WO2020039758A1

WO2020039758A1 - Information processing apparatus, sensor box, and program

Info

Publication number: WO2020039758A1
Application number: PCT/JP2019/026281
Authority: WO
Inventors: 塩田　奈津子; 保理江　大作; 和馬新田
Original assignee: コニカミノルタ株式会社
Priority date: 2018-08-20
Filing date: 2019-07-02
Publication date: 2020-02-27
Also published as: JP7230920B2; JPWO2020039758A1

Abstract

A mobile terminal (300) which is an example of this information processing apparatus comprises: a notification information generation unit (13) which generates, on the basis of behavior information about a watching target, information for providing a notification of the occurrence of a sign of a predetermined behavior performed by the watching target; an output unit (32) which outputs a notification about the information generated by the notification information generation unit (13); and a condition adjustment unit (14) which adjusts the sensitivity of the generation of information by the notification information generation unit (13), depending on the situation of the watching target.

Description

Information processing device, sensor box, and program

(4) The present disclosure relates to output of a notification about a watching target, and particularly to output of a notification based on a detection output of a behavior of the watching target.

Conventionally, for a monitoring target such as a cared person in a care facility, a notification is output based on the detection output of the behavior of the monitoring target. When such a notice is output at the facility, the staff responds to each notice, such as rushing to a room to be watched over.

スタッフ Frequent notification increases staff burden. From the viewpoint of reducing the burden on staff and the like, various techniques have been proposed to minimize unnecessary notifications. For example, Japanese Patent No. 5688155 (Patent Literature 1) discloses a leaving-bed notification device that sets a reporting time limit for limiting a report of a predictive action based on a past bed leaving situation of a sleeping person. In the report time limit, the report is suppressed even if the predictive action is detected.

Japanese Patent No. 5688155

(4) If notification is suppressed in a given time slot as proposed in Patent Literature 1, when an irregular event occurs in the time slot, a situation may occur in which a notification opportunity is missed. On the other hand, suppression of useless notification is always desired from the viewpoint of reducing the burden on staff.

(4) The present disclosure has been made in view of the above circumstances, and an object of the present disclosure is to provide a technique for suppressing a useless notification and not missing a notification opportunity with respect to a notification of a watching target.

According to an aspect of the present disclosure, a generation unit configured to generate information for notifying the occurrence of a sign of a predetermined behavior by the watching target based on the behavior information of the watching target, and information about the information generated by the generation unit. An information processing apparatus is provided that includes an output unit that outputs a notification, and an adjustment unit that adjusts the sensitivity of information generation by the generation unit according to a situation of a watching target.

The generating means includes: detecting means for detecting the occurrence of an action corresponding to the action information using the biological information to be monitored; and determining means for determining the occurrence of a sign when the occurrence of the action satisfies a predetermined condition. May be included. The adjusting means may adjust the sensitivity of information generation by adjusting at least one of the sensitivity of detecting the occurrence of the action by the detecting means and the sensitivity of determining the occurrence of the sign by the determining means.

Adjusting the detection sensitivity of the occurrence of the action may include adjusting the moving distance of the watching target, which is a condition for the occurrence of the action.

(4) Adjusting the sensitivity of the determination of the occurrence of the sign may include adjusting the number of actions within a certain period of time required for determining the occurrence of the sign.

The situation may include the attribute of the watching target.
The attribute may include at least one of the latest excretion time, the degree of need for nursing care, and the past wake-up time.

The situation may include a management system of the facility where the watching target is moved in.
According to another aspect of the present disclosure, there is provided a sensor box including the information processing device described above and a sensor for acquiring biological information.

According to yet another aspect of the present disclosure, a program executed by a computer is provided. The program is configured to generate, based on the information on the behavior of the watching target, information on a notification about the watching target when a predetermined behavior of the watching target is generated on the computer, and output the information on the notification. And let it run. The sensitivity of generating the notification information is adjusted according to the situation of the watching target.

The sensitivity of the generation of the notification information may be adjusted by adjusting at least one of the detection sensitivity of the occurrence of the action corresponding to the action information, and the sensitivity of determining the occurrence of the sign based on the occurrence of the action. .

According to the present disclosure, information for notifying the occurrence of a sign of a predetermined action by the watching target is generated according to the status of the watching target. As a result, a technique is provided in which useless notifications are not missed while suppressing useless notifications.

It is a figure showing an example of composition of a watching system. FIG. 9 is a diagram for explaining an example of a detection range of a sensor in a living room 900. FIG. 3 is a diagram illustrating a hardware configuration of a sensor box 100, a management server 200, and a mobile terminal 300 of the watching system. FIG. 3 is a diagram illustrating a hardware configuration of a cloud server 400. It is a figure showing an example of functional composition of a watching system. FIG. 5 is a diagram for explaining two sensitivities relating to generation of notification information by a notification information generation unit 13; 5 is a flowchart illustrating an example of a process performed by an action detection unit 12. 5 is a flowchart illustrating an example of a process performed by a notification information generation unit 13; 5 is a flowchart illustrating an example of a process performed by a condition adjustment unit. It is a figure which shows the modification of the function distribution in the component of a watching system. It is a figure which shows the modification of the function distribution in the component of a watching system. It is a figure which shows the modification of the function distribution in the component of a watching system. It is a figure which shows the modification of the function distribution in the component of a watching system. It is a figure which shows the modification of the function distribution in the component of a watching system. It is a figure which shows the modification of the function distribution in the component of a watching system.

Hereinafter, an embodiment of a watching system will be described with reference to the drawings. In the following description, the same parts and components are denoted by the same reference numerals. Their names and functions are the same. Therefore, the description will not be repeated.

