles 12 are provided in approximately the same number as the number of users who use the information processing system 10.

  Also, hereinafter, in order to simplify the description, the description of "via the network 14" in the case where the user terminal unit 11, the vehicle 12, and the server 13 communicate via the network 14 will be omitted.

<Configuration Example of User Terminal Unit>
FIG. 2 is a block diagram showing a configuration example of the user terminal unit 11. In this example, the user terminal unit 11 includes a mobile terminal 51 and a wearable terminal 52.

  The mobile terminal 51 is made of, for example, a portable information processing terminal such as a smartphone, a mobile phone, a tablet, a laptop personal computer, a portable game machine, a portable video or music player.

  The mobile terminal 51 includes a GNSS (Global Navigation Satellite System) receiver 61, an inertial sensor 62, an environment sensor 63, a biological sensor 64, an input unit 65, an output unit 66, a control unit 67, and a communication unit 68.

  The GNSS receiver 61 measures the current position of (the user having) the mobile terminal 51 by receiving a radio wave from a positioning satellite, and supplies position data indicating the measured current position to the control unit 67.

  The inertial sensor 62 detects various inertial data related to (the user having the mobile terminal 51), and supplies the detected inertial data to the control unit 67. The inertial data detected by the inertial sensor 62 includes, for example, one or more of an acceleration, an angular velocity, and the like.

  The environment sensor 63 detects various environment data around (the user having the mobile terminal 51), and supplies the detected environment data to the control unit 67. The environmental data detected by the environmental sensor 63 includes, for example, one or more of geomagnetism, atmospheric pressure, carbon dioxide concentration, and the like.

  The biometric sensor 64 detects various biometric data of the user, and supplies the detected biometric data to the control unit 67. The biological data detected by the biological sensor 64 is, for example, heart rate, amount of sweat, blood pressure, blood oxygen concentration, myoelectric potential, body temperature, body composition, alcohol concentration in exhalation, maximum oxygen intake, consumed calories, voice tone, conversation Including one or more of speed and the like.

  The input unit 65 includes an input device for inputting various data to the mobile terminal 51. For example, the input unit 65 includes one or more of a button, a switch, a key, a touch panel, a microphone, and the like. The input unit 65 supplies input data to the control unit 67.

  The output unit 66 includes an output device for outputting various types of information and data. For example, the output unit 66 includes one or more of a display, a speaker, a buzzer, a vibrator, and the like.

  The control unit 67 includes, for example, control devices such as various processors. The control unit 67 is based on the GNSS receiver 61, the inertial sensor 62, the environment sensor 63, the biometric sensor 64, data supplied from the input unit 65, data received from the outside via the communication unit 68, and the like. , Controls each part of the mobile terminal 51 and performs various processes. Further, the control unit 67 supplies data obtained by various processes to the output unit 66, and transmits the data to another device via the communication unit 68.

  The communication unit 68 communicates with other devices (for example, the vehicle 12, the server 13, the wearable terminal 52, and the like) by a predetermined communication method. As a communication method of the communication unit 68, any method of wireless or wired can be adopted. The communication unit 68 can also correspond to a plurality of communication methods.

  The wearable terminal 52 includes, for example, any type of wearable terminal such as a glasses type, a watch type, a bracelet type, a necklace type, a neckband type, an earphone type, a headset type, and a head mount type.

  The wearable terminal 52 includes a biometric sensor 81, an input unit 82, an output unit 83, a control unit 84, and a communication unit 85.

  Similar to the biometric sensor 64 of the mobile terminal 51, the biometric sensor 81 detects various biometric data of the user, and supplies the detected biometric data to the control unit 84. Note that the type of biological data detected by the biological sensor 81 and the type of biological data detected by the biological sensor 64 of the mobile terminal 51 may overlap.

  The input unit 82 includes an input device for inputting various data to the wearable terminal 52. For example, the input unit 82 includes one or more of a button, a switch, a key, a touch panel, a microphone, and the like. The input unit 82 supplies input data to the control unit 67.

  The output unit 83 includes an output device for outputting various types of information and data. For example, the output unit 83 includes one or more of a display, a speaker, a buzzer, a vibrator, and the like.

  The control unit 84 includes, for example, control devices such as various processors. The control unit 84 controls each part of the wearable terminal 52 and performs various processes based on data supplied from the biometric sensor 81 and the input unit 82, data received from the outside via the communication unit 85, and the like. Further, the control unit 84 supplies data obtained by various processes to the output unit 83, and transmits the data to another device via the communication unit 85.

  The communication unit 85 communicates with other devices (for example, the vehicle 12, the server 13, the mobile terminal 51, and the like) by a predetermined communication method. As a communication method of the communication unit 85, any method of wireless or wired can be adopted. The communication unit 85 can also support a plurality of communication methods.

<Example of Configuration of Vehicle>
FIG. 3 is a block diagram showing a configuration example of a part of the vehicle 12. The vehicle 12 includes an in-vehicle system 101. The in-vehicle system 101 includes a vehicle data acquisition unit 111, a video and audio acquisition unit 112, an input unit 113, an output unit 114, a control unit 115, and a communication unit 116.

  The vehicle data acquisition unit 111 includes, for example, various sensors, communication devices, control devices, and the like. The vehicle data acquisition unit 111 acquires vehicle data related to the vehicle 12, and supplies the acquired vehicle data to the control unit 115. The vehicle data acquired by the vehicle data acquisition unit 111 is, for example, vehicle speed, torque, steering angle, yaw angle, gear state, side brake state, accelerator pedal depression amount, brake pedal depression amount, direction indicator state , Light rotation state, tire rotation angle and rotation speed, data indicating diagnosis results of OBD (On-board Diagnostics) (hereinafter referred to as OBD data), and sensor data of millimeter wave radar and laser radar etc. Includes one or more.

  The video and audio acquisition unit 112 includes, for example, a camera and a microphone. The camera included in the video and audio acquisition unit 112 may be, for example, a special camera such as a ToF (Time Of Flight) camera, a stereo camera, or an infrared camera, in addition to a normal camera. For example, the video and audio acquisition unit 112 acquires video and audio around and inside the vehicle 12, and supplies video data and audio data indicating the acquired video and audio to the control unit 115.

  The input unit 113 includes an input device for inputting various data to the vehicle 12. For example, the input unit 113 includes one or more of a button, a switch, a key, a touch panel, and the like. The input unit 113 supplies input data to the control unit 115.

  The output unit 114 includes an output device for outputting various types of information and data. For example, the output unit 114 includes one or more of a display (for example, a head-up display), a speaker, a buzzer, a vibrator, an instrument panel, and the like.

  The control unit 115 includes, for example, a control device such as an ECU (Electronic Control Unit). The control unit 115 is a unit of the vehicle 12 based on data supplied from the vehicle data acquisition unit 111, the video and audio acquisition unit 112, and the input unit 113, data received from the outside via the communication unit 116, and the like. Control and various processes. Further, the control unit 115 supplies data obtained by various processes to the output unit 114, and transmits the data to another device via the communication unit 116.

  The communication unit 116 communicates with other devices (for example, the server 13, the mobile terminal 51, the wearable terminal 52, and the like) by a predetermined communication method. As a communication method of the communication unit 116, any method of wireless or wired can be adopted. The communication unit 116 can also support a plurality of communication methods.

<Example of server configuration>
FIG. 4 is a block diagram showing a configuration example of the server 13. The server 13 includes a communication unit 151, a state estimation unit 152, a peripheral data acquisition unit 153, a diagnosis unit 154, a driving behavior detection unit 155, a risk prediction unit 156, a damage prediction unit 157, a presentation control unit 158, an evaluation unit 159, and a learning unit. 160, a premium calculation unit 161, and a storage unit 162.

  The communication unit 151 communicates with other devices (for example, the vehicle 12, the mobile terminal 51, the wearable terminal 52, another server (not shown), etc.) via the network 14 by a predetermined communication method. As a communication method of the communication unit 151, any method of wireless or wired can be adopted. The communication unit 151 can also support a plurality of communication methods.

  The state estimation unit 152 acquires data related to the state of the user from the user terminal unit 11 and the vehicle 12 via the communication unit 151. The state estimation unit 152 generates and updates a state data log, which is a log of data related to the state of the user, and stores the state data log in the storage unit 162.

  In addition, the state estimation unit 152 performs estimation processing of the state of the user using the state estimation model stored in the storage unit 162 based on the state data log. Here, the state estimation model is a model used to estimate the state of the user, and is generated, for example, for each user. The state estimation unit 152 generates and updates an estimated state history, which is a history of estimation results of the user's state, and stores the estimated state history in the storage unit 162.

  The peripheral data acquisition unit 153 displays peripheral data indicating the state of the periphery of the vehicle 12 based on data received from the user terminal unit 11, the vehicle 12, and another server (not shown) via the communication unit 151. get. The peripheral data acquisition unit 153 supplies the acquired peripheral data to the diagnosis unit 154 and the risk prediction unit 156.

