JP2020081312A - Living body detection device, living body detection system, living body detection method, and living body data acquisition device - Google Patents

Abstract

To grasp a condition of a living body with accuracy.SOLUTION: A living body detection device includes: a transmission part capable of transmitting broadband or ultra broadband radio waves to a prescribed detection area; a reception part capable of receiving reflection waves of the radio waves transmitted by the transmission part; a signal intensity calculation part calculating signal intensity in each of a plurality of areas composing the detection area on the basis of the reflection waves received by the reception part; a position identification part identifying a present area where a living body is present out of a plurality of areas on the basis of temporal variation of the signal intensity in each of the plurality of areas; a tracking part which tracks movements of the living body on the basis of the temporal variation of the signal strength in each of the present areas and at least one adjacent area adjacent to the present area, and generates operation data; and a data generation part generating living body data on the basis of the time variation of the signal intensity in the present area.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a biological detection device, a biological detection system, a biological detection method, and a biological data acquisition device.

Temporary breathing stops and blood pressure rises may occur due to the feeling of discomfort during toilet defecation. At this time, a shock symptom called "a bowel shock" (for example, stroke, syncope, etc.) may occur due to a sudden change in blood pressure. The shock symptom is particularly likely to occur in an elderly person whose vascular system and respiratory system function are deteriorated due to aging.

In many cases, one person goes in and out of the place where the shock symptom is likely to occur, so if a person with the shock symptom falls to the floor, the discovery will be delayed. However, for privacy reasons, it is not preferable to install a camera in a toilet or the like to capture an image of a person. Therefore, various techniques have been proposed for detecting the state of a person using a radio wave sensor instead of a camera and notifying the family or the like when an abnormality occurs.

For example, Patent Documents 1 and 2 are radio wave biosensors that obtain biometric data such as heart rate and respiration by irradiating electromagnetic waves on the human body surface using a Doppler sensor and processing reflected waves from the human body surface. Disclosure.

JP, 2017-225559, A JP, 2017-225560, A

The present disclosure describes a living body detection device, a living body detection system, a living body detection method, and a living body data acquisition device capable of accurately grasping the state of a living body.

An animate body detection device according to one aspect of the present disclosure, a transmitter configured to be capable of transmitting a broadband or ultra-wideband radio wave toward a predetermined detection region, and a reflected wave of the radio wave emitted from the transmitter. A receiving unit configured to be receivable, based on a reflected wave received by the receiving unit, a signal strength calculating unit configured to calculate the signal strength in each of a plurality of areas forming the detection region, A position specifying unit configured to specify an existing area in which a living body exists among a plurality of areas based on a temporal change in signal intensity in each area, and at least one adjacent area adjacent to the existing area and the existing area And a tracking unit configured to track the movement of the living body based on the time variation of the signal strength in each of the and, and generate the living body data based on the time variation of the signal strength in the existing area. And a data generation unit configured as described above.

An animate body detection system according to another aspect of the present disclosure communicates between the above-mentioned device installed at a predetermined location in a building and the device to notify the information on the state of the living body transmitted from the device. And a notification device configured as described above.

A living body detection method according to another aspect of the present disclosure includes transmitting a wideband or ultrawideband radio wave toward a predetermined detection area, and a plurality of areas forming the detection area based on a reflected wave of the radio wave. Calculating the signal strength in each of the areas, and identifying the existing area in which the living body exists among the plurality of areas based on the time variation of the signal strength in each of the plurality of areas, and Generating motion data by tracking the movement of the living body based on the time variation of the signal strength in each of the at least one adjacent area where it matches, and generating biometric data based on the time variation of the signal strength in the existing area. Including that.

A biological data acquisition apparatus according to another aspect of the present disclosure is a transmitter configured to be capable of transmitting a wideband or ultrawideband radio wave toward a predetermined detection region, and a reflected wave of the radio wave emitted from the transmitter. A receiving unit configured to be capable of receiving, a signal intensity calculating unit configured to calculate a signal intensity in each of a plurality of areas forming a detection region based on a reflected wave received by the receiving unit, Based on the temporal variation of the signal strength in each of the areas, the position specifying unit configured to identify the existing area of the plurality of areas where the living body exists, and the living body based on the temporal change of the signal strength in the existing area. A data generator configured to generate data.

According to the living body detection device, the living body detection system, the living body detection method, and the biological data acquisition device according to the present disclosure, it is possible to accurately grasp the state of the living body.

FIG. 1 is a schematic view of the vicinity of the living body detection system and the toilet room as viewed from the side. FIG. 2 is a block diagram schematically showing the living body detection device. FIG. 3 is a block diagram mainly showing a control unit. FIG. 4 is a diagram illustrating an example of a temporal change in signal intensity based on a reflected wave from the body surface of the measurement target person. FIG. 5 is a diagram showing an example of a classification model. FIG. 6 is a diagram showing an example of a temporal change in signal intensity with respect to the distance from the living body detection device. FIG. 7 is a block diagram schematically showing the notification device. FIG. 8 is a flowchart for explaining the procedure of living body detection. FIG. 9A is a graph showing the experimental result according to the scenario 1, and FIG. 9B is a graph showing the experimental result according to the scenario 2.

Hereinafter, an example of an embodiment according to the present disclosure will be described in more detail with reference to the drawings. In the following description, the same elements or elements having the same function will be denoted by the same reference symbols, without redundant description.

[Biological detection system configuration]
The configuration of the living body detection system 1 will be described with reference to FIG. The living body detection system 1 is configured, for example, to detect the measurement target person H (living body) in the toilet room 30 and notify the detection result to a place away from the toilet room 30. The living body detection system 1 includes a living body detection device 10 and a notification device 20.

Here, the configuration of the toilet room 30 will be described. The toilet room 30 is a private room separated by a door D. In the toilet room 30, a toilet bowl 31 is installed so as to face the door D. The toilet bowl 31 includes a toilet bowl body 32, a toilet seat 33 and a toilet lid 34 provided on the seat surface of the toilet bowl body 32, and a tank 35 provided at the rear portion of the toilet bowl body 32.

The living body detection device 10 has a function of detecting the movement (relatively large movement), minute movement, position, respiration, pulsation, etc. of the measurement target person H in the toilet room 30. The living body detection device 10 may be provided in the front portion of the tank 35, for example. In this case, the living body detection device 10 faces the door D and the back surface of the measurement target person H seated on the toilet seat 33.