[Configuration of watching system]
FIG. 1 is a diagram illustrating an example of the configuration of a watching system. As an example of the watching target, a resident in each living room provided in the living room region RM of the facility is adopted. In the watching system of FIG. 1,

living rooms

900A and 900B are provided in the living room area RM. Living room 900A is assigned to resident 800A. Living room 900B is assigned to resident 800B. In the example of FIG. 1, the number of living rooms included in the watching system is two, but the number is not limited to this.

In the watching system, the sensor box 100A installed in the living room 900A, the sensor box 100B installed in the living room 900B, the management server 200 installed in the management center ST, and the access point AP are connected via the network NT. Is done.

In the watching system, the portable terminal 300A carried by the staff NA and the portable terminal 300B carried by the staff NB are connected to the network NT via the access point AP. Further, the

sensor boxes

100A and 100B, the management server 200, and the access point AP can communicate with the cloud server 400 via the network NT.

The living room 900A includes a bed 901A, a toilet 902A, and furniture 903A as facilities. The door of the living room 900A is provided with a door sensor 510A that detects opening and closing of the door. A toilet sensor 520A that detects opening and closing of the toilet 902A is provided on the door of the toilet 902A. The bed 901A is provided with an odor sensor 530A for acquiring excretion information of the resident 800A. The resident 800A is wearing a vital sensor 540A that detects vital information of the resident 800A. One example of detected vital information is a resident's body temperature. Another example is the resident's breathing. Yet another example is the resident's heart rate. Still another example is two or more types of information among these pieces of information. In living room 900A, resident 800A can operate care call slave device 500A.

では In this specification, the term “sensor box 100” that generically refers to the

sensor boxes

100A and 100B is used to refer to matters common to the plurality of

sensor boxes

100A and 100B. Similarly,

tenants

800A, 800B,

living rooms

900A, 900B,

beds

901A, 901B,

toilets

902A, 902B,

furniture

903A, 903B, care call

slave units

500A, 500B,

door sensors

510A, 510B,

toilet sensors

520A, 520B, odor sensor Similarly, for each of 530A, 530B and

vital sensors

540A, 540B, the terms "resident 800", "living room 900", "toilet 902", "furniture 903", "care call slave unit 500", "door sensor 510" , “Toilet sensor 520”, “odor sensor 530”, and “vital sensor 540” are used.

The sensor box 100A has a built-in sensor for detecting the behavior of an object in the living room 900A. One example of a sensor is a Doppler sensor for detecting the movement of an object. Another example is a camera. Still other examples are the care call slave device 500, the door sensor 510, the toilet sensor 520, the odor sensor 530, or the vital sensor 540. The sensor box 100A includes at least one of these sensors as a sensor.

FIG. 2 is a diagram for explaining an example of the detection range of the sensor in the living room 900. In the example of FIG. 2, the sensor box 100 is installed on the ceiling CL of the living room 900.

Range AR schematically represents the detection range of the sensor. When the sensor is a Doppler sensor, the Doppler sensor detects a behavior occurring in the range AR. When the sensor is a camera, the camera captures an image within the range AR.

に Returning to FIG. 1, the management server 200 installed in the management center ST is connected to the display 206 and the input device 209. The input device 209 is, for example, a keyboard.

In the monitoring system of FIG. 1, the number of mobile terminals connected to the network NT via the access point AP is two (

mobile terminals

300A and 300B), but the number is not limited to this. In this specification, when referring to items common to the

mobile terminals

300A and 300B, the term "mobile terminal 300" that generically refers to the

mobile terminals

300A and 300B is used.

通信 The communication between the elements in the watching system of FIG. 1 may be wired or wireless.

Note that the sensor box 100 does not necessarily need to include the camera 105 and / or the Doppler sensor 106. The camera 105 and / or the Doppler sensor 106 may be provided outside the sensor box 100 like the door gate sensor 510 and the like. The control device 101 may acquire the detection output of the camera 105 and / or the Doppler sensor 106 provided outside the sensor box 100 via a given interface.

The vital sensor 540 does not necessarily have to be worn by the resident. In one example, the vital sensor 540 is realized by an infrared sensor or the like installed at a distance from the resident, and outputs vital information (body temperature) by detecting the temperature of the resident. In another example, vital sensor 540 is implemented by Doppler sensor 106. The Doppler sensor 106 emits microwaves to the resident. The microwave causes the Doppler effect due to slight displacement of the chest due to the pulsation of the resident's heart, and fluctuates its frequency. The Doppler sensor 106 detects a resident's heartbeat based on the fluctuation of the frequency. In yet another example, Doppler sensor 106 detects a resident's breathing.

[Configuration of each element of the watching system]
FIG. 3 is a diagram illustrating a hardware configuration of the sensor box 100, the management server 200, and the mobile terminal 300 of the watching system. FIG. 4 is a diagram illustrating a hardware configuration of the cloud server 400. Hereinafter, an example of a configuration of each device in the watching system will be described with reference to FIGS. 3 and 4.

(Sensor box 100)
The sensor box 100 includes a control device 101, a read only memory (ROM) 102, a random access memory (RAM) 103, a communication interface 104, a camera 105, a Doppler sensor 106, a wireless communication device 107, and a storage device. 120.

(4) The control device 101 controls the sensor box 100. The control device 101 is composed of, for example, at least one integrated circuit. The integrated circuit includes, for example, at least one CPU (Central Processing Unit), at least one ASIC (Application Specific Integrated Circuit), at least one FPGA (Field Programmable Gate Array), or a combination thereof.

アンテナ An antenna (not shown) and the like are connected to the communication interface 104. The sensor box 100 exchanges data with an external communication device via the antenna. External communication devices include, for example, management server 200, mobile terminal 300, access point AP, cloud server 400, and other communication terminals.