  The diagnosis unit 154 acquires the user's estimated state history, the driving behavior history, and the driving diagnosis model from the storage unit 162. Here, the driving behavior history is a history of detection results of the driving behavior which is the behavior of the user or the vehicle 12 while driving, and is generated for each user, for example. Further, the driving diagnosis model is a model used for driving diagnosis for diagnosing the aptitude of the user for driving the vehicle, and is generated for each user, for example. The diagnosis unit 154 performs driving diagnosis of the user using the driving diagnosis model based on the acquired history. The diagnosis unit 154 generates and updates a driving diagnosis history, which is a history of the driving diagnosis result of the user, and stores the driving diagnosis history in the storage unit 162.

  The driving behavior detection unit 155 receives data from the user terminal unit 11 and the vehicle 12 via the communication unit 151. Further, the driving behavior detection unit 155 acquires the estimated state history of the user and the driving behavior detection model from the storage unit 162. Here, the driving behavior detection model is a model used to detect the driving behavior, and is generated, for example, for each user. Furthermore, the driving behavior detection unit 155 acquires, from the damage prediction unit 157, the risk relating to the driving of the vehicle by the user and the prediction result of the damage that occurs due to the risk. The driving behavior detection unit 155 detects the driving behavior of the user using the driving behavior detection model based on the acquired history, data, and the like. The driving behavior detection unit 155 generates and updates a driving behavior history, which is a history of detection results of the user's driving behavior, and stores the driving behavior history in the storage unit 162.

  The risk prediction unit 156 acquires the user's estimated state history, the driving diagnosis history, the driving behavior history, and the risk prediction model from the storage unit 162. Here, the risk prediction model is a model used to predict the risk relating to the driving of the vehicle 12 by the user, and is generated, for example, for each user. The risk prediction unit 156 performs risk prediction using the risk prediction model based on the acquired history. The risk prediction unit 156 supplies the prediction result of the risk to the damage prediction unit 157.

  The damage prediction unit 157 predicts the damage caused by the risk predicted by the risk prediction unit 156 while using the degree of user compliance evaluated by the evaluation unit 159 as necessary. Here, the degree of compliance is the degree to which the user follows the proposal from the server 13 and the like. The damage prediction unit 157 supplies the prediction result of the risk and the damage to the driving behavior detection unit 155 and the presentation control unit 158.

  The presentation control unit 158 acquires, from the storage unit 162, the driving diagnostic history of the user and the premium calculated by the premium calculation unit 161. The presentation control unit 158 generates feedback information to be presented to the user, including information on the predicted risk, based on the prediction result of the risk and damage, and the driving diagnostic history and the premium of the user. The presentation control unit 158 controls the presentation of feedback information to the user by transmitting the generated feedback information to the user terminal unit 11 or the vehicle 12 of the user via the communication unit 151. Also, the presentation control unit 158 supplies feedback information to the evaluation unit 159.

  The evaluation unit 159 acquires the estimated state history and the driving behavior history of the user from the storage unit 162. Then, the evaluation unit 159 evaluates the user's compliance based on the acquired history and feedback information. The evaluation unit 159 supplies the degree of compliance of the user to the damage prediction unit 157 and stores the degree of compliance in the storage unit 162.

  The learning unit 160 acquires the estimated state history of the user from the storage unit 162. The learning unit 160 learns the pattern of the standard state of the user (hereinafter referred to as a standard state pattern) based on the acquired estimated state history, and stores data indicating the obtained standard state pattern in the storage unit 162. Remember.

  Further, the learning unit 160 acquires, from the storage unit 162, the estimated state history of each user included in a predetermined user set. The learning unit 160 learns an average state pattern of the users in the user set (hereinafter referred to as a user set state pattern) based on the acquired estimated state history, and indicates the obtained user set state pattern. The data is stored in the storage unit 162.

  Furthermore, the learning unit 160 acquires the state data log of the user, the estimated state history, the driving diagnosis history, and the driving behavior history from the storage unit 162. The learning unit 160 learns the state estimation model, the driving diagnosis model, the driving behavior detection model, and the risk prediction model based on the acquired log and history, and causes the storage unit 162 to store the learning result.

  The premium calculating unit 161 acquires from the storage unit 162 the driving diagnostic history, the driving behavior history, and the compliance degree of the user. The premium calculating unit 161 calculates the premium of the user's car insurance based on the acquired history and the degree of compliance. The premium calculation unit 161 causes the storage unit 162 to store data indicating the calculated premium.

<Driving support processing>
Next, the driving support process executed by the server 13 will be described with reference to the flowcharts of FIGS. 5 and 6.

  Although the following description will focus mainly on the processing for one specific user (hereinafter referred to as the target user), in reality, processing for other users other than the target user is performed in parallel.

  In step S1, the server 13 starts estimation processing of the state of the user (attention user) at the time of non-operation. Specifically, for example, the following processing is started.

  The state estimation unit 152 acquires data on the state of the user of interest from among data (for example, inertia data, environment data, biometric data, input data, etc.) received by the communication unit 151 from the user terminal unit 11 of the user of interest. . The state estimation unit 152 causes the storage unit 162 to store each data together with the acquired time. Thereby, the state data log of the noted user is updated.

  Note that the state data log of the user of interest may include not only data regarding the state of the user of interest, but also data regarding the state of the surroundings of the user of interest.

  The state estimation unit 152 estimates the current state of the user of interest using the state estimation model of the user of interest stored in the storage unit 162 based on the state data log of the user of interest within the most recent predetermined period. . For example, the state estimation unit 152 estimates the current biological condition, behavior, and emotion of the user of interest as the current state of the user of interest.

  For example, as illustrated in FIG. 7, the state estimation unit 152 determines, based on the time-series change of the sensor data group indicating the state of the user of interest, the biological condition and action of the user of interest for each frame of a predetermined time. Estimate For example, various living states of the user of interest such as the degree of concentration, alertness, fatigue, stress, tension, exercise intensity and the like are estimated based on the heartbeat and the amount of sweating of the user of interest. For example, the type of action (for example, stillness, walking, running, cycling, climbing up and down stairs, eating, sleeping, etc.) of the user of interest is estimated based on the acceleration and angular velocity of the user of interest and ambient pressure and the like. .

  Also, for example, the state estimation unit 152 estimates the moving distance, moving speed, and action range of the user of interest based on the position data and acceleration of the user of interest.

  Furthermore, the state estimation unit 152 estimates the emotion of the user of interest based on the biometric data of the user of interest, the estimation result of the biological condition of the user of interest, and the like. For example, the state estimation unit 152 estimates the degree of excitement, excitement, irritability, anxiety and the like of the user of interest.

  It is to be noted that the biological condition and the emotion of the user of interest are not necessarily clearly distinguished from one another, and some may overlap. For example, the degree of excitement can be any of the physical condition and emotion of the user of interest.

  Further, any method can be adopted as a method of estimating the state of the user. Furthermore, the type of the user's state to be estimated is not limited to the above-described example, and may be added or deleted as needed.

  The state estimation unit 152 stores the estimated state of the noted user in the storage unit 162 together with the estimated time. Thus, the estimated state history of the user of interest is updated.

  For example, as illustrated in FIG. 7, the estimated state history is assigned data for each frame in a time series, such as the alertness level, or for each frame, such as an action (type of action (type of action (Indicates) containing data arranged in chronological order.

  In step S2, the learning unit 160 determines whether to learn a pattern (standard state pattern) of a standard state of the user (user of interest). For example, when learning the standard state pattern of the user of interest, when the user of interest starts using the information processing system 10, the data amount of the estimated state history of the user of interest increases by a predetermined amount or more each time a predetermined time elapses. It is executed at a predetermined timing such as every time. Then, when it is time to learn the standard state pattern of the user of interest, the learning unit 160 determines that the standard state pattern of the user of interest is learned, and the process proceeds to step S3.

  In step S3, the learning unit 160 learns a pattern (standard state pattern) of the standard state of the user (user of interest). For example, as illustrated in FIG. 8, the learning unit 160 uses the standard state pattern of the user of interest based on the estimated state history within the last relatively long period of the user of interest (eg, monthly unit, year unit). To learn

  For example, the learning unit 160 calculates, as the standard state pattern of the user of interest, an average and a variance for each period of a predetermined time (for example, 1 minute, 10 minutes, 30 minutes, or 1 hour) of the following items. By doing this, a transition pattern indicating a standard transition of a predetermined period (for example, one day) of each item is learned. For example, one day such as concentration, alertness, fatigue, stress, tension, exercise intensity, heart rate, amount of sweating, exercise, degree of emotion, degree of excitement, excitement, anxiety, etc. of the noted user The standard transition pattern of is learned.

  Also, for example, the learning unit 160 calculates a predetermined period (for example, one week) of each item by calculating the average and the variance, etc. of each item (every day) of the following items as the standard state pattern of the noted user ) Learn standard transition patterns per area. For example, standard transition of one week such as sleep time, wake time, bedtime, exercise amount, movement range, number of meals, meal time, meal time zone, driving time, driving time zone, commuting time zone, attending school time zone, etc. Patterns are learned.

