Information processing device, information processing system, information processing method and program

Abstract

Provided is an information processing apparatus comprising: a sensing data items acquiring unit (246) for acquiring a plurality of sensing data items from a device worn or carried by a user; a calculating unit (248) for calculating, on the basis of inertial data included in the plurality of sensing data items, the number of steps taken or the distance travelled by the user; a reliability calculating unit (252) for calculating reliability on the basis of a feature amount of each of position data, biometric data, and environment data pertaining to the user that are obtained from the plurality of sensing data items; a determining unit (254) for determining, on the basis of the calculated reliability, whether the calculated number of steps or distance travelled may be accepted; and an output unit (256) for outputting accepted data of the number of steps or the distance travelled.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing system, an information processing method, and a program. [Background technology]

[0002] In recent years, with growing interest in health, various services that encourage health promotion have been proposed. One such service is an insurance product called health promotion medical insurance. While life insurance and medical insurance premiums are determined based on the insured's attribute information (age, gender, address, occupation, medical history, smoking history, etc.), health promotion insurance evaluates the insured's health status and efforts to improve their health (for example, walking), and provides premium discounts and refunds based on the evaluation. With such insurance, insureds are encouraged to actively and continuously engage in health promotion activities, such as walking, even after signing the insurance contract, in order to receive incentives such as premium discounts and refunds. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-23768 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the emergence of the above-mentioned products, some insured persons have begun to falsify the number of steps taken and the distance traveled by using pedometers or other devices to measure the number of steps taken and the distance traveled in an unfair manner, in order to obtain unfair incentives, rather than actually walking and having the pedometer measure the number of steps taken and the distance traveled.

[0005] Therefore, the present disclosure proposes an information processing device, an information processing system, an information processing method, and a program that can prevent the number of steps and the like from being falsified. [Means for solving the problem]

[0006] According to the present disclosure, there is provided an information processing device comprising: a sensing data acquisition unit that acquires multiple sensing data from a device worn by or carried by a user; a calculation unit that calculates the number of steps or distance traveled by the user based on inertial data included in the multiple sensing data; a reliability calculation unit that calculates reliability based on each feature of position data, biometric data, and environmental data related to the user obtained from the multiple sensing data; a determination unit that determines whether or not to accept the calculated number of steps or distance traveled based on the calculated reliability; and an output unit that outputs the accepted data on the number of steps or distance traveled.

[0007] Furthermore, according to the present disclosure, there is provided an information processing system including a server that calculates an incentive for a user, and an information processing device worn by or carried by the user, wherein the information processing device has: a sensing data acquisition unit that acquires multiple pieces of sensing data from a device worn by or carried by the user; a calculation unit that calculates the number of steps or the distance traveled of the user based on inertial data included in the multiple pieces of sensing data; a reliability calculation unit that calculates reliability based on each feature of position data, biometric data, and environmental data related to the user that are obtained from the multiple pieces of sensing data; a determination unit that determines whether or not to accept the calculated number of steps or the distance traveled based on the calculated reliability; an output unit that outputs the accepted data of the number of steps or the distance traveled to the server; and a presentation unit that presents the incentive calculated by the server based on the data of the number of steps or the distance traveled to the user.

[0008] Furthermore, according to the present disclosure, an information processing method is provided, including an information processing device acquiring a plurality of sensing data from a device worn by or carried by a user, calculating the number of steps or distance traveled by the user based on inertial data included in the plurality of sensing data, calculating reliability based on each feature of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data, determining whether to accept the calculated number of steps or the distance traveled based on the calculated reliability, and outputting data on the accepted number of steps or the distance traveled.

[0009] Furthermore, according to the present disclosure, a program is provided that causes a computer to execute the following functions: acquiring multiple pieces of sensing data from a device worn by or carried by a user; calculating the number of steps or distance traveled by the user based on inertial data included in the multiple pieces of sensing data; calculating reliability based on each feature of position data, biometric data, and environmental data related to the user obtained from the multiple pieces of sensing data; determining whether or not to accept the calculated number of steps or distance traveled based on the calculated reliability; and outputting the accepted data on the number of steps or distance traveled. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is an explanatory diagram illustrating a configuration example of an information processing system 10 according to an embodiment of the present disclosure. [Figure 2] 1 is an explanatory diagram showing an example of the appearance of a wearable device 100 according to an embodiment of the present disclosure. [Figure 3] FIG. 1 is a block diagram showing an example of a configuration of a wearable device 100 according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a block diagram illustrating an example of a configuration of a mobile device 200 according to an embodiment of the present disclosure. [Figure 5] FIG. 2 is a block diagram showing an example of a configuration of a server 300 according to an embodiment of the present disclosure. [Figure 6] FIG. 10 is a sequence diagram illustrating an example of an information processing method according to an embodiment of the present disclosure. [Figure 7] FIG. 1 is an explanatory diagram (part 1) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 8] FIG. 10 is an explanatory diagram (part 2) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 9] FIG. 10 is an explanatory diagram (part 3) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is an explanatory diagram (part 4) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 11] FIG. 5 is an explanatory diagram (part 5) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 12] FIG. 10 is an explanatory diagram (part 6) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 13] FIG. 10 is an explanatory diagram (part 7) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 14] FIG. 8 is an explanatory diagram (part 8) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 15] FIG. 9 is an explanatory diagram (part 9) illustrating an example of a display screen according to an embodiment of the present disclosure. [Figure 16] 1 is a flowchart illustrating an example of an information processing method according to an embodiment of the present disclosure. [Figure 17] FIG. 1 is an explanatory diagram (part 1) for explaining an example of a feature amount according to an embodiment of the present disclosure. [Figure 18] FIG. 10 is an explanatory diagram (part 2) for explaining an example of a feature amount according to the embodiment of the present disclosure. [Figure 19] FIG. 10 is an explanatory diagram (part 3) for explaining an example of a feature amount according to an embodiment of the present disclosure. [Figure 20A] FIG. 10 is an explanatory diagram (part 4) for explaining an example of a feature amount according to an embodiment of the present disclosure. [Figure 20B] FIG. 5 is an explanatory diagram (part 5) for explaining an example of a feature amount according to an embodiment of the present disclosure. [Figure 21]FIG. 10 is an explanatory diagram (part 6) for explaining an example of a feature amount according to an embodiment of the present disclosure. [Figure 22] FIG. 10 is an explanatory diagram for explaining reliability according to an embodiment of the present disclosure. [Figure 23] 1 is a table (part 1) illustrating an example of coefficients according to an embodiment of the present disclosure. [Figure 24] 10 is a table (part 2) illustrating an example of coefficients according to an embodiment of the present disclosure. [Figure 25] FIG. 1 is a block diagram illustrating an example of a schematic functional configuration of a smartphone. DETAILED DESCRIPTION OF THE INVENTION

[0011] Preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted. Furthermore, in this specification and the drawings, multiple components having substantially the same or similar functional configurations may be distinguished by adding different letters after the same reference numeral. However, when there is no particular need to distinguish between multiple components having substantially the same or similar functional configurations, only the same reference numerals will be used.

[0012] The explanation will be given in the following order. 1. Background leading to the creation of embodiments of the present disclosure 2. Implementation form 2.1 Overview of the information processing system 10 according to an embodiment of the present disclosure 2.2 Detailed Configuration of Wearable Device 100 2.3 Detailed Configuration of the Mobile Device 200 2.4 Detailed configuration of the server 300 2.5 Information Processing Methods 2.6 Calculating the number of steps 2.7 Features 2.8 Calculation of reliability 3. Summary 4. Hardware Configuration 5. Supplementary Information

[0013] <<1. Background leading to the creation of the embodiments of the present disclosure>> Before describing the embodiments of the present disclosure, the background that led the inventors to create the embodiments of the present disclosure will be described.

[0014] As explained above, as interest in health has grown, various services designed to promote health have been developed. One such service is a health promotion insurance product. While life insurance and health insurance premiums are determined based on the insured's attribute information (e.g., age, gender, address, occupation, medical history, smoking history), health promotion insurance evaluates the insured's health status and health promotion efforts, and provides premium discounts and refunds based on the evaluation. With such insurance, insureds actively and continuously work to improve their health, even after signing the insurance contract, in order to receive incentives such as premium discounts and refunds. Daily walking, for example, is one example of a health promotion initiative that can earn such incentives. Specifically, insurance companies detect the insured's step count, and if the step count is expected to be effective in improving the insured's health, they provide the insured with the incentives based on the number of steps.

[0015] However, the emergence of these types of products has led some insured persons to falsify their step counts in order to unfairly obtain incentives. For example, insured persons engaging in such fraudulent practices intentionally vibrate step-counting devices, causing the devices to count steps even when they are not actually walking. Because step counts are calculated by analyzing acceleration data, it is difficult to distinguish between acceleration changes caused by the vibrator and those caused by actual walking. While it is possible to count steps using Global Navigation Satellite System (GNSS) signals, it is difficult to accurately detect GNSS signals indoors, resulting in unavoidable large measurement errors. Furthermore, if insurance premiums (discount amounts) are calculated based on step counts with large errors, even insured persons who have not engaged in the fraudulent practices described above find it difficult to feel satisfied with their premiums, ultimately resulting in a decrease in the number of insurance subscribers.

[0016] In view of this situation, the inventors have come up with an embodiment of the present disclosure that can prevent step count falsification. In the embodiment of the present disclosure described below, the reliability of the number of steps measured using various types of sensing data related to the user, such as behavior recognition, is calculated, and whether or not to use the number of steps when calculating insurance premiums is determined based on the reliability. Furthermore, in order to prevent falsification, it is preferable to perform personal authentication in this embodiment.

[0017] The embodiments of the present disclosure described below will be described as being applied to information processing for acquiring the number of steps for health promotion insurance. Note that the present embodiments are not limited to being applied to information processing for acquiring the number of steps for calculating insurance premiums and discounts (rebates) for such health promotion insurance. For example, the present embodiments may be applied to a service that provides users with points (incentives) that can be used for shopping instead of cash based on the number of steps, or a service that provides health advice to users based on the number of steps.