As shown in FIG. 2, the living body detection device 10 includes a transmitter 11 (a transmitter), a receiver 12 (a receiver), a communication device 13, a controller 14 (a controller), and a bus 15. ..

The transmitter 11 is configured to emit a wideband or ultrawideband (UWB: Ultra Wide Band) radio wave toward the inside of the toilet room 30 based on an instruction from the control unit 14. The directivity angle of the transmitter 11 on the horizontal plane of the antenna may be, for example, about 40° to 80° or about 60° to 80°. The directivity angle of the transmitter 11 on the vertical plane of the antenna may be, for example, about 30° to 40°, or may be 30° or less. The transmitter 11 has a detection region R that roughly corresponds to the range of the directivity angle.

In the present specification, the term "wide band" refers to a case where the frequency bandwidth is 100 MHz or more and 500 MHz or less. Therefore, the frequency bandwidth of the broadband radio wave transmitted by the transmitter 11 may be, for example, 100 MHz or more, or 300 MHz or more. “Ultra-wide band” means a case where the frequency bandwidth exceeds 500 MHz. Therefore, the frequency bandwidth of the ultra wideband radio wave transmitted by the transmitter 11 may be, for example, 3 GHz or more, but may be 5 GHz or less in view of the Radio Law and cost performance. Therefore, the transmitter 11 may be an ultra wideband wireless sensor having a frequency bandwidth of more than 500 MHz. When a wide band or ultra wide band radio wave is used, the transmission output of the radio wave can be reduced, and the influence of the radio wave on the measurement target person H can be reduced.

The receiver 12 is configured to be able to receive the reflected wave of the radio wave transmitted from the transmitter 11. Since the transmitter 11 uses a wideband or ultrawideband radio wave, the receiver 12 can separately receive the reflected wave of the radio wave on the time axis corresponding to the reflection path length. That is, as illustrated in FIG. 1, the receiver 12 can extract a signal for each area (also referred to as a range bin, which is determined by a frequency bandwidth) divided into a plurality in the distance direction of the detection region R. Is. The width of each range bin may be, for example, 10 cm or less. The number of range bins in the detection region R can be appropriately changed according to the width of the range bin and the size of the detection region R.

The communication device 13 is configured to be communicable with the communication device 23 of the notification device 20. The communication system of the communication device 13 with the communication device 23 is not particularly limited, and examples thereof include LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access). ), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB, Bluetooth (registered trademark) or another communication method may be used.

The control unit 14 is configured to send and receive signals to and from the transmitter 11, the receiver 12, and the communication device 13 via the bus 15 and control these operations. The control unit 14 includes, for example, a processor 16, a memory 17 (storage unit), and a storage 18 (storage unit).

When a predetermined software (program) is read into the hardware such as the memory 17 and the storage 18, the processor 16 performs a predetermined calculation to transmit a radio wave from the transmitter 11 and to reflect a reflected wave received by the receiver 12. Analysis, communication by the communication device 13, and reading or writing of data in the memory 17 and the storage 18 are executed. As a result, each function of the living body detection device 10 is realized.

Each function of the living body detection device 10 will be described with reference to FIG. The control unit 14 includes, as functional blocks, a storage unit 14a, a transmission/reception processing unit 14b, a signal strength calculation unit 14c, a position identification unit 14d, a tracking unit 14e, a data generation unit 14f, a state determination unit 14g, and a classification. It includes a model generation unit 14h, a class determination unit 14i, and an entry/exit determination unit 14j.

The storage unit 14a has a function of storing various data. Examples of data stored in the storage unit 14a include a read program, operation setting data of the transmitter 11, data of a reflected wave received by the receiver 12, biometric data generated by the data generation unit 14f, and a state determination unit 14g. The generated motion data, reference data or analysis data in which biometric data and motion data are associated with each other, various classification models generated by the classification model generation unit 14h, data regarding determination results by the state determination unit 14g and the class determination unit 14i, and the like. Can be mentioned.

The transmission/reception processing unit 14b has a function of transmitting and receiving signals among the transmitter 11, the receiver 12, and the communication device 13. Specifically, the transmission/reception processing unit 14b transmits an instruction signal to the transmitter 11 to cause the transmitter 11 to emit a radio wave. The transmission/reception processing unit 14b receives the reflected wave data from the receiver 12 and stores the data in the storage unit 14a. The transmission/reception processing unit 14b transmits an instruction signal to the communication device 13 and causes the notification device 20 to transmit the determination results of the state determination unit 14g and the class determination unit 14i.

The signal strength calculation unit 14c has a function of calculating the signal strength in each range bin based on the reflected wave data received by the transmission/reception processing unit 14b. The signal strength calculation unit 14c may calculate the signal strength smoothed on the time axis in each range bin. As the smoothing processing, for example, various processing methods such as simple moving average and weighted moving average may be adopted. The signal strength calculated by the signal strength calculation unit 14c may be stored in the storage unit 14a.

The position specifying unit 14d has a function of specifying in which of the range bins the measurement target person H exists based on the time variation of the signal strength of each range bin calculated by the signal strength calculating unit 14c. The range bin specified by the position specifying unit 14d is an area where the measurement target person H exists, and is therefore referred to as an “existence range bin” (presence area) in the present specification.

The tracking unit 14e measures the measurement target person H based on the time variation of the signal intensity in each of the three range bins of the existing range bin specified by the position specifying unit 14d and a pair of adjacent range bins (adjacent areas) located on both sides of the existing range bin. It has the function of tracking the position of. The tracking unit 14e has a function of updating the other range bin as an existing range bin and updating a pair of range bins adjacent to the other range bin as adjacent range bins when the measurement target person H moves to another range bin.

The data generation unit 14f has a function of generating biometric data based on the time variation of the signal intensity in the existing range bin specified by the position specification unit 14d. For example, when the measurement subject H breathes, the chest expands and contracts accordingly. Therefore, the data generation unit 14f may generate the respiration of the measurement target person H as biometric data based on the time variation of the signal intensity in the existing range bin corresponding to the body surface of the measurement target person H (see FIG. 4). .. For example, the heart expands and contracts according to the heartbeat of the measurement subject H. Therefore, the data generation unit 14f may generate the pulsation of the measurement target person H as biometric data based on the time variation of the signal intensity in the existing range bin corresponding to the heart of the measurement target person H. The data generated by the data generation unit 14f may be stored in the storage unit 14a. The data generation unit 14f may temporarily stop the biometric data generation process when the tracking process by the tracking unit 14e is being performed (when the measurement target person H is operating).

