JP2023070989A - Information processing method, information processing device and program - Google Patents

Abstract

To provide an information processing method, etc. determining and presenting a state relating to an end-of-life care of a monitoring object person lying in a bed.SOLUTION: A computer acquires biological information from a bed sensor that detects the biological information of a monitoring object person lying in a bed. The computer determines a state relating to an end-of-life care of the monitoring object person based on the acquired biological information. The computer outputs end-of-life care information relating to the end-of-life care of the monitoring object person based on the determination result.SELECTED DRAWING: Figure 1

Description

The present application relates to an information processing method, an information processing apparatus, and a program.

In nursing care facilities, a system is being introduced that monitors the condition of a care recipient using various sensors and promptly notifies nursing care staff when a situation requiring nursing care occurs. Patent Literature 1 discloses a system that determines whether a person to be watched over on a bed is lying down or sitting by detecting a heat radiation area on the bed using an infrared sensor. In the system disclosed in Patent Document 1, by determining the posture of the person being watched over on the bed, it can be detected at an early stage that the person being watched over will perform a dangerous action on the bed, and an accident around the bed can be prevented. It is possible to prevent

Japanese Patent No. 6582305

On the other hand, in nursing care facilities, nursing care staff regularly observe whether or not there are any signs of dying when the person being cared for (person to be watched over) approaches the end of life. It is difficult to reduce the burden of Therefore, there is a demand for a system that detects and notifies the care recipient who is about to die of signs of dying. However, the system disclosed in Patent Literature 1 is not supposed to observe the patient's dying state, and cannot detect the appearance of dying signs.

The present disclosure has been made in view of such circumstances, and the purpose thereof is to provide an information processing method, etc., capable of determining and presenting a state related to the end-of-life care of a person to be monitored lying in bed. to do.

An information processing method according to an aspect of the present invention acquires the biological information from a bed sensor that detects the biological information of a monitoring subject lying on a bed, and performs end-of-life care of the monitoring subject based on the acquired biological information. The computer executes a process of judging the state and outputting end-of-life information regarding the end-of-life care of the person to be monitored according to the judgment result.

According to one aspect of the present invention, it is possible to determine and present a state related to the end-of-life care of a monitoring subject lying on a bed.

1 is an explanatory diagram showing a configuration example of an information processing system; FIG. 3 is a block diagram showing a configuration example of a server and staff terminals; FIG. FIG. 4 is an explanatory diagram showing an example of record layouts of a monitored person DB, a sensor data DB, and an event DB; FIG. 9 is an explanatory diagram showing an example of a notification screen; FIG. 5 is an explanatory diagram showing an example of an operation menu; FIG. 10 is an explanatory diagram showing an example of a personal screen; FIG. 11 is a flowchart illustrating an example of a notification screen update processing procedure; FIG. FIG. 11 is an explanatory diagram showing another screen example of alert history; It is a flowchart which shows an example of the setting process procedure of the temporary stop of end-of-life mode. FIG. 11 is an explanatory diagram showing another screen example of a room list; FIG. 12 is a flowchart illustrating an example of a notification screen updating process procedure according to the second embodiment; FIG. It is a flowchart which shows an example of the recommendation processing procedure of end-of-life mode. FIG. 11 is an explanatory diagram showing another screen example of a room list; FIG. 4 is an explanatory diagram showing a configuration example of a learning model; FIG. 16 is a flow chart showing an example of a procedure for updating a notification screen according to the fourth embodiment; FIG.

An information processing method, an information processing apparatus, and a program according to the present disclosure will be described in detail below based on drawings showing embodiments thereof.

(Embodiment 1)
FIG. 1 is an explanatory diagram showing a configuration example of an information processing system. In this embodiment, the state of care recipients such as the elderly and the physically handicapped living in each room in a facility such as a nursing facility or medical facility is monitored, and the situation in which nursing care is required by nursing care staff is monitored. An information processing system that notifies care staff when it is detected will be described. In the following description, the cared person is called a monitoring target person, and the occurrence of a situation requiring nursing care by a care staff is called the occurrence of an event.

The information processing system of this embodiment includes a server 10, a sensor I/F (InterFace) device 20, a staff terminal 30, and the like. It is The network N may be the Internet or a LAN (Local Area Network) provided in a nursing facility.

The sensor I/F device 20 is provided, for example, for each person to be monitored. A type of sensor is connected. In the example shown in FIG. 1, bed sensor 21, toilet sensor 22, door sensor 23, environment sensor 24, human sensor 25, and call button 26 are connected to sensor I/F device 20 by wire or wirelessly. The sensor I/F device 20 is an information processing device that acquires signals from the sensors 21 to 25 and the call button 26 and transmits the acquired signals to the server 10 via the network N. When any one of the sensors 21 to 25 outputs an analog signal, the sensor I/F device 20 has a configuration for performing A/D conversion. Send to

The sensor I/F device 20, the sensors 21 to 25, and the call button 26 are provided, for example, in the room (living room) where the monitored person lives. 20, sensors 21 to 25 and call button 26 are provided. For example, a plurality of sensor I/F devices 20 may be provided for one person to be monitored, and the bed sensor 21 and toilet sensor 22 may be connected to separate sensor I/F devices 20 . Alternatively, a plurality of environment sensors 24 or a plurality of motion sensors 25 may be provided for one person to be monitored, and the plurality of sensors 24 and 25 may be connected to one sensor I/F device 20 . The sensor I/F device 20 may be appropriately arranged at a position corresponding to the installation location of each sensor 21 to 25 and call button 26, and may be built in each sensor 21 to 25 and call button 26. . Although FIG. 1 shows only the sensor I/F device 20 for the monitored person B, the sensors 21 to 25 and the call button 26 are also connected to the sensor I/F device 20. .

One bed sensor 21 is installed on the bed of one person to be monitored. The bed sensor 21 is, for example, a sheet sensor, installed between a bed mattress and a sheet, and detects the pulse (heartbeat), respiration, body movement, body temperature, etc. of the monitoring subject lying on the bed. The bed sensor 21 detects, for example, the air pressure in the air mattress, thereby detecting the heart rate, respiratory state, and body motion state of the person to be monitored while in bed (during sleep). The bed sensor 21 is composed of conductive fabric and a plurality of piezoelectric elements, and detects the heart rate, respiratory state, and body movement state of the monitoring subject by detecting periodic minute vibrations. may be configured. Alternatively, the bed sensor 21 may be a sensor that is installed at the bedside of the bed or on the wall of the room and detects the pulse, respiration, body movement, body temperature, etc. of a person lying on the bed using microwaves or infrared rays. Based on the detected signals, the bed sensor 21 detects the body movement of the monitoring subject, the state of occurrence of apnea, the depth of sleep, the state of occurrence of midway awakening (a state in which sleep is interrupted and is in an awake state), heart rate, Sleep data (biological information) such as respiratory rate and body temperature is analyzed and output to the sensor I/F device 20 . Moreover, the bed sensor 21 may further have a configuration capable of detecting the blood pressure and oxygen saturation (blood oxygen concentration) of the monitoring subject. In this embodiment, when the server 10 acquires sleep data (biological information) as described above detected by the bed sensor 21 via the sensor I/F device 20, the monitored person is in bed. If it becomes impossible to obtain the information, it is determined that the person to be monitored has left the bed (leaving the bed). That is, the server 10 of the present embodiment determines whether or not the person to be monitored has left the bed based on the biological information of the person to be monitored detected by the bed sensor 21 .

The toilet sensor 22 is a sensor installed in the toilet provided in the living room of the person to be monitored, and detects that the toilet is in use. The toilet sensor 22 can be, for example, a sensor that detects seating on the toilet (toilet seat) or a motion sensor that detects the movement of a person in the toilet. A detection signal indicating the detection result (toilet in use) is output to the sensor I/F device 20 . The door sensor 23 is a sensor installed on the door for the person to be monitored to go in and out of the living room, and detects the opening and closing of the door or the passage of a person through the door. When the door sensor 23 detects that the door is opened or closed or that a person has passed through the door, the door sensor 23 outputs a detection signal indicating the detected state to the sensor I/F device 20 .

The environmental sensor 24 is a sensor that measures environmental data such as the temperature and humidity in the living room of the person to be monitored. The environment sensor 24 is installed, for example, on the wall surface of the living room. The environmental sensor 24 outputs environmental data such as measured temperature and humidity to the sensor I/F device 20 . The motion sensor 25 is a sensor that detects motion of a person in the living room of the person to be monitored. do. The human sensor 25 is installed, for example, on the wall surface of a living room. When the motion of a person is detected, the human sensor 25 outputs to the sensor I/F device 20 a detection signal indicating that there is a person in the living room.

The call button 26 is a button that is manually operated when the person to be monitored desires help on his or her own judgment, and is installed, for example, on the wall of the room of the person to be monitored. The call button 26 outputs a detection signal indicating the operation to the sensor I/F device 20 when operated by the person to be monitored.

In this embodiment, a sensor I/F device 20, sensors 21 to 25, and a call button 26 are provided for each person to be monitored. , is associated with a person to be monitored. In addition to such a configuration, when one sensor 21 to 25 is installed in a place where there is a possibility of detecting a plurality of persons to be monitored, face authentication or ID (IDentification) tags can be used together. , a configuration may be provided for specifying the person to be monitored detected by each of the sensors 21 to 25. FIG.

The sensor I/F device 20 acquires signals from the sensors 21 to 25 and the call button 26, and transmits information corresponding to the acquired signals (information indicating the state of the monitored person) to the server 10 via the network N. do. The server 10 is provided in, for example, a care facility and managed by a care provider using the information processing system of the present embodiment. Note that the server 10 may be a server managed by a business operator that provides the information processing system of the present embodiment to nursing care facilities. The server 10 is an information processing device capable of various information processing and transmission/reception of information, and is, for example, a server computer, a personal computer, or the like. The server 10 accumulates the information of the monitored person sequentially received from the sensor I/F device 20 provided for each monitored person, and when a situation (event) requiring nursing care occurs, the nursing care staff to notify the staff terminal 30 of the occurrence of the event.

The staff terminal 30 is an information terminal used by nursing staff of a nursing facility, and is, for example, a personal computer. The staff terminal 30 may be a portable communication terminal such as a smart phone, a tablet terminal, or a notebook computer. The staff terminal 30 has a display unit 36 (see FIG. 2), and displays the notification information received from the server 10 to notify the care staff of the status of each monitored person and the event that has occurred.

FIG. 2 is a block diagram showing a configuration example of the server 10 and the staff terminal 30. As shown in FIG. The staff terminal 30 has a control section 31, a main storage section 32, an auxiliary storage section 33, a communication section 34, an input section 35, a display section 36, etc., and these sections are connected via a bus. The control unit 31 includes one or more processors such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), or a GPU (Graphics Processing Unit). The control unit 31 reads the program 33P stored in the auxiliary storage unit 33 into the main storage unit 32 and executes it, thereby executing information processing and control processing that the staff terminal 30 should perform.

