JP2023059601A - Program, information processing method, and information processing apparatus - Google Patents

Abstract

To provide a program, or the like, for accumulating the contents of conversations of a caregiver regarding conditions of a person to be monitored (care receiver) without increasing the burden on care staff.SOLUTION: A computer acquires sensor data from a sensor which detects condition of a person to be monitored in a care facility or surrounding conditions of the person to be monitored. The computer determines an event which has occurred on or around the person to be monitored on the basis of the acquired sensor data, and outputs the occurrence of the determined event to terminals of a plurality of caregivers. The computer acquires voice data on conversations of the caregivers from the terminals of the caregivers, and converts the acquired voice data to text data. The computer stores the event and the text data converted from the voice data on the conversations of the caregivers regarding the event, in association with each other, on a storage unit.SELECTED DRAWING: Figure 1

Description

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

In nursing care facilities, a plurality of staff members provide nursing care such as physical care and life support to a plurality of care recipients. In such a situation, for example, each staff member carries an intercom and uses the intercom to communicate with each other while providing nursing care. is realized. In Patent Document 1, a work target (cared person) and work content (care work content) are specified from the uttered voice of a worker (care staff), and the specified work is performed under preset conditions (work conditions). A system has been proposed that notifies an alert to a worker when conditions such as the order of execution) are not satisfied.

JP 2021-71973 A

In the system disclosed in Patent Literature 1, it is possible to identify the work content of the care staff from the speech voice of the care staff, but it is necessary for the care staff to confirm the state of the cared person. In addition, in the system disclosed in Patent Document 1, the pattern of the utterance content when performing each work is determined, and the nursing staff needs to speak in the determined pattern, reducing the burden on the nursing staff. difficult to do.

The present disclosure has been made in view of such circumstances, and the purpose thereof is to provide information on the content of a caregiver's conversation regarding the status of a person to be monitored (care recipient) without increasing the burden on the care staff. The object is to provide a program or the like that can be accumulated.

A program according to an aspect of the present invention acquires sensor data from a sensor that detects the state of a person to be monitored in a nursing care facility or the state of the surroundings of the person to be monitored, and based on the acquired sensor data, performs the monitoring An event occurring around the target person or the monitoring target person is determined, the occurrence of the determined event is output to terminals of a plurality of caregivers, and the plurality of caregivers converse from the terminals of the plurality of caregivers. acquire voice data, convert the acquired voice data into text data, associate the determined event with the text data converted from the voice data of the conversations of the plurality of caregivers regarding the event, and store the text data in a storage unit; Make the computer perform the process to

According to one aspect of the present invention, the state of a monitoring subject can be determined, and when an event occurs, the contents of a conversation made by a caregiver in response to the event can be stored in association with the event. .

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; 4 is a flow chart showing an example of a processing procedure in an information processing system; 4 is a flow chart showing an example of a processing procedure in an information processing system; FIG. 4 is an explanatory diagram showing a configuration example of a learning model; FIG. 4 is an explanatory diagram showing a display example of text data of conversation; 9 is a flow chart showing an example of a processing procedure in the information processing system of Embodiment 2; 5 is a flow chart showing an example of a processing procedure for creating report information; FIG. 4 is an explanatory diagram showing an example of report information; FIG. 12 is an explanatory diagram showing a configuration example of an information processing system according to Embodiment 4; 14 is a flow chart showing an example of a processing procedure by a server according to Embodiment 4; 14 is a flow chart showing an example of a processing procedure in the information processing system of Embodiment 5. FIG.

A program, an information processing method, and an information processing apparatus of 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 elderly people and people with mental and physical disabilities living in each room of a nursing care facility is monitored, and when a situation in which nursing care by nursing staff is required is detected, nursing staff An information processing system that notifies to 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, a sleep sensor 21, a toilet sensor 22, a door sensor 23, an environment sensor 24, a human sensor 25, and a call button 26 are connected to the 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. FIG. 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 sleep 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 sleep sensor 21 is installed in the bed of one person to be monitored. The sleep sensor 21 is, for example, a sheet-like sensor, installed between a bed mattress and a sheet, and detects the pulse, respiration, body movement, body temperature, etc. of a person lying on the bed. The sleep sensor 21 uses, for example, a condenser microphone, a pressure sensor that uses a piezoresistive effect, a pressure sensor that uses a piezoelectric effect, etc., and detects the air pressure in the air mattress installed on the bed to detect the input of the monitoring subject. Bed and bed (leaving), heart rate while in bed (during sleep), respiratory state, body movement state, etc. are detected. The sleep sensor 21 is installed on the bedside of the bed or on the wall of the room, and detects the arrival and departure of the person to be monitored, the pulse, respiration, body movement, body temperature, etc. of the person lying on the bed by microwaves or infrared rays. You may use a sensor that Based on the detected signals, the sleep sensor 21 detects bed entry and exit, body movement, apnea occurrence state, sleep depth, midway awakening occurrence state (sleep interrupted and wakeful state), heart rate Sleep data such as number, respiration rate, and body temperature are analyzed and output to the sensor I/F device 20 .

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 human sensor that detects the presence 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 human detection sensor 25 is a sensor that detects whether or not a person exists in the living room of a person to be monitored. Detect presence. The human sensor 25 is installed, for example, on the wall surface of a living room. When detecting the presence of a person, the human sensor 25 outputs to the sensor I/F device 20 a detection signal indicating the presence of 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 person to be monitored) 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 carried by a nursing care staff of a nursing facility, and is a portable communication terminal such as an intercom, a smart phone, or a tablet terminal. The staff terminal 30 outputs the notification information received from the server 10 to notify the care staff of the status of each monitored person (occurred event). Also, the staff terminal 30 is configured to transmit and receive voice messages to and from other staff terminals 30 , and the care staff can converse with other care staff via the staff terminal 30 . In this embodiment, the staff terminal 30 is configured to use an intercom in which a headset is provided with a microphone 35, an earphone 36, and a communication unit 34 (see FIG. 2 for all), but is not limited to this configuration. For example, a smartphone or tablet terminal may be used as the staff terminal 30 by connecting a headset provided with a microphone and earphones or headphones via a wire or wirelessly.