The state determination unit 14g determines at which position in the toilet room 30 the measurement target person H is based on the presence range bin specified by the position specifying unit 14d or the presence range bin updated by the tracking unit 14e (for example, for the toilet seat 33). The seating position) is determined. During the tracking process by the tracking unit 14e, the state determination unit 14g determines whether or not the measurement target person H is moving and/or slightly moving based on the time variation of the signal intensity in each of the existing range bin and the adjacent range bin. Have a function. The data (hereinafter, collectively referred to as “motion data”) regarding the motion (change in posture), fine body motion, position, and the like of the measurement target person H acquired by the state determination unit 14g may be stored in the storage unit 14a. ..

The state determination unit 14g has a function of determining that the measurement target person H has an abnormality when the temporal variation of the signal intensity in the existing range bin has exceeded a predetermined threshold value. The state determination unit 14g has a function of determining that the measurement target person H has an abnormality when the measurement target person H is in a stationary state for a predetermined time as a result of the tracking processing by the tracking unit 14e.

The state determination unit 14g has a function of determining whether or not an abnormality has occurred in the measurement target person H, based on the biometric data generated by the data generation unit 14f. For example, the state determination unit 14g determines that the measurement target person H has an abnormality when the breathing, the pulsation, or the like is weak or stopped or when it shows a high value.

The classification model generation unit 14h uses a plurality of pieces of reference data by machine learning using a plurality of pieces of reference data in which the biometric data generated by the data generation unit 14f and the motion data acquired by the state determination unit 14g are associated with each other. It has a function of classifying into any one of the individual classes of (1) to generate a classification model. For example, when a data set including a predetermined number of reference data is input to the classification model generation unit 14h, the classification model generation unit 14h may perform supervised learning or unsupervised learning, Reinforcement learning may be conducted. Examples of the supervised learning algorithm include support vector machine, logistic regression, random forest, decision tree, k-nearest neighbor method, perceptron, and neural network. Examples of unsupervised learning algorithms include k-means, principal component analysis, and self-organizing map. Examples of the reinforcement learning algorithm include Q learning, Monte Carlo method, SARSA and the like. The classification model generated by the classification model generation unit 14h may be stored in the storage unit 14a.

For example, when the data set DS shown in FIG. 5 is input to the classification model generation unit 14h, the classification model generation unit 14h determines that the reference data marked with ◯, the reference data marked with □ and the reference data marked with Δ in the data set DS. A boundary line L that divides the reference data may be generated. In the example shown in FIG. 5, the data set DS is a set of a plurality of reference data in which motion data and respiratory data are associated with each other. In the example shown in FIG. 5, the plurality of reference data constituting the data set DS is divided into a class C1 (a set of reference data marked with a circle), a class C2 (a set of reference data marked with a square), and a class by a boundary line L. It is classified into any one of C3 (set of reference data marked with Δ). Each of the classes C1 to C3 may be, for example, a classification indicating that the measurement target person H is “Mr. X”, “Mr. Y”, and “Mr. Z”. The boundary line L may be a straight line or a curved line. Hereinafter, the classification model configured by the classes C1 to C3 divided by the boundary line L may be referred to as a “classification model M”.

As described above, the biometric data may include data related to the respiration, the pulsation, and the like of the measurement target person H, and the motion data may include data related to the motion, the small body movement, the position, and the like of the measurement target person H. Therefore, the reference data may be data in which at least one biometric data and at least one motion data are associated with each other.

Returning to FIG. 3, the class determination unit 14i uses the classification model generation unit 14h to generate analysis data in which the biometric data generated by the data generation unit 14f and the motion data generated by the state determination unit 14g are associated with each other. It has a function of classifying into any one of the plurality of classes C1 to C3 in the generated classification model M. That is, the class determination unit 14i applies the analysis data to the classification model M and determines which class of the plurality of classes C1 to C3 the analysis data belongs to.

The entry/exit determination unit 14j has a function of determining whether the measurement target person H enters or exits the toilet room 30. A method of determining whether a person is entering or leaving the room by the entry/exit judging unit 14j will be described with reference to FIG. In FIG. 6, the brighter the signal intensity (reception power) is, the darker the signal intensity (reception power) is.

First, the entry/exit determination unit 14j acquires the signal strength according to the distance from the receiver 12 based on the reflected wave data received by the transmission/reception processing unit 14b. Specifically, when the measurement subject H does not exist in the toilet room 30, the signal intensity of the reflected wave from the door D is predominant (see the "unmanned" portion in FIG. 6). On the other hand, when the measurement target person H is present in the toilet room 30, the measurement target person H is located closer to the living body detection device 10 than the door D. That is, the distance d1 from the living body detection device 10 to the measurement target person H is shorter than the distance d2 from the living body detection device 10 to the door D. At this time, a part of the radio wave from the transmitter 11 is reflected by the measurement target person H and does not reach the wall. Therefore, the signal intensity of the reflected wave from the door D becomes smaller, and the signal intensity of the reflected wave from the front side (receiver 12 side) than the door D becomes larger (“entry”, “seated”, “seating” in FIG. 6). "Leaving room"). Therefore, the entry/exit determination unit 14j acquires the signal intensity over time, and when the reflected wave from the front side of the door D becomes larger than a predetermined threshold value, the measurement target person H enters the toilet room 30. You may decide that you did. The room entry/exit determination unit 14j acquires the signal intensity of the reflected wave from the door D over time, and when the reflected wave from the front side of the door D becomes less than or equal to a predetermined threshold value, the measurement subject person H It may be determined that the user has left the room 30.

The entry/exit determination unit 14j may also consider the signal intensity of the reflected wave from the door D when determining the entry/exit of the measurement subject H to/from the toilet room 30. Specifically, the entry/exit determination unit 14j acquires the signal strength over time, the reflected wave from the front side of the door D becomes larger than a predetermined threshold, and the signal strength of the reflected wave from the door D is predetermined. It may be determined that the measurement target person H has entered the toilet room 30 when the threshold value is equal to or less than the threshold value. The entry/exit determination unit 14j acquires the signal intensity over time, and when the reflected wave from the front side of the door D becomes less than or equal to a predetermined threshold value and the signal intensity of the reflected wave from the door D becomes greater than the predetermined threshold value. Alternatively, it may be determined that the measurement target person H has left the toilet room 30. By considering the time variation of the signal intensity of the reflected wave from the door D, it becomes possible to more accurately determine the entering/leaving of the measurement target person H.