The main storage unit 32 is a temporary storage area such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), flash memory, etc., and temporarily stores data generated when various programs 33P are executed by the control unit 31. Remember. The auxiliary storage unit 33 is a nonvolatile storage area such as a flash memory, hard disk, SSD (Solid State Drive), etc., and stores various programs 33P (program products) executed by the control unit 31 and various data. The program 33P and various data may be written to the auxiliary storage unit 33 at the manufacturing stage of the staff terminal 30, and the control unit 31 downloads them from another device via the communication unit 34 and stores them in the auxiliary storage unit 33. may The auxiliary storage unit 33 may be another storage device connected to the staff terminal 30 .

The communication unit 34 is a communication module for performing processing related to wired communication or wireless communication, and transmits and receives information to and from other devices via the network N. The input unit 35 receives an operation input by the care staff and sends a control signal corresponding to the operation content to the control unit 31 . The display unit 36 is a liquid crystal display, an organic EL display, or the like, and displays various information according to instructions from the control unit 31 . A part of the input unit 35 and the display unit 36 may be a touch panel integrally configured.

In addition to the configuration described above, the staff terminal 30 of this embodiment includes a microphone that collects surrounding sounds and generates digital audio data, a speaker that outputs messages or warning sounds according to instructions from the control unit 31, and earphones. Or you may have headphones.

The server 10 has a control unit 11, a main storage unit 12, an auxiliary storage unit 13, a communication unit 14, etc., and these units are connected via a bus. Since the above-described units 11 to 14 of the server 10 have the same configuration as the units 31 to 34 of the staff terminal 30, description of the configuration will be omitted. In addition to various programs 13P (program products) executed by the control unit 11, the auxiliary storage unit 13 of the server 10 stores a monitored person DB 13a, a sensor data DB 13b, and an event DB 13c. The monitored person DB 13a is a database that stores information about a monitored person in this system. The sensor data DB 13b is a database that stores the state of the monitored person detected by the sensors 21 to 25 and the operation state of the call button 26. FIG. The event DB 13c is a database that stores information about events that have occurred with respect to each monitored person. The monitoring subject DB 13a, the sensor data DB 13b, and the event DB 13c may be stored in another storage device with which the server 10 can communicate via the network N.

In this embodiment, the server 10 may be a multicomputer consisting of a plurality of computers, a virtual machine virtually constructed by software, or a cloud server. In addition to the configuration described above, the server 10 may have an input unit for receiving operation input, a display unit such as a liquid crystal display or an organic EL display, and the like. The server 10 also includes a reading unit that reads a non-temporary computer-readable portable storage medium 10a. good too. Also, the program 13P may be executed on a single computer, or may be executed on a plurality of computers interconnected via a network N.

FIG. 3 is an explanatory diagram showing an example of record layouts of the monitored person DB 13a, the sensor data DB 13b, and the event DB 13c. The monitored person DB 13a includes a subject ID column, a name column, an age column, a sex column, a room number column, an alert setting column, a star setting column, an operation mode column, and a real-time information column. The target person ID column stores an ID uniquely assigned to the monitoring target person. The name column, age column, gender column, and room number column store the name, age, sex, and room number of the monitoring subject in association with the subject ID. The alert setting column stores information (for example, event name, event identification information) of an event that should be notified (alert output) to the care staff among the events that have occurred in the monitored person. Note that the alert setting may be configured so that it can be set for each time period, and in this case, the alert setting column includes each time period and the event to be notified to the care staff when it occurs in each time period. Information is stored in association with the information. The alert settings are set by the care staff according to the condition of the monitoring subject, for example, when the monitoring subject moves into a nursing care facility. The star setting column stores setting information indicating whether or not the monitored person is treated as a focused person (star). A target person is a monitoring target person who needs to be more careful in nursing care than other monitoring target people. be. Note that the star setting may be set by the nursing staff when the monitored person moves into a nursing care facility, or when the monitored person's condition changes after moving in, for example. The server 10 may automatically set according to the name of the disease, the condition of the disease, and the like. The operation mode column stores information on the operation mode set for the person to be monitored. In the information processing system of the present embodiment, as operation modes, there is a monitoring mode (normal mode) in which the state of the person being monitored or the state of the surroundings of the person being monitored is monitored based on the detection results of the sensors 21 to 25; A terminal care mode is provided to monitor signs of death (conditions related to end-of-life care) based on the detection results of 21. Therefore, "normal" or "end-of-life" is stored in the operation mode column as information on the operation mode. The setting of the operation mode is performed by the care staff according to the condition of the person to be monitored. The real-time information string stores information indicating the real-time status of the person being monitored, and specifically includes a status string, a heart rate/breathing string, and the like. The status column stores status information indicating the status (event) of the monitored person. The status information indicates the state of the person to be monitored or the state of the surroundings of the person to be monitored determined from the detection results of the sensors 21 to 25 . The heartbeat/breathing train stores the heart rate and breathing rate of the monitored person for one minute, for example. The control unit 11 of the server 10 updates each column of the real-time information column based on the information acquired from each of the sensors 21 to 25 via the sensor I/F device 20. FIG. In addition to the columns described above, the real-time information column may include a temperature/humidity column storing the temperature and humidity in the living room of the monitoring subject, and a body temperature column storing the body temperature of the monitoring subject. Also, if any of the sensors 21-25 can measure the blood pressure and oxygen saturation of the monitored subject, the real-time information column may have columns that store the blood pressure and oxygen saturation of the monitored subject.

The event is an event that occurs in the state of the monitoring subject or in the surrounding environment of the monitoring subject, and includes events that are different from normal conditions, events that should be notified to care staff, and events that require nursing care. Note that the event includes an event in the normal mode and an event in the end-of-life mode. Events in the normal mode include, for example, the monitored person leaving the bed (getting out of bed), increased body movement of the monitored person while in bed (in bed, sleeping), use of the toilet and staying in the toilet for a long time, door or the passage of a person, room temperature or humidity outside the predetermined range, stoppage of operation of the sensors 21 to 25 or the sensor I/F device 20, operation of the call button 26, and the like. In addition, in the information processing system, if a personal authentication terminal using face authentication or an ID tag is installed at the entrance of the nursing care facility or the door of each monitored person's room, etc., the pre-registered registrant ( The event may include the detection of a person to be monitored and care staff), the detection of an unregistered person, the wandering of a person to be monitored, and the like. End-of-life mode events include rapid changes (increase or decrease) in the monitored subject's heart rate and respiratory rate, cessation of the monitored subject's heart rate and breathing, and the like. Occurrence of an event is determined by the control unit 11 of the server 10 based on information obtained from the sensors 21 to 25 and the call button 26 via the sensor I/F device 20 . The control unit 11 determines whether or not an event has occurred according to the set operation mode for each monitored person, and when it determines that an event has occurred for each monitored person, stores information about the determined event in the event DB 13c. register.

The sensor data DB 13b is provided for each person to be monitored, and stores detection results by the sensors 21 to 25 and operation information for the call button 26 in association with the person ID of the person to be monitored. The sensor data DB 13b includes a date/time column, a bed sensor column, a toilet sensor column, a door sensor column, an environment sensor column, a human sensor column, and a call button column. The date and time column stores the date and time of detection by each of the sensors 21 to 25 and the date and time of operation of the call button 26 . The date and time column may store the date and time when the server 10 acquires the detection results and operation information from the sensors 21 to 25 and the call button 26 . The bed sensor column stores sleep data indicating the sleeping state of the monitored person detected by the bed sensor 21 . The sleep data includes body motion data indicating the magnitude of body motion, apnea data indicating the state of occurrence of an apnea phenomenon, sleep depth data indicating sleep depth, heart rate data indicating heart rate, and breathing rate data indicating breathing rate. , containing body temperature data indicating body temperature. The sleep data includes data obtained when the monitoring subject is asleep lying in bed, data obtained when the subject is awake, and data obtained when the subject is in a coma near death. As for the sleep data, in addition to the configuration in which each data is stored in association with the date and time, graph data showing temporal changes in the state of the monitoring subject may be stored. For example, a graph showing changes over time in body movement, a graph showing changes over time in the occurrence of apnea, a graph showing changes over time in depth of sleep, a graph showing changes over time in heart rate, and time of breathing rate. A graph showing changes in body temperature over time and a graph showing changes in body temperature over time may be stored in the bed sensor column. The data of the graph is, for example, a series of data in which a set of the time when the bed sensor 21 performs the measurement and the measured value is recorded each time the measurement is performed. The apnea phenomenon is a phenomenon in which the airflow in the mouth and nose stops for 10 seconds or longer during sleep. The depth of sleep is detected in three stages, for example, waking, light sleep, and deep sleep, and the sleep depth data may include the occurrence of midway awakening and the total sleep time of the day.

The toilet sensor column stores information (used/not used) indicating whether or not the toilet sensor 22 has detected the use of the toilet by the monitored person. The door sensor array stores information (open/no movement) indicating whether or not the door sensor 23 has detected the opening of the door or the passage of the door by the person to be monitored. The environmental sensor column stores environmental data indicating the temperature and humidity in the monitoring subject's living room detected by the environmental sensor 24 . As for the environmental data, in addition to the configuration in which the temperature and humidity are stored in association with the date and time, graph data showing temporal changes in the temperature and humidity may be stored in the environment sensor array. The human sensor column stores information (presence/absence in the living room) indicating whether or not the human sensor 25 has detected the movement of the person to be monitored. The call button row stores information (used/not used) indicating whether or not the monitored person has operated (used) the call button 26 . The control unit 11 of the server 10 updates each column of the sensor data DB 13b based on the information obtained from the sensors 21 to 25 and the call button 26 via the sensor I/F device 20. FIG. The toilet sensor row may store only information (use) indicating use of the toilet, and the door sensor row may store only information (open) indicating opening of the door or passage of the monitored person. Alternatively, the motion sensor row may store only information (presence) indicating the presence of the person to be monitored, and the call button row may store only information (use) indicating operation of the call button 26. may

The event DB 13c is provided for each person to be monitored, and stores information on events occurring in the person to be monitored in association with the person's ID of the person to be monitored. The event DB 13c includes a date/time column, an event item column, an event content column, a progress information column, and a comment column. The date and time column is the date and time when the event occurred, and stores the date and time when the control unit 11 of the server 10 determined the occurrence of the event based on the information obtained from the sensors 21 to 25 and the call button 26 . The event item column and the event content column store items related to events that have occurred and their content. For example, when an event of getting out of bed due to awakening occurs in the normal mode, "getting out of bed" is registered as the event item, and "middle awakening" is registered as the event content. When an event of room temperature outside the predetermined range occurs, "room temperature" is registered as the event item and "30° C. (measured room temperature)" is registered as the event content. When an event of staying in the bathroom for a long time occurs, "toilet" is registered as the event item, and "20 minutes (measured time)" is registered as the event content. Further, when an event of increased body movement during bed rest occurs, "body movement" is registered as the event item, and "increase" is registered as the event content. Further, when an event of operation of the call button 26 occurs, "call" is registered as an event item. In addition, if an event such as a sudden change in the heart rate and respiratory rate of the monitored person or a cessation of the heart rate and breathing of the monitored person occurs for the monitored person in the end-of-life mode, the event item is "end-of-life alert ” is registered as the event content, and “sudden change in heart rate and respiration rate” or “stop of heartbeat and respiration” are registered, respectively. The progress information column stores information indicating the progress of the care staff's response to the event that has occurred (hereinafter referred to as nursing care). The comment column stores comments input by the care staff using the staff terminal 30 for the event. The event DB 13c is not limited to the configuration shown in FIG. For example, the event DB 13c may store photographs and videos taken when the care staff treats the monitored person for the event, and recorded sounds, etc., in association with the item and content of the event.