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, a microphone 35, an earphone 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 auxiliary storage unit 33 also stores a conversation application program 33AP (hereinafter referred to as a conversation application 33AP) for transmitting and receiving voice messages to and from other staff terminals 30 via the network N. The program 33P, conversation application 33AP and various data may be written in 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 be stored. 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 wireless communication, and transmits and receives information to and from other devices via the network N. The microphone 35 is an audio input unit that collects surrounding sounds and generates digital audio data, and transmits the acquired audio data to, for example, the main storage unit 32 for storage. The earphone 36 is an audio output unit that outputs audio according to instructions from the control unit 31 , and outputs messages or warning sounds according to instructions from the control unit 31 . The staff terminal 30 may be configured to include headphones or speakers instead of the earphones 36 .

In addition to the configuration described above, the staff terminal 30 may have an input unit for receiving operation input by the care staff, a display unit such as a liquid crystal display or an organic EL display, a camera, and the like.

The server 10 has a control section 11, a main storage section 12, an auxiliary storage section 13, a communication section 14, etc., and these sections 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 monitoring subject DB 13a includes a subject ID column, a name column, an age column, a gender column, a room number column, and a notification target event 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 (room number) of the monitoring subject in association with the subject ID. The notification target event column stores information (for example, event name, event identification information) of an event to be notified to the care staff among the events occurring in the monitoring target.

An event is an event that occurs in the monitored person's condition or the surrounding environment of the monitored person. include. For example, an event may include a person to be monitored leaving the bed (getting out of bed), an increase in body movement of the person to be monitored while in bed (in bed, sleeping), use of the toilet and staying in the toilet for a long time, opening the door, or room temperature or humidity out of a predetermined range, heartbeat or respiration of the person to be monitored stops, operation of the sensors 21 to 25 or the sensor I/F device 20 stops, 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 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. 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 . When determining that an event has occurred for each person to be monitored, the control unit 11 registers information about the determined event in the event DB 13c.

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 sleep sensor column, a toilet sensor column, a door sensor column, an environment sensor column, a motion 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 sleep sensor column stores sleep data indicating the sleep state of the monitoring subject detected by the sleep sensor 21 . The sleep data includes data indicating the state of getting in and out of bed, body movement data indicating the magnitude of body movement, apnea data indicating the occurrence state of an apnea phenomenon, sleep depth data indicating the depth of sleep, and heart rate. Includes heart rate data, respiration rate data indicating respiration rate, and body temperature data indicating body temperature. 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 temporal changes in the state of getting in and out of bed, a graph showing temporal changes in body movement, a graph showing temporal changes in the occurrence of apnea, and a graph showing temporal changes in sleep depth. , a graph showing temporal changes in heart rate, a graph showing temporal changes in respiration rate, and a graph showing temporal changes in body temperature may be stored in the sleep sensor array. The data of the graph is, for example, a series of data in which a set of the time when the sleep 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. Sleep depth is detected, for example, in three stages of awakening, light sleep, and deep sleep, and the sleep depth data may include the state of occurrence of midway awakening and the total sleep time per 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 (passage/no movement) indicating whether or not the door sensor 23 has detected the opening of the door or the passage of the monitored person through the door. 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) indicating whether or not the human sensor 25 has detected the presence of a person to be monitored (in the room). 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. Note that the toilet sensor array may store only information indicating use of the toilet (use), and the door sensor array may store only information indicating door passage (passage). The column may store only information (presence) indicating the presence of the person to be monitored, and the call button column may store only information (use) indicating the operation of the call button 26 .

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 ID of the person to be monitored. The event DB 13c includes a date and time column, an event item column, an event content column, a conversation text column, a conversation voice column, and a progress information 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 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 in the middle occurs in a person to be monitored, "getting out of bed" is registered as the event item, and "awakening in the middle" 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. The conversation voice string stores voice data of the conversation conducted by the care staff for the event, and the conversation text string stores text data obtained by converting the voice data of the conversation into text. The voice data and text data of the conversation include the date and time when the staff terminal 30 transmitted the voice data and the information of the nursing care staff who is speaking. 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 event DB 13c is not limited to the configuration shown in FIG. For example, in association with the item and content of the event, the event DB 13c may be configured to store photographs and videos taken when nursing care staff provide nursing care to a person to be monitored for the event, as well as recorded audio and the like. .

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 detects the occurrence of an event in the monitored person, and stores the event in the event DB 13c. Update the date and time column, event item column, and event content column. Further, the control unit 11 acquires a conversation exchanged by voice between the staff terminals 30, and when the acquired conversation voice is converted into text data, stores the generated conversation text in a conversation text string, Store the speech in a conversational speech string. The event DB 13c registers information on all events that have occurred in the monitored person. Staff will be notified. Therefore, in the conversation text string and the conversation voice string of the event DB 13c, the text and voice related to the conversation exchanged between the care staff for the event notified to the care staff are stored. In addition to such a configuration, only information of events (events registered as notification target events) notified to the care staff may be registered in the event DB 13c.