[0018] In this specification, the term "number of steps" does not only include the number of steps taken by the user walking, but also the number of steps taken by the user running. In other words, the term "number of steps" in this specification can be said to be the number of steps taken by the user when moving through their own physical exercise.

[0019] <<2. Embodiment>> 2.1 Overview of the information processing system 10 according to an embodiment of the present disclosure First, an overview of an information processing system 10 according to an embodiment of the present disclosure will be described with reference to Fig. 1. Fig. 1 is an explanatory diagram illustrating an example configuration of the information processing system 10 according to the present embodiment.

[0020] As shown in FIG. 1, an information processing system 10 according to this embodiment includes a wearable device 100, a mobile device 200, and a server 300, which are communicatively connected to one another via a network 400. In particular, the wearable device 100, the mobile device 200, and the server 300 can be connected to the network 400 via a base station (not shown) or the like (e.g., a mobile phone base station, a wireless LAN (Local Area Network) access point, etc.). Note that any communication method can be used in the network 400, whether wired or wireless (e.g., WiFi (registered trademark), Bluetooth (registered trademark), etc.), but it is preferable to use a communication method that can maintain stable operation. Below, an overview of each device included in the information processing system 10 according to this embodiment will be sequentially described.

[0021] (Wearable Devices 100) The wearable device 100 may be a device that can be worn on a part of the user's body (such as an earlobe, neck, arm, wrist, or ankle), or may be an implant device (implant terminal) inserted into the user's body. More specifically, the wearable device 100 may be a variety of types of wearable device, such as an HMD (Head Mounted Display) type, eyeglasses type, ear device type, anklet type, bracelet (wristband) type, collar type, eyewear type, pad type, badge type, or clothing type. Furthermore, the wearable device 100 has a plurality of sensors, such as a sensor that detects a pulse wave signal based on the user's pulse. In the following description, the wearable device 100 is assumed to be, for example, a bracelet (wristband) type wearable device. Details of the wearable device 100 will be described later.

[0022] (Mobile device 200) The mobile device 200 is an information processing terminal carried by a user. Specifically, the mobile device 200 can receive information input by the user and sensing data from the wearable device 100, process the received information, and output the processed information to the server 300 (described later). For example, the mobile device 200 can be a tablet PC (Personal Computer), a smartphone, a mobile phone, a laptop PC, a notebook PC, an HMD, or other device. The mobile device 200 further includes a display unit (not shown) that displays information to the user, an input unit (not shown) that receives input operations from the user, a speaker (not shown) that outputs audio to the user, and a microphone (hereinafter referred to as a microphone) (not shown) that captures ambient audio. In the following description, the mobile device 200 is assumed to be, for example, a smartphone. The mobile device 200 will be described in detail later.

[0023] In this embodiment, the mobile device 200 may be provided with the various sensors that the wearable device 100 has, or the sensors may be provided separately from the wearable device 100 or the mobile device 200.

[0024] (Server 300) Server 300 is configured by, for example, a computer. Server 300 processes, for example, sensing data and information acquired by wearable device 100 and mobile device 200, and outputs the information obtained by the processing to another device (for example, mobile device 200). In detail, server 300 can calculate insurance premiums (for example, discount amounts, etc.) (incentives) by processing, for example, step count data obtained by processing sensing data from wearable device 100 by mobile device 200. Furthermore, server 300 can output the calculated insurance premiums to mobile device 200. Details of server 300 will be described later.

[0025] 1, the information processing system 10 according to the present embodiment is shown as including one wearable device 100 and one mobile device 200, but this is not limited to this in the present embodiment. For example, the information processing system 10 according to the present embodiment may include a plurality of wearable devices 100 and mobile devices 200. Furthermore, the information processing system 10 according to the present embodiment may include other communication devices, such as a relay device when transmitting information from the wearable device 100 or the mobile device 200 to the server 300.

[0026] Furthermore, the information processing system 10 according to the present embodiment may not include the wearable device 100. In such a case, for example, the mobile device 200 may function like the wearable device 100, and the sensing data acquired by the mobile device 200 or information obtained by processing the sensing data may be output to the server 300.

[0027] 2.2 Detailed configuration of the wearable device 100 Next, a detailed configuration of the wearable device 100 according to an embodiment of the present disclosure will be described with reference to Fig. 2 and Fig. 3. Fig. 2 is an explanatory diagram showing an example of the appearance of the wearable device 100 according to the present embodiment, and Fig. 3 is a block diagram showing an example of the configuration of the wearable device 100 according to the present embodiment.

[0028] As described above, various types of wearable devices, such as a bracelet type and an HMD type, can be used as the wearable device 100. Fig. 2 shows an example of the appearance of the wearable device 100 according to this embodiment. As shown in Fig. 2, the wearable device 100 is a bracelet type wearable device that is worn on the wrist of a user.

[0029] 2, the wearable device 100 has a belt-like band. The band is worn by wrapping it around the user's wrist, and is made of a material such as soft silicone gel so that it takes a ring shape that fits the shape of the wrist. The control unit (not shown) is the part where the above-mentioned sensors and the like are provided, and is provided inside the band so that it comes into contact with the user's arm when the wearable device 100 is worn on the user's arm.

[0030] 3, wearable device 100 mainly includes an input unit 110, an authentication information acquisition unit 120, a display unit 130, a control unit 140, a sensor unit 150, a storage unit 170, and a communication unit 180. Details of each functional unit of wearable device 100 will be explained below.

[0031] (input unit 110) The input unit 110 accepts data and commands input from the user to the wearable device 100. More specifically, the input unit 110 is realized by a touch panel, buttons, a microphone (hereinafter referred to as a "mic"), etc. In addition, in this embodiment, the input unit 110 may be, for example, an eye gaze sensor that detects the user's line of sight and accepts a command linked to a display in the direction of the user's line of sight. The eye gaze sensor may be, for example, an imaging device configured by a lens, an imaging element, etc. Furthermore, the input unit 110 may be an input unit that accepts input by detecting gestures made by the hand or arm wearing the wearable device 100 using an IMU (Inertial Measurement Unit) 152 included in the sensor unit 150 described later.

[0032] (Authentication information acquisition unit 120) The authentication information acquisition unit 120 can acquire a fingerprint pattern image, an iris pattern image, a vein pattern image, a face image, or a voiceprint based on the user's voice, etc., of the user to perform personal authentication of the user, and transmits the acquired information to the mobile device 200, which will be described later. In addition, in this embodiment, the authentication information acquisition unit 120 may accept a password, a trajectory shape, etc., input by the user to perform personal authentication of the user.

[0033] In this embodiment, for example, when personal authentication is performed using a user's fingerprint information, the authentication information acquisition unit 120 can be a capacitance detection fingerprint sensor that acquires a fingerprint pattern by sensing the capacitance at each point on the sensing surface that occurs when the user places their fingertip on the sensing surface. The capacitance detection fingerprint sensor arranges microelectrodes in a matrix on the sensing surface, and detects the potential difference that appears in the capacitance that occurs between the microelectrodes and the fingertip by passing a small current through them, thereby detecting the fingerprint pattern.

[0034] In this embodiment, the authentication information acquisition unit 120 may be, for example, a pressure-detection fingerprint sensor that acquires a fingerprint pattern by sensing the pressure at each point on the sensing surface when a fingertip is placed on the sensing surface. In this pressure-detection fingerprint sensor, for example, micro semiconductor sensors whose resistance value changes depending on the pressure are arranged in a matrix on the sensing surface.

[0035] In this embodiment, the authentication information acquisition unit 120 may be, for example, a heat-sensitive fingerprint sensor that acquires a fingerprint pattern by sensing a temperature difference that occurs when a fingertip is placed on a sensing surface. In this heat-sensitive fingerprint sensor, for example, minute temperature sensors whose resistance value changes depending on the temperature are arranged in a matrix on the sensing surface.

[0036] In this embodiment, the authentication information acquisition unit 120 may be, for example, an optical fingerprint sensor that detects reflected light generated when a fingertip is placed on a sensing surface to acquire a captured image of a fingerprint pattern. The optical fingerprint sensor includes, for example, a micro lens array (MLA), which is an example of a lens array, and a photoelectric conversion element. In other words, the optical fingerprint sensor can be considered a type of imaging device.

[0037] Furthermore, in this embodiment, the authentication information acquisition unit 120 may be, for example, an ultrasonic fingerprint sensor that emits ultrasonic waves and detects the ultrasonic waves reflected by the unevenness of the skin surface of the fingertip to acquire a fingerprint pattern.

[0038] (Display section 130) The display unit 130 is a device for presenting information to the user, and outputs various pieces of information to the user as images, for example. More specifically, the display unit 130 is realized by a display or the like. Note that some of the functions of the display unit 130 may be provided by the mobile device 200. In addition, in this embodiment, the functional block that presents information to the user is not limited to the display unit 130, and the wearable device 100 may have functional blocks such as a speaker, earphones, a light-emitting element (e.g., a light-emitting diode (LED)), a vibration module, etc.

[0039] (control unit 140) The control unit 140 is provided in the wearable device 100 and can control each functional unit of the wearable device 100 and acquire sensing data from the above-mentioned sensor unit 150. The control unit 140 is realized by hardware such as a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). Note that some of the functions of the control unit 140 may be provided by a server 300, which will be described later.

[0040] (sensor unit 150) The sensor unit 150 is provided in the wearable device 100 worn on the user's body and has various sensors that detect the state of the user or the user's surrounding environment. The sensing data acquired by these various sensors is transmitted to the mobile device 200, which will be described later. In detail, the sensor unit 150 has an IMU (Inertial Measurement Unit) 152 that detects inertial data generated by the user's movement, a positioning sensor 154 that measures the user's position, and a biometric information sensor 156 that detects the user's pulse or heart rate. The sensor unit 150 may also have an image sensor 158 that acquires images (video) of the user's surroundings, one or more microphones 160 that detect environmental sounds around the user, etc. The various sensors of the sensor unit 150 will be described in detail below.