Based on the information obtained from the sensors 21 to 25 and the call button 26 via the sensor I/F device 20, the control unit 11 of the server 10 controls the real-time information column of the monitored person DB 13a and each column of the sensor data DB 13b. and update. When the control unit 11 detects that an event has occurred in the monitored person based on the information obtained from the sensors 21 to 25 and the call button 26, the control unit 11 updates the date/time column, the event item column, and the event content column of the event DB 13c. Update. Further, for example, when the control unit 11 receives the end of the nursing care of the nursing care staff for the event via the staff terminal 30, stores "completed" in the progress information column of the event DB 13c, and receives a comment on the event. Store comments in the comment column. Note that the control unit 11 may store "completed" indicating the end of the nursing care in the progress information string in association with the date and time when the end of the nursing care is accepted. The event DB 13c registers information about all events that have occurred to the person being monitored. Staff will be notified. For those who are monitored in the end-of-life care mode, only events related to end-of-life care (specifically, sudden changes in heart rate and breathing rate, heartbeat and breathing stoppage) will be alerted to nursing care staff. be notified. The event DB 13c may have a configuration in which information on all events is registered, or a configuration in which only information on events notified to care staff (events for which alerts are set) is registered.

FIG. 4 is an explanatory diagram showing an example of a notification screen. The notification screen is a screen for notifying the care staff of the status of each monitored person, and is generated by the control unit 11 of the server 10 based on the contents stored in the monitored person DB 13a and the event DB 13c. The control unit 11 transmits the generated notification screen to the staff terminal 30 , and the control unit 31 of the staff terminal 30 displays the notification screen acquired from the server 10 on the display unit 36 . When the control unit 31 of the staff terminal 30 receives an operation input via the input unit 35 on the displayed notification screen, the control unit 31 transmits the operation content to the server 10 . The control unit 11 of the server 10 changes the display state of the notification screen and switches the display contents according to the operation content, and transmits the updated notification screen to the staff terminal 30 . As a result, the updated notification screen is displayed on the staff terminal 30 .

The notification screen shown in FIG. 4 includes a display area for a room list that displays the current status of each monitored person in the nursing care facility, and an alert that displays the occurrence history of events set for each monitored person. and a history display area. The room list has a plurality of individual columns R1, and one individual column R1 displays information about one monitored person stored in the monitored person DB 13a. Specifically, the room number, name, temperature and humidity in the living room, body temperature, respiratory rate, and heart rate of one person to be monitored are displayed in characters, and the current state of the person to be monitored is displayed in characters and each state. is displayed with the corresponding icon. Characters and icons indicating the status of the monitored person are prepared in advance corresponding to each status stored in the monitored person DB 13a.

For example, when a person to be monitored for whom the normal mode is set gets out of bed, an icon I1 indicating that he/she got out of bed and the characters "I got out of bed" are displayed in the personal field R1. In addition to the icon I1, the icons corresponding to the status of the monitoring subject include an icon I2 indicating that the person is asleep, an icon I3 indicating that the person is in the bathroom, an icon I4 indicating that there is body movement, and the like. Also, for the monitored person for whom the end-of-life care mode is set, an icon I5 indicating that the end-of-life care mode is in operation and the characters "end-of-life care mode: ON" are displayed in the personal field R1. In FIG. 4, it is displayed that the end-of-life mode is set for the person to be monitored in room 106. In FIG. By displaying the status of the monitoring subject using icons in this way, the status of each monitoring subject and the setting of the end-of-life care mode can be easily grasped. Icons and characters corresponding to the status of the monitoring subject and setting of the end-of-life mode are pre-installed, for example, in the program 13P, and when the control unit 11 generates the notification screen, an icon corresponding to the status of each monitoring subject is displayed. It can be displayed by selecting icons and characters. Further, when the person is set as the target person, an indicator (mark) I6 indicating that the person is set as the target person (star setting) is displayed in some place in the individual field R1. In the example shown in FIG. 4, an index I6 is displayed at the right end position of the individual column R1 corresponding to the person to be monitored in room No. 102. As a result, the control unit 11 outputs to the staff terminal 30 the index I6 indicating the star setting (target person) in association with the information (status information) displayed in the personal column R1 regarding the monitoring target person who has been set as a star. can. In the room list, the personal columns R1 of the persons to be monitored who are star-set may be collectively displayed at the top. The star setting registration instruction is received, for example, via the input unit 35 of the staff terminal 30, and the control unit 11 of the server 10 stores "setting" in the star setting column of the monitored person DB 13a, thereby completing the setting. do.

A scroll bar is provided at the right end of the room list display area. When the scroll bar is operated via the input unit 35 of the staff terminal 30, a screen is displayed in which the display contents (each individual column R1) are scrolled up and down. The living room list has a "watching over" tab, a "starred" tab, and an "all" tab, and by switching the tab selection, a living room list corresponding to the selected tab is displayed. For example, when the "all" tab is selected, the personal column R1 corresponding to all monitored persons stored in the monitored person DB 13a is displayed in the room list. When the "watching over" tab is selected, a personal field corresponding to the monitored person being watched over (monitored person whose status is being monitored) among the monitored persons stored in the monitored person DB 13a R1 is displayed in the room list. When the "starred" tab is selected, the individual column R1 corresponding to the monitored person who has been set as a star among the monitored persons stored in the monitored person DB 13a is displayed in the room list. . In addition, for example, when the person to be monitored by each care staff is fixed, a tab is provided for switching to a room list in which the personal column R1 corresponding to the person to be monitored by each care staff is displayed. may be In addition, the living room list may be configured to be switchable for each floor or area in the nursing facility, and the individual column R1 displayed in the living room list is arranged according to the layout of the rooms in each floor or each area. position may be displayed.

When a predetermined operation (for example, right-clicking of the mouse) is performed on one individual column R1 in the room list, an operation menu is displayed for setting the person to be monitored in this individual column R1. FIG. 5 is an explanatory diagram showing an example of an operation menu. FIG. 5 shows a display example of an operation menu when a predetermined operation is performed on the personal column R1 of the person to be monitored in room No. 103. FIG. In the operation menu shown in FIG. 5, each item of "star the living room", "end-of-life mode setting", "resident basic information", "alert setting", "monitor stop", and "leave" is displayed. ing. "Add a star to a living room" is an item for instructing a person to be monitored to set a star and cancel the star setting. "End-of-life mode setting" is an item for instructing the monitored person to set the end-of-life mode and cancel the end-of-life mode (that is, set the normal mode). "Resident basic information" is an item for instructing a change of registered information about a person to be monitored. "Alert setting" is an item for instructing a person to be monitored to change an event for which an alert is set. "Monitoring Pause" is an item for instructing a temporary stop and restart of monitoring (monitoring) of a person to be monitored, and "Leave" is an item for instructing to end monitoring of a person to be monitored.

When the selection of the item "star the room" is accepted via the operation menu as shown in FIG. to set the star. When the star setting is performed, the server 10 displays a mark I6 indicating the target person in the personal column R1 of the monitoring target person on the notification screen being displayed on the staff terminal 30 . When the selection of the item "end-of-life mode setting" is accepted via the operation menu, the server 10 updates the operation mode column of the monitored person in the monitored person DB 13a to "end-of-life care" and sets the end-of-life care mode. . Specifically, the control unit 31 of the staff terminal 30 accepts the selection of the item “end-of-life care mode setting” in the operation menu via the input unit 35, thereby providing each monitored person with Receives a setting as to whether or not to be monitored. Then, when the control unit 31 receives the setting of the monitoring target related to the end-of-life care, the control unit 31 notifies the server 10 and the server 10 sets the end-of-life care mode. Note that "normal" is stored in the operation mode column by default. When the end-of-life mode is set, the server 10 displays an icon I5 and text indicating that the end-of-life mode is in operation in the personal field R1 of the person to be monitored on the notification screen being displayed on the staff terminal 30 .

Further, when the selection of the item "resident basic information" is accepted via the operation menu, the server 10 displays a setting screen (change screen) of the registered information of the resident (person to be monitored) on the staff terminal 30, An instruction to set or change the registration information is received via the setting screen, and the registration information is set or changed. The registered information of the monitored person is stored, for example, in the monitored person DB 13a, and the server 10 sets or changes the registered information of the monitored person by updating the stored contents of the monitored person DB 13a. . When the selection of the "alert setting" item is accepted through the operation menu, the server 10 displays an alert setting screen on the staff terminal 30, accepts an event for which an alert should be set through the alert setting screen, and stores the monitored person DB 13a. , update the alert setting column for the person being monitored.

Further, when the selection of the item “pause watching” is received via the operation menu, the server 10 temporarily stops monitoring (watching process) for the monitored person. For example, the server 10 stores, as the information of the monitoring target in the monitoring target DB 13a, information indicating that the monitoring target is being suspended. When a suspension is set, the server 10 may display a message informing that the monitoring process is suspended in the individual column R1 of the monitoring target on the notification screen. After setting the temporary stop, the server 10 is controlled so as not to acquire information from the sensors 21 to 25 and the call button 26 corresponding to the monitored person, or not to perform processing based on the acquired information. be. Temporary suspension of monitoring of a monitoring target is set, for example, when a resident of a nursing care facility (monitoring target) is temporarily hospitalized in a medical institution, or temporarily returns home. When the selection of the "leave" item is received via the operation menu, the server 10 terminates the monitoring of the monitoring subject. For example, the server 10 stores information indicating withdrawal as information of the monitored person in the monitored person DB 13a. When leaving is registered, the server 10 deletes the personal column R1 of the monitoring subject from the notification screen.