  In addition, the learning unit 160 calculates an average standard state pattern (user group state pattern) in the user group based on the estimated state history of each user in the predetermined user group as a comparison target of the standard state pattern of the noted user. To learn

  Here, all of the users of the information processing system 10 may be included in the user set, or only some of the users may be included. In the latter case, for example, it may be a user set consisting of users similar to the user of interest. Here, a user similar to the user of interest is, for example, a user whose attributes (eg, age, gender, occupation, address, etc.), behavior patterns, preferences, etc. are similar to the user of interest. Further, the user set may or may not include the noted user.

  For example, as illustrated in FIG. 9, the learning unit 160 learns the user aggregation state pattern by aggregating the average of the standard state patterns of the respective users in the user aggregation. For example, by averaging the average of standard transition patterns of each item per day in the user set, the average daily transition pattern of each item in the user set is learned. Also, for example, by averaging the standard transition patterns of one week of each item in the user set, the average one week transition pattern of each item in the user set is learned.

  The learning unit 160 causes the storage unit 162 to store data indicating the standard state pattern of the user of interest and the learning result of the user aggregation state pattern.

  The learning of the standard state pattern of the user of interest and the learning of the user aggregation state pattern do not necessarily have to be synchronized, and may be performed at different timings.

  Thereafter, the process proceeds to step S4.

  On the other hand, if it is determined in step S2 that the standard state pattern of the user of interest is not learned, the process of step S3 is skipped, and the process proceeds to step S4.

  In step S4, the diagnosis unit 154 performs operation diagnosis during non-operation. For example, based on the estimated state history of the user of interest, the diagnosis unit 154 determines, for the same item as the standard state pattern described above, the transition pattern (for example, one day and one week) within the latest relatively short period Detect the most recent state pattern).

  Next, the diagnosis unit 154, for example, as illustrated in FIG. 10, a divergence degree vector x indicating the divergence between the nearest state pattern of the noted user and the standard state pattern, and the nearest state pattern of the noted user and the user A divergence degree vector y indicating the degree of divergence from the aggregate state pattern is calculated. For example, the divergence degree vector x and the divergence degree vector y are vectors including values obtained by normalizing the divergence degree for each item of two state patterns to be compared.

  Then, using the driving diagnostic model of the user of interest represented by the function f of the following equation (1), the diagnosis unit 154 calculates the driving aptitude degree u of the user of interest when the user is not driving.

u = f (x, y, wx, wy) (1)

  Note that wx is a weight for the divergence degree vector x, and wy is a weight for the divergence degree vector y.

  The driving aptitude degree u increases as the deviation degree of each item included in the deviation degree vector x decreases. That is, as the nearest state pattern of the noted user is closer to the standard state pattern, in other words, as the difference between the nearest state of the noted user and the standard state is smaller, it is determined that the state is more suitable for driving. . On the other hand, the driving aptitude degree u decreases as the degree of deviation of each item included in the degree of deviation vector x increases. That is, it is determined that the closer the state pattern of the noted user is to the standard state pattern, in other words, the larger the difference between the nearest state of the noted user and the standard state, the less suitable the driving is. Ru.

  In addition, the driving aptitude degree u increases as the degree of deviation of each item included in the degree of deviation vector y decreases. That is, the closer the state pattern of the user of interest is to the user group state pattern, in other words, the smaller the difference between the state of the user of interest and the average state of the user group, the more suitable for driving. It is determined that On the other hand, the driving aptitude degree u decreases as the degree of deviation of each item included in the degree of deviation vector y increases. That is, as the nearest state pattern of the noted user is further from the user set state pattern, in other words, the larger the difference between the nearest state of the noted user and the average state in the user set, the more unsuitable the driving is. It is determined that there is.

  As the weight wx increases, the influence of the deviation degree vector x (that is, the difference between the nearest state pattern of the user of interest and the standard state pattern) with respect to the driving aptitude degree u increases. On the other hand, as the weight wy increases, the influence of the deviation degree vector y (that is, the difference between the user group state pattern of the user of interest and the standard state pattern) with respect to the driving aptitude degree u increases.

  In addition, for example, when the driving aptitude degree u is less than a predetermined threshold value, the diagnosis unit 154 estimates a reduction factor of the driving aptitude degree u. For example, in the divergence degree vector x, the diagnosis unit 154 extracts an item in which the product of the weight wx and the divergence degree is equal to or more than a predetermined value. Further, the diagnosis unit 154 extracts an item in which the product of the weight wy and the degree of divergence is equal to or larger than a predetermined value in the degree of divergence vector y. Then, the diagnosis unit 154 estimates the reduction factor of the driving aptitude degree u by comparing the latest state pattern with the standard state pattern or the user group average pattern for each of the extracted items.

  For example, when the sleep time in the latest state pattern of the user of interest is significantly less than the standard state pattern or the user group average pattern, it is estimated that the lack of sleep is a reduction factor.

  For example, if one or more of exercise time, heart rate, and amount of sweating in the most recent state pattern of the noted user is significantly greater than the standard state pattern or the user group average pattern, physical fatigue due to heavy exercise is a decreasing factor It is estimated to be.

  For example, if one or more of the degree of stress, the degree of tension, and the degree of frustration in the nearest state pattern of the noted user is significantly greater than the standard state pattern or the user group average pattern, It is estimated that there is.

  In addition, when the driving aptitude degree u is more than a predetermined | prescribed threshold value, for example, the fall factor of the driving aptitude degree u will be nothing.

  The diagnosis unit 154 causes the storage unit 162 to store the driving aptitude degree u and the estimated reduction factor together with the diagnosed time as the diagnosis result of the driving aptitude of the noted user. Thus, the driving diagnosis history of the user of interest is updated.

  In step S5, the risk prediction unit 156 performs risk prediction. Specifically, the risk prediction unit 156 acquires the driving diagnosis history and the risk prediction model of the user of interest from the storage unit 162. The risk prediction unit 156 predicts the risk in the case where the focused user is driving at the present time using the risk prediction model of the focused user based on the driving diagnosis history of the focused user.

  For example, when the factor of decreasing the driving aptitude u is sleep deprivation or physical fatigue, it is estimated that there is a risk of drowsy driving.

  For example, when the factor of lowering the driving aptitude u is the intimacy of the noted user, for example, a collision or contact with another vehicle due to overspeeding or excessive overtaking, etc., and an obstacle due to the attention of the noted user (eg, other It is estimated that there is a risk of collision or contact with vehicles, bicycles, pedestrians, etc.).

  Also, the risk prediction unit 156 estimates the occurrence probability of the predicted risk. For example, as the sleep time of the user of interest is shorter, the estimated occurrence probability of drowsy driving is higher.

  Generally, the lower the driving aptitude degree u, the larger the predicted risk and the probability of occurrence.

  The risk prediction unit 156 supplies the prediction result of the risk to the damage prediction unit 157. The risk prediction result includes the predicted risk, the basis for predicting the risk (for example, a factor that decreases the driving aptitude u), and the probability of occurrence of the risk.

  In step S6, the loss prediction unit 157 performs loss prediction. Specifically, the loss prediction unit 157 predicts the damage (for example, the risk / penalty value) generated due to the risk predicted by the risk prediction unit 156. At this time, the risk occurrence probability is taken into consideration. That is, the higher the probability of occurrence, the greater the expected damage, and the lower the probability of occurrence, the smaller the predicted damage. The damage prediction unit 157 supplies the prediction result of the risk and the damage to the driving behavior detection unit 155 and the presentation control unit 158.

  In step S7, the driving behavior detection unit 155 adjusts the detection parameter of the driving behavior. For example, the driving behavior detection unit 155 adjusts a parameter for detection of dangerous driving among various driving behaviors according to the predicted risk and damage.

  Here, the driving behavior related to the detection of the dangerous driving includes, for example, a sudden start, a sudden acceleration, a sudden braking, and a sudden operation such as a sudden steering, meandering driving, drowsy driving, a decrease in arousal level or concentration, wandering driving Dangerous driving behavior such as forward carelessness, speed over, excessive overtaking, lack of distance between vehicles, and approach to obstacles.

  Also, the detection parameters are adjusted such that the level (risk) of the dangerous driving to be detected becomes lower as the estimated risk and damage increase. This allows dangerous driving to be detected from an earlier and lesser stage.

  For example, when occurrence of drowsy driving is predicted, the threshold value of the number of blinks in the drowsiness determination is reduced so as to detect drowsiness of the user earlier. For example, when occurrence of a look-ahead operation, forward carelessness, overspeed, or the like is predicted, the threshold value for detecting rapid acceleration or sudden braking is decreased so that rapid acceleration or sudden braking is easily detected.

  Furthermore, the lower the level of dangerous driving to be detected, the lower the level of risk to be predicted (risk). In other words, earlier and smaller risks can be predicted.