Processing performed by each device in the information processing system of this embodiment will be described below. 4 and 5 are flowcharts showing an example of a processing procedure in the information processing system. 4 and 5, 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 processing is executed by the control unit 11 according to the program 13P stored in the auxiliary storage unit 13 of the server 10, and is controlled according to the program 33P and the conversation application 33AP stored in the auxiliary storage unit 33 of the staff terminal 30. It is executed by the unit 31 . 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 (sensor data 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). Based on the sensor data stored in the sensor data DB 13b, the control unit 11 (determining unit) identifies an event that has occurred in the monitoring target here (S14). For example, when receiving from the sleep sensor 21 a signal indicating that the person to be monitored is getting out of bed, the control unit 11 identifies the occurrence of an event that the person to be monitored is getting out of bed. Further, when receiving a signal indicating the state of body movement from the sleep sensor 21, if the magnitude of body movement indicated by the received signal is equal to or greater than a predetermined value, the control unit 11 detects the body movement of the monitoring subject on the bed. 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 identified. Further, when receiving a signal indicating zero heart rate and zero breathing rate from the sleep sensor 21, the control unit 11 identifies occurrence of an event in which a biological reaction cannot be detected (stop of heartbeat and breathing). 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 authentication 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 events described above, and may be any event that occurs in the person to be monitored or in the surroundings of the person to be monitored, and is specified based on detection signals from the sensors 21 to 26. It can contain various possible states. Note that the reference values for determining whether body movement, time spent in the bathroom, 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.

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 monitored person (S15). For example, when the control unit 11 specifies the occurrence of an event of getting out of bed due to awakening in the middle of sleep of the monitoring subject, it stores "getting out of bed" as the event item and "waking up in the middle of the night" as the event content. 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 the occurrence of an event such as a high humidity state or a dry state, it stores "humidity" as an event item, and stores the measured humidity as an event content. When the control unit 11 identifies the occurrence of an event such as heartbeat and respiration stop, it stores "heartbeat" as an event item, and stores the measured heart rate and respiration rate (measured number of zero) as event contents. 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 identifies the occurrence of an event such as malfunction of the sensor I/F device 20 or the sensors 21 to 25, it stores "equipment malfunction" as the event item, and detects the occurrence of unnecessary operation as the event content. The device information of the received device is stored.

Further, when the control unit 11 specifies occurrence of an event of detection of a registrant and detection of an unregistered person, it stores "human detection" as an event item, and detects a monitored person or an unregistered person as an 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 the event specified in step S14 is an event to be notified to the care staff (S16). Here, the control unit 11 determines whether or not the event specified in step S14 is included in the notification target events set for the monitored person specified in step S12. If it is determined that the event is not an event to be notified (S16: 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 . As a result, the server 10 accumulates the sensor data received from the sensor I/F device 20 in the sensor data DB 13b of each monitored person, and accumulates the information of the event occurring in each monitored person in the event DB 13c.

When it is determined that the event is a notification target event (S16: YES), the control unit 11 generates alert information to be notified to the care staff (S17). The alert information includes the content of the event to be notified and the information of the person to be monitored for whom the event occurred. For example, in the case of an event in which a person to be monitored has left the bed, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating that the person to be monitored has left the bed. Specifically, alert information such as "Room 503, Mr. Taro Yamada, got out of bed" is generated. Also, in the case of an event of large body movements, the control unit 11 generates alert information including the room number and name of the monitored person and a message indicating that the monitored person's body movements are large. Also, in the event of a long stay in the restroom, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating the length of stay in the restroom. Also, in the case of an event of door opening, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating that the door is open. Also, in the event of a high temperature state or a low temperature state, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating the room temperature. Also, in the case of an event of high humidity or dryness, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating the humidity. In addition, in the case of an event of cardiac arrest and respiratory arrest, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating the possibility of cardiac arrest and respiratory arrest. Also, in the case of an event of operation of the call button 26, the control unit 11 generates alert information including the room number and name of the person to be monitored, and a message indicating the operation of the call button 26. FIG. In addition, in the case of an event of malfunction of the sensor I/F device 20 or the sensors 21 to 25, the control unit 11 generates alert information including the room number and name of the monitored person and a message indicating the malfunction of the device. do.

Next, the control unit 11 (output unit) transmits the generated alert information to the staff terminal 30 via the network N (S18). For example, the control unit 11 transmits alert information to all communicable staff terminals 30 by broadcast communication. Thereby, the server 10 can output the occurrence of the event in the person to be monitored to the plurality of staff terminals 30 . 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 the alert information transmitted by the server 10 via the communication unit 34, and outputs the received alert information as voice via the earphone 36 (S19). The control unit 11 of the server 10 may generate text data alert information, convert the generated alert information into voice data alert information, and transmit the obtained voice data alert information to the staff terminal 30. good. In this case, the controller 31 of the staff terminal 30 can output the alert information of the received voice data from the earphone 36 as voice. Further, the control unit 11 of the server 10 may generate text data alert information and transmit the generated text data alert information to the staff terminal 30 . In this case, the control unit 31 of the staff terminal 30 can convert the received text data alert information into voice data alert information and output the obtained voice data alert information from the earphone 36 as voice. For example, the control unit 31 voice-outputs the alert information "Room 503, Taro Yamada, got out of bed". By the above-described processing, when the server 10 detects the occurrence of an event set as a notification target for each monitored person, the occurrence of the event can be notified to the care staff via the staff terminal 30. can.

When the care staff is notified of the occurrence of an event via the staff terminal 30, the care staff uses the staff terminal 30 to have a conversation with other care staff, and performs care care (necessary treatment) for the event that has occurred. do. The control unit 31 of the staff terminal 30 determines whether or not the voice data of the speech voice (conversation voice) uttered by the nursing staff who is the user of the own terminal 30 is acquired via the microphone 35 (S20). When determining that the care staff's uttered voice has been acquired (S20: YES), the control unit 31 transmits the acquired voice data to the other staff terminal 30 and the server 10 via the network N (S21).