Returning to FIG. 1, the notification device 20 is mounted, for example, in a room separate from the toilet room 30 by a wall W. As shown in FIG. 7, the notification device 20 includes a monitor 21 (notification unit), a speaker 22 (notification unit), a communication device 23, a control unit 24 (controller), and a bus 25.

Each of the monitor 21 and the speaker 22 notifies the person (for example, a family member) in the other room of the determination result by the state determination unit 14g received via the communication device 23 by video and/or sound. It is configured. The communication device 23 has the same configuration as the communication device 13 of the living body detection device 10 and functions similarly to the communication device 13.

The control unit 24 includes a processor 26, a memory 27, and a storage 28, and functions similarly to the control unit 14 of the living body detection device 10. The bus 25 has the same configuration as the bus 15 of the living body detection device 10 and functions similarly to the bus 15.

[Biometric detection method]
Subsequently, a living body detection method (a monitoring method of the toilet room 30) will be described with reference to FIG. The storage unit 14a of the living body detection device 10 may store at least one learned classification model obtained by machine learning using a plurality of reference data.

First, the transmission/reception processing unit 14b instructs the transmitter 11 to cause the transmitter 11 to transmit a radio wave into the toilet room 30. Next, the transmission/reception processing unit 14b receives the reflected wave data of the radio wave via the receiver 12. The signal strength calculator 14c calculates the signal strength of the reflected wave received by the receiver 12 for each range bin over time, and smoothes the signal strength on the time axis. As the smoothing processing, for example, various processing methods such as simple moving average and weighted moving average may be adopted.

Next, the entry/exit determination unit 14j determines whether or not the measurement target person H has entered the toilet room 30 based on the fluctuation of the signal intensity of the reflected wave from the predetermined area (step S1 in FIG. 8). .. Specifically, the entry/exit determination unit 14j determines whether or not the signal intensity of the reflected wave from the front side of the door D is larger than a predetermined threshold value. For example, FIG. 6 shows that the signal intensity of the range bin existing at about 0 m to 1.5 m from the living body detection device 10 is almost 0 from about 0 second to 40 seconds. In this case, the entry/exit determination unit 14j determines that the measurement target person H has not entered during this period. When the entry/exit determination unit 14j determines that the measurement target person H has not entered the toilet room 30 (NO in step S1 of FIG. 8 ), the process of step S1 is repeated.

On the other hand, for example, FIG. 6 shows a state in which the signal intensity of the range bin existing at about 0 m to 1.5 m from the living body detection device 10 is abruptly changed in about 40 seconds to about 65 seconds. .. In this case, the entry/exit determination unit 14j determines that the measurement target person H has entered the room at this point (between about 40 seconds and about 65 seconds). When the entry/exit determination unit 14j determines that the measurement target person H has entered the toilet room 30 (YES in step S1 in FIG. 8 ), the signal strength calculation unit 14c determines the reflected wave received by the signal strength calculation unit 14c. The signal strength of each range bin is calculated at a predetermined sampling cycle based on the above data (step S2 in FIG. 8). The sampling cycle may be, for example, about 0.01 seconds to 0.1 seconds.

Next, the position identifying unit 14d identifies the existing range bin in which the measurement target person H exists based on the smoothed signal intensity in each range bin calculated by the signal intensity calculation unit 14c (step S3 in FIG. 8). Specifically, the position identifying unit 14d calculates, for each range bin, a temporal change in the signal intensity after smoothing in each range bin (for example, the difference between the current signal intensity and the signal intensity before a certain time). Next, the position identifying unit 14d compares the calculated time variation for each range bin with a threshold value, and identifies the range bin indicating the time variation exceeding the threshold value. It should be noted that a person may appropriately set the threshold value size based on an experiment result or the like, or may set an optimum threshold value size by using the result of machine learning.

By the way, the movement of the human body is not constant, and the temporal fluctuation of the signal strength when the human body moves tends to be extremely large. Therefore, when the time variation of the signal strength exceeds the threshold value, the presence of the measurement target person H is detected. That is, it is possible to exclude movements other than the measurement target person H as disturbance.

Next, the tracking unit 14e tracks the position of the measurement target person H based on the signal intensities of the existing range bin and the adjacent range bins identified by the position identifying unit 14d. Next, the state determination unit 14g generates the motion data of the measurement target person H through the tracking process by the tracking unit 14e (step S4 in FIG. 8).

For example, FIG. 6 shows a state in which the signal intensity of the range bin existing at about 0 m to 1.5 m from the living body detection device 10 is rapidly changed before and after about 100 seconds and about 140 seconds, respectively. .. That is, with the passage of time, a large signal intensity shifts from the existing range bin to the adjacent range bin. In this case, in step S7 described later, the state determination unit 14g determines that the measurement target person H has moved from the existing range bin to the adjacent range bin during that time. After that, the tracking unit 14e treats the adjacent range bin after the transition as a new existing range bin and treats the range bin adjacent to the new existing range bin as a new adjacent range bin. That is, the tracking unit 14e tracks the measurement target person H on the basis of the rate of change of the signal intensity with respect to the range bin (distance from the living body detection device 10) (difference between the current signal intensity and the signal intensity before a fixed time). It can be said that there is.

For example, FIG. 6 shows a state in which the signal intensity of the range bin existing at about 0 m to 1.5 m from the biological detection device 10 does not change much in about 65 seconds to about 100 seconds. That is, with the passage of time, a large signal intensity continuously occurs in the existing range bin, but the signal intensity remains small in the adjacent range bin. In this case, in step S7, which will be described later, the state determination unit 14g determines that the measurement target person H remains in the specific existing range bin for that time (the measurement target person H did not significantly move).

By the way, for example, in FIG. 6, in about 100 seconds to about 130 seconds, the signal intensity of the range bin existing at about 0.2 m to 0.5 m from the living body detecting device 10 becomes small, and from the living body detecting device 10. It is shown that the signal intensity of the range bin existing at about 0.4 m to 0.7 m is increasing. This is because the person H to be measured leans forward on the toilet seat 33, and the existing range bin moves rearward. In this case, in step S7, which will be described later, the state determination unit 14g determines that the measurement target person H is bent forward at that time.