The camera 105 is a near-infrared camera in one implementation. The near-infrared camera includes an IR (Infrared) projector that emits near-infrared light. By using the near-infrared camera, an image representing the inside of the living room 900 can be captured even at night. In another implementation, camera 105 is a surveillance camera that receives only visible light. In still other implementations, a 3D sensor or a thermographic camera may be used as camera 105. The sensor box 100 and the camera 105 may be configured integrally or may be configured separately.

The Doppler sensor 106 is, for example, a microwave Doppler sensor, and emits and receives radio waves to detect the behavior (movement) of an object in the living room 900. Thereby, the biological information of the resident 800 in the living room 900 can be detected. In one example, the Doppler sensor 106 radiates a microwave in the 24 GHz band toward the bed 901 of each living room 900 and receives a reflected wave reflected by the resident 800. The reflected wave is Doppler shifted by the operation of the resident 800. The Doppler sensor 106 can detect the respiratory state and the heart rate of the resident 800 from the reflected wave.

The wireless communication device 107 receives signals from the care call slave device 500, the door sensor 510, the toilet sensor 520, the odor sensor 530, and the vital sensor 540, and transmits the signals to the control device 101. For example, care call slave device 500 includes care call button 501, and when care call button 501 is operated, transmits a signal indicating that the operation has been performed to wireless communication device 107. Each of the door sensor 510, the toilet sensor 520, the odor sensor 530, and the vital sensor 540 transmits their respective detection outputs to the wireless communication device 107.

The storage device 120 is, for example, a storage medium such as a hard disk or an external storage device. The storage device 120 stores a program executed by the control device 101 and various data used for executing the program. The various data may include behavior information of the resident 800.

At least one of the above-described program and data is a storage device other than the storage device 120 (for example, a storage area (for example, a cache memory or the like) of the control device 101, a ROM 102, The RAM 103 may be stored in an external device (for example, the management server 200 or the mobile terminal 300).

(Behavior information)
The above behavior information will be described. The action information is, for example, information indicating that the resident 800 has performed a predetermined action. In one example, the predetermined actions are “wake up” indicating that the resident 800 has woken up, “getting out” indicating that the resident 800 has left the bedding, and “falling down” indicating that the resident 800 has fallen off the bedding. , And “falling” indicating that the resident 800 has fallen.

In one embodiment, control device 101 generates behavior information of resident 800 associated with each room 900 based on an image captured by camera 105 installed in each room 900. The control device 101 detects, for example, the head of the resident 800 from the image, and based on the detected temporal change in the size of the head of the resident 800, “wakes up” and “gets out” of the resident 800. , “Fall” and “fall” are detected. Hereinafter, a specific example of the generation of the behavior information will be described in more detail.

First, the storage device 120 stores the area where the bed 901 is located in the living room 900, the first threshold Th1, the second threshold Th2, and the third threshold Th3. The first threshold Th1 identifies the size of the resident's head between the lying position and the sitting position in the area where the bed 901 is located. The second threshold value Th2 identifies whether or not the resident is in the standing posture based on the size of the resident's head in the living room 900 excluding the area where the bed 901 is located. The third threshold value Th3 identifies whether or not the resident is in the recumbent posture based on the size of the resident's head in the room RM excluding the area where the bed 901 is located.

The control device 101 extracts a moving body region from the target image as a region of the resident 800 by, for example, the background subtraction method or the frame difference method. The control device 101 further derives from the extracted moving body region by, for example, a circular or elliptical Hough transform, by pattern matching using a prepared head model, and by a neural network learned for head detection. Using the threshold value obtained, the head area of the resident 800 is extracted. The control device 101 detects “wake up”, “get out of bed”, “fall”, and “fall” from the extracted position and size of the head.

The control device 101 determines that the position of the head extracted as described above is within the area where the bed 901 is located, and the size of the head extracted as described above is lying down by using the first threshold Th1. When it is detected that the size of the posture has changed to the size of the sitting posture, it may be determined that the action “wake up” has occurred.

The control device 101 determines that the position of the head extracted as described above has moved from within the area where the bed 901 is located to outside the area where the bed 901 is located, and the size of the head extracted as described above. When it is detected that a certain size has changed to a standing posture size by using the second threshold value Th2, it may be determined that the action “getting out of bed” has occurred.

The control device 101 determines that the position of the head extracted as described above has moved from within the area where the bed 901 is located to outside the area where the bed 901 is located, and the size of the head extracted as described above. If the time changes from a certain size to a recumbent size by using the third threshold value Th3, the action “fall” may be determined to have occurred.

The control device 101 is configured such that the position of the head extracted as described above is located in the living room 900 excluding the area where the bed 901 is located, and the size of the extracted head uses the third threshold Th3. When it is detected that the size has changed from a certain size to the size of the recumbent posture, it may be determined that the action “fall” has occurred.

As described above, in one specific example, the control device 101 of the sensor box 100 generates the behavior information of the resident 800. In the watching system, another element may use the image in the living room 900 to generate the behavior information of the resident 800.

(Management server 200)
The management server 200 includes a control device 201, a ROM 202, a RAM 203, a communication interface 204, a display interface 205, an operation interface 207, and a storage device 220.

(4) The control device 201 controls the management server 200. The control device 201 is composed of, for example, at least one integrated circuit. The integrated circuit includes, for example, at least one CPU, at least one ASIC, at least one FPGA, or a combination thereof.

アンテナ An antenna (not shown) and the like are connected to the communication interface 204. The management server 200 exchanges data with an external communication device via the antenna. The external communication device includes, for example, the sensor box 100.

The display interface 205 is connected to the display 206, and sends out an image signal for displaying an image to the display 206 in accordance with a command from the control device 201 or the like.

The operation interface 207 is, for example, a USB (Universal Serial Bus) terminal, and is connected to the input device 209. Operation interface 207 receives a signal indicating a user operation from input device 209. The input device 209 is, for example, a mouse, a keyboard, a touch panel, or another device capable of receiving a user's input operation.