When it is determined that the uttered voice of the care staff of the own terminal 30 has not been acquired (S20: NO), the control section 31 proceeds to the process of step S22. That is, the control unit 31 of the staff terminal 30 that has not acquired the uttered voice of the care staff determines whether it has received voice data transmitted by another staff terminal 30 that has acquired the uttered voice of the care staff (S22 ). When the control unit 31 determines that the voice data transmitted by the other staff terminal 30 has been received (S22: YES), based on the received voice data, the conversation voice emitted by the other care staff is transmitted via the earphone 36. (S23). If the control unit 31 determines that it has not received voice data from another staff terminal 30 (S22: NO), it skips the process of step S23 and returns to the process of step S20. The process of transmitting the acquired voice data to the other staff terminal 30 and the server 10 is repeated each time the voice uttered by the staff is acquired. Also, the control unit 31 repeats the process of outputting the conversational voice based on the received voice data from the earphone 36 each time voice data transmitted by another staff terminal 30 is received. Thereby, the nursing staff can talk with each other via the staff terminal 30 . For example, when nursing staff A says, "Mr. Yamada at 503, you're out of bed. Is anyone nearby?" Send to other staff terminals 30 . The other staff terminal 30 outputs the received voice data as voice, and when the care staff B who heard this voice says, "B. The terminal 30 acquires the voice data uttered by the care staff B and transmits it to other staff terminals 30 . The other staff terminal 30 outputs the received voice data as a voice, and when the care staff A who hears this voice says "Mr. B, please", the staff terminal 30 of the care staff A obtains the voice data emitted by the staff terminal 30 and transmits it to another staff terminal 30.例文帳に追加The other staff terminal 30 outputs the received voice data as voice, and each care staff who hears this voice can understand that the care staff B will provide care in response to the notified event (alert).

In addition, when the care staff B needs help or advice from another care staff while performing care care for the alert, he/she emits a conversation voice asking for help or advice. In this case, the staff terminal 30 of the care staff B acquires the voice data uttered by the care staff B and transmits it to the other staff terminals 30, thereby requesting help or advice from the other care staff. Further, when nursing care staff B completes the nursing care for the notified event, the nursing staff B emits a conversation voice reporting the completion of the nursing care. In this case, the staff terminal 30 of the care staff B acquires the voice data uttered by the care staff B and transmits it to the other staff terminal 30, thereby reporting the completion of the care to the other care staff. . In this way, each nursing staff can provide nursing care while conversing via the staff terminal 30 .

The control unit 11 (audio data acquisition unit) of the server 10 receives the audio data transmitted by each staff terminal 30 (S24). In addition, the control unit 31 of the staff terminal 30 transmits voice data and the identification information of the own terminal 30 or the identification information of the care staff who uses the own terminal 30, and the control unit 11 of the server 10 transmits the voice data is received, the staff terminal 30 that is the transmission source or the care staff that uses the staff terminal 30 can be specified. The control unit 11 (conversion unit) converts the received voice data into text data, and generates text data of conversation voice of the care staff (S25).

Then, the control unit 11 stores the text data generated in step S25 and the voice data received in step S24 in the event DB 13c (storage unit) of the monitored person (monitored person for whom an event has occurred). is stored (S26). Specifically, the control unit 11 associates the identification information of the nursing care staff who issued the received voice data, the date and time when the voice data was received, and the text data of the generated conversation voice, and stores them in a conversation text string, The identification information of the care staff, the reception date and time of the voice data, and the voice data received in step S24 are associated with each other and stored in the conversation voice string. Note that the control unit 11 stores the conversation text and the conversation voice in the event DB 13c in association with the event stored in the event DB 13c in step S15. Through the above-described processing, the control unit 11 can acquire voice data of conversations between care staff members from each staff terminal 30, and the event that occurred in the monitored person and the conversation conducted by each care staff regarding the event can be obtained. text data and voice data can be stored in association with each other.

The control unit 11 determines whether or not the care staff has finished providing care for the event notified to the care staff by sending the alert information to the staff terminal 30 in step S18 (S27). For example, the staff terminal 30 may be provided with an input unit (input button) for inputting termination of nursing care, and when the input button is operated, termination of nursing care may be determined. Further, the control unit 11 may determine whether or not the nursing care has ended, depending on whether or not the voice data uttered by the nursing care staff who is providing the nursing care includes a predetermined keyword. For example, keywords such as "end" and "end (completion)" are registered in advance in the auxiliary storage unit 13, and when the keyword is included, the control unit 11 may determine that nursing care has ended. . In addition to determining whether or not the keyword is included in the voice data uttered by the care staff, it may be determined whether or not the keyword is included in the text data converted from the voice data.

In addition, the end of nursing care by the nursing staff may be determined 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, using algorithms such as CNN (Convolution Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), Transformer, BERT (Bidirectional Encoder Representations from Transformers), GPT (Generative Pre-Training), A learning model that learns to output information indicating whether or not the conversation data (voice data or text data) by nursing staff is input, indicating whether or not the content of nursing care for the person being monitored is included in the conversation data. can be used. In this case, the control unit 11 inputs the conversation data of the care staff to the learning model, determines whether or not the content related to care care by the care staff is included based on the output information from the learning model, and determines from the determination result , it can be determined whether or not the nursing care by the nursing care staff has ended.