  Here, the level of the dangerous driving to be detected and the level of the risk to be predicted change according to the driving aptitude degree u of the noted user. For example, as described above, generally, the lower the driving aptitude u, the larger the predicted risk and the probability of damage occurrence, and the larger the predicted damage. Therefore, the detection parameters are adjusted to lower the level of the dangerous operation to be detected. As a result, the lower the driving aptitude degree u, the lower the level of dangerous driving to be detected and the level of risk to be predicted.

  In step S8, the presentation control unit 158 determines whether or not to perform feedback to the user (user of interest). The feedback to the user of interest is performed at a predetermined timing. For example, when a request for feedback is transmitted from the user terminal unit 11 of the user of interest, the feedback is performed each time a predetermined time passes or when a serious risk is predicted. Then, the presentation control unit 158 determines that feedback to the user of interest is to be performed when the current time is the timing of feedback to the user of interest, and the process proceeds to step S9.

  In step S9, the server 13 performs feedback to the user (user of interest). Specifically, the presentation control unit 158 generates feedback information to be presented to the user of interest. This feedback information is, for example, the result of the driving diagnosis of the noted user, the content of the predicted risk, the basis of the driving diagnostic result or the basis for predicting the risk, and the proposal for avoiding the risk (hereinafter referred to as a risk avoidance plan Include one or more of The presentation control unit 158 transmits the generated feedback information to the user terminal unit 11 of the user of interest via the communication unit 151.

  For example, when the mobile terminal 51 of the user of interest receives the feedback information, the output unit 66 of the mobile terminal 51 uses at least one of visual information (for example, video) and auditory information (for example, audio) for feedback information. Is presented to the noted user. Also, for example, when the wearable terminal 52 of the user of interest receives feedback information, the output unit 83 of the wearable terminal 52 presents feedback information to the user of interest using at least one of visual information and auditory information.

  For example, when it is estimated that the focused user's sleep lacks, a voice message such as "It is a sleepless condition. It is recommended to take a little sleep and then drive" is output.

  Also, for example, as the driving diagnosis result of the noted user, the driving aptitude degree u is presented by the value of a predetermined stage (for example, 10 stages), and the basis thereof is presented.

  Furthermore, for example, an estimation result of the state of the user of interest may be presented. For example, emotion quotients such as emotions, excitement, aggression and the like of the noted user may be presented from values of predetermined stages (e.g., ten stages).

  Thereafter, the process proceeds to step S10.

  On the other hand, if it is determined in step S8 that feedback to the user of interest is not to be performed, the process of step S9 is skipped, and the process proceeds to step S10.

  In step S10, the state estimation unit 152 determines whether the user (the noted user) has started driving. Specifically, the state estimation unit 152 determines whether the focused user has started driving based on data received from at least one of the user terminal unit 11 and the vehicle 12 of the focused user via the communication unit 151. Determine if

  The determination process of the driving start may be performed by any of the user terminal unit 11, the vehicle 12, and the server 13. For example, the mobile terminal 51 may execute the driving start determination process by performing the driving recognition process of the user of interest or performing the beacon synchronization with the vehicle 12. Further, for example, a measurement device integrated with an on-vehicle display device or the like of the vehicle 12 may execute the process of determining the start of driving.

  When the determination process is performed by the user terminal unit 11 or the vehicle 12, the determination result is included in the data transmitted from the user terminal unit 11 or the vehicle 12, and the state estimation unit 152 focuses on the determination result. It is determined whether the user has started driving.

  Then, if it is determined that the focused user has not started driving, the process returns to step S2. Thereafter, in step S10, the processes of steps S2 to S10 are repeatedly executed until it is determined that the focused user has started driving. As a result, the driving diagnosis, the risk prediction, and the damage prediction of the user of interest are appropriately performed, and adjustment of detection parameters for dangerous driving and feedback to the user of interest are performed based on the results. In addition, the standard state pattern of the noted user and the user aggregation state pattern are updated as appropriate.

  On the other hand, when it is determined in step S10 that the focused user has started driving, the process proceeds to step S11.

  In step S11, the server 13 starts the process of estimating the state of the user (user of interest) at the time of driving. This estimation process is largely different from the estimation process of step S1 in that the estimation process is performed based on data transmitted from the vehicle 12 in addition to the user terminal unit 11 of the user of interest.

  For example, based on the video data from the vehicle 12, the gaze, blink, expression, etc. of the user of interest are detected, and used to estimate the degree of concentration, arousal, fatigue, emotion, etc. of the user of interest. Further, for example, based on the vehicle data from the vehicle 12, the content of the driving operation of the user of interest is estimated.

  Furthermore, for example, the state of the user of interest is estimated based on the travel route of the vehicle 12 and the time zone in which the user of interest is driving. For example, after the heart rate and the amount of exercise of the user of interest rapidly rise, the user of interest may drive in a time zone different from normal (for example, midnight or early morning) or the vehicle 12 is out of the daily life range of the user of interest When traveling or the like, it is estimated that the user of interest is irritated by an emergency.

  Further, the state estimation unit 152 appropriately updates the state data log and the estimated state history of the user of interest, similarly to the process of step S1.

  In step S12, the peripheral data acquisition unit 153 starts acquisition of peripheral data of the vehicle 12. For example, based on the position information transmitted from the user terminal unit 11 or the vehicle 12 and the map information received from another server or the like via the communication unit 151, the surrounding data acquisition unit 153 may select the vehicle of the focused user It detects the state of structures, roads, traffic jams, weather, etc. around 12. In addition, for example, the peripheral data acquisition unit 153 may use an object (for example, a vehicle, a person, or the like) around the vehicle 12 based on video data, audio data, sensor data, and the like transmitted from the user terminal unit 11 or the vehicle 12. Detect obstacles, structures, roads, traffic lights, traffic signs, road markings, etc.). The user terminal unit 11 or the vehicle 12 may perform detection processing of an object around the vehicle 12 and transmit the detection result to the server 13.

  The peripheral data acquisition unit 153 supplies the acquired peripheral data of the vehicle 12 to the diagnosis unit 154 and the risk prediction unit 156.

  In step S13, the server 13 starts the process of detecting the driving behavior. Specifically, for example, the following processing is started.

  The driving behavior detection unit 155 transmits data on the driving behavior (for example, the behavior of the watching user or the vehicle 12 during driving) among the data received by the communication unit 151 from the user terminal unit 11 of the watching user and the vehicle 12. Get from In addition, the driving behavior detection unit 155 is based on the acquired data on the driving behavior, the estimated state history of the noted user stored in the storage unit 162, and the peripheral data of the vehicle 12 acquired from the peripheral data acquisition unit 153. Driving behavior is detected using the driving behavior detection model of the user of interest stored in the storage unit 162. That is, the behavior of the user of interest while driving and the behavior of the vehicle 12 are detected. For example, the speed, acceleration, deceleration, brake operation, steering angle, traveling route and the like of the vehicle 12 are detected.

  Note that a part of the behavior of the user of interest while driving may be detected (estimated) by the state estimation unit 152 in step S11.

  Further, the detection of the driving behavior may be performed by any of the user terminal unit 11, the vehicle 12, and the server 13, or the user terminal unit 11, the vehicle 12, and the server 13 may be shared and performed. .

  Next, the driving behavior detection unit 155 performs dangerous driving detection processing based on the detected driving behavior, the estimated state history of the user of interest, and the peripheral data of the vehicle 12.

  For example, the sudden operation is detected by a sudden change such as the speed of the vehicle 12 based on the OBD information or the like, a steering angle, or a torque or a sudden change such as an acceleration detected by the user terminal 12 or an angular velocity.

  For example, the meandering operation is detected by periodic fluctuation such as the speed of the vehicle 12, steering angle, or torque based on OBD information or the like or periodic fluctuation such as acceleration or angular velocity detected by the user terminal unit 12. .

  For example, the shortage of the inter-vehicle distance is detected by the position of the preceding vehicle detected using a stereo camera, a laser radar, and a millimeter wave radar.

  Here, the detection parameter adjusted in step S7 mentioned above or step S20 mentioned later is used for the detection process of dangerous driving | operation. Therefore, as described above, the lower the driving aptitude degree u of the user of interest, the lower the level of the dangerous driving to be detected, and the detection target is detected as the dangerous driving from an earlier and lighter stage. .

  The driving behavior detection unit 155 stores the detection result of the driving behavior in the storage unit 162 together with the detected time. Thus, the driving behavior history of the user of interest is updated.

  In step S14, the diagnosis unit 154 makes a driving diagnosis during driving. For example, based on the estimated state history of the noted user after the start of driving and the driving behavior history, the diagnosis unit 154 uses the driving diagnosis model of the noted user stored in the storage unit 162 to determine the driving aptitude degree u. to correct.