The storage device 220 is, for example, a storage medium such as a hard disk or an external storage device. In one implementation, the storage device 220 stores a program executed by the control device 201, but the program may be stored in another storage device that can be accessed by the control device 201.

(Mobile terminal 300)
The mobile terminal 300 includes a control device 301, a RAM 303, a communication interface 304, a display 305, an input device 306, and a built-in memory 320.

(4) The control device 301 controls the mobile terminal 300. The control device 301 is composed of, for example, at least one integrated circuit. The integrated circuit includes, for example, at least one CPU, at least one ASIC, at least one FPGA, or a combination thereof.

アンテナ An antenna (not shown) and the like are connected to the communication interface 304. The mobile terminal 300 exchanges data with an external communication device via the antenna and the access point AP (FIG. 1). External communication devices include, for example, the sensor box 100, the management server 200, and the like.

Display 305 is realized by, for example, an organic EL (Electro Luminescence) display. The input device 306 is realized by, for example, a touch sensor superimposed on the display 305. The touch sensor receives various operations on the mobile terminal 300 by a touch operation, and outputs the contents of the operations to the control device 301.

The internal memory 320 is a storage medium such as eMMC (Embedded MultiMediaCard). As an example, the built-in memory 320 stores a program executed by the control device 301, and the program is stored in a storage device other than the built-in memory 320 as long as the storage device is accessible by the control device 301. Is also good.

(Cloud server 400)
The cloud server 400 includes a control device 401, a ROM 402, a RAM 403, a communication interface 404, and a storage device 420.

(4) The control device 401 controls the cloud server 400. The control device 401 is configured by, for example, at least one integrated circuit. The integrated circuit includes, for example, at least one CPU, at least one ASIC, at least one FPGA, or a combination thereof.

アンテナ An antenna (not shown) and the like are connected to the communication interface 404. The cloud server 400 exchanges data with an external communication device via the antenna. The external communication device includes, for example, the sensor box 100 and the management server 200.

The storage device 420 is, for example, a storage medium such as a hard disk or an external storage device. In one implementation, the storage device 420 stores a program executed by the control device 401, but the program may be stored in another storage device that can be accessed by the control device 401.

(Significance of the term "program" in this specification)
In the watching system, various “programs” may not be provided as a single program but may be provided by being incorporated in a part of an arbitrary program. Various “programs” can be realized by cooperation of arbitrary plural programs. In one example, when the control device 101 of the sensor box 100 realizes the function described in the present specification by executing the first program, the first program includes some modules of the second program. May be used. Even if the first program does not include some modules for realizing the function, if the first program mainly contributes to the realization of the function, the first program deviates from the purpose of the program for realizing the function. It does not do. Further, some or all of the functions described in this specification may be realized by dedicated hardware. Furthermore, in an apparatus that provides the functions described in this specification, some or all of the functions may be provided as a so-called cloud service from an external apparatus.

[Functional configuration of watching system]
FIG. 5 is a diagram illustrating an example of a functional configuration of the watching system. In the example illustrated in FIG. 5, the sensor box 100 functions as the data collection unit 11, the behavior detection unit 12, the notification information generation unit 13, the condition adjustment unit 14, and the notification information transmission unit 15. The management server 200 functions as a recording storage unit 21, a condition setting unit 22, a notification information input unit 23, a notification information output unit 24, and a notification information storage unit 25. The mobile terminal 300 functions as the notification information receiving unit 31 and the output unit 32. Hereinafter, each function will be described.

(Data collection unit 11)
The data collection unit 11 collects the resident's biological information. One example of the biological information is image data in the living room 900. In this case, the data collection unit 11 is realized by the camera 105. Another example of the biological information is vital information. In this case, the data collection unit 11 is realized by the vital sensor 540. The biological information can be realized by any information for detecting the behavior of the resident. In this case, the data collection unit 11 can be realized by any sensor for acquiring such information.

(Behavior detector 12)
The behavior detection unit 12 detects the resident's behavior using the biological information collected by the data collection unit 11. In one example, the behavior detecting unit 12 detects the resident's behavior by generating the above-mentioned “behavior information” (wake-up, leaving, falling, and falling). In this example, an action for generating each action information corresponds to an action corresponding to the action information. In the image acquired by the camera 105, the control device 101 determines that the position of the head is within the area where the bed 901 is located, and that the size of the head is reduced from the size of the recumbent posture by using the first threshold Th1. In the example of determining that the action “wake up” has occurred when detecting that the posture has changed to the size of the sitting posture, the action of the resident for the occurrence of the action “wake up” is described as “generating action information. Action to do ". In the example of FIG. 5, the action detection unit 12 is realized by the control device 101.

(Notification information generation unit 13)
The notification information generation unit 13 generates information for notification about the resident using the detection result of the resident's behavior by the behavior detection unit 12. In one example, the notification information generation unit 13 detects the occurrence of a sign of a predetermined action in the resident based on the detection result of the resident's action, and generates the notification information when the omen occurs. Is also good. More specifically, the notification information generation unit 13 determines that a sign of the action “wake-up” has occurred when the behavior “wake-up” has occurred in the resident more than a predetermined number of times within a predetermined time, and Generate notification information about the user. That is, in this example, occurrence of the action “wake up” a predetermined number of times or more within the predetermined time corresponds to a sign of the action “wake up”. In response to the occurrence of the action “wake up” a predetermined number of times or more within the predetermined time, the notification information generation unit 13 determines the occurrence of a sign of the action “wake up” and generates notification information.

(4) The notification information includes, for example, information for identifying a resident in which a sign has occurred. The information specifying the resident may be the ID of the resident or the ID of the sensor box 100 associated with the resident. The notification information may include the type of the sign that has occurred (for example, information that specifies which action (such as “getting out of bed”) the sign is a sign). In the example of FIG. 5, the notification information generation unit 13 is realized by the control device 101.