FIG. 6 is an explanatory diagram showing a configuration example of a learning model. The learning model shown in FIG. 6 is input with conversation data (speech data or text data) conducted by the care staff using the staff terminal 30, and based on the input data, the conversation is interpreted as a nursing care by the care staff. It is learned to perform an operation to determine whether or not the content is related to and to output the result of the operation. The learning model shown in FIG. 6 has two output nodes. The output node 0 outputs the probability that it should be determined that the input conversation data contains content related to nursing care by the nursing care staff, and the output node 1 outputs the probability that it should be determined as other content, for example, chat. 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. 6 includes training conversation data (speech data or text data) and information indicating whether the conversation data includes content related to nursing care or other content (chat) ( Correct label) is used to machine-learn an unlearned learning model. In the learning model, when conversational data for training is 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 approaches 0.0. Learn to get closer. In the learning process, the learning model performs calculations based on the input conversation 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. The parameter optimization method is not particularly limited, but error backpropagation, steepest descent method, or the like can be used. As a result, when conversation data is input, a learning model trained to determine whether the input conversation data includes content related to nursing care or whether it is a chat that does not include content related to nursing care. 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. 6, and the number of discrimination objects discriminated by the learning model is not limited to two. For example, the learning model may be configured to determine whether input conversation data includes content related to nursing care, chat, or content indicating the end of nursing care. In this case, the control unit 11 can determine whether or not the nursing care staff has completed the nursing care based on the output information from the learning model. In addition, the learning model determines whether the input conversation data includes content related to nursing care, chat, content indicating the start of nursing care, content indicating the implementation of nursing care, or content indicating the end of nursing care. may be configured to determine. In this case, it is possible to determine the progress of the notified event, such as whether nursing care by the nursing care staff has started, is in progress, or has ended.

Returning to the description of the processing shown in FIG. If it is determined that the nursing care staff has not finished nursing care (S27: NO), the control unit 11 returns to the process of step S24, and responds to the voice data transmitted from the staff terminal 30 in steps S24 to S27. process. As a result, the voice data of the conversation transmitted from the staff terminal 30 and the text data of the conversation generated from the voice data can be accumulated in the event DB 13c. Therefore, voice data and text data of conversations conducted by the care staff using the staff terminal 30 are accumulated in the event DB 13c.

When it is determined that the nursing care by the nursing care staff has ended (S27: YES), the control unit 11 puts "completed" indicating the end of nursing care in the progress information column of the event DB 13c of the monitored subject for whom the nursing care has ended. Store (S28) and terminate the series of processes. By the above-described processing, the server 10 can determine the state of each person to be monitored based on the signals from the sensors 21 to 25 and the call button 26 provided in association with each person to be monitored. can detect the occurrence of an event that needs to be notified to In addition, the server 10 can notify each nursing staff via the staff terminal 30 when it detects the occurrence of an event for each monitored person. The care staff can have a conversation with other care staff using the staff terminal 30, and the server 10 stores the text data and voice data of the conversation between the care staff to the generated event. They can be associated and stored.

The text data of conversations between care staff members accumulated in the event DB 13c through the above-described processing can be viewed using, for example, the staff terminal 30 or another terminal. FIG. 7 is an explanatory diagram showing a display example of text data of conversation. When browsing the text data of the conversation accumulated in the event DB 13c, the viewer designates an arbitrary person to be monitored and an arbitrary date and time or an event that occurred, and reads the text data of the conversation corresponding to the designated event. Make a request to the server 10. The control unit 11 of the server 10 reads event information and conversation text data (conversation text) corresponding to the content of the request from the event DB 13c and transmits them to the requesting terminal.

When receiving the event information and conversation text data from the server 10, the requesting terminal generates a screen as shown in FIG. 7A and displays it on the display unit. On the screen shown in FIG. 7A, the alert information generated by the control unit 11 of the server 10 in step S17 in FIG. 4 and the date and time of occurrence of the alert (event) are displayed in the bold display frame. Information of the nursing care staff member who spoke, the date and time of the speech, and the text data of the conversation of the care staff member generated by the control unit 11 of the server 10 in step S25 in FIG. are displayed in chronological order. With the screen as shown in FIG. 7A, the viewer can grasp the content of the event that occurred, the conversation content of the care staff regarding the event, and the content of the care given to the monitoring target.

In this embodiment, a plurality of types of sensors 21 to 25 are provided to determine the state of the person being monitored. ) are monitored. Further, it is possible to set an event to be notified to the care staff among the events that have occurred for each person to be monitored. Therefore, different events can be set as events to be notified to the care staff according to the health condition of the monitoring subject.

In this embodiment, when the control unit 11 of the server 10 generates text data from the voice data of the conversation by the nursing care staff received from the staff terminal 30, the control unit 11 extracts a pre-registered keyword from the generated text data and extracts it. It may be configured to perform highlighting processing for highlighting the keyword that has been entered. For example, after the processing of step S25 in FIG. 5, the control unit 11 identifies predetermined keywords from the generated text data, and executes emphasis processing on each keyword. In such a configuration, when browsing the text data of the conversation accumulated in the event DB 13c of the server 10, a predetermined keyword is highlighted and displayed as shown in FIG. 7B. Therefore, the viewer can grasp important keywords from the content of conversations between a plurality of nursing care staff members without overlooking them. In the example shown in FIG. 7B, the room number and name of the person to be monitored, the content of the event, and the content of nursing care are displayed surrounded by frames.