[0041] ~IMU152~ The IMU 152 can acquire sensing data (inertial data) that indicates changes in acceleration and angular velocity that occur in conjunction with the user's movements. Specifically, the IMU 152 includes an acceleration sensor, a gyro sensor, a geomagnetic sensor, and the like (not shown).

[0042] ~Positioning Sensor 154~ The positioning sensor 154 is a sensor that detects the position of the user wearing the wearable device 100, and specifically can be a GNSS (Global Navigation Satellite System) receiver or the like. In this case, the positioning sensor 154 can generate sensing data indicating the latitude and longitude of the user's current location based on signals (GNSS signals) from GNSS satellites. In addition, in this embodiment, since the relative position of the user can be detected from information such as RFID (Radio Frequency Identification), Wi-Fi access points, and wireless base stations, it is also possible to use such communication devices as the positioning sensor 154.

[0043] In this embodiment, Proof of Location (PoL) technology may be used in addition to the above to improve the reliability of positioning using GNSS signals. For example, PoL technology is a technology that improves the reliability of positioning using GNSS signals by confirming that the user is at a location by performing short-distance communication with a fixed access point that exists near the positioning location using GNSS signals, simultaneously with positioning using GNSS signals.

[0044] ~Biometric Information Sensor 156~ The biometric information sensor 156 is a sensor that detects the biometric information of the user, and can be, for example, any of various sensors that are attached directly to a part of the user's body and measure the user's heart rate, pulse, blood pressure, brain waves, breathing, sweating, myoelectric potential, skin temperature, skin electrical resistance, etc.

[0045] For example, a heartbeat sensor (an example of a pulse sensor) is a sensor that detects the heartbeat, which is the pulsation of the user's heart. A pulse sensor (an example of a pulse sensor) is a sensor that detects the pulse, which is the pulsation of the arteries that appears on the body surface, as a result of changes in pressure occurring on the inner walls of the arteries due to the pulsation of the heart (heartbeat), causing blood to be sent to the entire body through the arteries. A blood flow sensor (including a blood pressure sensor) is a sensor that, for example, radiates infrared rays or the like to the body and detects blood flow, pulse, heart rate, and blood pressure based on the light absorptance or reflectance or changes therein. The heartbeat sensor or pulse sensor may also be an imaging device that captures an image of the user's skin. In this case, the user's pulse or heartbeat can be detected based on changes in the light reflectance of the skin obtained from the image of the user's skin.

[0046] For example, the respiration sensor can be a respiratory flow sensor that detects changes in respiration rate. The brain wave sensor is a sensor that detects brain waves by attaching multiple electrodes to the user's scalp and extracting periodic waves by removing noise from fluctuations in the potential difference between the measured electrodes. The skin temperature sensor is a sensor that detects the user's surface body temperature, and the skin conductivity sensor is a sensor that detects the user's electrical resistance of the skin. The sweat sensor is a sensor that is attached to the user's skin and detects the voltage or resistance between two points on the skin that changes due to sweating. Furthermore, the electromyography sensor is a sensor that quantitatively detects the amount of muscle activity by using multiple electrodes attached to the user's arm or other part to measure the electromyography (EMG) generated in muscle fibers when the muscles of the arm or other part contract and propagating to the body surface.

[0047] ~Image Sensor 158~ The image sensor 158 is, for example, a color image sensor having a Bayer array that can detect blue, green, and red light. The RGB sensor may also be configured with a pair of image sensors to grasp depth (stereo system).

[0048] The image sensor 158 may also be a Time of Flight (ToF) sensor that acquires depth information of the real space around the user. Specifically, the ToF sensor irradiates the user with light such as infrared light and detects the light reflected from the surfaces of surrounding objects. The ToF sensor can then calculate the phase difference between the irradiated light and the reflected light to acquire the distance (depth information) from the ToF sensor to the real object. Therefore, a distance image can be obtained as three-dimensional shape data from such depth information. The method of acquiring distance information using the phase difference as described above is called an indirect ToF method. In this embodiment, a direct ToF method can also be used, which can acquire the distance (depth information) from the ToF sensor to the object by detecting the round-trip time of light from the time when the irradiated light is emitted until the irradiated light is reflected by the object and received as reflected light. Specifically, the ToF sensor can acquire the distance (depth information) from the ToF sensor to the object. Therefore, a distance image including the distance (depth information) to the object can be obtained as three-dimensional shape data of the real space. Here, the distance image is, for example, image information generated by linking distance information (depth information) acquired for each pixel of the ToF sensor with position information of the corresponding pixel.

[0049] ~Mic 160~ The microphone 160 is a sound sensor that detects sounds generated by the user's speech or movements, or sounds generated around the user. Note that in this embodiment, the number of microphones 160 is not limited to one, and there may be multiple microphones 160. Also, in this embodiment, the microphone 160 is not limited to being provided inside the wearable device 100, and one or multiple microphones 160 may be installed around the user, for example.

[0050] The sensor unit 150 may also include an ambient environment sensor that detects the state of the user's ambient environment, and more specifically, may include various sensors that detect the temperature, humidity, brightness, etc. of the user's ambient environment. In this embodiment, sensing data from these sensors may be used to improve the accuracy of user behavior recognition, which will be described later.

[0051] Furthermore, the sensor unit 150 may have a built-in clock mechanism (not shown) that keeps track of the accurate time, and may associate acquired sensing data with the time at which the sensing data was acquired. As described above, the various sensors do not have to be provided within the sensor unit 150 of the wearable device 100, and may be provided, for example, as separate entities from the wearable device 100, or may be provided in another device used by the user.

[0052] Furthermore, the sensor unit 150 may include a sensor for detecting the wearing state of the sensor unit 150. For example, the sensor unit 150 may include a pressure sensor or the like that detects that the sensor unit 150 is correctly worn on a part of the user's body (for example, that the sensor unit 150 is worn so as to be in close contact with the part of the body).

[0053] (Storage unit 170) The storage unit 170 is provided in the wearable device 100 and stores programs, information, etc. for the control unit 140 to execute various processes, as well as information obtained through the processes. The storage unit 170 is realized by, for example, a nonvolatile memory such as a flash memory.

[0054] (Communication unit 180) The communication unit 180 is provided within the wearable device 100 and can transmit and receive information to and from external devices such as the mobile device 200 and the server 300. In other words, the communication unit 180 can be said to be a communication interface that has the function of transmitting and receiving data. The communication unit 180 is realized by a communication device such as a communication antenna, a transmission / reception circuit, or a port. Furthermore, in this embodiment, the communication unit 180 may function as a radio wave sensor that detects the radio wave intensity and the direction from which the radio waves arrive.

[0055] In this embodiment, the configuration of wearable device 100 is not limited to that shown in FIG. 3, and may further include, for example, functional blocks not shown.

[0056] 2.3 Detailed configuration of the mobile device 200 Next, a detailed configuration of the mobile device 200 according to this embodiment will be described with reference to FIG. 4. FIG. 4 is a block diagram showing an example of the configuration of the mobile device 200 according to this embodiment. As described above, the mobile device 200 is a device such as a tablet, smartphone, mobile phone, laptop PC, notebook PC, or HMD. In detail, as shown in FIG. 4, the mobile device 200 mainly includes an input unit 210, a display unit 230, a processing unit 240, a storage unit 270, and a communication unit 280. Below, the details of each functional unit of the mobile device 200 will be sequentially described.

[0057] (input unit 210) The input unit 210 accepts data and commands input from a user to the mobile device 200. More specifically, the input unit 210 is realized by a touch panel, buttons, a microphone, and the like.

[0058] (Display section 230) The display unit 230 is a device for presenting information to the user, and can output various types of information to the user, for example, as images based on information acquired from the server 300. More specifically, the display unit 130 is realized by a display or the like. In this embodiment, the functional block for presenting information to the user is not limited to the display unit 230, and the mobile device 200 may have functional blocks such as a speaker, earphones, a light-emitting element, a vibration module, etc.

[0059] (Processing unit 240) The processing unit 240 can process sensing data from the sensor unit 150 of the wearable device 100. The processing unit 240 is realized by hardware such as a CPU, a ROM, and a RAM. As shown in Fig. 4, the processing unit 240 has an authentication information acquisition unit 242, an authentication unit 244, a sensing data acquisition unit 246, a step count calculation unit (calculation unit) 248, a feature amount calculation unit 250, a reliability calculation unit 252, a determination unit 254, an output unit 256, and an insurance premium information acquisition unit (presentation unit) 260. Details of each functional block of the processing unit 240 will be explained below in order.

[0060] ~Authentication Information Acquisition Unit 242~ The authentication information acquisition unit 242 can acquire a fingerprint pattern image, an iris pattern image, a vein pattern image, a face image, or a voiceprint based on the user's voice from the authentication information acquisition unit 120 of the wearable device 100 to perform personal authentication of the user. Furthermore, the authentication information acquisition unit 242 can output the acquired information to the authentication unit 244, which will be described later. In this embodiment, for example, when performing personal authentication using the user's fingerprint information, the authentication information acquisition unit 242 may acquire the user's fingerprint pattern from the authentication information acquisition unit 120 of the wearable device 100 and perform predetermined processing such as enhancing the fingerprint pattern or removing noise. More specifically, the authentication information acquisition unit 242 can use various filters for smoothing and noise removal, such as a moving average filter, a differential filter, a median filter, or a Gaussian filter. Furthermore, the authentication information acquisition unit 242 may perform processing using various algorithms for binarization and thinning, for example.

[0061] ~Authentication Section 244~ The authentication unit 244 can perform personal authentication by acquiring the user's fingerprint information (fingerprint pattern), iris information, facial image, password, trajectory, etc. from the above-mentioned authentication information acquisition unit 242 and comparing it with personal authentication information linked to a personal ID (Identification) in a personal information database (DB) previously stored in the memory unit 270 described later.