(Condition adjuster 14)
The condition adjustment unit 14 determines the sensitivity of at least one of the action detection unit 12 and the notification information generation unit 13 in accordance with the status of the resident (for example, at least one of the status of the resident itself and the status of the facility where the resident moves in). To adjust. In the example of FIG. 5, the condition adjusting unit 14 is realized by the control device 101.

The condition adjusting unit 14 may adjust the sensitivity of the action detection unit 12 by adjusting the condition for the action detection unit 12 to generate the action information. In one example, the condition adjustment unit 14 limits the sensitivity of the action detection unit 12 by limiting the “location area of the bed 901” for determining the occurrence of the action “wake up” to “a partial area of the bed 901”. Lower. In this example, even if the position of the resident's head is within the area where the bed 901 is located, but outside the “partial area”, it is not determined that the action “wake up” has occurred. . That is, the range of the situation in which the action “wake up” is detected by the action detection unit 12 is narrowed. In another example, the condition adjustment unit 14 increases the sensitivity of the action detection unit 12 by changing the value of the first threshold Th1 for determining the occurrence of the action “wake up”. In this example, the first threshold Th1 is changed so that the action “wake up” is detected in more situations. The magnitude of the change in the size of the head specified in the image may vary with the magnitude of the change in the distance between the camera 105 and the resident's head. In this sense, changing the first threshold Th1 may correspond to changing the moving distance of the resident's head necessary for detecting the occurrence of the action “wake up”. That is, the condition adjustment unit 14 can adjust the sensitivity of the activity detection unit 12 by changing the moving distance of the resident's head necessary for detecting the occurrence of the activity “wake up”.

The condition adjusting unit 14 may adjust the sensitivity of the notification information generating unit 13 by adjusting the condition for the notification information generating unit 13 to generate the notification information. In one example, the condition adjusting unit 14 may reduce the number of occurrences of the action “wake up” within a predetermined time period necessary to generate the notification information. Thereby, notification information is generated in more situations. Therefore, the sensitivity of the notification information generation unit 13 increases. On the other hand, the condition adjusting unit 14 may increase the number of occurrences. Thereby, the situation where the notification information is generated is further reduced. Therefore, the sensitivity of the notification information generation unit 13 decreases. Here, “the number of times required to generate notification information” is an example of satisfying a predetermined condition for generating notification information.

の一 An example of the resident's situation that is the basis of the sensitivity adjustment is the elapsed time from the previous excretion time of the resident. The excretion time may be obtained from the nursing care record, or may be obtained from a database that manages the detection results of sensors such as the toilet sensor 520. More specifically, condition adjustment unit 14 may adjust the sensitivity based on the excretion time and a given excretion interval.

In one example, if the elapsed time from the previous excretion time is less than half (for example, 1.5 hours) of a given excretion interval (for example, 3 hours), the action detection unit 12 and / or the notification information generation unit 13 Is low, and the sensitivity of the action detection unit 12 and / or the notification information generation unit 13 is high if the time is equal to or longer than the half time. The excretion interval can be appropriately updated by machine learning or deep learning using history information such as the excretion time of each resident (and history information of other occupants). The threshold for switching the sensitivity (the half time) may itself be changed according to the situation of each resident (for example, the time and / or amount of water intake). For example, if the water intake after the last excretion time is equal to or more than a given amount, the threshold value may be set to a time shorter than the “half time” (for example, one hour). In this case, the sensitivity is low if the elapsed time is less than 1 hour, and the sensitivity is high if the elapsed time is 1 hour or more. The sensitivity may be set from three or more stages according to the occupant's situation.

の他 Another example of a resident's situation is the degree of care required by the resident. The condition adjustment unit 14 reads, for example, the degree of care required of each resident from the care record of each resident. The condition adjusting unit 14 sets a higher sensitivity as the degree of need for nursing care of the resident is higher.

さらに Still another example of a resident's situation is a past wake-up time. The condition adjustment unit 14 may set the sensitivity based on the relationship between the current time and the resident's past wake-up time. In one example, the condition adjustment unit 14 sets a high sensitivity in a time zone from a given time before the current wake-up time of the resident to a given time after the wake-up time in the past, and Set a low sensitivity at other times. Thereby, a higher sensitivity can be set in a time zone in which the resident is likely to excrete than in a time zone in which the probability is low.

Specifically, when the resident's past wake-up time is 6:00, the condition adjusting unit 14 determines that the time from 5:00 60 minutes before the wake-up time to 6:30 30 minutes after the wake-up time. A high sensitivity is set in the time zone of, and a low sensitivity is set in other time zones. The length of time from the wake-up time for defining such a time zone can be determined, for example, by machine learning using the relationship between the wake-up time and the excretion time of the resident and / or other occupants. Alternatively, it can be appropriately changed based on deep learning.

さらに Yet another example of a resident situation is a management system for facilities where the resident moves. In one example, the condition adjustment unit 14 sets a high sensitivity when the number of staffs working at the facility is equal to or more than a given value, and sets a low sensitivity when the number is less than the given value. Staff numbers can vary throughout the day. The condition adjusting unit 14 may change the sensitivity to be set in accordance with a change in the number of staff members working.

As described above, the sensitivity is adjusted according to the resident's situation, such as the elapsed time from the previous excretion time of the resident, so that when the need for notification is low, the notification is suppressed by the low sensitivity, and If the need is high, the high sensitivity can more reliably prevent missed notification opportunities.

(Notification information transmission unit 15)
The notification information transmission unit 15 transmits the notification information generated by the notification information generation unit 13 to a device (a mobile terminal 300 in the example of FIG. 5) that outputs a notification related to the notification information. In the example of FIG. 5, the notification information transmitting unit 15 transmits the notification information to the management server 200 functioning as a device that relays the notification information. Information (for example, sensor box ID) for specifying the sensor box 100 that is the transmission source of the notification information may be given. The notification information transmitting unit 15 can transmit the notification information to each of the two or more mobile terminals 300. In the example of FIG. 5, the notification information transmitting unit 15 is realized by the communication interface 104.