The alert history has a plurality of alert columns R2, and one alert column R2 displays information about one event that has occurred for one monitored person. Specifically, the room number, name, and date and time of the event (alert) occurrence of the monitored person where the event for which the alert was set occurred are displayed in text, and the status of the monitored person (content of the event) is displayed in text and text. Each event is represented by an icon corresponding to it. Icons corresponding to events are icons similar to the icons I1 to I5 used for the room list, for example. When an alert (event related to end-of-life care) occurs for a person to be monitored for whom the end-of-life care mode is set, the alert field R2 for the person to be monitored is displayed or blinked in a color different from that of the other alert fields R2. may be displayed. In this case, the nursing care staff can be notified of the occurrence of an alert that is different from that of other persons to be monitored. Also in the alert column R2, an indicator I6 is displayed for the monitoring target who is set as a star. Note that the alert column R2 related to the person to be monitored who is star-set may be displayed in a predetermined color or may be displayed in a blinking manner so as to be highlighted in a display mode indicating a high degree of importance. An unread mark is displayed in the alert column R2 when the displayed alert has not been confirmed by the care staff. Note that when a predetermined operation (for example, a left click of the mouse) is performed on the alert column R2, the detailed content of the alert in the alert column R2 is displayed, and when the detailed content is displayed, the alert is already displayed. Read state. In the read state, the unread mark displayed in the alert column R2 is no longer displayed. Note that instead of the unread mark not being displayed, a read mark indicating the read state may be displayed.

Further, when a predetermined operation (for example, a right click of the mouse) is performed on the alert column R2, an operation menu (not shown) for performing processing for the alert of this alert column R2 is displayed. For example, an operation menu is displayed for accepting a selection of processing such as input of information and comments regarding nursing care provided by the nursing care staff in response to the alert, change to an unread state, and the like. When inputting a comment for an alert is selected via such an operation menu, a comment input screen is displayed, and the comment input via the input screen is stored in the event DB 13c. Further, when a change to the unread state is selected via the operation menu, the read state of the alert is changed to the unread state.

A scroll bar is provided at the right end of the alert history display area. When the scroll bar is operated via the input unit 35 of the staff terminal 30, a screen is displayed in which the display contents (each alert column R2) are scrolled up and down. The alert history has an "all" tab, an "unread" tab, and a "read" tab, and by switching tab selection, a list of alert history corresponding to the selected tab is displayed. For example, when the "All" tab is selected, an alert column R2 for all alerts notified so far is displayed in the alert history. When the "Unread" tab is selected, among the alerts that have been notified so far, the alert column R2 for alerts that are in an unread state is displayed in the alert history, and when the "Read" tab is selected, Among the alerts notified to , an alert column R2 related to alerts in a read state is displayed in the alert history. Information on alerts notified so far includes information indicating whether or not it has been confirmed by nursing care staff (unread or read), and whether or not it has been handled by nursing care staff (already providing nursing care). It is stored in a DB provided in the auxiliary storage unit 13 of the server 10, for example, in association with the information indicating whether it is handled or not (handled or unhandled). Therefore, the control unit 11 of the server 10 can generate an alert history corresponding to each tab by reading information corresponding to the selected tab from the DB. Also, the alert history may be configured to be switchable for each floor or area within the nursing facility.

By displaying the notification screen configured as described above on the staff terminal 30, the care staff can grasp the current state of each monitored person, and an alert has been set for the monitored person for whom the normal mode is set. It is possible to grasp the occurrence status of events, and it is possible to grasp the occurrence status of events (alerts) related to end-of-life care for a person to be monitored for whom the end-of-life care mode is set. In the notification screen shown in FIG. 4, for example, when any individual column R1 in the room list is selected (for example, when the mouse is left-clicked), the information of the person to be monitored in the selected individual column R1 is displayed. A personal screen displaying a list is displayed on the staff terminal 30 . FIG. 6 is an explanatory diagram showing an example of a personal screen. The personal screen is generated by the control unit 11 of the server 10 based on each information stored in the sensor data DB 13b of each monitored person. The personal screen has a real-time data field R3, a previous day's sleep field R4, a vital history field R5, and the like. The real-time data column R3 displays real-time information indicating the current status of the monitored person. The real-time data column R3 has a "last 12 hours" tab and a "last 30 minutes" tab, and by switching the tab selection, information for the most recent 12 hours in the past or information for the most recent 30 minutes in the past information is displayed. The real-time data column R3 displays graphs showing temporal changes in sleep state, respiration rate, heart rate, activity state, toilet usage history, door opening history, room temperature, and the like. The horizontal axis of each graph indicates time, and the right end of the horizontal axis indicates the current time.

The sleep state is displayed by a band graph, and the hatched portion in the band graph indicates the sleeping time, and the blank portion indicates the waking time. In addition, the graph showing the sleep state may have a configuration in which the hours of deep sleep and the hours of light sleep are indicated by different hatching. Respiration rate and heart rate are displayed in a line graph. The activity state is displayed by a bar graph, and the hatched portion in the bar graph indicates the time during which the motion sensor 25 detects the movement of the person to be monitored in the living room. The use history of the toilet is displayed in a bar graph, and the hatched portion in the bar graph indicates the time during which the toilet sensor 22 detects the use of the toilet by the monitoring subject. The door opening history is displayed as a bar graph, and the hatched portion in the bar graph indicates the time during which the door sensor 23 detects the opening of the door or the passage of the person to be monitored. Room temperature is displayed as a line graph. A line graph indicating humidity may be displayed together with the room temperature.

The previous day's sleep column R4 displays information regarding the previous day's sleep, such as sleep time, degree of recovery from fatigue, comfortable sleep index, comfortable environment index, and the like. Each of these pieces of information is calculated by the control unit 11 of the server 10 based on the information stored in the sensor data DB 13b. The sleep time is a letter indicating the sleep time calculated based on the sleep data detected by the bed sensor 21, a mark (five stars in FIG. 6) and a letter (in FIG. 6) indicating the evaluation corresponding to the sleep time. I'm sleeping well.") is displayed. The degree of recovery from fatigue is also calculated based on the sleep data, and the degree of recovery from fatigue due to sleep is indicated on a scale of 100, for example. A good sleep index is also calculated based on the sleep data, and indicates the degree of good sleep, for example, out of 100 points. The comfort environment index is calculated based on the environmental data detected by the environment sensor 24, and indicates the comfort level of the environment during sleep on a scale of 100, for example.

The vital history column R5 displays vital data of the monitoring subject detected by the bed sensor 21. FIG. In the example shown in FIG. 6, the vital history field R5 displays the current numerical values of body temperature, blood pressure, and oxygen saturation, and graphs showing temporal changes in the most recent past week. The horizontal axis of each graph indicates the date (day of the week), and the right end of the horizontal axis indicates the current date (day of the week). Also, in the vital history column R5, a message indicating the status of the monitored person corresponding to the current numerical value of each vital data is displayed. For example, if the body temperature is 37.5 degrees Celsius or higher, the message "I have a fever" is displayed. Also, if the blood pressure is classified into, for example, high normal blood pressure, high blood pressure, class I hypertension, class II hypertension, class III hypertension, etc., a message indicating that the blood pressure falls under each class is displayed. Also, when the oxygen saturation is less than 95%, a message is displayed indicating that the oxygen saturation is an abnormal value.

The personal screen has a "return to room list" button for returning to the display of the screen shown in FIG. , the screen displayed on the staff terminal 30 is switched to the notification screen shown in FIG. The care staff appropriately switches between the notification screen shown in FIG. 4 and the personal screen shown in FIG. status can be checked individually.

Below, in the information processing system of the present embodiment, processing performed by each device for updating the notification screen displayed on the staff terminal 30 will be described. FIG. 7 is a flowchart illustrating an example of a notification screen updating process procedure. In FIG. 7, the processing performed by the server 10 is shown on the left side, and the processing performed by the staff terminal 30 is shown on the right side. The following processes are executed by the control unit 11 according to the program 13P stored in the auxiliary storage unit 13 of the server 10, and executed by the control unit 31 according to the program 33P stored in the auxiliary storage unit 33 of the staff terminal 30. be done. In the following processing, when the sensor I/F device 20 acquires detection signals from the sensors 21 to 25 and operation signals from the call button 26, the sensor I/F device 20 transmits the acquired signals to the server 10 via the network N. ing. Note that the sensor I/F device 20 may be configured to transmit signals from the sensors 21 to 25 and the call button 26 to the server 10 in response to a signal request from the server 10 .

The control unit 11 of the server 10 receives signals (sensor data) from the sensors 21 to 25 or the call button 26 connected to the sensor I/F device 20 via one of the sensor I/F devices 20. It is determined whether or not it has been received (S11). If the control unit 11 determines that the sensor data has not been received (S11: NO), it waits until the sensor data is received. When the control unit 11 (acquisition unit) determines that the sensor data has been received (S11: YES), the received sensor data identifies the sensor data that detected the state of the person to be monitored (S12). . For example, the server 10 stores a table in which the identification information (subject ID) of each monitored person and the identification information (device ID) of each sensor I/F device 20 are associated and registered. The /F device 20 is configured to transmit sensor data and identification information of the sensor I/F device 20 to the server 10 . In this case, the control unit 11 of the server 10 can specify the monitored person corresponding to the received sensor data based on the identification information of the sensor I/F device 20 received from the sensor I/F device 20 and the table. Further, the sensor I/F device 20 may be configured to store the identification information of the corresponding monitoring subject and transmit the sensor data and the identification information of the monitoring subject to the server 10. . In this case, the control unit 11 of the server 10 can specify the monitored person for the received sensor data based on the monitored person identification information received from the sensor I/F device 20 .

The control unit 11 associates and stores the date and time at this point in time with the received sensor data in the sensor data DB 13b of the specified person to be monitored (S13). The control unit 11 also stores real-time information indicating the current state of the monitored person based on the received sensor data in the monitored person DB 13a. Based on the sensor data stored in the sensor data DB 13b, the control unit 11 generates display information to be displayed in the individual column R1 of the room list on the notification screen (S14). For example, the control unit 11 generates display information by associating the information of the monitoring target identified in step S12 (for example, the target ID) with the state information (status information) of the monitoring target based on the sensor data. The control unit 11 transmits the generated display information to the staff terminal 30 (S15). When receiving the display information of the room list from the server 10, the control unit 31 of the staff terminal 30 updates the room list of the notification screen being displayed on the display unit 36 based on the received display information (S16). Specifically, the control unit 31 displays the state indicated by the received state information of the monitored person in the individual column R1 corresponding to the received information of the monitored person. For example, when the control unit 31 receives "getting out of bed" from the server 10 as the status information of the monitored person in room 101, an icon I1 corresponding to "getting out of bed" and " I'm out of bed" is displayed and the room list is updated.