[0062] In this embodiment, for example, when personal authentication is performed using fingerprint information of a user, the authentication unit 244 calculates the feature amount of the fingerprint pattern. Here, the feature amount of the fingerprint pattern refers to the distribution of feature points on the fingerprint pattern, that is, the number and distribution density of feature points (distribution information). Furthermore, feature points refer to attribute information such as the shape, orientation, and position (relative coordinates) of the center point, ridge bifurcation points, intersection points, and end points (called minutiae) of the fingerprint pattern pattern. Furthermore, the feature points may be attribute information such as the shape, orientation, width, spacing, and distribution density of ridges.

[0063] For example, the authentication unit 244 can authenticate a user by comparing feature points extracted from a part of the fingerprint pattern output from the authentication information acquisition unit 242 with feature points of a fingerprint pattern previously stored in the storage unit 130 or the like (feature point method). Furthermore, for example, the authentication unit 244 can authenticate a user by comparing the fingerprint pattern output from the authentication information acquisition unit 242 with a fingerprint template of a fingerprint pattern previously stored in the storage unit 270 or the like (pattern matching method). Furthermore, for example, the authentication unit 244 can authenticate a user by slicing the fingerprint pattern into strips, spectrally analyzing the pattern of each slice, and comparing the results with the spectral analysis results of the fingerprint pattern previously stored in the storage unit 270 or the like (frequency analysis method).

[0064] In this embodiment, when the authentication unit 244 has successfully authenticated the user, it can start acquiring sensing data, process the sensing data, and transmit the data obtained by processing the sensing data to an external device (e.g., server 300).

[0065] ~Sensing data acquisition unit 246~ The sensing data acquisition unit 246 can acquire a plurality of pieces of sensing data from the wearable device 100 and output them to the step count calculation unit 248 and the feature amount calculation unit 250, which will be described later.

[0066] ~Step Count Calculation Unit 248~ The step count calculation unit 248 can calculate (count) the number of steps of the user based on changes in inertial data (acceleration data, angular velocity data, etc.) from the sensing data acquisition unit 246 described above. Note that the step count calculation unit 248 may calculate the number of steps of the user by referring to a model previously obtained by machine learning. Furthermore, the step count calculation unit 248 can output data on the calculated number of steps to the output unit 256, which will be described later, etc. Note that in this embodiment, the step count calculation unit 248 may also calculate the distance traveled by the user.

[0067] ~Feature Calculation Unit 250~ The feature amount calculation unit 250 can calculate feature amounts from the inertial data, position data, biological data, and environmental data included in the multiple pieces of sensing data from the sensing data acquisition unit 246 (details of the inertial data, position data, biological data, and environmental data will be described later). Furthermore, the feature amount calculation unit 250 can output the calculated feature amounts to the reliability calculation unit 252 (described later). For example, the feature amount calculation unit 250 can calculate feature amounts by performing statistical processing (average, variance, normalization, etc.) on one or more pieces of sensing data. Alternatively, the feature amount calculation unit 250 may calculate feature amounts from sensing data by referring to a model previously obtained by machine learning.

[0068] Furthermore, for example, the feature amount calculation unit 250 can obtain the distance traveled by the user by walking (second distance data) by multiplying data on the number of steps taken by the user, obtained from the inertial data, by data on the stride length input by the user. Furthermore, the feature amount calculation unit 250 may calculate the distance traveled by the user by walking (first distance data) based on the sensing data from the positioning sensor 154, and calculate, as a feature amount, the difference between the walking distance based on the inertial data and the walking distance based on the sensing data from the positioning sensor 154.

[0069] Furthermore, the feature amount calculation unit 250 can recognize the user's behavior (walking, running, riding, etc.) as a feature amount based on at least one of the plurality of sensing data from the sensing data acquisition unit 246. For example, if the same type of sensor (e.g., IMU 152) is mounted on both the wearable device 100 and the mobile device 200, the feature amount calculation unit 250 can recognize the user's behavior by comparing the same type of sensing data (inertial data) from the different devices. Note that the calculation of the feature amount in this embodiment will be described in detail later.

[0070] ~Reliability calculation unit 252~ The reliability calculation unit 252 can calculate reliability based on each feature amount from the position data, biometric data, environmental data, and behavior recognition data related to the user, which are obtained by the above-mentioned feature amount calculation unit 250. Furthermore, the reliability calculation unit 252 can output the calculated reliability to the determination unit 254, which will be described later. In detail, the reliability calculation unit 252 can calculate the reliability by weighting each feature amount using a predetermined coefficient assigned to each feature amount. Furthermore, in this embodiment, the reliability calculation unit 252 may dynamically change the predetermined coefficient according to the user's position, behavior recognition data, position change amount, etc. Note that the calculation of reliability in this embodiment will be described in detail later.

[0071] ~Judgment section 254~ The determination unit 254 can determine whether or not to accept the data on the number of steps calculated by the step count calculation unit 248 (more specifically, whether the data is genuine and not a faked number of steps) based on the reliability calculated by the reliability calculation unit 252. In more detail, the determination unit 254 compares the reliability with a predetermined threshold, and if the reliability is equal to or greater than the predetermined threshold, determines to accept the data on the number of steps calculated, and outputs the determination result to the output unit 256, which will be described later. Furthermore, in this embodiment, the determination unit 254 may dynamically change the predetermined threshold based on information from the server 300.

[0072] ~Output section 256~ Based on the determination by the determination unit 254, the output unit 256 outputs the data on the number of steps calculated by the step number calculation unit 248 to the server 300. Note that the output unit 256 may output the data on the number of steps to the display unit 230 or the storage unit 270.

[0073] ~Insurance Premium Information Acquisition Unit 260~ The insurance premium information acquisition unit 260 can acquire from the server 300 information on insurance premiums or insurance premium discount amounts (incentives) calculated based on data on the number of steps in the server 300 and output it to the display unit 230.

[0074] (Storage unit 270) Storage unit 270 is provided in mobile device 200 and stores programs, information, etc. for executing various processes by processing unit 240 described above, and information obtained through the processes. Note that storage unit 270 is realized by, for example, a nonvolatile memory such as a flash memory.

[0075] (Communication unit 280) The communication unit 280 is provided in the mobile device 200 and can transmit and receive information to and from the wearable device 100 and external devices such as the server 300. In other words, the communication unit 280 can be said to be a communication interface having the function of transmitting and receiving data. The communication unit 280 is realized by a communication device such as a communication antenna, a transmission / reception circuit, or a port. Furthermore, in this embodiment, the communication unit 280 may function as a radio wave sensor that detects the distance to the wearable device 100, or detects the radio wave intensity and the direction of arrival of the radio waves.

[0076] In this embodiment, the configuration of the mobile device 200 is not limited to that shown in FIG. 4, and may further include functional blocks not shown, such as the sensor unit 150 of the wearable device 100.

[0077] <2.4 Detailed configuration of the server 300> Next, a detailed configuration of the server 300 according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a block diagram showing an example of the configuration of the server 300 according to this embodiment. As described above, the server 300 is configured by, for example, a computer. In detail, as shown in Fig. 5, the server 300 mainly includes an input unit 310, a display unit 330, a processing unit 340, a storage unit 370, and a communication unit 380. Details of each functional unit of the server 300 will be described below in order.

[0078] (Input unit 310) The input unit 310 accepts data and commands input from a user to the server 300. More specifically, the input unit 310 is realized by a touch panel, a keyboard, or the like.

[0079] (Display section 330) The display unit 330 is configured by, for example, a display, a video output terminal, etc., and outputs various information to the user in the form of images, etc.

[0080] (Processing unit 340) The processing unit 340 is provided in the server 300 and can control each block of the server 300. Specifically, the processing unit 340 controls various processes, such as calculation of insurance premiums, performed in the server 300. The processing unit 340 is realized by hardware, such as a CPU, a ROM, and a RAM. The processing unit 340 may execute some of the functions of the processing unit 240 of the mobile device 200. In detail, as shown in FIG. 5 , the processing unit 340 includes a step count information acquisition unit 342, an insurance premium calculation unit 344, a threshold calculation unit 346, and an output unit 356. Details of each functional block of the processing unit 340 will be described below in order.

[0081] ~Step count information acquisition unit 342~ The step count information acquisition unit 342 can acquire step count data from the mobile device 200 and output it to the insurance premium calculation unit 344 and storage unit 370, which will be described later.

[0082] ~Insurance Premium Calculation Department 344~ The insurance premium calculation unit 344 can calculate the user's insurance premium based on the step count data from the step count information acquisition unit 342 described above, and output the calculated premium to the output unit 356 described below. In detail, the insurance premium calculation unit 344 can calculate the user's insurance premium based on the user's step count and attribute information (gender, age, place of residence, medical history, occupation, desired compensation, etc.) by referring to an insurance premium table stored in the storage unit 370 described below. At this time, the insurance premium calculation unit 344 may also calculate and output the difference (discount amount) between the insurance premium currently paid by the user and the newly calculated insurance premium.

[0083] ~Threshold calculation unit 346~ The threshold calculation unit 346 can determine a predetermined threshold to be used by the determination unit 254 of the mobile device 200 described above by referring to the history (number of steps, etc.) of the user (or multiple users) and the insurance company's guarantee record and investment record, and output the determined threshold to the mobile device 200 via the output unit 356 described below. In detail, for example, the threshold calculation unit 346 adjusts the threshold so that the insurance company can make a profit even if the insurance premium is reduced for each user according to the user's step record.

[0084] ~Output section 356~ The output unit 356 can output the insurance premium and threshold calculated by the insurance premium calculation unit 344 and threshold calculation unit 346 described above to the mobile device 200.

[0085] (Storage unit 370) The storage unit 370 is provided in the server 300 and stores programs and the like for the above-mentioned processing unit 340 to execute various processes, as well as information obtained through the processes. More specifically, the storage unit 370 is realized by, for example, a magnetic recording medium such as a hard disk (HD).