In the processing shown in FIGS. 4 and 5 of the present embodiment, when the server 10 acquires the conversational voice of the care staff from the staff terminal 30, the conversational voice is associated with any event occurring in any monitored person. It may be configured to carry out a process of identifying whether it was spoken to. The control unit 11 of the server 10 performs the processing of steps S12 to S18 each time it receives sensor data from each sensor I/F device 20. FIG. Therefore, the server 10 may continuously transmit alert information regarding different events to the staff terminal 30 . That is, after alert information about one event is sent to the staff terminal 30, before the nursing care staff finishes nursing care for the event, a situation occurs in which alert information about another event is sent to the staff terminal 30. . In this case, since the care staff will talk about a plurality of events, it will be necessary to determine which event each care staff's conversation is about. Therefore, the control unit 11 of the server 10, for example, after the processing of step S25 in FIG. Identify an event corresponding to voice data (conversation voice of care staff).

For example, the control unit 11 determines that a conversational voice received within a predetermined time after sending the alert information is a conversation corresponding to the event of the sent alert information. Specifically, the control unit 11 controls the conversation voice received from the staff terminal 30 within a predetermined time (for example, within 30 seconds) after sending the alert information in step S18, and the conversation voice received for a predetermined time. Conversation voices of other care staff received within (for example, within 10 seconds) are judged to be conversations corresponding to the event that sent the alert information in step S18. As a result, a conversation held within a predetermined period of time after notification of the occurrence of an event can be identified as a conversation related to the event. Further, the control unit 11 may determine from the content of the received conversation whether the conversation relates to which event occurred in which monitored person. For example, if the conversation content includes information about the monitored person or information about an event, the control unit 11 can identify the event corresponding to the received conversation voice based on the information included in the conversation content. In this case, even if a predetermined time or more has passed since the alert information was sent, it is possible to identify which event the conversation voice of the care staff is related to. Note that if there is only one event being notified to the care staff, the control unit 11 may determine that the audio data received in step S24 is the conversational audio related to the event for which the alert information was sent in step S18.

After that, in step S26, the control unit 11 stores the text data of the conversation voice of the care staff in the conversation text string corresponding to the identified event in the event DB 13c of the monitoring subject for whom the event has occurred, and The voice data of the care staff's conversational voice is stored in the conversational voice string corresponding to . Thereby, the conversation voice and conversation text of the care staff can be stored in association with the corresponding event.

In the above-described embodiment, the server 10 is configured to convert the acquired voice data into text data each time the voice data of the conversation conducted by the care staff using the staff terminal 30 is acquired and stored in the event DB 13c. is. However, the process of converting voice data into text data does not need to be performed at the timing when voice data is acquired, and may be performed, for example, at predetermined time intervals. For example, when the server 10 acquires voice data of a conversation by a nursing care staff, it stores the acquired voice data in the event DB 13c, converts each voice data into text data at a predetermined timing, and stores the data in the event DB 13c. You may

(Embodiment 2)
When the server 10 acquires the conversation voice of the nursing care staff from the staff terminal 30, it determines whether or not the conversation voice is a conversation about the response (nursing care) to the event that occurred in the monitored person, An information processing system for accumulating conversation information 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.

FIG. 8 is a flowchart illustrating an example of a processing procedure in the information processing system according to the second embodiment; The process shown in FIG. 8 is obtained by adding steps S31 to S32 between steps S25 and S26 in the processes shown in FIGS. Description of the same steps as those in FIGS. 4 and 5 will be omitted. Also, in FIG. 8, illustration of each step in FIG. 4 is omitted.

The server 10 and staff terminal 30 of this embodiment perform the same processing as steps S11 to S25 in FIGS. As a result, the server 10 acquires signals from the sensors 21 to 25 and the call button 26 via each sensor I/F device 20, and based on the acquired signals, generates an event for each person to be monitored. detect. Further, when detecting the occurrence of an event to be notified to the care staff, the server 10 notifies the care staff of the occurrence of the event via the staff terminal 30 . Furthermore, when the server 10 acquires the uttered voice of the care staff from the staff terminal 30, the server 10 converts the acquired voice data into text data.

After the process of step S25, the control unit 11 of the server 10 of this embodiment identifies the content of the conversation voice received from the staff terminal 30 (S31). For example, the control unit 11 specifies whether the content of the conversational voice is related to nursing care provided by the nursing care staff to the person being monitored, whether it is a chat, or the like. For example, if the content of conversation includes information about a person to be monitored or information about an event, the control unit 11 determines that the content of the conversation is related to nursing care for the person to be monitored. In addition, when the content of the conversation does not include the information of the monitoring target and the information about the event, the control unit 11 may determine that the conversation voice is not the content related to nursing care for the monitoring target, but is, for example, a chat. . Further, the control unit 11 may use a learning model to determine whether the content of the conversational voice is content related to nursing care for the monitored person or chat. For example, the learning model shown in FIG. 6 can be used. In this case, the control unit 11 inputs the voice data (or text data generated from the voice data) received from the staff terminal 30 to the learning model, and based on the output information from the learning model, the content of the received conversation voice However, it can be determined whether the content is related to nursing care by the nursing staff or whether it is a chat.

Based on the identified conversation content, the control unit 11 determines whether or not the conversation received from the staff terminal 30 is related to nursing care for the person being monitored (S32). If it is determined that the content is related to nursing care for the monitored person (S32: YES), the control unit 11 stores the text data generated in step S25 and the and store the received audio data (S26). On the other hand, if it is determined that the content is not related to nursing care for the monitoring target (S32: NO), for example, if it is a chat, the control unit 11 skips the process of step S26.