(Record storage unit 21)
The record storage unit 21 stores information such as a care record of each resident. The nursing care record includes at least one type of information of the resident's degree of nursing care, a history of the resident's excretion time, wake-up time, leaving time, falling time, and falling time. In the example of FIG. 5, the record storage unit 21 is realized by the storage device 220.

(Condition setting unit 22)
The condition setting unit 22 receives an input of information that can be a condition for the condition adjusting unit 14 to set the sensitivity. The input information may be the resident's excretion time, the resident's moisture intake time and amount, the resident's need for nursing care, or the resident's It may be a facility management system. In the example of FIG. 5, the condition setting unit 22 is realized by the operation interface 207. The condition setting unit 22 may be realized by a terminal (for example, a time clock) that manages the attendance of staff.

(Notification information input unit 23)
The notification information input unit 23 receives the notification information transmitted from the notification information transmission unit 15. In the example of FIG. 5, the notification information input unit 23 is realized by, for example, the communication interface 204.

(Notification information output unit 24)
The notification information output unit 24 outputs the notification information received by the notification information input unit 23 to the portable terminal 300 that should receive the notification information. By including the notification information input unit 23 and the notification information output unit 24, the management server 200 functions as a device that relays the transmission of notification information from the sensor box 100 to the mobile terminal 300.

では In one example, the watching system includes a plurality of sensor boxes 100 and a plurality of mobile terminals 300. Each sensor box 100 is associated with each resident. Each mobile terminal 300 is associated with each staff. Information relating each resident to one or more staff (resident-staff correspondence information) is stored in any device in the watching system. The notification information output unit 24 specifies the sensor box 100 that is the transmission source of the notification information received by the notification information input unit 23, specifies the resident associated with the specified sensor box 100, and associates the resident with the resident. One or more staff members specified are specified, and one or more mobile terminals 300 associated with the specified one or more staff members are specified. Then, the notification information output unit 24 transmits the notification information received by the notification information input unit 23 to the specified portable terminal 300. In the example of FIG. 5, the notification information output unit 24 is realized by, for example, the control device 201 and the communication interface 204.

(4) The notification information output unit 24 further registers the notification information transmitted to the mobile terminal 300 in a notification information storage unit 25 described below.

(Notification information storage unit 25)
The notification information storage unit 25 stores the notification information transmitted to the mobile terminal 300. In the example of FIG. 5, the notification information output unit 24 also transmits the notification information to be transmitted to the mobile terminal 300 to the notification information storage unit 25. In the example of FIG. 5, the notification information storage unit 25 is realized by, for example, the storage device 220. That is, the notification information storage unit 25 stores information for specifying when and for which resident the notification information is generated.

The information stored in the notification information storage unit 25 can be used by other elements in the watching system. For example, the notification information generating unit 13 may change the generation mode of the notification information for a certain resident according to the history of the notification information generated for the resident.

(Notification information receiving unit 31)
The notification information receiving unit 31 receives the notification information transmitted from the notification information storage unit 25. In the example of FIG. 5, the notification information receiving unit 31 is realized by the communication interface 304.

(Output unit 32)
The output unit 32 outputs a notification related to the notification information in response to the notification information receiving unit 31 receiving the notification information. An example of the notification output is display of information for identifying a resident. The output of the notification may be an audio output, vibration of a housing, or a combination thereof.

[Specific example of sensitivity adjustment]
FIG. 6 is a diagram for explaining two sensitivities related to generation of notification information by the notification information generation unit 13. FIG. 6 shows (A) a high sensitivity state and (B) a low sensitivity state. In both (A) and (B), the item “wake-up detection” indicates the timing at which the action detection unit 12 detects the action “wake-up”. The item “notification information generation” indicates the timing at which the notification information generation unit 13 generates notification information.

(A) In the high sensitivity state, the notification information generation unit 13 generates notification information when the action “wake up” occurs five times during the time T. On the other hand, in the (B) low-sensitivity state, the notification information is generated when the action “wake up” occurs ten times during the time T. That is, in the (B) low-sensitivity state, the number of actions “wake up” required to generate the notification information is larger than in the (A) high-sensitivity state.

[Processing by Behavior Detection Unit 12]
FIG. 7 is a flowchart of an example of a process executed by the action detection unit 12. The process in FIG. 7 is realized, for example, by the control device 101 executing a given program.

As shown in FIG. 7, in step S10, the control device 101 determines whether the action “wake up” has occurred, and repeats the control in step S10 until it determines that the action “wake up” has occurred ( When it is determined that the action “wake up” has occurred (YES in step S10), the control proceeds to step S12.

In step S12, the control device 101 registers the event (the occurrence of the action "wake up") and the time at which the action "wake up" is determined to have occurred in the wakeup record, and then returns the control to step S10. The wakeup record is, for example, information stored in a storage device such as the storage device 120, and is information regarding a resident associated with the sensor box 100 in which the control device 101 is mounted.

As described above, in the processing described with reference to FIG. 7, when it is determined that the action “wake up” has occurred, the event corresponding to the action “wake up” and the time when the occurrence of the action “wake up” is detected Is registered in association with the resident.

[Processing by Notification Information Generating Unit 13]
FIG. 8 is a flowchart of an example of a process performed by the notification information generation unit 13. The process of FIG. 8 is realized, for example, by the control device 101 executing a given program.