[0086] (Communication unit 380) The communication unit 380 is provided in the server 300 and can transmit and receive information to and from an external device such as the mobile device 200. The communication unit 380 is realized by a communication device such as a communication antenna, a transmission / reception circuit, or a port, for example.

[0087] In this embodiment, the configuration of server 300 is not limited to that shown in FIG. 5, and may further include, for example, functional blocks (not shown) that perform some of the functions of mobile device 200 described above.

[0088] <2.5 Information Processing Method> Next, an information processing method according to an embodiment of the present disclosure will be described with reference to Fig. 6 to Fig. 15. Fig. 6 is a sequence diagram illustrating an example of the information processing method according to the embodiment, and Fig. 7 to Fig. 15 are explanatory diagrams showing examples of display screens according to the embodiment.

[0089] In detail, the information processing method according to this embodiment can mainly include a plurality of steps from step S100 to step S700, as shown in Fig. 6. Details of each of these steps according to this embodiment will be sequentially explained below.

[0090] First, the wearable device 100 and the mobile device 200, which are user-side devices, perform personal authentication of the user (step S100). For example, in step S100, the mobile device 200 performs unlocking or the like using the fingerprint pattern of the user's fingertip.

[0091] Furthermore, in this embodiment, upon first use, authentication information such as a fingerprint pattern used for the above unlocking and information on the user's insurance contract (such as insured person identification information, insurance coverage information, and insurance premiums) are linked in advance and stored in server 300. For example, as shown in FIG. 7 , after the first unlocking, mobile device 200 presents the user with an image for applying for insurance (such as an image of the insurance company's homepage). When the user performs an operation indicating their intention to apply for insurance, application information is sent to server 300 along with authentication information such as a fingerprint pattern, thereby enabling the above-described linking. At this time, it is preferable that the user installs an insurance app on wearable device 100 or mobile device 200. Furthermore, it is preferable that the image clearly states that the insurance premium will be recalculated using only the number of steps determined to be valid for calculating the insurance premium. Furthermore, from the perspective of protecting the user's privacy, it is preferable that the screen clearly states that sensing data obtained from various sensors will be used.

[0092] Next, the wearable device 100 or the mobile device 200, which is a user-side device, transmits the user's authentication information or identification information (policyholder information) linked to the user to the server 300, and queries the policyholder information (step S200).

[0093] Then, the server 300 checks whether the policyholder information, etc. sent from the wearable device 100 or the mobile device 200 matches the pre-stored policyholder information, etc., and sends the check result to the wearable device 100 or the mobile device 200 as a query result (step S300).

[0094] If the confirmation result transmitted from the server 300 indicates a match, the wearable device 100 or the mobile device 200 starts detecting the number of steps (step S400). On the other hand, if the confirmation result transmitted from the server 300 indicates a mismatch, the wearable device 100 or the mobile device 200 ends the process. At this time, as shown in, for example, FIGS. 8 and 9, the wearable device 100 or the mobile device 200 presents an image for obtaining approval for use of the sensing data from the user in order to start acquiring sensing data using various sensors mounted on the wearable device 100. Note that when both the wearable device 100 and the mobile device 200 are used, the wearable device 100 and the mobile device 200 may be connected to each other so as to be able to communicate with each other via short-range communication or the like, and approval for use of the sensing data may be performed on the wearable device 100 side, as shown in FIG. 9.

[0095] Furthermore, in this embodiment, while the number of steps is being detected, the wearable device 100 or the like may notify the user that the number of steps is being detected, as shown in FIG.

[0096] Then, for example, when wearable device 100 is removed from the user's body or when short-range communication between wearable device 100 and mobile device 200 is interrupted, wearable device 100 and mobile device 200 cancel the authentication of the user (step S500). Furthermore, when the authentication is cancelled, wearable device 100 and mobile device 200 transmit data such as the number of steps and reliability calculated up to that point to server 300. Note that in this embodiment, the timing of transmitting the data such as the number of steps and reliability calculated up to that point to server 300 is not limited to the timing of de-authentication, but may be at the end of a day or at predetermined intervals, and is not particularly limited.

[0097] At this time, as shown in Fig. 11, for example, the mobile device 200 may present information on the number of steps that are valid for calculating the insurance premium and the number of steps that are invalid, along with the user's walking path displayed on a map. In this way, by presenting the user with the number of invalid steps and the reason for the invalidation, the number of steps that will be reflected in the insurance premium can be confirmed later, thereby improving the user's satisfaction with the calculation of the insurance premium. Furthermore, when authentication is cancelled, as shown in Fig. 12, the mobile device 200 may present the user with a notification that authentication has been cancelled and a notification that requests re-authentication. Details of the calculation of the number of steps and reliability in this embodiment will be described later.

[0098] Next, server 300 calculates the insurance premium based on the data such as the number of steps transmitted from wearable device 100 and mobile device 200 (step S600). Then, server 300 redefines and updates the user's insurance contract conditions based on the calculated insurance premium, and transmits information such as the insurance premium (premium discount amount) and the insurance contract conditions to wearable device 100 and mobile device 200.

[0099] Then, the wearable device 100 and the mobile device 200 present to the user information such as the insurance premium and the insurance contract conditions transmitted from the server 300 (step S700). For example, as shown in Fig. 13, the mobile device 200 may present the difference (discount amount) between the updated insurance premium and the insurance premium before the renewal, together with the updated insurance premium.

[0100] In addition, in this embodiment, the wearable device 100 or the mobile device 200 may analyze previously stored sensing data (for example, sensing data acquired by the wearable device 100 before the insurance contract is signed) and calculate the number of steps to be reflected in the insurance premium. Furthermore, in this embodiment, the wearable device 100 or the mobile device 200 may have a configuration that can be used as a standalone device, capable of simulating or determining insurance premiums using past data. In this case, for example, as shown in FIG. 14, the mobile device 200 may present the user with a button for issuing an instruction to read past data or a screen that displays the calculated insurance premium.

[0101] Furthermore, in this embodiment, when environmental sounds around the user are acquired to acquire features, for example, and the environmental sounds include sounds that suggest danger to the user (e.g., a car horn, etc.), the wearable device 100 may alert the user by displaying a screen as shown in FIG. 15 or by vibrating the user. Furthermore, in this embodiment, when the mobile device inertial data suggests that the user has fallen, or when voice data suggests that the user has been abducted by a suspicious person (e.g., the voice data contains the word "help"), the mobile device 200 may automatically notify the user's family or automatically request rescue from an ambulance or the police. Adding such a function has the effect of encouraging the user to approve the constant acquisition of sensing data using various sensors.

[0102] <2.6 Calculating the number of steps> Next, the step count calculation shown in step S400 in Fig. 6 will be described in detail with reference to Fig. 16. Fig. 16 is a flowchart illustrating an example of an information processing method according to this embodiment. In detail, as shown in Fig. 16, step S400 in Fig. 6 may mainly include a plurality of sub-steps from sub-step S401 to sub-step S410. Details of each of these sub-steps according to this embodiment will be described in order below.

[0103] First, as explained in step S100 of FIG. 6, the wearable device 100 or the mobile device 200, which is a user-side device, performs personal authentication of the user (substep S401).

[0104] The wearable device 100 and the mobile device 200 determine whether to start step detection (substep S402). For example, if the user's personal authentication is successful in substep S401 and the wearable device 100 and the mobile device 200 have received an operation indicating the user's consent to step detection from the user (substep S402: Yes), the wearable device 100 and the mobile device 200 proceed to substep S403 to start step detection. On the other hand, if the user's personal authentication is not successful in substep S401 or the wearable device 100 and the mobile device 200 have not received an operation indicating the user's consent to step detection from the user (substep S402: No), the wearable device 100 and the mobile device 200 repeat the process of substep S402.

[0105] The wearable device 100 and the mobile device 200 store step count data D step is set to 0, and step detection (specifically, acquisition of inertial data) is started (substep S403).

[0106] The wearable device 100 and the mobile device 200 start acquiring sensing data for acquiring feature amounts (substep S404). Details of the calculation of feature amounts in this embodiment will be described later.

[0107] The wearable device 100 and the mobile device 200 calculate the user's step count data D based on the changes in the inertial data (acceleration data, angular velocity data, etc.) that have been acquired so far. step (sub-step S405). In this embodiment, the inertial data may be analyzed with reference to a model obtained in advance by machine learning, and the number of steps of the user may be calculated.

[0108] The wearable device 100 or the mobile device 200 determines whether or not there has been no step detection for a predetermined time or longer (substep S406). If there has been no step detection for a predetermined time or longer (substep S406: Yes), the wearable device 100 or the mobile device 200 proceeds to substep S407. On the other hand, if there has not been no step detection for a predetermined time or longer (i.e., there has been step detection) (substep S406: No), the wearable device 100 or the mobile device 200 returns to substep S405.

[0109] The wearable device 100 and the mobile device 200 calculate feature amounts based on the sensing data acquired up to that point, and calculate reliability based on the calculated feature amounts (substep S407). Details of the feature amounts and reliability in this embodiment will be described later.

[0110] In this embodiment, it is basically preferable that the timing for calculating the reliability and the length of the sensing data acquisition period for calculating the feature amount are long from the viewpoint of reliability. However, if the length of time is made too long, it is likely that many time periods during which the person is not walking will be included. Therefore, in this embodiment, it is preferable to set and adjust the length of time in consideration of the balance between the acquisition status of the sensing data, the reliability value, the processing load and power consumption of the mobile device 200, etc.

[0111] The wearable device 100 or the mobile device 200 determines whether the reliability calculated in the above-described substep S407 is equal to or greater than a predetermined threshold (substep S408). If the reliability is equal to or greater than the predetermined threshold (substep S408: Yes), the wearable device 100 or the mobile device 200 proceeds to substep S409. On the other hand, if the reliability is not equal to or greater than the predetermined threshold (substep S408: No), the wearable device 100 or the mobile device 200 proceeds to substep S410.