  For example, the driving aptitude degree u is lowered in the case where the degree of concentration or arousal of the noted user decreases, and the degree of fatigue, stress or tension of the noted user is increased. On the other hand, for example, when the concentration degree or the awakening degree of the user of interest is increased, the degree of fatigue, stress or tension of the user of interest is decreased, the driving aptitude u is raised. Further, for example, when the dangerous driving is detected, the driving aptitude degree u is lowered according to the detection frequency. On the other hand, when the state where the dangerous driving is not detected continues, the driving aptitude degree u is raised according to the continuation time.

  Note that the driving aptitude factor u is corrected based on the user's attention to driving operation such as how smooth the brakes and accelerator pedals are, how to steer the steering wheel at cornering, and smoothness of acceleration and deceleration. May be

  The diagnosis unit 154 causes the storage unit 162 to store the corrected driving aptitude degree u and the estimated reduction factor together with the diagnosed time as the diagnosis result of the driving aptitude of the noted user. Thus, the driving diagnosis history of the user of interest is updated.

  In step S15, the risk prediction unit 156 performs risk prediction. Here, unlike the process of step S5, the risk prediction unit 156 further uses the estimated state history and driving behavior history of the noted user stored in the storage unit 162 in addition to the driving diagnosis history of the noted user. Make predictions. For example, even if the driving aptitude degree u of the noted user is high, the predicted risk increases as the detection frequency of the dangerous driving increases and as the risk degree of the detected dangerous driving increases. On the other hand, for example, even if the driving aptitude degree u of the noted user is low, when the dangerous driving is not detected, the predicted risk is reduced. As described above, the risk prediction is performed by further using the driving condition and driving behavior of the actual user of interest, so that the accuracy of the risk prediction is improved as compared with the process of step S5.

  Also, the risk prediction unit 156 can predict not only the risk and its occurrence probability but also a time when the risk occurrence probability becomes high (hereinafter referred to as a risk rise time). For example, the risk prediction unit 156 estimates the time at which they fall below a predetermined threshold as the risk increase time, based on the concentration degree of the user of interest, the tension degree, or the time series change of the awakening degree.

  The risk prediction unit 156 supplies the prediction result of the risk to the damage prediction unit 157. The prediction result of this risk includes the content of the predicted risk, the basis for which the risk was predicted (for example, the cause of the decrease in the driving aptitude degree u and the detection result of the dangerous driving), and the occurrence probability of the risk. In addition, risk rise time is included as needed.

  In step S16, damage prediction is performed as in the process of step S6. However, unlike the process of step S6, the loss prediction unit 157 further performs loss prediction using the degree of compliance of the user of interest. That is, the higher the degree of compliance of the user of interest, the higher the possibility of avoiding the risk, and the lower the degree of compliance, the lower the possibility of avoiding the risk. Thus, the higher the compliance, the smaller the expected damage, and the lower the compliance, the larger the predicted damage. The damage prediction unit 157 supplies the prediction result of the risk and the damage to the driving behavior detection unit 155 and the presentation control unit 158.

  Here, the level of dangerous driving to be detected and the level of risk to be predicted change depending on the degree of compliance of the noted user. For example, as described above, the lower the compliance of the user of interest, the greater the loss of predicted risk. Therefore, the detection parameters are adjusted to lower the level of the dangerous operation to be detected. As a result, the lower the degree of compliance, the lower the level of dangerous driving to be detected and the level of risk to be predicted.

  In step S17, the presentation control unit 158 determines whether to perform feedback to the user (the user of interest). For example, when the occurrence of the risk that needs to be notified to the focused user is predicted, the presentation control unit 158 determines that feedback to the focused user is to be performed, and the process proceeds to step S18.

  In step S18, feedback to the user of interest is performed as in the process of step S8. Here, a specific example of feedback information presented to the user of interest will be described.

  For example, when the lack of sleep of the user of interest is estimated, when sudden operation or meandering operation is detected, warning for dangerous driving is performed. For example, in the user terminal unit 11 of the user of interest or the vehicle 12, a voice message such as "It is a sleep shortage condition. Please drive with caution." Is output. For example, the part of "Please drive with caution" is a risk aversion plan, and the portion of "insufficient sleep state" is a basis for presenting a risk aversion plan.

  For example, when it is estimated that the noted user is out of the range of daily life, or when it is estimated that he / she feels a strong stress, a warning for dangerous driving is performed when an approach to a forward vehicle is detected. It will be. For example, in the user terminal unit 11 or the vehicle 12 of the user of interest, a voice message such as "Are you in a hurry? Let's calmly drive." Is output. For example, the part of "Let's drive calmly" is a risk aversion plan, and the portion of "is it in a hurry?" Is a basis for presenting a risk abatement plan.

  For example, when it is estimated that the focused user was doing intense exercise before driving, when one point concentration of the focused user's line of sight is detected, or when a large number of pedestrians are detected around the vehicle 12, A warning will be issued for the fear of driving. For example, in the user terminal unit 11 or the vehicle 12 of the user of interest, a voice message such as "Did you feel sleepy? Drive with attention to the surroundings" is output. For example, the part of "Please drive with caution to the surroundings" is a risk aversion plan, and the portion of "Do you feel sleepy?" Is a basis for presenting a risk aversion plan.

  For example, when it is estimated that the user of interest is out of the range of daily life, or when the lack of sleep of the user of interest is estimated, a sudden operation or meandering operation is detected while traveling on a freeway. Attention is given to driving. For example, in the user terminal 11 or the vehicle 12 of the user of interest, a voice message such as "How about taking a break in the next service area? Ru. For example, the part of "How would you like to take a break in the next service area" is a risk aversion plan, and the portion of "You are sleepless and you are currently meandering driving" presents a risk abatement plan. It becomes.

  For example, in a case where sleep condition or extreme tension state of a noted user is estimated, when dangerous driving is frequently detected, a warning of a premium increase of automobile insurance and presentation of the cause thereof are performed. For example, in the user terminal 11 or the vehicle 12 of the user of interest, “dangerous driving frequently occurs due to lack of sleep (or tension). If x more dangerous drivings are detected, the premium cashback right A voice message such as "I will lose" is output. For example, the part “I lose the right to premium cashback when the x more dangerous drivings are detected” is a warning to the target user, “the dangerous driving due to lack of sleep (or tension) is occurring frequently "Mass" is the basis for giving a warning.

  For example, if it is estimated that the watched user is traveling on an unfamiliar road outside the daily life area and the risk rise time due to fatigue is estimated, “Don't you feel tired? How about taking a break in service area A? A voice message such as “U?” Is output. Note that the service area A is a service area that is estimated to be reachable by the vehicle 12 of the focused user before the risk rise time is reached. For example, the part of "Would you like to take a break in the service area A" is a risk aversion plan, and the portion of "are you tired?" Is a basis for presenting a risk aversion plan.

  In addition, it is also possible to use more specific content, such as "Please lower the speed to 60 km / h." Or "Please turn to the front immediately", for example.

  Also, the presentation control unit 158 supplies feedback information to the evaluation unit 159.

  In step S19, the evaluation unit 159 evaluates the degree of compliance of the user (user of interest). Specifically, the evaluation unit 159 acquires, from the storage unit 162, the estimated state history and the driving behavior history of the user of interest after feedback to the user of interest has been performed. Then, the evaluation unit 159 detects the reaction (for example, the content of driving) of the user of interest to the feedback based on the acquired history.

  Further, the evaluation unit 159 updates the evaluation value of the degree of compliance of the noted user based on the reaction of the noted user. For example, if the feedback information presented this time includes a risk avoidance plan and the attention user follows the risk avoidance plan, the degree of compliance of the attention user increases. In addition, the shorter the time it takes the focused user to follow the risk avoidance plan (the faster the response speed), or the smaller the difference between the focused user's reaction and the risk avoidance plan, the larger the increase in the degree of compliance of the focused user . Conversely, the longer the time it takes the focused user to follow the risk avoidance plan (the slower the response speed), or the greater the difference between the focused user's reaction and the risk avoidance plan, the smaller the increase in the degree of compliance of the focused user Become.

  On the other hand, if the focused user does not follow the risk avoidance plan, for example, if the focused user ignores the risk avoidance plan, or if the focused user responds differently to the risk avoidance plan, then the degree of compliance of the focused user is descend. In particular, when the user of interest performs dangerous driving without following the risk avoidance plan, the degree of decrease in the degree of compliance of the user of interest becomes large.

  The evaluation unit 159 supplies the updated degree of compliance of the noted user to the damage prediction unit 157 and stores the degree of compliance in the storage unit 162.

  Thereafter, the process proceeds to step S20.

  On the other hand, if it is determined in step S17 that feedback to the user of interest is not to be performed, the processes of steps S18 and S19 are skipped, and the process proceeds to step S20.

  In step S20, the detection parameter of the driving behavior is adjusted as in the process of step S7.

  In step S21, the state estimation unit 152 determines whether the user has stopped driving. That is, the state estimation unit 152 focuses on data based on data received from at least one of the user terminal unit 11 of the user of interest and the vehicle 12 via the communication unit 151, similarly to the determination processing of driving start in step S10. It is determined whether the user has stopped driving.