制御 As shown in FIG. 8, in step S20, control device 101 reads out the sensitivity setting. The sensitivity setting is stored in a storage device that can be accessed by the control device 101, such as the storage device 120. In one example, the sensitivity setting defines one of a high sensitivity state and a low sensitivity state as the sensitivity state of the action detection unit 12 and the notification information generation unit 13. When the control device 101 determines that the sensitivity setting is in the high sensitivity state, the control proceeds to step S22, and when it determines that the sensitivity setting is in the low sensitivity state, the control proceeds to step S24.

In steps S22 and S24, the control device 101 sets the value of the variable X used for generating the notification information, and then advances the control to step S26. The variable X is the number of occurrences of the action “wake up” required to generate the notification information described with reference to FIG. In step S22, control device 101 sets “5” as the value of variable X. In step S24, control device 101 sets “10” as the value of variable X.

In step S26, the control device 101 determines whether or not the occurrence of the action “wake up” has been detected X times at the latest time T by referring to the wakeup record mentioned for the processing in FIG. . If the control device 101 determines that the occurrence of the action “wake up” has been detected X times or more in the latest time T (YES in step S26), the control proceeds to step S28, otherwise (NO in step S26). ), Control is returned to step S20.

In step S28, after generating the notification information, the control device 101 returns the control to step S20. The generated notification information includes information for identifying the resident in which the occurrence of the action “wake up” has been detected X times or more in the latest time T.

The process of FIG. 8 described above is an example in which the sensitivity of the notification information generation unit 13 is adjusted according to the sensitivity setting. As described above, the target whose sensitivity is to be adjusted may be the behavior detection unit 12. In this case, for example, the control device 101 functioning as the action detection unit 12 detects the occurrence of the action “wake up” with high sensitivity in the high sensitivity state, and detects the occurrence of the action “wake up” with low sensitivity in the low sensitivity state. To detect.

The process of FIG. 8 adjusts the number of occurrences of the action “wake up” within the time T required to generate the notification information, as adjustment of the sensitivity of the notification information generation unit 13. The sensitivity of the notification information generator 13 may be adjusted in another manner.

[Processing by Condition Adjustment Unit 14]
FIG. 9 is a flowchart of an example of a process executed by the condition adjusting unit 14. The process of FIG. 9 is a process of managing the sensitivity setting, and is realized, for example, by the control device 101 executing a given program.

As shown in FIG. 9, in step S30, the control device 101 refers to the nursing care record of the resident to determine whether 1.5 hours (90 minutes) have elapsed since the previous excretion of the resident. It is determined whether or not it is, and if so (YES in step S30), the control proceeds to step S32; otherwise (NO in step S30), the control proceeds to step S34.

にて At step S32, control device 101 updates the value of the sensitivity setting to “high sensitivity state”, and then returns control to step S30.

にて At step S34, control device 101 updates the sensitivity setting value to “low sensitivity state”, and then returns control to step S30.

According to the processing of FIG. 9 described above, the value of the sensitivity setting until 1.5 hours elapses from the last excretion of the resident is “low sensitivity state”, and the value of 1. After 5 hours, the value of the sensitivity setting is “low sensitivity state”.

In the example of FIG. 9, the sensitivity is set according to the elapsed time from the previous excretion of the resident. The setting of the sensitivity may be set according to other conditions (for example, the degree of nursing care required, the resident's past wake-up time, and / or the number of staff working at the facility).

[Modified Example of Functional Configuration of Watching System]
Each function shown in FIG. 5 can be realized by any hardware resources. The same function may be realized by a plurality of hardware resources. Two or more functions described as being realized by the same hardware resource in FIG. 5 need not necessarily be realized by the same hardware resource. For example, the condition adjusting unit 14, the action detecting unit 12, and the notification information generating unit 13 may be realized by different hardware resources. Each of FIGS. 10 to 15 is a diagram showing a modification of the function distribution of the components of the watching system.

In the example of FIG. 10, the condition adjusting unit 14 is realized by the management server 200 (control device 201) as compared with the example of FIG. In the example of FIG. 10, the management server 200 determines the behavior of the action detection unit 12 and the notification information generation unit 13 for each of the plurality of sensor boxes 100 in the watching system according to the status of the resident associated with each sensor box 100. At least one sensitivity is set, and the sensitivity of at least one of the action detection unit 12 and the notification information generation unit 13 of each sensor box 100 is controlled according to the setting.

In the example of FIG. 11, the condition adjusting unit 14 is realized by the cloud server 400 (control device 401) as compared with the example of FIG. The control device 401 reads information as appropriate from the record storage unit 21 and / or the condition setting unit 22 by communicating with the management server 200, and functions as the condition adjusting unit 14.

The information may be uploaded from the management server 200 to the cloud server 400, and the control device 401 may function as the condition adjusting unit 14 by using the uploaded information. The control device 201 of the management server 200 transmits the information stored in the record storage unit 21 and / or the information input to the condition setting unit 22 to the cloud server 400 at regular time intervals or every time the information is updated. You may upload to.

In the example of FIG. 12, the action detection unit 12 and the notification information generation unit 13 are realized by the control device 301 of the mobile terminal 300, as compared with the example of FIG.

In the example of FIG. 12, the management server 200 further functions as the information relay unit 26. The information relay unit 26 receives the biological information output from the sensor box 100 (the data collection unit 11), and transmits the biological information to the mobile terminal 300 associated with the sensor box 100. Each sensor box 100 and each mobile terminal 300 are associated, for example, in the resident-staff correspondence information described above.

In the example of FIG. 12, at least one of the functions of the action detection unit 12, the notification information generation unit 13, and the output unit 32 includes a notification application (hereinafter, appropriately referred to as “ Notification application ”).