[0112] In this embodiment, the predetermined threshold value may be fixed to a preset value, or may be determined or changed by the server 300 with reference to the histories (number of steps, etc.) of multiple users and the insurance company's guarantee and investment performance. In this way, for example, even if the insurance premium is reduced for each user according to the number of steps, the insurance company can still make a profit.

[0113] The wearable device 100 and the mobile device 200 output the number of steps calculated up to that point to the server 300 (substep S409).

[0114] The wearable device 100 and the mobile device 200 finish acquiring the sensing data for acquiring the feature amount, and return to sub-step S402 (sub-step S410).

[0115] In this embodiment, it is preferable to acquire sensing data and calculate the number of steps and features only when the number of steps is detected, thereby reducing the processing load and power consumption on the wearable device 100 and the mobile device 200.

[0116] <2.7 Features> In this embodiment, the reliability of the step count is calculated to confirm that the calculated step count is not a faked step count. To calculate the reliability, feature quantities that characterize each piece of sensing data obtained by various sensors mounted on the wearable device 100 are calculated, and the reliability is calculated using the calculated feature quantities. For example, in this embodiment, the step count and walking distance estimated from each feature quantity are compared with the step count calculated using inertial data or the walking distance obtained by multiplying the step count by a stride length previously registered by the user. If the difference is small, the step count is determined not to be a faked step count. In this embodiment, the step count obtained using inertial data can be considered a valid step count that can be reflected in the calculation of insurance premiums.

[0117] In detail, in this embodiment, the feature amount can be calculated from inertial data, position data, biological data, and environmental data contained in the plurality of sensing data. Details of each data will be explained below with reference to Fig. 17 to Fig. 21. Fig. 17 to Fig. 21 are explanatory diagrams for explaining an example of the feature amount in this embodiment.

[0118] (Inertial data) In this embodiment, the inertial data is data that changes due to the user's three-dimensional inertial movement (translational movement in three orthogonal axial directions and rotational movement), and specifically refers to acceleration data, angular velocity data, etc. In more detail, in this embodiment, as described above, the user's step count data D is calculated based on the change in the inertial data (acceleration data, angular velocity data, etc.). stepFurthermore, in this embodiment, the walking distance can be calculated as a feature by multiplying the calculated number of steps by the stride length registered in advance by the user. Note that in this embodiment, if it is troublesome to measure the stride length, for example, the user's height may be multiplied by a predetermined coefficient (e.g., 0.45) and used as a numerical value in place of the stride length. Furthermore, in this embodiment, the predetermined coefficient may be dynamically changed according to the results of the user's behavior recognition (e.g., walking, running, etc.) (for example, since the stride length changes when walking and when running, the coefficient when running is set larger than the coefficient when walking).

[0119] Furthermore, in this embodiment, user behavior (running, walking, etc.) can be recognized as one of the feature quantities based on inertial data (acceleration data, angular velocity data, etc.), and the recognition result is referred to as behavior recognition data. Here, behavior recognition data refers to data indicating the exercise or movement performed by the user, and specifically refers to data indicating the exercise or movement performed by the user, such as walking or running. Note that in this embodiment, behavior recognition may be performed by referring to a model previously obtained by machine learning the inertial data of many users. Furthermore, in this embodiment, behavior recognition may be performed using a model trained by machine learning on inertial data obtained by the IMU 152 attached to the target user, thereby improving the accuracy of behavior recognition for a specific user.

[0120] Furthermore, in this embodiment, not only inertial data but also schedules (such as wake-up time, arrival time at work, departure time from work, and bedtime) input in advance by the user may be used for behavior recognition. Alternatively, in this embodiment, behavior recognition may be performed using location data (sensing data) (such as home, work, school, and station) obtained by the positioning sensor 154. In this way, the accuracy of behavior recognition can be improved.

[0121] Furthermore, in this embodiment, for example, if both the wearable device 100 and the mobile device 200 are equipped with an IMU 152, the user's behavior may be recognized by comparing the inertial data of the two devices. More specifically, if the time difference between the peaks of acceleration in the gravity direction between the wearable device 100 and the mobile device 200 is within a predetermined time, walking may be recognized. Also, if the acceleration data obtained by the wearable device 100 shows periodic changes in the arm swing direction but the acceleration data obtained by the mobile device 200 does not show periodic changes in the arm swing direction, walking may be recognized. Furthermore, if these two conditions are met, walking may be recognized. In addition, in this embodiment, it may be determined from radio wave strength or the like that the wearable device 100 and the mobile device 200 are capable of short-range communication, that is, that they are within a predetermined distance (for example, within 1 meter), and if this condition and the above two conditions are also met, walking may be recognized.

[0122] (location data) In this embodiment, position data refers to information indicating the user's position in a global coordinate system or a relative coordinate system. Specifically, in this embodiment, the user's position data can be acquired based on sensing data from the positioning sensor 154. For example, as shown in FIG. 17 , the user's position on a map 800 and its trajectory 802 can be acquired as position data based on the sensing data from the positioning sensor 154. Furthermore, data on the distance walked by the user can be acquired as a feature based on the change history of the position data. Note that, when the user is indoors, the use of GNSS signals is prone to errors. Therefore, in this embodiment, it is preferable to combine this with pedestrian dead reckoning (indoor positioning technology) such as a Wi-Fi access point. Furthermore, in this embodiment, it is preferable to acquire position data at short intervals (e.g., every minute) and calculate the distance to improve the accuracy of the distance.

[0123] (biometric data) In this embodiment, biometric data refers to information indicating the user's physical condition, such as the user's pulse rate, heart rate, blood pressure, blood flow rate, respiratory rate, skin temperature, sweat rate, electroencephalogram (EEG), myoelectricity, skin resistance, etc. Specifically, in this embodiment, the user's behavior can be recognized as a feature from the user's biometric data based on sensing data from the biometric information sensor 156. For example, as shown in FIG. 18 , the user's walking can be recognized based on changes in the pulse rate from the biometric information sensor 156. Specifically, since the pulse rate (heart rate) is higher when walking than when stationary, for example, walking may be recognized when the average pulse rate (heart rate) over a five-minute period is significantly higher than the immediately preceding value. Alternatively, in this embodiment, walking or running may be recognized when the pulse rate is equal to or greater than a predetermined value. Furthermore, in this embodiment, walking may be recognized based not only on the pulse rate (heart rate), but also on significant increases in blood pressure, blood flow rate, respiratory rate, skin temperature, or sweat rate, or significant changes in electroencephalogram (EEG), electroencephalogram (EEG), skin resistance, etc.

[0124] (Environmental Data) In this embodiment, environmental data refers to information indicating the state of the environment around the user, obtained as, for example, an image, sound, or radio wave (more specifically, for example, a change in radio wave intensity). Specifically, in this embodiment, the user's behavior, number of steps, walking distance, and the like can be calculated as feature quantities from the environmental data based on sensing data from the microphone 160, the image sensor 158, and the communication unit 180. For example, in this embodiment, as shown in FIG. 19 , sound changes characteristic of the user's walking can be extracted based on changes in the sensing data from the microphone 160, and the number of steps the user takes can be calculated. Furthermore, in this embodiment, for example, if the correlation between the time-dependent change in inertial data due to walking and the time-dependent change in sound is equal to or greater than a predetermined value, walking may be recognized.

[0125] Furthermore, in this embodiment, for example, as shown in FIGS. 20A and 20B, the movement of the user, i.e., walking (running), may be detected as a feature based on changes in the direction of arrival and volume of each sound source included in the environmental sound around the user. Specifically, as shown in FIG. 20A, when the user moves (walks, runs) from point A to point B, the direction of arrival and volume of each sound source 1 to 3 detected by microphone 160 worn by the user should change. Therefore, in this embodiment, the sound detected by microphone 160 is separated into each sound source, and as shown in FIG. 20B, the changes in the direction of arrival and volume of each sound source 1 to 3 are analyzed as a feature. Then, for example, when changes (over time) in the direction of arrival and volume of sounds from three or more sound sources are observed, walking (running) may be recognized.

[0126] Furthermore, in this embodiment, the movement of the user, i.e., walking (running), may be detected as a feature based on a change in the strength of radio waves (e.g., WiFi (registered trademark), Bluetooth (registered trademark), etc.) detected by the communication unit 180. Specifically, when the user moves (walks or runs), the strength of radio waves from each access point detected by the communication unit 180 of the wearable device 100 worn by the user should change. Therefore, in this embodiment, the radio wave strength for each access point identification information (e.g., SSID) is detected, and if the strength of radio waves from the same identification information changes after a certain period of time, walking (running) may be recognized. Furthermore, in this embodiment, the user's movement distance can be calculated by applying the amount of attenuation of the radio wave strength to a predetermined formula, and therefore the distance the user moves per unit of time, i.e., the speed, can also be calculated. Then, by comparing the calculated speed with a predetermined threshold, it can be determined whether the user is walking or running. Furthermore, the number of steps the user takes can be calculated by dividing the distance by the user's stride length (the stride length may differ between walking and running).

[0127] Furthermore, in this embodiment, the user's behavior and walking distance may be detected as feature quantities based on changes in the image acquired by the image sensor 158. Specifically, as shown in FIG. 21 , when the user moves (walks or runs), the image of the user's surroundings acquired by the image sensor 158 worn by the user should change. Therefore, feature points of the subject (e.g., building edges 812a and 812b) are extracted from each of images 810a and 810b acquired consecutively within a short period of time, and the user's behavior (walking, running, etc.) can be recognized and speed and distance can be calculated based on changes in the relative positional relationship (coordinates) and direction of the same feature points in both images 810a and 810b. Furthermore, as described above, the number of steps of the user can also be calculated by dividing the distance by the user's stride length (the stride length may be different for walking and running).

[0128] In this embodiment, the sensing data is not limited to the sensing data acquired by the various sensors described above or the features obtained from the sensing data, but may be sensing data or features obtained from other sensors, and is not particularly limited.