Next, the control unit 11 determines whether or not the monitored person specified in step S12 is a monitored person for whom the end-of-life mode is set (S17). Specifically, the control unit 11 reads the operation mode set for the identified monitoring subject from the monitoring subject DB 13a, and determines whether or not the end-of-life mode is set. If it is determined that the end-of-life mode is not set (S17: NO), that is, if the normal mode is set, the control unit 11, based on the sensor data stored in the sensor data DB 13b in step S13, An event related to the normal mode that has occurred in the person to be monitored is specified (S18). For example, when a signal indicating zero heart rate and zero respiratory rate of the monitoring subject (a signal indicating that the biological reaction of the monitoring subject cannot be detected) is received from the bed sensor 21, the control unit 11 determines that the monitoring subject is getting out of bed. Identify event occurrences. Note that the control unit 11 may specify occurrence of an event of getting out of bed when receiving a signal indicating that other biological information of the monitored person is zero (a signal indicating that detection is not possible). Further, when receiving a signal indicating the state of body movement from the bed sensor 21, the control unit 11 detects the body movement of the monitored person on the bed if the magnitude of the body movement indicated by the received signal is equal to or greater than a predetermined value. Identify occurrences of events where is large. Further, when receiving a signal indicating use of the toilet from the toilet sensor 22, the control unit 11 identifies occurrence of an event of use of the toilet. Further, when the control unit 11 receives a signal indicating use of the toilet continuously for a predetermined time or longer, the control unit 11 identifies occurrence of an event of a long stay in the toilet. Further, when receiving a signal indicating that the door is opened from the door sensor 23, the control unit 11 identifies the occurrence of an event that the door is opened. Further, when the control unit 11 receives a signal indicating temperature (room temperature) from the environment sensor 24, if the received temperature is equal to or higher than a predetermined range, the control unit 11 identifies occurrence of an event of a high temperature state, and determines whether the received temperature is within the predetermined range. If it is less than, it identifies the occurrence of a low temperature event. Further, when receiving a signal indicating humidity from the environment sensor 24, the control unit 11 identifies occurrence of an event of a high humidity (high humidity) state if the received humidity is greater than or equal to a predetermined range. If it is less than the predetermined range, the occurrence of an event of low humidity (dry) is specified. Further, when receiving an operation signal from the call button 26 , the control unit 11 identifies occurrence of an event of operation of the call button 26 . In addition, if the control unit 11 does not receive a signal from any sensor I/F device 20 or a signal from any of the sensors 21 to 26 for a predetermined time or longer, the sensor I/F device 20 , or the occurrence of an event of malfunction of any of the sensors 21-25.

In addition, when a personal authentication terminal using face recognition or an ID tag is provided at an appropriate location in the nursing care facility, the control unit 11 detects the registrant based on the signal received from the personal authentication terminal, and Identifies the occurrence of an event called Subscriber Detection. Further, when the same person to be monitored is detected more than a predetermined number of times within a predetermined time by one personal authentication terminal, the control unit 11 identifies the occurrence of an event of loitering of the person to be monitored. The event whose occurrence is detected by the control unit 11 is not limited to the above-described event, and may be an event that occurs in the person to be monitored or in the surroundings of the person to be monitored. It can contain various possible states. Note that the reference values for determining whether body movement, time spent in the toilet, temperature, and humidity are within normal ranges are stored in advance in the auxiliary storage unit 13 of the server 10, and are set for each person to be monitored. The determined reference value may be stored in advance.

On the other hand, if it is determined that the end-of-life mode is set (S17: YES), the control unit 11 (determining unit) determines that the sensor data stored in the sensor data DB 13b in step S13 is detected by the bed sensor 21. Based on the sensor data (biological information of the monitoring subject), an event related to the end-of-life mode that has occurred in the monitoring subject here is identified (S19). Specifically, based on the heart rate data and the respiration rate data detected by the bed sensor 21, the control unit 11 detects a sudden change (increase or decrease) in the heart rate and respiration rate, or stops the heartbeat and respiration ( Identifies the occurrence of events such as zero heart rate and zero breathing rate).

The control unit 11 associates and stores the detection date and time of the sensor data used to specify the occurrence of the event and the information of the determined event in the event DB 13c of the person to be monitored (S20). For example, when the control unit 11 identifies the occurrence of an event related to end-of-life care for a person to be monitored for whom the end-of-life care mode is set, the control unit 11 stores "end-of-life alert" as the event item, and "heart rate and respiration rate" as the event content. Memorize "rapid changes" or "cessation of heartbeat and breathing." Further, when the control unit 11 identifies the occurrence of an event of getting out of bed due to awakening in the middle of sleep for a person to be monitored for whom the normal mode is set, the control unit 11 stores "getting out of bed" as an event item, and " Mid-Awakening” is memorized. Further, when the control unit 11 identifies the occurrence of an event that the body movement is large, it stores "body movement" as the event item and "large" or "increase" as the event content. When the occurrence of the event of using the toilet is specified, the control unit 11 stores "toilet" as the event item, and when the occurrence of the event of staying in the toilet for a long time is specified, the duration of stay in the toilet is stored as the event content. memorize Further, when the control unit 11 identifies the occurrence of the event of opening the door, it stores "door" as the event item and "open" as the event content. When the control unit 11 identifies the occurrence of an event such as a high temperature state or a low temperature state, it stores "room temperature" as the event item and stores the measured room temperature as the event content. Further, when the control unit 11 identifies occurrence of an event such as a high humidity state or a dry state, it stores "humidity" as the event item and stores the measured humidity as the event content. Further, when the control unit 11 identifies the occurrence of the event of the operation of the call button 26, it stores "call button" as the event item and "operation" as the event content. Further, when the control unit 11 specifies the occurrence of an event such as malfunction of the sensor I/F device 20 or the sensors 21 to 25, it stores "device malfunction" as the event item, and detects the occurrence of unnecessary operation as the event content. device information of the device received.

Further, when the control unit 11 specifies the occurrence of an event of detection of a registrant and detection of an unregistered person, it stores "human detection" as an event item, and the monitored person or unregistered person detected as the event content. store the information shown. Further, when the control unit 11 identifies the occurrence of the event of the monitored person's loitering, the control unit 11 stores "wandering" as the event item and stores the detected monitored person's information as the event content. In addition, when the personal authentication terminal is provided in the common area of the monitored person, an event DB for the nursing care facility is prepared on the server 10, and the detection of registrants, the detection of unregistered persons, and the wandering of the monitored person are performed. The event information to be displayed and the identification information or installation location information of the personal authentication terminal may be stored in the event DB for the nursing facility.

The control unit 11 determines whether or not the event specified in step S18 or step S19 is an event for which an alert has been set for the person to be monitored (S21). Here, the control unit 11 determines whether or not the event specified in step S18 is included in the events for which an alert has been set for the person to be monitored specified in step S12. Note that the control unit 11 determines that the event identified in step S19 is an event for which an alert has been set. That is, when an event related to end-of-life care occurs for a person to be monitored for whom the end-of-life care mode is set, the event is determined to be an event for which an alert is set.

When determining that the event is not an alert-set event (S21: NO), the control unit 11 terminates the process. It should be noted that the control unit 11 executes the processing after step S12 each time it receives sensor data from the sensor I/F device 20 .

If it is determined that the event is for which an alert has been set (S21: YES), the control unit 11 generates alert information to be displayed in the alert column R2 of the alert history of the notification screen based on the information stored in the event DB 13c. (S22). For example, the control unit 11 generates alert information by associating the current date and time, information (room number and name) of the person to be monitored identified in step S12, and event information indicating the details of the event. The control unit 11 transmits the generated alert information to the staff terminal 30 (S23). Thereby, the control unit 11 can output an alert to the person to be monitored for whom the normal mode is set when an event for which the alert is set occurs. Further, the control unit 11 (output unit) can output alert information (end-of-life information) related to end-of-life care when an event related to end-of-life care occurs for a person to be monitored for whom the end-of-life care mode is set. Note that the control unit 11 may store the alert information in the event DB 13c in association with the event information. The control unit 31 of the staff terminal 30 receives alert information (end-of-life information related to end-of-life care) to be displayed in the alert history from the server 10, and based on the received alert information, displays the alert history of the notification screen being displayed on the display unit 36. is updated (S24). Specifically, the control unit 31 generates a new alert column R2, and fills the generated alert column R2 with the current date and time, the room number and name of the person to be monitored for whom the alert (event for which the alert is set) has occurred. and status. By arranging the latest alert column R2 at the top of the alert history, the control unit 31 can display each alert column R2 in order of alert generation. In the example shown in FIG. 4, the alert history is updated by displaying the alert column R2 indicating that the "end-of-life alert" has been issued to the person to be monitored in room 106 as the latest alert. An unread mark is displayed in the newly generated alert column R2.

By the above-described processing, the server 10 monitors the status of each monitored person based on the sensor data received from the sensor I/F device 20, and the status of the monitored person is displayed in the room list displayed on the staff terminal 30. care staff can be notified via In addition, when an event for which an alert is set occurs for a person to be monitored for whom the normal mode is set, the server 10 notifies the occurrence of the event via the alert history displayed on the staff terminal 30. Nursing staff can be notified. Furthermore, when an event related to end-of-life care occurs for a person to be monitored for whom the end-of-life care mode is set, the server 10 can notify the care staff of the occurrence of the event via the alert history. Therefore, the care staff can grasp the condition of each monitoring subject, and can quickly grasp and start nursing care when an alert is generated for one of the monitoring subjects. In particular, for a monitoring target for whom the end-of-life care mode is set, it is possible to appropriately determine the timing of contacting the monitoring target's family, a doctor who attends the end-of-life care, and the like.

In the above-described process, if the staff terminal 30 is configured to have an audio output unit such as a speaker or an earphone, when alert information is received from the server 10, in addition to updating the displayed alert history, the staff terminal 30 outputs the alert information. It may be configured to output audio. For example, when the control unit 31 of the staff terminal 30 receives alert information indicating that a "end-of-life alert" has occurred for a person to be monitored in room 106, "room 106, Ms. Hanako Suzuki, end-of-life alert has occurred." message may be output by voice. According to such a configuration, the nursing staff can grasp that an event (alert) has occurred in the monitored person without checking the display contents of the display section 36 of the staff terminal 30 .

In this embodiment, a plurality of types of sensors 21 to 25 are provided to determine the state of the person to be monitored. ) are monitored. Such an information processing system can also be used to monitor the occurrence of dying symptoms in a subject who is approaching death. Therefore, in this embodiment, for a normal monitoring subject, the monitoring subject's getting out of bed and the state of the monitoring subject are detected based on the monitoring subject's biological information detected by the bed sensor 21, and the monitoring subject's approaching death is detected. , the end-of-life condition can be detected without detecting that the monitored person is out of bed. Therefore, by switching between the normal mode and the end-of-life mode, one bed sensor 21 can be used to detect two types of states. In nursing care facilities and the like, nursing care staff regularly observes whether or not signs of dying are observed for a person to be monitored who is approaching death. By using the system, it is only necessary to observe the condition of the person to be monitored when an alert regarding end-of-life care is generated, and the burden on care staff can be reduced. In addition, for each monitored person for whom the normal mode is set, it is possible to set an event to be notified as an alert to the nursing care staff among the events that have occurred for each monitored person. Therefore, different events can be set as events to be notified to the care staff depending on the health condition of the monitored person.