  When it is determined that the focused user has not stopped driving, the process returns to step S14. Thereafter, in step S21, the processes of steps S14 to S21 are repeatedly executed until it is determined that the focused user has stopped driving. As a result, the driving diagnosis, the risk prediction, and the damage prediction of the user of interest are appropriately performed, and adjustment of detection parameters for dangerous driving and feedback to the user of interest are performed based on the results. Further, the degree of compliance of the noted user is updated as appropriate.

  On the other hand, when it is determined in step S21 that the user of interest has stopped driving, the process proceeds to step S22.

  In step S22, as in the process of step S1, the process of estimating the state of the user of interest during non-operation is started.

  In step S23, the surrounding data acquisition unit 153 stops acquisition of data around the vehicle 12.

  In step S24, the driving behavior detection unit 155 stops the detection processing of the driving behavior.

  In step S25, the learning unit 160 performs a learning process. For example, the learning unit 160 detects a state estimation model, a driving diagnosis model, and a driving behavior detection based on the state data log of the user of interest, the estimated state history, the driving diagnosis history, and the driving behavior history stored in the storage unit 162. Learn models and risk prediction models.

  For example, even if the driving aptitude degree u is evaluated to be low, when the safe driving is performed, the weight wx and the weight wy of the equation (1) representing the driving diagnostic model described above are set small. As a result, the driving aptitude level u of the user of interest can be evaluated higher than ever. Conversely, if dangerous driving is frequently performed even though the driving aptitude degree u is highly evaluated, the weight wx and the weight wy of equation (1) are set large. As a result, the driving aptitude level u of the user of interest can be evaluated lower than before.

  Further, for example, when safe driving is performed despite the fact that the difference between the nearest state pattern of the noted user and the user group state pattern is large and the driving suitability factor u is evaluated to be low, Weight wx is increased and weight wy is decreased. That is, in driving diagnosis, the difference between the closest state pattern of the user of interest and the standard state pattern is more emphasized.

  Note that, for example, initially when the focused user starts using the service, a model corresponding to an average user obtained by a previous experiment or the like is used. Thereafter, each model is updated (personalized) to a model more suitable for the user of interest through learning processing.

  Note that this learning process does not have to be performed every time the driving of the user of interest ends, for example, every predetermined period, every time the driving is performed a predetermined number of times, or every time the operating time increases by a predetermined time or more. It may be performed at any timing. Further, it is not necessary to perform learning processing of all models simultaneously, and learning processing may be performed at different timings for each model.

  Also, for example, the learning unit 160 may learn the fatigue level estimation model for predicting the fatigue level of the user of interest based on the transition of the fatigue level of the user of interest before and during driving shown in the estimated state history. Good. For example, the state estimation unit 152 can estimate the degree of fatigue of the user of interest at each point of the planned travel route using the degree of fatigue estimation model. Furthermore, for example, the learning unit 160 learns the fatigue level estimation model in consideration of the state around the vehicle 12 such as time zone, weather, traffic congestion status, and road type (for example, general road or highway). By doing this, the estimation accuracy of the degree of fatigue can be improved.

  In addition, as a method of learning processing, for example, machine learning such as a neural network or any other method can be used.

  In step S26, the premium calculation unit 161 calculates the premium of the user (user of interest). For example, when the premium of the user's insurance or the cashback amount for the premium of the user's insurance changes in real time, the premium calculation unit 161 stores the driving diagnostic history and the driving behavior history of the user of interest stored in the storage unit 162. And, based on the degree of compliance, update the premium or cashback amount. The premium calculating unit 161 stores the updated premium or cashback amount of the noted user in the storage unit 162.

  For example, the lower the average value of the driving aptitude degree u, the higher the premium (or the lower the cashback amount), and the higher the average value of the driving aptitude degree u, the lower the premium (or the cashback amount Go up).

  Also, for example, the premium increases (or the cashback amount decreases) as the frequency or cumulative number of dangerous operations increases, and the premium decreases as the frequency or cumulative number of dangerous operations decreases (or cashback amount) Go up). Furthermore, for example, the higher the average or the total expected losses for dangerous operation, the higher the premium (or the lower the cashback amount) and the lower the average or total expected losses for dangerous operation. As you go, the premium goes down (or the cashback amount goes up).

  Also, for example, as the degree of compliance is lower, a decrease in risk can not be expected, the premium increases (or the cashback amount decreases), and as the degree of compliance is higher, a decrease in risk can be expected, the premium decreases. (Or the cashback amount goes up). In particular, when the focused user performs dangerous driving without following the risk avoidance plan, for example, the increase in premium (or the decrease in cashback amount) increases as a penalty.

  Note that this premium calculation process does not have to be performed every time the operation of the user of interest is finished, for example, every predetermined period, every time the operation is performed a predetermined number of times, and every time the operation time increases by a predetermined time or more. Or the like may be performed at any timing such as

  Also, this premium calculation process may be executed, for example, to calculate the estimated premium amount at the next insurance renewal.

  Furthermore, for example, in the case of automobile insurance for each driving or daily driving, the premium may be calculated by executing this premium calculation processing before driving. In this case, for example, the premium is calculated using at least one of the driving aptitude degree u and the compliance degree of the noted user.

  Also, the calculated premium or cashback amount may be presented to the user of interest as feedback information.

  Thereafter, the process returns to step S2, and the processes after step S2 are performed.

  For example, the driving behavior is influenced not only by the state of the user while driving but also by the state of the user before driving (e.g., behavior, living state, emotion, etc.). On the other hand, as described above, in addition to the user's driving state and driving behavior, the driving aptitude degree u is more appropriately evaluated by comprehensively considering the user's state before driving. Further, as the accuracy of the driving aptitude degree u is improved, the accuracy of the risk prediction and the damage prediction is improved. As a result, appropriate feedback information can be presented at more appropriate timing, safety can be improved, and occurrence of an accident can be prevented.

  Further, since the feedback information indicates the basis of the result of the driving diagnosis or the basis for predicting the risk, the user's sense of satisfaction is improved, and the probability of the user following the risk avoidance plan is increased. Further, if the presented basis is incorrect, for example, the user instructs the server 13 to make a correction and reflects it in the learning process, whereby the accuracy of the driving diagnosis model or the risk prediction model is improved.

  Furthermore, the user's degree of compliance is evaluated, and the level of dangerous driving to be detected and the level of risk to be predicted change based on the degree of compliance, and the user can more reliably avoid the risk. Will be able to

  In addition, it is possible to set a more appropriate premium for each user by calculating the insurance premium (including the cashback amount) of automobile insurance based not only on the driving behavior of the user but also on the driving aptitude degree u and the compliance degree. Can. This allows the user, for example, to be motivated to follow the risk avoidance plan, and allows the user to more reliably avoid the risk.

<< 2. Modified example >>
Hereinafter, modifications of the embodiment of the technology according to the present disclosure described above will be described.

<Modification on system configuration>
The configuration example of the information processing system 10 in FIGS. 1 to 4 is an example thereof, and can be changed as needed.

  For example, although in the above description, the server 13 performs most of the processing based on the data acquired from the user terminal unit 11 and the vehicle 12 (in-vehicle system 101), for example, the user terminal unit 11 and the vehicle 12 and the server 13 can share processing, or the user terminal unit 11 or the vehicle 12 can perform processing independently.

  For example, at least one of the user terminal unit 11 and the vehicle 12 can perform part or all of the processing of the server 13.

  For example, at least one of the user terminal unit 11 and the vehicle 12 performs part or all of the processing of the state estimation unit 152, the driving behavior detection unit 155, and the evaluation unit 159, and transmits the estimation result and the detection result to the server 13. You may do it.

  For example, at least one of the user terminal unit 11 and the vehicle 12 may perform part or all of the processing of the peripheral data acquisition unit 153 and transmit the acquired peripheral data to the server 13.

  For example, at least one of the user terminal unit 11 and the vehicle 12 performs part or all of the processes of the diagnosis unit 154, the risk prediction unit 156, and the damage prediction unit 157, and transmits the diagnosis result and the prediction result to the server 13. You may do so.

  In addition, for example, processing related to driving support may be performed by the user terminal unit 11. In this case, the user terminal unit 11 may be configured by a plurality of devices or may be configured by one device. Also, the user terminal unit 11 may obtain various data (for example, vehicle data, video data, audio data, etc.) from the vehicle 12 and use it for processing, or use data from the vehicle 12 for processing. It may not be. In addition, the user collection state pattern may or may not be used in the driving diagnosis process. When using the user aggregation state pattern, for example, the server 13 learns the user aggregation state pattern based on the standard state pattern of each user acquired from the user terminal unit 11 of each user. Then, the server 13 transmits data indicating the user aggregation state pattern to the user terminal unit 11 of each user.

  In this case, the calculation of the premium may be performed by either the user terminal unit 11 or the server 13. When the user terminal unit 11 performs, for example, an application program for calculating the premium is provided from the server 13. On the other hand, when the server 13 performs, for example, data necessary for calculating the premium is provided from the user terminal unit 11 to the server 13.