When it is determined that the content of the conversation of the nursing staff is chatting by the above-described processing, the text data and voice data of the conversation are not stored in the event DB 13c, thereby accumulating the conversation information of the chatting of the nursing staff in the event DB 13c. can be avoided. Therefore, the server 10 can extract conversation information about nursing care by the nursing staff from the conversation information (conversation voice and conversation text) by the nursing staff, and store the extracted conversation information in association with the occurred event. In the above-described process, both the conversation information about nursing care by the nursing care staff and the conversation information of chatting by the nursing care staff are stored in the event DB 13c, and each conversation information includes whether it is about nursing care or chatting. It may be configured such that information indicating whether or not is associated with and stored.

In this embodiment, the same effects as those of the first embodiment described above can be obtained. Further, in the present embodiment, among the conversation information by the care staff received from the staff terminal 30, the server 10 can accumulate conversation information that needs to be accumulated, such as conversation regarding nursing care for the person to be monitored. can. Therefore, when confirming the nursing care provided by the nursing care staff for each event, it is possible to efficiently view the conversation information regarding the nursing care provided by the nursing staff. 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 will be described in which the server 10 prepares a report on an event occurring in a monitoring subject based on conversation contents (conversation text) of care staff accumulated for the event. 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 server 10 and the staff terminal 30 execute the same processes as those shown in FIGS. 4 and 5. FIG. As a result, the server 10 detects the occurrence of an event for each person to be monitored based on signals from the sensors 21 to 25 and the call button 26 acquired via each sensor I/F device 20, and Alert information can be transmitted to each staff terminal 30 accordingly. In addition, when alert information (occurrence of an event) is notified to the care staff, the server 10 converts the speech voice of the care staff acquired from the staff terminal 30 into text data, associates it with the event, and accumulates it.

The server 10 of the present embodiment stores information (nursing care record information) as a nursing care record based on the information about the event that occurred in the monitoring subject, which is accumulated in the event DB 13c by the processing shown in FIGS. Automatically create various types of report information (reports) such as information to be reported to medical professionals such as doctors (doctor report information) and information to be reported to the family of the monitored person (family report information) have a function.

FIG. 9 is a flow chart showing an example of the report information creation processing procedure, and FIG. 10 is an explanatory diagram showing an example of the report information. The following processing is executed by the control section 11 according to the program 13P stored in the auxiliary storage section 13 of the server 10. FIG. Note that the control unit 11 of the server 10 is configured to periodically execute the following processes, and when a predetermined execution timing arrives, it starts executing the processes after step S41. For example, when the report information is created once a day, the predetermined execution timing may be the timing at which a predetermined time has arrived. It may be the timing. Note that the frequency of creating the report information is not limited to once a day or once a week. times. Alternatively, it may be determined that the execution timing has come when a creation request from a care staff or the like is received. In addition, different generation frequencies may be set for each of the nursing care record information, the doctor report information, and the family report information, and the generation frequency of each report information may be set differently for each monitored person. good too. In the case of a configuration in which the generation frequency of each report information is set for each monitored person, the generation frequency of each report information may be registered in the monitored person DB 13a in association with the monitored person.

When a predetermined execution timing arrives, the control unit 11 of the server 10 determines whether or not there is a target (monitoring target) for which report information should be created at this time (S41). For example, when it is time to create each item of report information, the control unit 11 creates report information corresponding to each person to be monitored, with all persons to be monitored as persons to be created for report information. Further, when the timing for creating report information set for an arbitrary monitoring target person arrives, the control unit 11 sets the monitoring target person as the target person for creating report information, and creates report information corresponding to the monitoring target person. conduct.

When it is determined that there is a target person for creating report information (S41: YES), the control unit 11 reads out information on events accumulated in the event DB 13c corresponding to one monitoring target person (S42). The control unit 11 reads information on events that have occurred within a predetermined period corresponding to the timing of creating report information, thereby reading information on events for which report information has not yet been created (unreported events). For example, the event DB 13c may be configured to store status information indicating whether or not report information has been created (reported) in association with information on each event. 11 may read the information of events whose status information has not yet been reported. Note that the control unit 11 reads the date and time, event item, event content, conversation text, and progress information from the event DB 13c as information of each event.

The control unit 11 identifies the content of one event from the read information of each event (S43). For example, the control unit 11 identifies the date and time of event occurrence and the content of the event based on the read date and time, event item, and event content. For example, the control unit 11 specifies "2021/9/1 1:00 getting out of bed (halfway awakening)" as the content of the event. Next, the control unit 11 identifies the details of the nursing care provided by the nursing care staff for the identified event from the read conversation text (S44). For example, the control unit 11 specifies “2021/9/1 1:05 nursing staff A: toilet assistance” and “2021/9/1 1:15 completion of response” as nursing care performed by the nursing staff. In addition, information related to nursing care that may be provided by the nursing care staff is registered in advance in the auxiliary storage unit 13 of the server 10, and the control unit 11 extracts the registered information from the conversation text, thereby performing nursing care. May identify the care provided by the staff.

In addition, the control unit 11 may summarize the conversation text using the learning model and specify the details of the nursing care provided by the nursing staff. For example, when text data of conversation is input using algorithms such as CNN, RNN, LSTM, Transformer, BERT, GPT, care staff identified from the content of the conversation by summarizing the content of the conversation A learning model can be used that has been trained to output information about care by. In this case, the control unit 11 inputs the conversation text to the learning model, and based on the output information from the learning model, identifies the care staff who provided care for the event and the care provided by the care staff. be able to.