Next, the data generation unit 14f, based on the time variation of the signal intensity in the existing range bin specified by the position specifying unit 14d or the new existing range bin updated by the tracking unit 14e, the biometric data (for example, breathing, pulsation). ) Is generated (step S5 in FIG. 8).

Next, the class determination unit 14i applies the analysis data in which the motion data generated in steps S4 and S5 are associated with the biometric data to the classification model M to personally identify the measurement target person H (FIG. 8). Step S6). For example, when the data generation unit 14f generates the analysis data x shown in FIG. 5, the class determination unit 14i determines that the analysis data x belongs to the class C3. That is, the class determination unit 14i determines that the measurement target person H is “Mr. Z”. At this time, the control unit 14 may store the motion data and biometric data generated in steps S4 and S5 in the storage unit 14a in association with the personal information of the measurement target person H obtained in step S6. ..

Next, the state determination unit 14g determines the state of the measurement target person H (step S7 in FIG. 8). Specifically, the state determination unit 14g determines the measurement subject H's motion, microscopic movement, position, respiration, and pulsation, and whether the measurement subject H is in a dangerous state.

The presence/absence of the motion of the measurement target person H may be determined based on the time variation of the signal strength between the existing range bin and the adjacent range bin. For example, when the existing range bin is updated in the tracking unit 14e, the state determination unit 14g may determine that there is an operation. On the other hand, when the existing range bin is not updated in the tracking unit 14e, the state determination unit 14g may determine that the measurement target person H is in a dangerous state because the measurement target person H is not operating.

The determination of the presence or absence of the small body movement of the measurement target person H may be performed based on the time variation of the signal intensity in the existing range bin. For example, when the time variation of the signal intensity in the existing range bin is within a predetermined range, the state determination unit 14g may determine that there is a small body movement. When the time variation of the signal intensity in the existing range bin is less than the predetermined range, the state determination unit 14g may determine that the measurement target person H is in a dangerous state because the measurement target person H has no minute body movement. ..

By the way, when the person H to be measured falls, faints, etc., the person H to be measured operates larger than usual. At this time, in the existing range bin, a larger time variation of signal strength than usual appears. Therefore, when the time variation of the signal intensity in the existing range bin exceeds the predetermined range, the state determination unit 14g may determine that the measurement target person H is in a dangerous state.

Next, as a result of the determination in step S7, when the measurement target person H is abnormal (YES in step S8 of FIG. 8), the transmission/reception processing unit 14b transmits an instruction signal to the communication device 13, and the determination result Is transmitted to the notification device 20. As a result, the danger of the measurement target person H is notified to the person in the room other than the living body detection apparatus 10 through the monitor 21 or the speaker 22 of the notification apparatus 20 in the room (step S9 in FIG. 8). ), the biometric detection process ends. The notification of the abnormality by the notification device 20 may be performed when the determination of the danger by the state determination unit 14g continues for a predetermined time or longer.

On the other hand, as a result of the determination in step S7, when the measurement target person H has no abnormality (NO in step S8 of FIG. 8), the entry/exit determination unit 14j determines whether or not the measurement target person H has left the toilet room 30. It is determined (step S10 in FIG. 8). Specifically, the entry/exit determination unit 14j acquires the signal intensity over time and determines whether or not the reflected wave from the front side of the door D is below a predetermined threshold value. When the entry/exit determination unit 14j determines that the measurement target person H has not left the toilet room 30 (NO in step S11 of FIG. 8 ), the processes of step S2 and subsequent steps are repeated.

By the way, for example, FIG. 6 shows a state in which the signal intensity of the range bin existing at about 0 m to 1.5 m from the living body detection device 10 rapidly changes in about 140 seconds to 160 seconds. In this case, the entry/exit determination unit 14j determines that the measurement target person H has exited the room at this time point (between about 140 seconds and about 160 seconds) (YES in step S11 of FIG. 8 ), and the living body detection process ends. ..

[Action]
According to the above example, the position identifying unit 14d recognizes that the living body is present in the area where the time variation is large, based on the time variation of the signal intensity calculated for each of the plurality of areas. As described above, by using the magnitude of the time variation as a reference, the influence of the variation other than the living body is suppressed. In addition, the tracking unit 14e uses the time variation of the signal intensity in each of the existing area and the adjacent area specified by the position specifying unit 14d for tracking the measurement target person H. Therefore, even if the temporal variation of the signal intensity suddenly increases outside these areas, it is suppressed that the measurement subject H is erroneously detected. Further, the data generation unit 14f generates biometric data such as respiration and pulsation based on the time variation of the signal intensity in the existing area where the measurement target person H is present. As described above, by using the time variation of the signal intensity in the existing area specified by the position specifying unit 14d, it is possible to continuously generate the biometric data before and after the movement of the measurement target person H. Therefore, the state of the measurement target person H can be accurately grasped.

According to the above example, in order to track the position of the measurement target person H, the existing area and the areas before and after the existing area are used. Therefore, since the area for tracking is enlarged, it is possible to easily perform tracking regardless of whether the measurement target person H moves to the front or back of the existing area.

According to the above example, the individual measurement target persons H are classified into different individual classes by machine learning using a plurality of reference data in which motion data and biometric data are associated. Therefore, by determining the individual class to which the analysis data belongs based on such a classification model M, the individual to be analyzed can be accurately specified.

[Modification]
Although the embodiments according to the present disclosure have been described above in detail, various modifications may be added to the above embodiments without departing from the scope of the claims and the gist thereof.

(1) The biological detection device 10 may be provided at a location other than the tank 35. For example, when the toilet 31 is a tankless toilet, the living body detection device 10 may be provided on the wall of the toilet room 30 facing the door D. Alternatively, it may be provided in the toilet lid 34 or the remote control cleaning unit of the toilet 31 depending on the antenna directivity angle of the transmitter 11. The living body detection device 10 may be used for detecting a living body in a space other than the toilet room 30 (for example, a bathroom, a bedroom, a living room, an office, an automobile, etc.).

(2) The living body detection device 10 may be connected to the notification device 20 by wire.