  Furthermore, for example, among the processes related to driving support, almost all the processes except the process of estimating the state of the user during non-driving and the process of learning the standard state pattern may be performed by the vehicle 12 (in-vehicle system 101). In this case, for example, the user terminal unit 11 performs estimation processing of the user's state during non-driving and learning processing of the standard state pattern, and the data indicating the estimated state history and standard state pattern obtained as a result is Send to 12 Then, the vehicle 12 executes the remaining processing. In this case, the user aggregation state pattern may or may not be used in the driving diagnosis process. When using the user aggregation state pattern, when using the user aggregation state pattern, for example, the server 13 learns the user aggregation state pattern based on the standard state pattern of each user acquired from the user terminal unit 11 of each user. . Then, the server 13 transmits data indicating the user aggregation state pattern to the user terminal unit 11 or the vehicle 12 of each user.

  In this case, the calculation of the premium may be performed by any of the user terminal unit 11, the vehicle 12, and the server 13. In the case where the user terminal unit 11 or the vehicle 12 performs, for example, an application program for performing a premium calculation process is provided from the server 13. On the other hand, when the server 13 performs, for example, data necessary for the calculation of the premium is provided from the user terminal unit 11 and the vehicle 12 to the server 13.

  Also, for example, the processing may be shared between the user terminal unit 11 and the server 13. In this case, data from the vehicle 12 may or may not be used for processing.

  Furthermore, for example, processing may be shared between the vehicle 12 and the server 13. In this case, for example, data (for example, the standard state pattern and the latest state pattern of the user, etc.) necessary for the processing are provided from the user terminal unit 11 to the vehicle 12 and the server 13.

  Also, for example, processing may be shared by a plurality of servers. For example, the processing for driving support and the processing for calculating the premium may be performed by different servers.

  Furthermore, for example, communication between the vehicle 12 and the server 13 may be performed via the user terminal unit 11. In this case, for example, data from the vehicle 12 is once transmitted to the user terminal unit 11 and then transferred from the user terminal unit 11 to the server 13. Also, after data from the server 13 is once transmitted to the user terminal unit 11, the data is transferred from the user terminal unit 11 to the vehicle 12.

  Also, for example, communication between the user terminal unit 11 and the server 13 may be performed via the vehicle 12. In this case, for example, data from the user terminal unit 11 is transferred to the server 13 from the vehicle 12 after being transmitted to the vehicle 12 once. In addition, after data from the server 13 is once transmitted to the vehicle 12, the data is transferred from the vehicle 12 to the user terminal unit 11.

  Furthermore, for example, instead of the estimated state history, the driving diagnosis of the diagnosis unit 154, the risk prediction of the risk predicting unit 156, and the driving behavior detecting unit 155 are directly used by directly using the state data log before the user's condition is estimated. Detection of driving behavior may be performed. In this case, the state estimation unit 152 can be deleted.

<Other Modifications>
For example, the driving aptitude degree u may be calculated using the current state of the user in addition to the degree of deviation between the user's nearest state pattern and the standard state pattern or the user aggregate average pattern. For example, even if the difference between the nearest state pattern of the user and the standard state pattern is small, for example, the degree of awakening of the user is low, excited or depressed, there is a high possibility of dangerous driving. Therefore, for example, among items indicating the user's condition, for items having a large influence on driving, the current condition (for example, the awakening degree, the excitement degree, the depression degree) of those items is It may be used for calculation.

  In addition, the state of the user to be estimated is not limited to the above-described three types of biological state, behavior, and emotion. For example, only one or two of the above three types may be estimated, or other types of states may be estimated.

  Furthermore, for example, the user's behavior that is usually assumed not to directly affect the driving may be used to calculate the driving aptitude degree u. For example, based on the user's purchase history, it is assumed that the user's state (for example, emotion) is different from normal when the user makes a shopping having a tendency different from the usual tendency (for example, very expensive shopping) Be done. Therefore, for example, the purchase history of the user may be used to calculate the driving aptitude degree u.

  Also, for example, the ability of the user detected based on the state of the user at the time of non-driving may be used to calculate the driving aptitude degree u, and also the ability to affect the driving. For example, the driving aptitude degree u of the user having high judgment ability for daily life may be set high, and the driving aptitude degree u of the user having low judgment ability may be set low.

  In this case, for example, even if users with high judgment ability and low users repeat lane changes frequently as well, the predicted risk for users with high judgment ability is low and the judgment ability is low. The predicted risk to the user is high. However, even if a user with high judgment ability is presented with a risk aversion plan to reduce lane change, it is predicted that the degree of compliance will be evaluated low if it is ignored and repeated lane change. Risk is high.

  Furthermore, for example, risk prediction may be performed based on only one or two of the estimation result of the user's state, the result of the driving diagnosis, and the detection result of the driving behavior. Furthermore, for example, when risk prediction is performed using the result of driving diagnosis, only one of the driving suitability degree u before driving and the driving suitability degree u during driving may be used.

  Further, for example, the driving diagnosis may be performed based only on the state of one of the user before driving and during driving.

  Furthermore, for example, it is possible to use an estimated state history, a driving diagnosis history, and a driving behavior history to find out the cause of the accident. For example, by recording the estimated state history, the driving diagnosis history, and the driving behavior history in the drive recorder, in addition to the user's (driver) 's state and behavior at the time of the accident, based on the user's state before driving. It becomes possible to investigate the cause of the accident.

  Also, for example, the user terminal unit 11 or the vehicle 12 can acquire the driving aptitude degree u of another user, the prediction result of the risk, and the like from the user terminal unit 11 or the vehicle 12 of the other user or the server 13 May be Thereby, for example, when there is a dangerous vehicle driven by a user whose driving aptitude degree u is low, for example, the user avoids being involved in an accident due to the dangerous vehicle by acquiring the information in advance. be able to.

  Furthermore, personalization of the state estimation model, the driving diagnosis model, the driving behavior detection model, and the risk prediction model is not necessarily performed, and a model using a predetermined algorithm or the like may be used. Further, for example, instead of performing learning of the above-described model for each user, for example, the entire user set may be performed, and a common model may be used for each user.

  Also, for example, the method of presenting feedback information, the frequency of presentation, and the content of presentation may be changed based on the degree of compliance of the user.

<Example of application>
In addition to the vehicles exemplified above, the driving support process of the present technology (for example, the present technology includes various moving bodies such as motorcycles, bicycles, personal mobility, airplanes, ships, construction machines, agricultural machines (tractors), etc. The present invention can also be applied to cases where driving is performed, that is, driving diagnosis, risk prediction, damage prediction, feedback to the user, etc. can be performed using estimation results of the user's state before and during driving. In addition, the mobile body to which the present technology can be applied is a part that performs work in a fixed place, such as some construction machines (eg, fixed cranes, etc.) other than those moving the place. Mobile bodies to which the present technology can be applied also include, for example, mobile bodies that a user, such as a drone or a robot, remotely operates (operates) without boarding.

  In addition to automobile insurance, the present technology can be applied to systems and devices that provide various types of insurance such as life insurance, non-life insurance and medical insurance. For example, various types of premiums (including cashback amounts) can be calculated based on the user's estimated state history and compliance. Specifically, for example, in the case of life insurance or medical insurance, the user terminal unit 11 or the server 13 performs the state estimation process of the user and accumulates the estimated state history. In addition, the user terminal unit 11 or the server 13 presents the user with a proposal (risk avoidance plan) for avoiding risks such as illness based on the user's lifestyle and living condition based on the estimated state history, and the reaction thereof Based on the degree of user compliance. Then, the user terminal unit 11 or the server 13 calculates the premium of the life insurance or the medical insurance based on the user's lifestyle and living condition, the compliance degree and the like.

  For example, the better the lifestyle and the living condition, the lower the premium, and the worse the lifestyle and the living condition, the higher the premium. Also, the higher the compliance, the lower the premium, and the lower the compliance, the higher the premium. As described above, by considering not only the user's lifestyle and physical condition but also the user's compliance, it is possible to set a more appropriate premium for each user, as in the case of the above-described automobile insurance.

<< 3. Other >>
<Example of computer configuration>
The series of processes described above can be performed by hardware or software. When the series of processes are performed by software, a program that configures the software is installed on a computer. Here, the computer includes, for example, a general-purpose personal computer that can execute various functions by installing a computer incorporated in dedicated hardware and various programs.

  FIG. 11 is a block diagram showing an example of a hardware configuration of a computer that executes the series of processes described above according to a program.

  In the computer, a central processing unit (CPU) 401, a read only memory (ROM) 402, and a random access memory (RAM) 403 are mutually connected by a bus 404.

  Further, an input / output interface 405 is connected to the bus 404. An input unit 406, an output unit 407, a recording unit 408, a communication unit 409, and a drive 410 are connected to the input / output interface 405.