[0129] <2.8 Calculation of reliability> Next, details of calculation of reliability according to this embodiment will be described with reference to Fig. 22 to Fig. 24. Fig. 22 is an explanatory diagram for explaining reliability according to this embodiment, and Fig. 23 and Fig. 24 are tables showing examples of coefficients according to this embodiment.

[0130] It is considered that the reliability of behavior recognition (walking, running) and the reliability of distance and number of steps differ depending on the type of feature. Therefore, in this embodiment, when calculating the reliability, multiple feature values ​​are used, and the weighting (coefficient) when calculating the reliability for each type of feature value is changed.

[0131] In detail, in this embodiment, as shown in FIG. 22, when behavior recognition based on inertial data and pulse rate changes, and the number of steps based on inertial data, radio wave intensity, and changes in feature amounts in an image are obtained, the reliability r ican be calculated, for example, by the following formula (1).

number

[0132] In this embodiment, the coefficient Coeff in Equation (1) HR (Coefficient for step count due to pulse rate change), Coeff WiFi (Coefficient for steps due to changes in radio wave strength) and Coeff video The coefficient for the number of steps due to changes in feature points in the image can be a value determined in advance depending on the nature of the feature. More specifically, for features related to distance and number of steps, the difference between the distance and number of steps obtained from the inertial data is calculated, and the average value (variance value) or normalized value is multiplied by each coefficient (coefficient ratio) and added together to obtain the reliability r i can be obtained.

[0133] In this embodiment, the reliability r i The calculation formula is not limited to the above formula (1), and is not particularly limited as long as it is a formula that can assign weights (coefficients) to the respective feature amounts during calculation.

[0134] In this embodiment, as shown in FIG. 23, the coefficients for each feature may be dynamically changed depending on the acquisition status of the feature. In this embodiment, for example, the coefficients for the feature from the user's position data from the GNSS signal may be changed depending on whether or not PoL technology is used. In this embodiment, for example, the coefficients for the feature from the voice data may be changed depending on the acquisition status of the voice (for example, noise ratio, etc.). Furthermore, in this embodiment, for example, the coefficients for the feature from the environmental data acquired by radio waves may be changed depending on the number of radio wave sources (number of access points) of the acquired radio waves.

[0135] Furthermore, in this embodiment, as shown in FIG. 24 , the coefficients for each feature may be dynamically changed depending on the user's behavior and location. In this embodiment, for example, at or near the user's home, the number of access points is likely to be small, so it is preferable to set the coefficients for the feature amounts due to changes in radio wave strength to small values. On the other hand, indoors, such as in a company, the number of access points is likely to be large, so it is expected that accuracy will be increased accordingly. Also, in this embodiment, for example, when the user is walking outdoors, it is preferable to set the coefficients for the feature amounts due to changes in feature points in the image to large values. Furthermore, in this embodiment, for example, when the user is riding a bus, the change in the number of steps is small, so it is preferable to set the coefficients for the feature amounts for behavior recognition to large values.

[0136] In this embodiment, the values ​​of the coefficients are not limited to those shown in FIGS. 23 and 24, but can be selected as appropriate.

[0137] <<3. Summary>> As described above, according to the embodiment of the present disclosure, it is possible to prevent falsification of the number of steps, etc., and as a result, insurance premiums are calculated based on a fair number of steps, etc., which can create a sense of satisfaction with the insurance premiums. As a result, the health of the insured person is improved, and an increase in the number of insurance subscribers can be expected. Note that, although the above-described embodiment has been described using an example in which application to preventing falsification of the number of steps is described, the present embodiment is not limited thereto and can also be applied to preventing falsification of the distance traveled by the user.

[0138] In the above description, it has been mainly described that the number of steps and reliability are calculated by the mobile device 200, and the insurance premium is calculated by the server 300, but the embodiment of the present disclosure is not limited to this. In the embodiment of the present disclosure, for example, the calculation of the number of steps and reliability, and the calculation of the insurance premium may be performed by either or both of the wearable device 100 and the mobile device 200, and further, all or part of the processing may be performed by multiple information processing devices on the cloud.

[0139] As described above, the embodiments of the present disclosure are not limited to application to information processing for acquiring the number of steps for health promotion insurance. The embodiments of the present disclosure may also be applied to, for example, a service that provides a user with points (incentives) that can be used for shopping instead of cash according to the number of steps, or a service that provides health advice to a user according to the number of steps.

[0140] <<4. Hardware Configuration>> 25 is a block diagram showing an example of a schematic functional configuration of a smartphone 900, and for example, the smartphone 900 can be the above-described mobile device 200. Therefore, with reference to FIG. 25, a configuration example of the smartphone 900 as the mobile device 200 to which an embodiment of the present disclosure is applied will be described.

[0141] 25, the smartphone 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, and a RAM (Random Access Memory) 903. The smartphone 900 also includes a storage device 904, a communication module 905, and a sensor module 907. The smartphone 900 also includes an imaging device 909, a display device 910, a speaker 911, a microphone 912, an input device 913, and a bus 914. The smartphone 900 may also include a processing circuit such as a DSP (Digital Signal Processor) instead of or in addition to the CPU 901.

[0142] The CPU 901 functions as an arithmetic processing device and a control device, and controls all or part of the operations of the smartphone 900 in accordance with various programs recorded in the ROM 902, the RAM 903, the storage device 904, or the like. The ROM 902 stores programs and calculation parameters used by the CPU 901. The RAM 903 temporarily stores programs used in the execution of the CPU 901 and parameters that change as appropriate during the execution. The CPU 901, the ROM 902, and the RAM 903 are interconnected by a bus 914. The storage device 904 is a data storage device configured as an example of a storage unit of the smartphone 900. The storage device 904 is configured, for example, by a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or the like. The storage device 904 stores the programs and various data executed by the CPU 901, as well as various data acquired from the outside.

[0143] The communication module 905 is, for example, a communication interface configured with a communication device for connecting to a communication network 906. The communication module 905 may be, for example, a communication card for a wired or wireless local area network (LAN), Bluetooth (registered trademark), or wireless USB (WUSB). The communication module 905 may also be a router for optical communication, a router for asymmetric digital subscriber line (ADSL), or a modem for various types of communication. The communication module 905 transmits and receives signals, for example, between the Internet and other communication devices using a predetermined protocol such as TCP (Transmission Control Protocol) / IP (Internet Protocol). The communication network 906 connected to the communication module 905 is a network connected by wire or wirelessly, for example, the Internet, a home LAN, infrared communication, or satellite communication.

[0144] The sensor module 907 includes various sensors such as a motion sensor (e.g., an acceleration sensor, a gyro sensor, a geomagnetic sensor, etc.), a biometric sensor (e.g., a pulse sensor, a blood pressure sensor, a fingerprint sensor, etc.), or a position sensor (e.g., a GNSS (Global Navigation Satellite System) receiver, etc.).

[0145] The imaging device 909 is provided on the surface of the smartphone 900 and can capture an image of an object located on the front or back side of the smartphone 900. Specifically, the imaging device 909 can include an imaging element (not shown) such as a CMOS (Complementary MOS) image sensor, and a signal processing circuit (not shown) that performs imaging signal processing on a signal photoelectrically converted by the imaging element. The imaging device 909 can further include an optical system mechanism (not shown) including an imaging lens, a zoom lens, a focus lens, and the like, and a drive system mechanism (not shown) that controls the operation of the optical system mechanism. The imaging element collects incident light from an object as an optical image, and the signal processing circuit photoelectrically converts the formed optical image on a pixel-by-pixel basis, reads out the signal of each pixel as an imaging signal, and performs image processing to obtain a captured image.

[0146] The display device 910 is provided on the surface of the smartphone 900, and can be, for example, a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The display device 910 can display an operation screen, captured images acquired by the above-described imaging device 909, and the like.

[0147] The speaker 911 can output, for example, a call voice, a voice accompanying the video content displayed by the display device 910 described above, and the like to the user.

[0148] The microphone 912 can collect, for example, the user's call voice, voice including a command to activate a function of the smartphone 900, and voice from the surrounding environment of the smartphone 900.

[0149] The input device 913 is a device operated by a user, such as a button, a keyboard, a touch panel, or a mouse. The input device 913 includes an input control circuit that generates an input signal based on information input by the user and outputs the signal to the CPU 901. By operating the input device 913, the user can input various data to the smartphone 900 and instruct processing operations.

[0150] An example of the hardware configuration of the smartphone 900 has been described above. Note that the hardware configuration of the smartphone 900 is not limited to the configuration shown in FIG. 25. In detail, each of the above components may be configured using general-purpose components, or may be configured using hardware specialized for the function of each component. Such a configuration may be changed as appropriate depending on the technical level at the time of implementation.

[0151] Furthermore, the smartphone 900 according to the present embodiment may be applied to a system consisting of a plurality of devices that is premised on connection to a network (or communication between devices), such as cloud computing, etc. In other words, the mobile device 200 according to the present embodiment described above can also be realized as an information processing system 10 that performs processing according to the information processing method according to the present embodiment using a plurality of devices, for example.

[0152] <<5. Supplementary Information>> Although the preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person skilled in the art of the present disclosure can conceive of various modified or altered examples within the scope of the technical idea described in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

[0153] The above-described embodiment of the present disclosure may include, for example, a program for causing a computer to function as an information processing device according to the present embodiment, and a non-transitory tangible medium on which the program is recorded. The program may also be distributed via a communication line (including wireless communication) such as the Internet.

[0154] Furthermore, the steps in the processes of the above-described embodiments do not necessarily have to be processed in the order described. For example, the steps may be processed in a different order as appropriate. Furthermore, instead of being processed in chronological order, the steps may be partially processed in parallel or individually. Furthermore, the method of processing each step does not necessarily have to be processed in the manner described; for example, the steps may be processed in a different manner by another functional unit.

[0155] Furthermore, the effects described herein are merely descriptive or exemplary and are not limiting. In other words, the technology according to the present disclosure may achieve other effects that will be apparent to those skilled in the art from the description of this specification, in addition to or in place of the above-described effects.