In this embodiment, the alert for the monitoring subject for whom the end-of-life care mode is set is the occurrence of an event related to end-of-life care (rapid change in heart rate and respiration rate, or cessation of heartbeat and respiration), as well as the setting of the end-of-life care mode. It may be output based on the elapsed time from the start. For example, when 1 day (24 hours) has passed since the end-of-life mode was set, when 3 days have passed, when 1 week has passed, when 2 weeks have passed, etc. may be alerted events. In this case, not only the occurrence of a state (event) related to end-of-life care, but also the fact that a predetermined period of time has elapsed since the setting of the end-of-life care mode can be notified to the care staff as an alert. Specifically, in step S19 in FIG. 7, the control unit 11 determines the state of the end-of-life care based on the sensor data from the bed sensor 21. A process of determining whether or not a predetermined time has been reached is performed. Then, when determining that the predetermined time has elapsed, the control unit 11 identifies occurrence of an event (alert) that a predetermined time has passed since setting of the end-of-life mode was started. The setting date and time of the end-of-life mode can be stored, for example, in the operation mode column of the monitored person DB 13a.

FIG. 8 is an explanatory diagram showing another screen example of the alert history. In the example shown in FIG. 8, it is displayed that an alert (event) that three days have passed since the end-of-life mode was set for the monitored person in room No. 105 has occurred. When outputting an alert based on the elapsed time from the setting start of the end-of-life mode in this way, the elapsed time itself can be notified to the care staff by displaying the elapsed time in the alert column R2. In the case of such a configuration, the care staff can grasp the elapsed time from the setting of the end-of-life care mode by alerting the person to be monitored for whom the end-of-life care mode is set. Therefore, it is possible to predict future changes in the state of the person to be monitored, and to cancel the setting of the end-of-life mode as necessary. The elapsed time from the start of setting of the end-of-life mode may be displayed in the individual column R1 of the living room list as status information in addition to the alert indicating the passage of the predetermined time.

In this embodiment, in the alert history in the notification screen, depending on whether or not an unread mark is displayed in each alert column R2, it is presented whether nursing care has been performed by the nursing care staff in response to the alert. . In addition, by displaying a mark indicating the progress of each alert in each alert column R2, it may be configured to present the progress (response status) of nursing care by the nursing care staff for each alert. . For example, if the content of the alert has not been confirmed by the nursing staff, an unread mark is displayed, and if nursing care has been confirmed by the nursing staff and nursing care has started, it indicates that nursing care is in progress. A mark may be displayed, and when the nursing care is completed, a completed mark indicating that the nursing care has been completed may be displayed. In the case of such a configuration, since the progress of each alert displayed in the alert history can be easily grasped, the care staff can easily determine the order of priority in responding to each alert. In addition to switching the display of the mark, the display mode (for example, display color, blinking display) of the alert column R2 may be switched according to the progress of each alert. The progress status for each alert may be input by the care staff via the input unit 35 of the staff terminal 30, for example.

(Embodiment 2)
An information processing system that can temporarily stop monitoring the status of a person to be monitored for whom the end-of-life care mode is set will be described. The information processing system of the present embodiment can be realized using devices similar to those of the information processing system of the first embodiment shown in FIG. 1, so description of the configuration of each device will be omitted.

Patients who are nearing the end of their life and are placed in end-of-life care mode are bedridden. In order to prevent the occurrence of pressure ulcers, they are required to change their position, perform skin care to keep the body clean, and improve blood circulation. It is necessary to provide long-term care such as massage on a regular basis. When such nursing care is performed, there is a possibility that an occurrence of an event (alert) regarding end-of-life care may be erroneously detected based on sensor data (biological information) detected by the bed sensor 21 . Therefore, in the information processing system of the present embodiment, the processing in the end-of-life care mode can be temporarily stopped, so that when the care staff performs the above-described nursing care, the occurrence of an event (alert) related to end-of-life care is not detected. can be configured to avoid false alerts.

FIG. 9 is a flow chart showing an example of a setting process procedure for pausing the end-of-life mode, and FIG. 10 is an explanatory diagram showing another screen example of a room list. In the information processing system of the present embodiment, the control unit 11 of the server 10 determines whether or not a setting instruction to suspend the end-of-life mode has been acquired for any of the monitored persons for whom the end-of-life mode is set. (S31). For example, in the information processing system of the present embodiment, the staff terminal 30 is configured to be able to input an instruction to set temporary suspension of the end-of-life care mode and an instruction to cancel the temporary suspension. is received, the content of the received instruction is transmitted to the server 10 . In this case, the server 10 can acquire from the staff terminal 30 an instruction to set temporary suspension of the end-of-life care mode and an instruction to release the temporary suspension.

Further, the sensor I / F device 20 is provided with an input unit (for example, an operation button) for inputting an instruction to set a temporary stop of the end-of-life mode and an instruction to cancel the temporary stop, and the sensor I / F device 20 uses the input unit It may be configured to receive a temporary suspension setting instruction or a temporary suspension release instruction via the server 10 and transmit the received instruction content to the server 10 . In this case, the server 10 can acquire from the sensor I/F device 20 an instruction to set temporary suspension of the end-of-life care mode and an instruction to cancel the temporary suspension. Furthermore, the sensor I / F device 20 is provided with a communication unit capable of short-range wireless communication with, for example, a staff terminal 30 carried by a care staff or an ID tag, and the sensor I / F device 20 When wireless communication with the staff terminal 30 or the ID tag is possible (that is, when the staff terminal 30 or the ID tag exists within the communicable range), a setting instruction to suspend the end-of-life mode is transmitted to the server 10, and the staff terminal 30 Alternatively, if wireless communication with the ID tag cannot be performed (that is, if there is no staff terminal 30 or ID tag within the communicable range), an instruction to cancel the temporary suspension of the end-of-life care mode may be transmitted to the server 10. good. If the staff terminal 30 or the ID tag exists within the communicable range, it is possible that the nursing staff carrying the staff terminal 30 or the ID tag is providing nursing care to the monitored person in the vicinity of the sensor I/F device 20. highly sexual. On the other hand, when the staff terminal 30 or the ID tag is not present within the communicable range, the nursing staff carrying the staff terminal 30 or the ID tag is providing nursing care to the monitored person near the sensor I/F device 20. Most likely not. Therefore, depending on whether or not the sensor I / F device 20 can wirelessly communicate with the staff terminal 30 or the ID tag via the communication unit, by automatically switching the suspension of the nursing care mode or the cancellation of the suspension Since the staff does not need to operate the staff terminal 30 or the sensor I/F device 20, the operational burden does not increase. Also in the case of the above-described configuration, the server 10 can acquire from the sensor I/F device 20 an instruction to set temporary suspension of the end-of-life mode and an instruction to cancel the temporary suspension.

Therefore, the control unit 11 of the server 10 determines whether or not a setting instruction to suspend the end-of-life mode has been acquired from the staff terminal 30 or the sensor I/F device 20 . In addition to the staff terminal 30 or the sensor I / F device 20, a terminal for inputting a setting instruction to suspend the end-of-life mode and an instruction to cancel the suspension may be provided. It is possible to acquire a setting instruction to suspend the end-of-life care mode and an instruction to cancel the suspension from the terminal.

If it is determined that the setting instruction to suspend the end-of-life mode has been acquired (S31: YES), the control unit 11 specifies the person to be monitored for whom the end-of-life mode is to be temporarily suspended (S32). For example, when a setting instruction to suspend is obtained from the sensor I/F device 20, by specifying the monitoring subject associated with the sensor I/F device 20, the monitoring subject whose end-of-life mode is to be suspended is specified. can. Further, when acquiring a temporary stop setting instruction from the staff terminal 30, the identification information of the corresponding monitored person is acquired together with the setting instruction from the staff terminal 30, and the received setting instruction is handled based on the acquired identification information. It is possible to identify the person to be monitored. The control unit 11 sets the suspension of the end-of-life mode by storing information indicating that the end-of-life mode is suspended as the information of the identified monitoring subject in the monitoring subject DB 13a, for example (S33). .

Then, the control unit 11 generates display information for displaying that the end-of-life care mode for the monitoring target person is suspended in the individual column R1 of the room list on the notification screen, and transmits the display information to the staff terminal 30 (S34). ). For example, the control unit 11 generates display information by associating the information of the monitoring subject identified in step S32 (for example, the subject ID) with the information indicating the suspension of the end-of-life mode. When receiving the display information of the room list from the server 10, the control unit 31 of the staff terminal 30 updates the room list of the notification screen being displayed on the display unit 36 based on the received display information (S35). Here, the control unit 31 displays the received information indicating that the end-of-life care mode for the monitored person is temporarily stopped in the individual field R1 corresponding to the received information about the monitored person. In the example shown in FIG. 10, in the personal column R1 of the person to be monitored in room 105, the text "At-home care mode: paused" is displayed. Note that an icon indicating that the end-of-life mode is temporarily stopped may be displayed. If it is determined that the setting instruction to suspend the end-of-life mode has not been acquired (S31: NO), the control unit 11 skips the processes of steps S32 to S34.

On the other hand, the control unit 11 determines whether or not an instruction to cancel the suspension has been acquired for any of the monitored persons for whom the suspension of the end-of-life care mode is set (S36). The control unit 11 can acquire the pause release instruction from the same device as the pause setting instruction. If it is determined that the instruction to cancel the suspension has been acquired (S36: YES), the control unit 11 identifies the monitoring subject whose suspension of the end-of-life mode is to be canceled (S37). Here, the control unit 11 can specify the person to be monitored by the same process as in step S32. The control unit 11 cancels the suspension of the end-of-life mode by deleting information indicating that the end-of-life mode is suspended, which is stored as information of the specified monitoring subject in the monitoring target person DB 13a, for example. is set (S38).

Then, the control unit 11 transmits release information indicating that the suspension of the end-of-life care mode for the monitored person has been released to the staff terminal 30 (S39). For example, the control unit 11 associates the information of the monitoring subject identified in step S32 (for example, the subject ID) with the information indicating the cancellation of the temporary stop of the end-of-life care mode, and transmits the information to the staff terminal 30 . When the control unit 31 of the staff terminal 30 receives the release information from the server 10, in the room list of the notification screen being displayed on the display unit 36, the personal column R1 corresponding to the person to be monitored indicates that the end-of-life care mode is in operation. Information indicating that is is displayed and updated (S40). In this case, the characters "Facilitation mode: Temporarily stopped" displayed in the personal column R1 are updated to "Facilitation mode: ON". When determining that the instruction to cancel the suspension has not been obtained (S36: NO), the control section 11 skips the processing of steps S37 to S39.