(3) In the above embodiment, the notification device 20 is installed in the same building as the living body detecting device 10, but may be installed in a building different from the living body detecting device 10 and mobile communication is possible. It may be a portable terminal (for example, a mobile phone, a smartphone, etc.). Examples of the different building include a family home separated from the person H to be measured, a facility that provides emergency medical services (a fire station in Japan), a hospital, and the like. In these cases, a family member, a rescue team, a doctor, etc. who are located away from the measurement target person H can know the state of the measurement target person H. Therefore, even when the measurement target person H is a single-living person, it is possible to watch the state of the measurement target person H.

(4) The living body detection device 10 may include the notification device 20. That is, the living body detection device 10 may include the monitor 21 (notification unit), the speaker 22 (notification unit), and the like. In this case, the notification device 20 is arranged in the toilet room 30. Therefore, for example, in the case of a slight abnormality in which the person H to be measured falls asleep while sitting on the toilet seat 33 and is in a semi-awakening state, the monitor 21 blinks and an alarm from the speaker 22 (for example, an alarm sound, a warning announcement). And the like), it is possible to prevent the measurement target person H from shifting to a severe abnormality.

(5) The living body detection device 10 may include an input unit configured to receive an input operation from a user including the measurement target person H. Examples of the input unit include a switch and a touch panel. The living body detection device 10 may include an update unit configured to perform machine learning based on the input operation received by the input unit.

For example, when the class determination unit 14i determines that the measurement target person H is “Mr. Z”, but in reality it is “Mr. X”, the measurement target person “Mr. X” is the input unit. By inputting correct personal information via the, the updating unit may update the classification model M triggered by the input operation. In this case, the user feeds back the erroneous determination result through the input unit, so that the measurement target person H can be more accurately identified.

For example, when the notification device 20 issues an alarm, if an input operation from the user indicating that the alarm is a false alarm is input to the input unit (the notification device 20 indicates that the measurement target person H is in an abnormal state). Has issued an alarm, but the abnormality has not actually occurred in the measurement target person H), the update unit may perform machine learning triggered by the input operation. In this case, the user feeds back the false alarm through the input unit, so that the situation of the measurement target person H in the toilet room 30 can be detected more accurately.

(6) The control unit 14 sends a control signal for controlling other devices (for example, lighting in the toilet room 30) based on the data regarding the state of the measurement target person H determined by the state determination unit 14g. It may include a control signal generation unit for generating. The control signal generation unit may transmit the control signal to the other device via the communication device 13 (communication unit).

(7) The classification model M may be a learned model in which a plurality of reference data have been learned in advance, or may be a dynamic classification model in which analysis data is additionally learned in real time in the learned model. Good.

(8) Depending on the individual habits of the person H to be measured, the sitting position on the toilet seat 33 (sit down), posture change during sitting (body movement), breathing, etc. may change. Therefore, the person to be measured H may be personally identified based on these. The seating position on the toilet seat 33 may be identified based on the distance from the living body detection device 10 (for example, tracking processing by the tracking unit 14e). Posture changes and breathing during sitting may be identified based on the time variation of signal strength in the range bin.

(9) The living body detection device 10 may continue to operate to monitor the inside of the toilet room 30 even when the measurement target person H is not present in the toilet room 30. For example, the living body detection device 10 continues to operate even after the measurement target person H leaves the room to detect whether the measurement target person H is in a dangerous state after the measurement target person H exits from the toilet room 30. It becomes possible to do.

(10) The control unit 14 may separate and generate a plurality of biometric data from one reception signal by performing frequency analysis on the time variation of the signal intensity of the reflected wave received by the receiver 12. Examples of frequency analysis methods include Fourier transform and wavelet transform. Examples of the plurality of biological data separated and generated from one received signal by frequency analysis include the respiratory component and the pulsation component of the measurement target person H.

(11) The biological detection device 10 may be used as a biological data acquisition device. That is, the living body detection device 10 does not need to perform the determination by the state determination unit 14g after the biological data is generated by the data generation unit 14f. In this case, the control unit 14 may include at least a storage unit 14a, a transmission/reception processing unit 14b, a signal strength calculation unit 14c, a position identification unit 14d, and a data generation unit 14f.

(12) Although not shown, the door D may be provided on the side wall of the toilet room 30. In this case, the living body detection device 10 faces the front wall of the toilet room 30 and the back surface of the measurement target person H seated on the toilet seat 33.

(13) Whether the living body detection device 10 exists within a range of about 0 m to 0.5 m from the living body detection device 10 after the measurement target person H detects that the measurement target person H has entered the toilet room 30. You may judge whether or not. When the signal intensity of the range bin in this range does not change or the change is slight, the living body detection device 10 determines that the measurement target person H is not sitting on the toilet bowl 31 and is standing urine by a man. Good. In this case, the state determination of the measurement target person H may be performed without generating the biometric data of the measurement target person H and personal identification (steps S5 and S6 in FIG. 8 may be omitted and the process may proceed to step S7). ).

[Experimental example]
An experiment was conducted using the living body detection system 1 configured as described above. Specifically, as in the case of FIG. 1, the subject acted in the toilet room 30 based on the following two scenarios with the living body detection device 10 attached to the toilet lid 34.
-Scenario 1: The subject entered the toilet room 30 through the door D, then sat on the toilet seat 33, fainted in that state, and leaned against the wall surface of the toilet room 30.
-Scenario 2: The test subject entered the toilet room 30 through the door D, then sat on the toilet seat 33, fainted when standing up from the toilet seat 33, fell over, and lay on the floor.

The experimental results of scenario 1 are shown in FIG. The experimental results of scenario 2 are shown in FIG. 9(b). According to FIG. 9, it was confirmed that the state determination unit 14g could identify where the subject was as the subject moved. Further, according to FIG. 9, when the subject takes an action that assumes a dangerous state such as the subject leaning against the wall surface of the toilet room 30 or lying on the floor, the state determination unit 14g causes a risk. It was confirmed that this was judged.

[Example]
Example 1. The living body detection device according to an example of the present disclosure, a transmitter configured to be capable of transmitting a wideband or ultrawideband radio wave toward a predetermined detection area, and a reflected wave of the radio wave emitted from the transmitter. A receiving unit configured to be receivable, based on a reflected wave received by the receiving unit, a signal strength calculating unit configured to calculate the signal strength in each of a plurality of areas forming the detection region, A position specifying unit configured to specify an existing area in which a living body exists among a plurality of areas based on a temporal change in signal intensity in each area, and at least one adjacent area adjacent to the existing area and the existing area And a tracking unit configured to track the movement of the living body based on the time variation of the signal strength in each of the and, and generate the living body data based on the time variation of the signal strength in the existing area. And a data generation unit configured as described above.