[0156] The present technology can also be configured as follows. (1) a sensing data acquisition unit that acquires a plurality of pieces of sensing data from a device worn by or carried by a user; a calculation unit that calculates the number of steps or the moving distance of the user based on inertial data included in the plurality of sensing data; a reliability calculation unit that calculates reliability based on feature amounts of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; a determination unit that determines whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; an output unit that outputs the received data on the number of steps or the movement distance; An information processing device comprising: (2) The information processing device according to (1), wherein the reliability calculation unit calculates the reliability based on a feature amount of behavior recognition data relating to the user. (3) further comprising a feature amount calculation unit that calculates feature amounts from the inertial data, the position data, the biological data, and the environmental data included in the plurality of sensing data; The information processing device according to (2) above. (4) The information processing device according to (3), wherein the feature amount calculation unit calculates the feature amount by statistically processing at least one of the plurality of sensing data. (5) The information processing device according to (3), wherein the feature amount calculation unit calculates the feature amount by referring to a model obtained in advance by machine learning. (6) The feature amount calculation unit calculating first distance data from at least one of the plurality of sensing data; calculating, as the feature amount, a difference between the first distance data and second distance data based on the number of steps; The information processing device according to (3) above. (7) The feature amount calculation unit The information processing device according to (3) above, wherein the user's behavior is recognized based on at least one of the plurality of pieces of sensing data, and the feature amount is calculated from a recognition result. (8) the sensing data acquisition unit acquires the plurality of pieces of sensing data from a wearable device worn by the user and a mobile device carried by the user; the feature calculation unit recognizes the user's behavior by comparing the same type of sensing data from each device; The information processing device according to (7) above. (9) The information processing device according to any one of (2) to (8) above, wherein the reliability calculation unit calculates the reliability by weighting each of the feature amounts by a predetermined coefficient assigned to each of the feature amounts. (10) The information processing device according to (9), wherein the reliability calculation unit dynamically changes the predetermined coefficient according to at least one of the user's position, the behavior recognition data, and a position change amount of the user. (11) The information processing device according to any one of (1) to (10) above, wherein the determination unit determines whether or not to accept the calculated number of steps or the traveled distance by comparing the reliability with a predetermined threshold. (12) The information processing device according to (11), wherein the determination unit dynamically changes the predetermined threshold value. (13) The information processing device according to any one of (1) to (12) above, wherein the inertial data included in the plurality of sensing data is acquired from an acceleration sensor, an angular velocity sensor, or a geomagnetic sensor attached to or carried by the user. (14) The information processing device described in any one of (1) to (13) above, wherein the environmental data is generated from sensing data acquired from an audio sensor, an image sensor, or a radio wave sensor attached to or carried by the user. (15) the output unit outputs the received data on the number of steps or the travel distance to a server that calculates an incentive for the user; a presentation unit that presents the incentive calculated by the server based on the data of the number of steps or the distance traveled to the user, The information processing device according to any one of (1) to (14) above. (16) The information processing device according to (15) above, wherein the incentive is a discount on insurance premiums for the user. (17) The information processing device according to any one of (1) to (16) above, further comprising an authentication unit that authenticates the user. (18) a server that calculates incentives for users; an information processing device attached to or carried by the user; An information processing system comprising: The information processing device includes: a sensing data acquisition unit that acquires a plurality of pieces of sensing data from a device worn by or carried by the user; a calculation unit that calculates the number of steps or the moving distance of the user based on inertial data included in the plurality of sensing data; a reliability calculation unit that calculates reliability based on feature amounts of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; a determination unit that determines whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; an output unit that outputs the received data on the number of steps or the movement distance to the server; a presentation unit that presents the incentive calculated by the server based on the data of the number of steps or the distance traveled to the user; having Information processing system. (19) The information processing device acquiring a plurality of sensing data from a device worn by or carried by a user; Calculating the number of steps or the distance traveled by the user based on inertial data included in the plurality of pieces of sensing data; calculating a reliability based on each feature amount of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; determining whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; outputting the received data on the number of steps or the travel distance; An information processing method, including: (20) On the computer, A function of acquiring a plurality of pieces of sensing data from a device worn by or carried by a user; a function of calculating the number of steps or the distance traveled by the user based on inertial data included in the plurality of pieces of sensing data; a function of calculating reliability based on each feature amount of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; a function of determining whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; a function of outputting the received data on the number of steps or distance traveled; A program that executes. [Explanation of symbols]

[0157] 10 Information Processing Systems 100 Wearable Devices 110, 210, 310 Input section 120, 242 Authentication information acquisition section 130, 230, 330 display section 140 Control Unit 150 Sensor unit 152 IMU 154 Positioning Sensor 156 Biometric Sensor 158 Image Sensor 160 Mike 170, 270, 370 storage section 180, 280, 380 Communications Department 200 mobile devices 240, 340 Processing section 244 Authentication Department 246 Sensing data acquisition unit 248 Step Count Calculation Unit 250 Feature Calculation Unit 252 Reliability calculation unit 254 Judgment section 256, 356 output section 260 Insurance Premium Information Acquisition Department 300 servers 342 Step count information acquisition unit 344 Insurance Premium Calculation Department 346 Threshold calculation unit 400 Network 800 Map 802 Trajectory 810a, 810b images 812a, 812b Edge 900 smartphones 901 CPU 902 ROM 903 RAM 904 Storage devices 905 Communication Module 906 Communication Network 907 Sensor Module 909 Imaging device 910 Display device 911 Speaker 912 microphone 913 Input Device 914 Bus

Claims

1. a sensing data acquisition unit that acquires a plurality of pieces of sensing data from a device worn by or carried by a user; a calculation unit that calculates the number of steps or the moving distance of the user based on inertial data included in the plurality of sensing data; a reliability calculation unit that calculates reliability based on feature amounts of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; a determination unit that determines whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; an output unit that outputs the received data on the number of steps or the movement distance; An information processing device comprising:

2. The information processing device according to claim 1 , wherein the reliability calculation unit calculates the reliability based on a feature amount of behavior recognition data relating to the user.

3. further comprising a feature amount calculation unit that calculates feature amounts from the inertial data, the position data, the biological data, and the environmental data included in the plurality of sensing data; The information processing device according to claim 2 .

4. The information processing apparatus according to claim 3 , wherein the feature amount calculation unit calculates the feature amount by performing statistical processing on at least one of the plurality of pieces of sensing data.

5. The information processing device according to claim 3 , wherein the feature amount calculation unit calculates the feature amount by referring to a model previously obtained by machine learning.

6. The feature amount calculation unit calculating first distance data from at least one of the plurality of sensing data; calculating, as the feature amount, a difference between the first distance data and second distance data based on the number of steps; The information processing device according to claim 3 .

7. The feature amount calculation unit The information processing apparatus according to claim 3 , further comprising: recognizing the user's behavior based on at least one of the plurality of pieces of sensing data; and calculating the feature amount from a recognition result.

8. the sensing data acquisition unit acquires the plurality of pieces of sensing data from a wearable device worn by the user and a mobile device carried by the user; the feature calculation unit recognizes the user's behavior by comparing the same type of sensing data from each device; The information processing device according to claim 7 .

9. The information processing apparatus according to claim 2 , wherein the reliability calculation unit calculates the reliability by weighting each of the feature amounts by a predetermined coefficient assigned to each of the feature amounts.

10. The information processing device according to claim 9 , wherein the reliability calculation unit dynamically changes the predetermined coefficient in accordance with at least one of the user's position, the behavior recognition data, and a position change amount of the user.

11. The information processing device according to claim 1 , wherein the determination unit determines whether or not to accept the calculated number of steps or the traveled distance by comparing the reliability with a predetermined threshold value.

12. The information processing device according to claim 11 , wherein the determination unit dynamically changes the predetermined threshold value.

13. The information processing apparatus according to claim 1 , wherein the inertial data included in the plurality of sensing data is acquired from an acceleration sensor, an angular velocity sensor, or a geomagnetic sensor that is worn by or carried by the user.

14. The information processing apparatus according to claim 1 , wherein the environmental data is generated from sensing data acquired from a sound sensor, an image sensor, or a radio wave sensor attached to or carried by the user.

15. the output unit outputs the received data on the number of steps or the travel distance to a server that calculates an incentive for the user; a presentation unit that presents the incentive calculated by the server based on the data of the number of steps or the distance traveled to the user, The information processing device according to claim 1 .

16. The information processing device according to claim 15 , wherein the incentive is a discount on insurance premiums for the user.

17. The information processing apparatus according to claim 1 , further comprising an authentication unit that authenticates the user.

18. a server that calculates incentives for users; an information processing device attached to or carried by the user; An information processing system comprising: The information processing device includes: a sensing data acquisition unit that acquires a plurality of pieces of sensing data from a device worn by or carried by the user; a calculation unit that calculates the number of steps or the moving distance of the user based on inertial data included in the plurality of sensing data; a reliability calculation unit that calculates reliability based on feature amounts of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; a determination unit that determines whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; an output unit that outputs the received data on the number of steps or the movement distance to the server; a presentation unit that presents the incentive calculated by the server based on the data of the number of steps or the distance traveled to the user; having Information processing system.

19. The information processing device acquiring a plurality of pieces of sensing data from a device worn by or carried by a user; Calculating the number of steps or the distance traveled by the user based on inertial data included in the plurality of pieces of sensing data; calculating a reliability based on each feature amount of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; determining whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; outputting the received data on the number of steps or the travel distance; An information processing method, including:

20. On the computer, A function of acquiring a plurality of pieces of sensing data from a device worn by or carried by a user; a function of calculating the number of steps or the distance traveled by the user based on inertial data included in the plurality of pieces of sensing data; a function of calculating reliability based on each feature amount of position data, biometric data, and environmental data related to the user obtained from the plurality of sensing data; a function of determining whether or not to accept the calculated number of steps or the travel distance based on the calculated reliability; a function of outputting the received data on the number of steps or distance traveled; A program that executes.

Images