By the above-described processing, the server 10 acquires the instruction to set the temporary suspension of the end-of-life care mode and the instruction to cancel the temporary suspension via the sensor I/F device 20 or the staff terminal 30, can be set or the suspension can be canceled. The control unit 11 of the server 10 performs the above-described processing every time it acquires an instruction to set the temporary suspension of the end-of-life mode or an instruction to cancel the temporary suspension of the monitoring target for whom the end-of-life mode is set. As a result, when monitoring processing in the end-of-life mode is unnecessary, the execution of unnecessary processing is suppressed by suspending it, and when monitoring processing is necessary, the monitoring processing can be reliably performed by canceling the suspension. can be executed.

FIG. 11 is a flowchart illustrating an example of a notification screen updating process procedure according to the second embodiment. The process shown in FIG. 11 is obtained by adding step S41 between YES in step S17 and step S19 in the process shown in FIG. Description of the same steps as in FIG. 7 will be omitted. In FIG. 11, illustration of steps S11 to S16 in FIG. 7 is omitted.

The control unit 11 of the server 10 and the control unit 31 of the staff terminal 30 of this embodiment execute the same processes as steps S11 to S17 in FIG. When the control unit 11 of the server 10 of the present embodiment determines that the end-of-life mode is set (S17: YES), the monitoring target person here, specifically the monitoring target person specified in step S12, to determine whether or not the end-of-life mode is temporarily stopped (S41). Here, the control unit 11 determines whether or not information indicating that the end-of-life care mode is temporarily suspended is stored in the monitoring target person DB 13a in association with the monitoring target person. When it is determined that the end-of-life mode is suspended (S41: YES), that is, when information indicating that the end-of-life mode is suspended is stored in association with the monitored person, the control unit 11 ends the series of processes.

When it is determined that the end-of-life mode is not suspended (S41: NO), that is, when the information indicating that the end-of-life mode is suspended in association with the monitoring subject is not stored, the control unit 11 , the process proceeds to step S19. That is, the control unit 11 identifies an event related to the end-of-life mode that has occurred in the person to be monitored here based on the sensor data detected by the bed sensor 21 (S19), and executes the processes from step S20.

According to the above-described process, when the end-of-life mode is temporarily stopped for a person to be monitored for whom the end-of-life mode is set, the process of determining an event related to the end-of-life mode (state related to end-of-life care) is not performed. On the other hand, when the temporary stop of the end-of-life mode is canceled and the end-of-life mode is in operation, the process of determining an event related to the end-of-life mode (state related to end-of-life care) is performed.

In this embodiment, the same effects as those of the first embodiment described above can be obtained. In addition, in this embodiment, it is possible to suspend the end-of-life mode for a person to be monitored for whom the end-of-life mode is set, and it is possible to switch between the suspension of the end-of-life mode and the cancellation of the suspension as appropriate. . Therefore, it is possible to avoid outputting an erroneous alert by pausing the end-of-life mode when the nursing care staff provides nursing care to the person to be monitored. Also in the present embodiment, it is possible to apply the modified examples appropriately described in the first embodiment.

(Embodiment 3)
An information processing system that recommends whether or not to set the end-of-life mode to a person to be monitored who is set to the normal mode based on sensor data detected from the person to be monitored will be described. The information processing system of the present embodiment can be realized using devices similar to those of the information processing system of the first embodiment shown in FIG. 1, so description of the configuration of each device will be omitted.

The information processing systems of the first and second embodiments described above are configured such that the care staff manually sets the end-of-life mode for each person to be monitored via the operation menu shown in FIG. 5, for example. In the information processing system of the present embodiment, the server 10 monitors the biological information (for example, heart rate and respiratory rate) of each monitoring subject based on sensor data acquired from the sensor I / F device 20, and switches to the end-of-life mode. It has a function to determine whether or not to set and make a recommendation.

In the information processing system of this embodiment, the server 10 and the staff terminal 30 execute the same processing as the processing shown in FIG. As a result, in the information processing system of this embodiment as well, the server 10 monitors the status of the person to be monitored based on the sensor data received from the sensor I/F device 20, and stores the status of each person to be monitored in the room list. In addition to notifying the care staff of the occurrence of an alert in the alert history, when an alert is generated for any of the monitored persons.

FIG. 12 is a flowchart showing an example of a recommendation processing procedure in the end-of-life mode, and FIG. 13 is an explanatory diagram showing another screen example of a room list. The control unit 11 of the server 10 of the present embodiment performs the following processing at appropriate timings, such as once every 12 hours or once a day. The control unit 11 of the server 10 reads the sensor data of the monitoring subject for whom the normal mode is set from the monitoring subject's sensor data DB 13b (S51). For example, the control unit 11 reads out the heart rate data and respiration rate data of the monitoring subject for a predetermined period of time, such as the most recent several hours or one day.

The control unit 11 detects a change in the state of the person being monitored based on the read sensor data (S52). Specifically, the control unit 11 detects signs related to changes in biological information that appear in a person approaching death. For example, based on the read heart rate data and respiration rate data, the control unit 11 determines whether or not there has been a sudden change in the heart rate and respiration rate over the last few minutes to several tens of minutes. In addition, the normal heart rate and respiration rate of the monitoring subject are stored in the monitoring subject DB 13a as reference data, and the control unit 11 compares the heart rate and respiration rate with the normal heart rate and respiration rate. It may be determined whether sudden changes in heart rate and respiration rate per minute are occurring. In addition to the heart rate and the respiratory rate, the control unit 11 may also consider the body temperature and blood pressure of the monitoring subject to determine changes in the monitoring subject's condition.

The control unit 11 determines whether or not the end-of-life mode should be set as the operation mode of the monitoring subject based on the change in the monitoring subject's condition (S53). Here, the control unit 11 determines that the end-of-life care mode should be set when a symptom appearing in a person approaching death is detected. Note that the control unit 11 is not limited to a configuration that determines whether or not to set the end-of-life care mode based on symptoms that appear in a person who is approaching death, such as rapid changes in heart rate and respiratory rate. For example, it may be determined that the end-of-life care mode should be set for the person to be monitored when the duration of the in-bed state is longer than or equal to a predetermined period, that is, when the person does not leave the bed for a predetermined period or longer. In addition, when the server 10 can communicate with an electronic medical record server that manages an electronic medical record in which the medical record of the monitored person is registered, the control unit 11 acquires information on the status of the monitored person from the electronic medical record, It may be determined whether or not to set the end-of-life mode based on the acquired information.

When it is determined that the end-of-life mode should be set (S53: YES), the control unit 11 outputs to the staff terminal 30 recommendation information indicating that the end-of-life mode should be set for the monitoring subject. (S54). For example, as shown in FIG. 13, the control unit 11 instructs the staff terminal to display a mark indicating recommendation of the end-of-life mode in the individual field R1 of the monitored person for whom setting of the end-of-life mode should be recommended in the room list on the notification screen. 30. As a result, in the room list being displayed on the staff terminal 30, it is possible to present the person to be monitored for whom the end-of-life care mode should be set. In the example shown in FIG. 13, a mark of "recommend end-of-life mode" is displayed in the individual field R1 of the person to be monitored in room No. 108.

On the other hand, when it is determined that the end-of-life mode should not be set (S53: NO), the control unit 11 skips the process of step S54, and the monitoring target person who has not executed the above-described process (unprocessed monitoring target person ) is present (S55). If it is determined that there is an unprocessed person to be monitored (S55: YES), the control unit 11 returns to the process of step S51 and selects an unprocessed person to be monitored among the persons to be monitored for whom the normal mode is set. (S51), and the processing of steps S52 to S54 is executed based on the read sensor data.

If it is determined that there is no unprocessed person to be monitored (S55: NO), the control unit 11 terminates the series of processes. Through the above-described processing, the control unit 11 can determine whether or not to change to the end-of-life mode based on the sensor data for the person to be monitored for whom the normal mode is set. Therefore, it is possible to search for a monitoring target who should be changed to the end-of-life care mode from the monitoring targets for whom the normal mode is set, and to present to the care staff a recommendation to change the setting to the end-of-life care mode for the searched monitoring target. can. Therefore, the care staff can easily grasp the monitoring target for whom the end-of-life care mode should be set, and the need for the care staff to determine whether or not the end-of-care mode should be set for each monitoring target is eliminated. Therefore, it is possible to reduce the burden on care staff.

In the present embodiment, the server 10 is not limited to presenting recommendation information to the care staff via a room list when determining that the end-of-life care mode should be set. For example, the server 10 is configured to automatically change the settings to the end-of-life care mode for the monitored person who has determined that the end-of-life care mode should be set without presenting the recommendation information to the care staff. good too. In this case, the care staff does not need to change the setting of the operation mode, so the operation burden on the care staff can be reduced.

In the present embodiment, the process of determining whether to set the end-of-life mode based on the sensor data of the monitored person may be performed using a learning model learned by machine learning. The learning model is assumed to be used as a program module that functions as part of artificial intelligence software. For example, when sensor data is input using algorithms such as CNN (Convolution Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), the operation to be set for the person to be monitored A learning model trained to output information indicating the mode can be used. In this case, the control unit 11 inputs the sensor data detected from the monitored person to the learning model, and based on the output information from the learning model, sets the end-of-life mode for the monitored person or sets the normal mode. can decide what to do.

FIG. 14 is an explanatory diagram of a configuration example of a learning model. The learning model shown in FIG. 14 receives as input the heart rate data and respiratory rate data of the monitoring subject detected by the bed sensor 21, and based on the input data, the operation mode to be set for the monitoring subject is determined. It has learned to perform a discriminative operation and output the result of the operation. The learning model shown in FIG. 14 has two output nodes, the output node 0 outputs the probability that it should be determined that the end-of-life mode should be set, and the output node 1 outputs the other, that is, the normal mode output the probability that should be determined to be set. The output value of each output node is, for example, a value between 0 and 1.0, and the sum of the discrimination probabilities output from each output node is 1.0.

The learning model shown in FIG. 14 includes heart rate data and respiratory rate data for training, and information (correct label) indicating the operation mode (at-the-waiting mode or normal mode) to be set for the corresponding monitoring subject. It is generated by machine-learning an unlearned learning model using training data. In the learning model, when heart rate data and respiration rate data for training are input, the output value from the output node corresponding to the content indicated by the correct label approaches 1.0, and the output value from the other output nodes is learned to approach 0.0. In the learning process, the learning model performs calculations based on the input heart rate data and respiration rate data, and calculates output values from each output node. Then, the learning model compares the calculated output value of each output node with the value (0 or 1) corresponding to the correct label, and performs arithmetic processing so that each output value approximates the value corresponding to the respective correct label. Optimize the parameters used for The parameters are weights between neurons in the learning model, and the like. Although the parameter optimization method is not particularly limited, error backpropagation, steepest descent method, or the like can be used. As a result, when heart rate data and respiration rate data of a monitoring subject are input, a learning model that has learned to determine whether the operation mode to be set for the monitoring subject is the end-of-life mode or the normal mode. can get.