The movement of the living body is not constant, and the temporal fluctuation of the signal intensity when the living body moves tends to be extremely large. Therefore, the position identifying unit recognizes that the living body exists in the area where the time variation is large, based on the time variation of the signal intensity calculated for each of the plurality of areas. As described above, by using the magnitude of the time variation as a reference, the influence of the variation other than the living body is suppressed. In addition, the tracking unit uses the time variation of the signal intensity in each of the living body existing area specified by the position specifying unit and the adjacent area for tracking the living body. Therefore, even if the temporal fluctuation of the signal intensity suddenly increases outside these areas, it is suppressed from being erroneously detected as a living body. Furthermore, for example, the chest expands and contracts according to the breathing of the living body, and the heart expands and contracts according to the pulsation of the heart of the living body, so that the signal intensity of the reflected wave from the body surface of the living body or the heart fluctuates with time. Therefore, the data generation unit generates biometric data such as respiration and pulsation based on the time variation of the signal intensity in the existing area where the biometric body exists. As described above, by using the time variation of the signal intensity in the existing area specified by the position specifying unit, it is possible to continuously generate the biometric data before and after the movement of the biological body. Therefore, according to the living body detection device of Example 1, it is possible to accurately grasp the state of the living body.

Example 2. In the device of Example 1, the tracking unit may track the position of the living body based on the temporal variation of the signal intensity in each of the existing area and the pair of adjacent areas located on both sides of the existing area. In this case, in order to track the position of the living body, the existing area and the front and back areas adjacent to the existing area are used. Therefore, since the area for tracking is enlarged, it is possible to easily track whether the living body moves before or after the existing area.

Example 3. The device of Example 1 or Example 2 further includes a state determination unit configured to determine that the living body is in an abnormal state when the temporal variation of the signal strength in the existing area varies over a predetermined threshold value. You may. Here, when a living body (for example, a human body) falls down, the living body operates larger than usual. Therefore, a time variation of the signal strength larger than usual appears. Therefore, according to the example 3, it is possible to determine the abnormal state of the living body based on the time variation of the signal strength.

Example 4. The device according to any one of Examples 1 to 3 is configured to determine that the living body is in an abnormal state when the living body remains in a stationary state for a predetermined time as a result of tracking by the tracking unit. May be further provided. Here, even if a living body (for example, a human body) does not fall down, it is possible that the quiescent state continues due to stunning or the like. According to Example 4, even in such a case, it is possible to determine the abnormal state of the living body.

Example 5. In the device according to any one of Examples 1 to 4, the data generation unit separates and generates the respiratory component and the pulsation component of the living body by performing frequency analysis on the time variation of the signal intensity in the existing area. It may be configured as follows. In this case, it is possible to obtain a plurality of biometric data from one received signal by frequency analysis.

Example 6. The apparatus according to any one of Examples 1 to 5 may further include a notification unit configured to notify information regarding the state of the living body.

Example 7. The apparatus of Example 3 or Example 4 may further include a notification unit configured to notify an alarm when the living body is in an abnormal state as a result of the determination by the state determination unit. In this case, for example, in the case of a slight abnormality in which the living body falls asleep and is in a semi-wake state, the living body is awakened by an alarm to prevent the living body from transitioning to a severe abnormality. Is possible.

Example 8. The apparatus according to any one of Examples 1 to 7 classifies the reference data into any one of a plurality of individual classes by machine learning using a plurality of reference data in which motion data and biometric data are associated with each other. When the receiving unit receives the reflected wave to be analyzed, the storage unit configured to store the classified model and the tracking unit and the data generating unit generate operation data and biometric data, respectively, and these are associated with each other. It may further include an analysis data generation unit configured to generate the analyzed data, and a class determination unit configured to determine which of the plurality of individual classes the analysis data belongs to. By the way, the characteristic amount such as the movement of the living body, the respiration of the living body, the pulsation of the living body is different for each individual living body, and the distance spectrum of the signal intensity in the receiving unit changes according to these characteristic amounts. Therefore, each living body can be classified into different individual classes by machine learning using a plurality of reference data in which motion data and biological data are associated. Therefore, by determining the individual class to which the analysis data belongs based on such a classification model, the individual to be analyzed can be accurately specified.

Example 9. In the device according to any one of Examples 1 to 8, the transmitting unit may be configured to be capable of transmitting a broadband or ultra-wideband radio wave toward the back surface of the human body sitting on the toilet seat in the toilet room.

Example 10. A living body detection system according to another example of the present disclosure communicates between the device according to any one of Examples 1 to 9 installed at a predetermined location in a building, and the living body transmitted from the device. And a notification device configured to notify information regarding the state of. In this case, the behavior of the living body, the abnormal state of the living body, and the like detected by the device of any of Examples 1 to 9 can be grasped via the notification device located at a position different from that of the device. Therefore, for example, it becomes possible to watch the state of the person in the toilet room from the outside of the toilet room such as the kitchen, the living room, and the place where the user goes out.

Example 11. A living body detection system according to another example of the present disclosure includes a device of Example 3 or 4 installed at a predetermined location in a building, and a device when a living body is in an abnormal state as a result of determination by a state determination unit. And a notification device configured to notify the alarm by communicating between them. In this case, the abnormal state of the living body detected by the device of Example 3 or Example 4 can be grasped via the notification device located at a position different from that of the device. Therefore, for example, it becomes possible to watch the state of the person in the toilet room from the outside of the toilet room such as the kitchen, the living room, and the place where the user goes.

Example 12. An animate body detection method according to another example of the present disclosure is to transmit a wideband or ultrawideband radio wave toward a predetermined detection area, and a plurality of areas forming the detection area based on a reflected wave of the radio wave. Of the signal strength in each of the plurality of areas, and based on the time variation of the signal strength in each of the plurality of areas, specify the existing area where the living body exists among the plurality of areas, and Generating motion data by tracking the movement of the living body based on the time variation of the signal strength in each of at least one adjacent area that matches and generating biometric data based on the time variation of the signal strength in the existing area. Including that. In this case, the same effect as in Example 1 can be obtained.