The notification application receives the resident's biometric information input from the sensor box 100 (data collection unit 11) via the management server 200, and generates behavior information using the biometric information. 12 functions are realized. The notification application realizes the function of the notification information generation unit 13 by generating notification information using the activity information generated by the activity detection unit 12. The notification application realizes the function of the output unit 32 by outputting a notification according to the notification information generated by the notification information generation unit 13. In the example of FIG. 12, among the plurality of mobile terminals 300 in the watching system, only the notification information generation unit 13 (control device 301) of one mobile terminal 300 generates notification information, and the notification information generation unit 13 The notification information may be distributed to another mobile terminal 300.

In the example of FIG. 12, the notification information generation unit 13 outputs the notification information to the output unit 32 and transmits the notification information to the notification information storage unit 25.

では In the example of FIG. 13, the action detection unit 12 is realized by the sensor box 100 (control device 101), as compared with the example of FIG. In the example of FIG. 13, when the management server 200 communicates with the sensor box 100, the condition adjustment unit 14 adjusts the sensitivity of the action detection unit 12, and when the management server 200 communicates with the mobile terminal 300, the condition adjustment unit 14 adjusts the sensitivity of the notification information generation unit 13. In the example of FIG. 13 as well, the control device 301 may realize at least one of the notification information generation unit 13 and the output unit 32 by executing the notification application installed on the mobile terminal 300.

In the example of FIG. 14, the portable terminal 300 (control device 301) further functions as the condition adjusting unit 14 as compared with the example of FIG. The condition setting unit 22 is realized by the input device 306 of the mobile terminal 300. In the example of FIG. 14, each staff can use the condition setting unit 22 to input information that can be a condition for the condition adjusting unit 14 to set the sensitivity. Information input by each staff member can be shared among the plurality of mobile terminals 300 by communication between the mobile terminals 300.

The record storage unit 21 is realized by the storage device 420 of the cloud server 400. Information of the resident in the watching system can be uploaded to the cloud server 400 from various devices such as the sensor box 100 and the management server 200.

In the example of FIG. 15, the management server 200 functions as the notification information generation unit 13, the condition adjustment unit 14, and the notification information transmission unit 15 as compared with the example of FIG. The notification information generation unit 13 receives the biological information from each sensor box 100, and generates notification information corresponding to the sensor box 100 that is the transmission source of the biological information using the biological information. The notification information transmitting unit 15 transmits the generated notification information to the mobile terminal 300 corresponding to the sensor box 100 corresponding to the notification information. The correspondence between the sensor box 100 and the portable terminal 300 is based on, for example, the correspondence between the resident and the staff in the resident-staff correspondence information.

In the example of FIG. 15, the notification information transmitting unit 15 further registers the notification information transmitted to the mobile terminal 300 in the notification information storage unit 25.

各 Each embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims. Further, it is intended that the inventions described in the embodiments and the respective modified examples are implemented alone or in combination as much as possible.

11 data collection unit, 12 action detection unit, 13 notification information generation unit, 14 condition adjustment unit, 15 notification information transmission unit, 21 record storage unit, 22 condition setting unit, 31 notification information reception unit, 32 output unit, 100, 100A , 100B {sensor box, 101, 201, 301, 401} control device, 104, 204, 304, 404 {communication interface, 105} camera, 106 {Doppler sensor, 107} wireless communication device, 120, 220, 420 {storage device, 200} management server, 205 Display interface, 206, 305 display, 207 operation interface, 209, 306 input device, 300, 300A, 300B portable terminal, 320 built-in memory, 400 cloud server, 500, 500A, 50 B Care call slave unit, 501 Care call button, 510,510A, 510B Door sensor, 520,520A, 520B Toilet sensor, 530,530A, 530B Sensor, 540,540A, 540B Vital sensor, 800,800A, 800B Resident, 900, 900A, 900B living room, 901, 901A, 901B bed, 902, 902A, 902B toilet, 903, 903A, 903B furniture.

Claims

Generating means for generating information for notifying the occurrence of a sign of a predetermined action by the watching target based on the watching target action information;
Output means for outputting a notification about the information generated by the generation means,
An information processing apparatus comprising: an adjustment unit that adjusts the sensitivity of the generation of the information by the generation unit according to the situation of the watching target.
The generation means,
Detection means for detecting occurrence of an action corresponding to the action information using biological information of a watching target,
When the occurrence of the action satisfies a predetermined condition, the determining means for determining the occurrence of the sign,
The adjustment means adjusts at least one of sensitivity of detection of occurrence of the behavior by the detection means and sensitivity of determination of occurrence of the sign by the determination means, thereby adjusting sensitivity of generation of the information. Item 2. The information processing device according to item 1.
3. The information processing apparatus according to claim 2, wherein adjusting the detection sensitivity of the occurrence of the action includes adjusting a movement distance of the watching target, which is a condition for the occurrence of the action.
The method according to claim 2, wherein adjusting the sensitivity of the determination of the occurrence of the sign includes adjusting the number of times of the action within a predetermined time required for determining the occurrence of the sign. Information processing device.
(5) The information processing apparatus according to any one of (1) to (4), wherein the situation includes an attribute of a watching target.
6. The information processing apparatus according to claim 5, wherein the attribute includes at least one of a latest excretion time, a degree of need for nursing care, and a past wake-up time.
The information processing apparatus according to any one of claims 1 to 6, wherein the situation includes a management system of a facility where the watching target is moved in.
An information processing apparatus according to claim 2,
A sensor box comprising: a sensor for acquiring the biological information.
A program executed by a computer,
The program is stored in the computer,
Based on the activity information of the watching target, a step of generating notification information about the watching target when a sign of a predetermined action by the watching target occurs,
Outputting the information of the notification,
A program, wherein the sensitivity of generating the notification information is adjusted according to the situation of the watching target.
The sensitivity of the generation of the notification information is adjusted by adjusting at least one of the detection sensitivity of the occurrence of the action corresponding to the action information, and the sensitivity of determining the occurrence of the sign based on the occurrence of the action. The program according to claim 9, wherein the program is executed.