Training of the learning model is performed by another learning device. A trained learning model generated by learning in another learning device is downloaded from the learning device to the server 10 via, for example, the network N or the portable storage medium 10a and stored in the auxiliary storage unit 13. Note that the learning model is not limited to the configuration shown in FIG. 14, and data input to the learning model is not limited to heart rate data and respiration rate data. For example, the learning model may be configured such that body temperature data, blood pressure data, etc. are input in addition to heart rate data and respiration rate data. In this case, the learning model is configured to determine the operation mode to be set for the monitored person based on these data, and output determination probabilities for each of the end-of-life mode and the normal mode.

(Embodiment 4)
The information processing systems of the first to third embodiments described above are configured to switch between the normal mode and the end-of-life mode as operation modes for each person to be monitored. With such a configuration, based on the sensor data detected by the bed sensor 21, it is possible to detect entering and leaving the bed, etc. for the person to be monitored for whom the normal mode is set, and the end-of-life care mode is set. It is possible to detect the state of the end-of-life care of the person being monitored. In the present embodiment, an information processing system capable of detecting the end-of-life condition of a person to be monitored whose death is approaching will be described without switching the operation mode.

The information processing system of the present embodiment can be realized using devices similar to those of the information processing system of the first embodiment shown in FIG. 1, so description of the configuration of each device will be omitted. In the information processing system of this embodiment, the bed sensor 21 has the function of a load sensor for detecting the load applied to the bed, in addition to the function of the bed sensor 21 of the first embodiment. For example, the bed sensor 21 uses a condenser microphone, a pressure sensor using a piezoresistive effect, a pressure sensor using a piezoelectric effect, or the like, and detects the air pressure in the air mattress installed on the bed, thereby reducing the load applied to the bed. detect. The bed sensor 21 having such a configuration can detect the monitoring subject's entering and leaving (getting out of bed) in addition to the heart rate, respiratory state, and body movement state of the monitoring subject while in bed. That is, depending on whether or not the bed sensor 21 detects a load equivalent to the weight of the monitoring subject, it is possible to determine whether the monitoring subject enters and leaves (gets out of bed). For example, when the bed sensor 21 detects that the heart rate and the respiration rate are 0, the heart rate and respiration rate of the monitored person getting out of bed can be detected by the bed sensor 21. It can be determined whether the heartbeat and breathing of the monitored person who is in bed have stopped. Therefore, according to such a configuration, it is possible to allow the monitored person to get out of bed and stop the heartbeat and breathing of the monitored person on the bed (state related to end-of-life care) without switching the operation mode for the monitored person. They can be distinguished and detected.

FIG. 15 is a flowchart illustrating an example of a notification screen update processing procedure according to the fourth embodiment. The process shown in FIG. 15 is obtained by adding step S61 instead of steps S17 to S19 to the process shown in FIG. 7, and adding steps S62 to S64 between steps S20 and S21. Description of the same steps as in FIG. 7 will be omitted. 15, steps S11 to S14 in FIG. 7 are omitted.

The control unit 11 of the server 10 and the control unit 31 of the staff terminal 30 of this embodiment execute the same processes as steps S11 to S16 in FIG. After the process of step S15, the control unit 11 of the server 10 of the present embodiment identifies an event that occurred in the monitoring subject here based on the sensor data stored in the sensor data DB 13b in step S13 (S61). Note that the processing of step S61 includes the processing of steps S18 and S19 in FIG. 7, and the control unit 11 detects an event that has occurred in the monitoring subject regardless of whether the monitoring subject is nearing death. Identify.

After the process of step S20, the control unit 11 determines whether the event identified in step S61 is an event related to the end-of-life condition (S62). For example, the control unit 11 determines whether or not the identified event is an event indicating the stoppage of heartbeat and breathing. In addition, sudden changes in heart rate and respiration rate, sudden changes in body temperature or blood pressure, etc. may be events related to information related to end-of-life care. determine whether If it is determined that the event is not related to a state related to end-of-life care (S62: NO), that is, if a normal event other than an event related to end-of-life care has occurred, the control unit 11 proceeds to the process of step S21.

If it is determined that the event is related to the state of end-of-life care (S62: YES), the control unit 11 determines whether or not the person to be monitored is currently in bed (S63). For example, the control unit 11 determines whether or not the person to be monitored is in bed based on the real-time information (for example, status information) of the person to be monitored stored in the DB 13a of the person to be monitored. If it is determined that the person to be monitored is not in bed (S63: NO), that is, if the person to be monitored is out of bed, the control unit 11 assumes that a normal event has occurred, and proceeds to the process of step S21. When it is determined that the patient is in bed (S63: YES), the control unit 11 determines that an alert (event) related to end-of-life care has occurred, assuming that the monitored person in bed is in a state related to end-of-life care. (S64).

After the process of step S64, the control unit 11 proceeds to the process of step S22, and generates alert information for displaying an alert regarding end-of-life care in the alert column R2 of the alert history of the notification screen for the event specified in step S61. (S22), and transmitted to the staff terminal 30 (S23). As a result, when an alert related to end-of-life care is detected for the monitored person, the alert information related to end-of-life care is output in the alert history being displayed on the staff terminal 30, as in the example shown in FIG. .

In this embodiment, the same effects as those of the above-described embodiments can be obtained. In addition, in this embodiment, it is possible to determine whether the person to be monitored has left the bed or whether the heart rate and breathing of the person to be monitored on the bed have stopped without setting the operation mode for each person to be monitored. can be done. Therefore, the care staff does not need to perform operation mode setting operation, and the operation burden can be reduced. The configuration of this embodiment can be applied to the information processing systems of the first to third embodiments described above, and similar effects can be obtained even when applied to the information processing systems of the first to third embodiments. Also in this embodiment, it is possible to apply the modified examples appropriately described in each of the above-described embodiments.

In the information processing systems of the first to fourth embodiments described above, when an alert is generated for each person to be monitored, the content of the alert is stored in the event DB 13c. Therefore, it is possible to measure the occurrence frequency of each alert (alerted event) in nursing care facilities, and to analyze the occurrence distribution of each alert, the temporal change in the occurrence frequency of each alert, and the like. Also, for example, for each alert, it is possible to analyze the time zone, day of the week, and the like in which the occurrence frequency is high. According to such a configuration, it is possible to analyze the tendency of occurrence of alerts in each nursing facility. Appropriate staff allocation becomes possible.

Further, in the information processing systems of Embodiments 1 to 4 described above, when an alert is generated for each monitored person, the content of the alert is stored in the event DB 13c, and when the nursing care for the alert ends, the nursing care Information indicating the end of care is stored in the event DB 13c. Information indicating the end of nursing care is stored in the event DB 13c together with the end date and time of the nursing care, so it is possible to measure the time required from the generation of the alert to the end of the nursing care for each alert. In addition, by analyzing the chronological changes in the time required from the alert to the end of nursing care for each alert, it is possible to ascertain whether or not nursing care staff are realizing efficiency in nursing care. Moreover, when accumulating the information of the nursing care staff who performed nursing care for each alert in association with each alert, it is possible to grasp the time required for nursing care by each nursing staff for each alert. Therefore, it becomes possible to perform personnel evaluation for each nursing staff according to the time each nursing staff requires for nursing care. In addition, it is possible to identify nursing care staff who spend less time on nursing care and who are providing efficient nursing care. Human resource development can be carried out based on a model.

The embodiments disclosed this time are illustrative in all respects and should be considered not restrictive. The scope of the present invention is indicated by the scope of the claims rather than the above-described meaning, and is intended to include all modifications within the scope and meaning equivalent to the scope of the claims.

10 Server 11 Control Part 12 Main Storage Part 13 Auxiliary Storage Part 14 Communication Part 20 Sensor I/F Device 21 Bed Sensor 30 Staff Terminal 34 Communication Part 35 Input Part 36 Display Part 13a Monitoring Subject DB
13b Sensor data DB
13c Event database

Claims (10)

Acquiring the biological information from a bed sensor that detects the biological information of the monitoring subject lying on the bed,
Based on the acquired biological information, determine the state related to the end-of-life care of the monitoring subject,
An information processing method in which a computer executes a process of outputting end-of-life information related to end-of-life care of the person to be monitored according to a determination result. Receiving settings as to whether or not each of the multiple monitored persons in the facility is to be monitored for end-of-life care,
2. The information processing method according to claim 1, wherein the computer executes a process of setting the person to be monitored, who has received the setting as a monitoring target for end-of-life care, as a monitoring target for end-of-life care. determining whether or not the monitoring subject has left the bed based on the biological information of the monitoring subject acquired from the bed sensor;
2. The computer executes a process of judging the state of end-of-life care for a person to be monitored who is set as a monitoring target for end-of-life care based on the biometric information, without determining whether the person is getting out of bed. 2. The information processing method according to 2. The biological information includes heart rate and respiration rate,
4. The information processing method according to any one of claims 1 to 3, wherein the computer executes a process of determining the end-of-life state of the monitoring subject based on the heart rate and the respiratory rate of the monitoring subject. outputting status information indicating the status of each monitored person, the surrounding conditions of the monitored person, or the setting of the monitored object related to the end-of-life care, in association with each of a plurality of monitored persons in the facility;
When an event related to the state of the monitored person, the surrounding state of the monitored person, or the state of the end-of-life care occurs, event information indicating the content of the event is output in association with the monitored person. 5. The information processing method according to any one of claims 1 to 4, wherein the computer executes the processing. The information processing method according to any one of claims 1 to 5, wherein the computer executes a process of suspending the process of determining the end-of-life condition based on the biometric information. 7. The information processing method according to claim 6, wherein the computer executes a process of canceling the suspension of the process of determining the state related to the end-of-life care and restarting the process of determining the state related to the end-of-life care. 8. The information processing method according to any one of claims 1 to 7, wherein the computer executes a process of specifying a monitoring target to be set as a monitoring target related to the end-of-life care based on the biological information of the monitoring target. . an acquisition unit that acquires the biometric information from a bed sensor that detects the biometric information of a person to be monitored lying on the bed;
a determination unit that determines a state related to the end-of-life care of the monitored person based on the acquired biological information;
An information processing apparatus comprising: an output unit that outputs end-of-life information related to the end-of-life care of the person to be monitored according to a determination result. Receiving settings as to whether or not each of the multiple monitored persons in the facility is to be monitored for end-of-life care,
Acquiring end-of-life information about the end-of-life care for the monitoring target person set as the monitoring target related to the end-of-life care;
A program that causes a computer to output the acquired end-of-life information.

Images