Example 13. A biological data acquisition device according to another example of the present disclosure includes a transmitter configured to be capable of transmitting a broadband or ultra-wideband radio wave toward a predetermined detection area, and a reflected wave of the radio wave emitted from the transmitter. A receiving unit configured to be capable of receiving, a signal intensity calculating unit configured to calculate a signal intensity in each of a plurality of areas forming a detection region based on a reflected wave received by the receiving unit, Based on the time variation of the signal strength in each of the areas, the position specifying unit configured to identify the existing area where the living body exists among the plurality of areas, and the living body based on the time variation of the signal strength in the existing area. A data generator configured to generate data.

The movement of the living body is not constant, and the temporal fluctuation of the signal intensity when the living body moves tends to be extremely large. Therefore, the position identifying unit recognizes that the living body exists in the area where the time variation is large, based on the time variation of the signal intensity calculated for each of the plurality of areas. As described above, by using the magnitude of the time variation as a reference, the influence of the variation other than the living body is suppressed. Furthermore, for example, the chest expands and contracts according to the breathing of the living body, and the heart expands and contracts according to the pulsation of the heart of the living body, so that the signal intensity of the reflected wave from the body surface of the living body or the heart fluctuates with time. Therefore, the data generation unit generates biometric data such as respiration and pulsation based on the time variation of the signal intensity in the existing area where the biometric body exists. As described above, by using the time variation of the signal intensity in the existing area specified by the position specifying unit, it is possible to continuously generate the biometric data before and after the movement of the biological body. Therefore, according to the biometric data acquisition apparatus according to the thirteenth example, it is possible to accurately acquire biometric data.

DESCRIPTION OF SYMBOLS 1... Biological detection system, 10... Biological detection device, 11... Transmitter (transmission part), 12... Receiver (reception part), 13... Communication device, 14... Control part (controller), 14a... Storage part, 14b... Transmission/reception processing unit, 14c...Signal strength calculation unit, 14d...Position specifying unit, 14e...Tracking unit, 14f...Data generation unit, 14g...State determination unit, 14h...Classification model generation unit, 14i...Class determination unit, 16...Processor , 17... Memory (storage section), 18... Storage (storage section), 20... Notification device, 21... Monitor (report section), 22... Speaker (report section), 23... Communication device, 24... Control section (controller) , 30... Toilet room, H... Measurement subject (living body), R... Detection area.

Claims (13)

A transmitting unit configured to be capable of transmitting wideband or ultrawideband radio waves toward a predetermined detection area,
A receiver configured to be able to receive a reflected wave of a radio wave transmitted from the transmitter,
Based on the reflected wave received by the receiving unit, a signal strength calculating unit configured to calculate the signal strength in each of a plurality of areas constituting the detection region,
Based on the time variation of the signal strength in each of the plurality of areas, a position specifying unit configured to specify the existing area of the living body in the plurality of areas,
A tracking unit configured to track the movement of the living body based on the time variation of the signal intensity in each of the existing area and at least one adjacent area adjacent to the existing area, and to generate motion data,
A biometric device configured to generate biometric data based on a temporal change in signal intensity in the existing area. The device according to claim 1, wherein the tracking unit tracks the position of a living body based on a temporal change in signal intensity in each of the existing area and a pair of adjacent areas located on both sides of the existing area. The state determination unit configured to determine that the living body is in an abnormal state when the temporal variation of the signal intensity in the existing area varies over a predetermined threshold value, further comprising: apparatus. The result of tracking by the tracking unit, further comprising a state determination unit configured to determine that the living body is in an abnormal state when the living body is in a stationary state for a predetermined time, any one of claims 1 to 3. The device according to 1 above. The data generation unit is configured to generate a respiratory component and a pulsating component of a living body separately by performing frequency analysis on a time variation of signal intensity in the existing area. 5. The device according to any one of 4 to 4. The device according to any one of claims 1 to 5, further comprising a notification unit configured to notify information regarding a state of a living body. The device according to claim 3, further comprising a notification unit configured to notify an alarm when the living body is in an abnormal state as a result of the determination by the state determination unit. The reference data stores a classification model in which the reference data is classified into any one of a plurality of individual classes by machine learning using a plurality of reference data in which the motion data and the biometric data are associated with each other. Storage unit,
When the receiving unit receives the reflected wave to be analyzed, the tracking unit and the data generating unit generate the operation data and the biometric data, respectively, and generate analysis data in which these are associated with each other. A configured analysis data generator,
The apparatus according to claim 1, further comprising: a class determination unit configured to determine which of the plurality of individual classes the analysis data belongs to. 9. The device according to claim 1, wherein the transmitting unit is configured to transmit a broadband or ultra-wideband radio wave toward a back surface of a human body sitting on a toilet seat in a toilet room. .. The device according to any one of claims 1 to 9, which is installed at a predetermined location in a building,
A living body detection system, comprising: a notifying device configured to communicate with the device to notify the information regarding the state of the living body transmitted from the device. The device according to claim 3 or 4, which is installed at a predetermined location in a building,
A living body detection system, comprising: a notification device configured to communicate with the device to notify an alarm when the living body is in an abnormal state as a result of the determination by the state determination unit. Transmitting a wide band or ultra wide band radio wave toward a predetermined detection area,
Calculating signal strength in each of a plurality of areas forming the detection area based on a reflected wave of a radio wave,
Based on the time variation of the signal strength in each of the plurality of areas, to identify the existing area in which the living body exists in the plurality of areas,
Tracking the movement of the living body based on the time variation of the signal intensity in each of the existing area and at least one adjacent area adjacent to the existing area, and generating operation data,
Generating biometric data based on a temporal change in signal intensity in the existing area. A transmitting unit configured to be capable of transmitting wideband or ultrawideband radio waves toward a predetermined detection area,
A receiver configured to be able to receive a reflected wave of a radio wave transmitted from the transmitter,
Based on the reflected wave received by the receiving unit, a signal strength calculating unit configured to calculate the signal strength in each of a plurality of areas constituting the detection region,
Based on the time variation of the signal strength in each of the plurality of areas, a position specifying unit configured to specify the existing area of the living body in the plurality of areas,
A biometric data acquisition device, which is configured to generate biometric data based on a temporal change in signal intensity in the existing area.