  The input unit 406 includes an input switch, a button, a microphone, an imaging device, and the like. The output unit 407 includes a display, a speaker, and the like. The recording unit 408 includes a hard disk, a non-volatile memory, and the like. The communication unit 409 includes a network interface and the like. The drive 410 drives a removable recording medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

  In the computer configured as described above, for example, the CPU 401 loads the program recorded in the recording unit 408 into the RAM 403 via the input / output interface 405 and the bus 404 and executes the program. Processing is performed.

  The program executed by the computer (CPU 401) can be provided by being recorded on, for example, a removable recording medium 411 as a package medium or the like. Also, the program can be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

  In the computer, the program can be installed in the recording unit 408 via the input / output interface 405 by attaching the removable recording medium 411 to the drive 410. The program can be received by the communication unit 409 via a wired or wireless transmission medium and installed in the recording unit 408. In addition, the program can be installed in advance in the ROM 402 or the recording unit 408.

  Note that the program executed by the computer may be a program that performs processing in chronological order according to the order described in this specification, in parallel, or when necessary, such as when a call is made. It may be a program to be processed.

  Further, in the present specification, a system means a set of a plurality of components (devices, modules (parts), etc.), and it does not matter whether all the components are in the same case. Therefore, a plurality of devices housed in separate housings and connected via a network, and one device housing a plurality of modules in one housing are all systems. .

  Furthermore, the embodiments of the present technology are not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present technology.

  For example, the present technology can have a cloud computing configuration in which one function is shared and processed by a plurality of devices via a network.

  Further, each step described in the above-described flowchart can be executed by one device or in a shared manner by a plurality of devices.

  Furthermore, in the case where a plurality of processes are included in one step, the plurality of processes included in one step can be executed by being shared by a plurality of devices in addition to being executed by one device.

<Example of combination of configurations>
The present technology can also be configured as follows.

(1)
A diagnosis unit that diagnoses the suitability of the user for driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving, which are acquired in advance;
An information processing apparatus comprising: a presentation control unit that generates feedback information based on a diagnosis obtained by the diagnosis unit.
(2)
The vehicle further includes a driving behavior detection unit that detects a driving behavior that is a behavior of the user or the moving body during driving.
The information processing apparatus according to (1), wherein the level of dangerous driving to be detected by the driving behavior detection unit changes based on the result of the diagnosis.
(3)
The information processing apparatus according to (2), wherein the diagnosis unit further performs the diagnosis based on a detection result of the driving behavior.
(4)
The diagnosis unit diagnoses the aptitude for driving of the user before driving based on the state of the user before driving, and based on the detection result of the state of the user while driving and the driving behavior. The information processing apparatus according to (3), wherein the user's suitability for driving is diagnosed.
(5)
(2) to (4) further including a risk prediction unit that predicts a risk related to the driving of the mobile object by the user based on at least one of the diagnosis result and the detection result of the driving behavior The information processing apparatus according to any one of the above.
(6)
The information processing apparatus according to (5), wherein the feedback information includes the content of the risk and a basis on which the risk is predicted.
(7)
The information processing apparatus according to (6), wherein the basis on which the risk is predicted is based on the result of the diagnosis.
(8)
The information processing apparatus according to any one of (5) to (7), wherein the feedback information includes a plan for avoiding the risk.
(9)
The information processing apparatus according to any one of (2) to (8), wherein the level of dangerous driving to be detected by the driving behavior detection unit decreases as the driving suitability of the user based on the diagnosis decreases.
(10)
The information processing apparatus according to any one of (2) to (9), further including: a learning unit that learns a model that performs the diagnosis based on a result of the diagnosis and a detection result of the driving behavior.
(11)
The information processing apparatus according to any one of (1) to (10), wherein the diagnosis unit performs the diagnosis based on a difference between a latest state of the user and a standard state of the user.
(12)
The information processing apparatus according to (11), wherein the diagnosis unit further performs the diagnosis based on a difference between the latest state of the user and an average state of the user in a user group including a plurality of users. .
(13)
The system further includes a state estimation unit that estimates the state of the user before and during driving.
The information processing apparatus according to any one of (1) to (12), wherein the diagnosis unit performs the diagnosis based on an estimation result of the state of the user.
(14)
The information processing apparatus according to (13), wherein the state of the user includes at least one of a biological state, an action, and an emotion of the user.
(15)
The information processing apparatus according to any one of (1) to (12), wherein the diagnosis unit performs the diagnosis based on data indicating a state of the user acquired before and during driving of the user.
(16)
A diagnosis step of diagnosing a suitability of the user for driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving,
A presentation control step of generating feedback information based on the diagnosis obtained by the diagnosis unit.
(17)
A diagnosis step of diagnosing a suitability of the user for driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving,
A program for causing a computer to execute a process including a presentation control step of generating feedback information based on the diagnosis obtained by the diagnosis unit.

  In addition, the effect described in this specification is an illustration to the last, is not limited, and may have other effects.

  Reference Signs List 10 information processing system, 11 user terminal unit, 12 vehicle, 13 server, 51 mobile terminal, 52 wearable terminal, 61 GNSS receiver, 62 inertial sensor, 63 environment sensor, 64 biometric sensor, 66 output unit, 67 control unit, 81 Biometric sensor, 83 output unit, 84 control unit, 101 vehicle system, 111 vehicle data acquisition unit, 112 video and audio acquisition unit, 114 output unit, 115 control unit, 152 state estimation unit, 154 diagnosis unit, 155 driving behavior detection unit, 156 risk prediction unit, 157 damage prediction unit, 158 presentation control unit, 159 evaluation unit, 160 learning unit, 161 premium calculation unit

The information processing method according to one aspect of the present technology is directed to the driving of the user based on the pre-driving state of the user driving the moving body and the state of the driving user acquired during driving. And a presentation control step of generating feedback information based on the diagnosis obtained by the diagnosis unit .

The program according to one aspect of the present technology is suitable for the user's driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving. A computer is caused to execute processing including a diagnosis step of diagnosis and a presentation control step of generating feedback information based on the diagnosis obtained by the diagnosis unit .

In one aspect of the present technology , diagnosis of suitability for driving of the user based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving. And feedback information is generated based on the diagnosis obtained by the diagnosis unit.

Claims (17)

A diagnosis unit that diagnoses the suitability of the user for driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving, which are acquired in advance;
An information processing apparatus comprising: a presentation control unit that generates feedback information based on a diagnosis obtained by the diagnosis unit. The vehicle further includes a driving behavior detection unit that detects a driving behavior that is a behavior of the user or the moving body during driving.
The information processing apparatus according to claim 1, wherein the level of dangerous driving to be detected by the driving behavior detection unit changes based on the result of the diagnosis. The information processing apparatus according to claim 2, wherein the diagnosis unit performs the diagnosis based on a detection result of the driving behavior. The diagnosis unit diagnoses the aptitude for driving of the user before driving based on the state of the user before driving, and based on the detection result of the state of the user while driving and the driving behavior. The information processing apparatus according to claim 3, wherein the aptitude for driving of the user is diagnosed. The information processing apparatus according to claim 2, further comprising: a risk prediction unit that predicts a risk related to the operation of the mobile object by the user based on at least one of the diagnosis result and the detection result of the driving behavior. . The information processing apparatus according to claim 5, wherein the feedback information includes the content of the risk and a basis on which the risk is predicted. The information processing apparatus according to claim 6, wherein the ground on which the risk is predicted is based on a result of the diagnosis. The information processing apparatus according to claim 5, wherein the feedback information includes an avoidance plan for the risk. The information processing apparatus according to claim 2, wherein the level of dangerous driving to be detected by the driving behavior detection unit is lower as the driving suitability of the user based on the diagnosis is lower. The information processing apparatus according to claim 2, further comprising: a learning unit that learns a model to perform the diagnosis based on a result of the diagnosis and a detection result of the driving behavior. The information processing apparatus according to claim 1, wherein the diagnosis unit performs the diagnosis based on a difference between a latest state of the user and a standard state of the user. The information processing apparatus according to claim 11, wherein the diagnosis unit further performs the diagnosis based on a difference between a state closest to the user and an average state of the user in a user group including a plurality of users. The system further includes a state estimation unit that estimates the state of the user before and during driving.
The information processing apparatus according to claim 1, wherein the diagnosis unit performs the diagnosis based on an estimation result of the state of the user. The information processing apparatus according to claim 13, wherein the state of the user includes at least one of a biological state, an action, and an emotion of the user. The information processing apparatus according to claim 1, wherein the diagnosis unit performs the diagnosis based on data indicating a state of the user acquired before and during driving of the user. A diagnosis step of diagnosing a suitability of the user for driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving,
A presentation control step of generating feedback information based on the diagnosis obtained by the diagnosis unit. A diagnosis step of diagnosing a suitability of the user for driving based on the pre-driving state of the user driving the moving body and the state of the driving user obtained during driving,
A program for causing a computer to execute a process including a presentation control step of generating feedback information based on the diagnosis obtained by the diagnosis unit.

Images