The learning model here is a learning model trained to input text data of a conversation uttered by a care staff and output text data as a result of summarizing the input text data. Such a learning model is, for example, text data for training and a word or sentence to be extracted as a summary result of this text data for a learning model optimized as parameters for executing general-purpose summarization processing. It is generated by fine-tuning (transfer learning) using training data including (correct label). In fine-tuning, the learning model receives training text data, performs calculations based on the input text data, and calculates an output value between 0 and 1 for each word or sentence in the input text data. do. Then, the learning model compares the calculated output value for each word or each sentence with the value corresponding to the correct label (1 if correct, 0 if not correct), and performs arithmetic processing so that both are approximate. Optimize the parameters used for As a result, a learning model is obtained that, when text data of a conversation by a nursing care staff is input, outputs text data as a result of summarizing the input text data. Learning of the learning model here 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.

Based on the information read from the event DB 13c in step S42, the control unit 11 determines whether or not the contents of all events have been specified (S45). When determining that the contents of all events have not been specified (S45: NO), the control unit 11 returns to the process of step S43, and executes the processes of steps S43 and S44 for unspecified events. As a result, the control unit 11 identifies the content of other events from the event information read in step S42 (S43), and identifies the content of nursing care provided by the care staff for the identified event ( S44).

If the control unit 11 determines that the contents of all the events have been identified based on the information read in step S42 (S45: YES), the contents of the event identified in step S43 and the care staff identified in step S44 Nursing care record information is created based on the details of the nursing care provided by (S46). As shown in FIG. 10, the nursing care record information is created in association with the monitored person for whom the report information is created. This includes information such as the date, time and content of care provided, and the date and time of completion of care by care staff. For example, a format for nursing care record information is stored in the auxiliary storage unit 13 in advance, and the control unit 11 stores the details of the specified event and the details of nursing care provided by the nursing care staff in each column of the format for nursing care record information. to generate care record information.

Further, the control unit 11 creates report information to the doctor based on the details of the event specified in step S43 and the details of the care provided by the care staff specified in step S44 (S47). Physician report information is also created in association with the monitored person for whom report information is created. As shown in FIG. 10, the doctor report information includes information such as the date and time of occurrence and details of each identified event, details to be reported to the doctor based on the event that occurred, details to be confirmed with the doctor regarding the details of the report, and the like. . In the example of the doctor-reported information shown in FIG. 10, there is a report about a sleeping state in which the user leaves the bed multiple times during the night to go to the bathroom, and a sleep-related drug and a diuretic drug for the reported content. Confirmation contents to ask the doctor to confirm the relationship with the administration of Note that the content of the report to the doctor and the content of confirmation may be stored in advance in the DB prepared in the auxiliary storage unit 13 of the server 10 in association with the content of each event, the frequency of occurrence, etc., for example. In this case, the control unit 11 can acquire the content of the report and the content of confirmation to the doctor from the DB according to the content of the event specified in step S43. Further, the content of the report to the doctor or the content of confirmation may be input by the care staff from the staff terminal 30 or another terminal. Again, the format for the doctor report information is stored in advance in the auxiliary storage unit 13, and the control unit 11 inputs the contents of the specified event, etc. Generate information.

Further, the control unit 11 creates report information to the monitoring subject's family based on the details of the event specified in step S43 and the details of the care provided by the care staff specified in step S44 (S48). . The family report information is also created in association with the monitored person for whom the report information is created. As shown in FIG. 10, the family report information includes information on the daily life of the monitoring subject including the state of occurrence of each specified event, details of nursing care provided by the nursing care staff for the event, It includes information that is shared and indicates that appropriate nursing care is being provided in cooperation with doctors. In the example of the family report information shown in FIG. 10, there is information about the life of the monitoring subject that he/she leaves the bed several times to go to the bathroom in the middle of the night, and the details of the nursing care provided by the nursing care staff in response to this information. , and information indicating that the relationship with the medication being taken has been confirmed by a physician. The content of the report to the family may also be stored in advance in the DB prepared in the auxiliary storage unit 13 of the server 10 in association with the content of each event, the frequency of occurrence, and the like. In this case, the control unit 11 can acquire the content of the report to the family from the DB according to the content of the event specified in step S43. Also, the contents of the report to the family may be configured to be input by the care staff from the staff terminal 30 or another terminal. Here too, for example, the format for family report information is stored in advance in the auxiliary storage unit 13, and the control unit 11 stores the content of the specified event and the care provided by the care staff in each column of the format for family report information. Generate family report information by entering details of care.

When each report information is generated in steps S46 to S48, the control unit 11 may specify a pre-registered keyword from each report information and perform highlighting processing for highlighting the specified keyword. The control unit 11 stores the nursing care record information created in step S46, the doctor report information created in step S47, and the family report information created in step S48 in, for example, the monitoring target DB 13a in association with the target person ID (S49 ). Note that the control unit 11 may store the report information created in steps S46 to S48 in the event DB 13c of each monitored person, for example, in association with the date and time, item, and content of each event. In addition, the control unit 11 may transmit the created care record information to a server or terminal where care records are shared by care staff, or may transmit the created doctor report information to a terminal used by a corresponding doctor. Often, the created family report information may be transmitted to pre-registered family terminals. Further, the control unit 11 associates each piece of report information with the created event, and stores information indicating that the event has been reported in the event DB 13c. Specifically, the control unit 11 stores information indicating that the report has been completed in the event DB 13c in association with the event whose information was read out from the event DB 13c in step S42.

The control unit 11 returns to the process of step S41, and determines whether or not there is a monitored person for whom report information should be created but has not yet created report information (S41). If it is determined that there is no monitored person for whom report information should be created (S41: NO), the control section 11 terminates the series of processes. By the above-described processing, various types of report information can be automatically created based on the conversation texts of the care staff accumulated in the server 10 in association with the event occurring in the monitoring target. In addition, it is possible to create report information with content corresponding to the destination of the report information, such as other care staff, doctors, family members of the monitoring subject, and the like. Note that when different generation timings are set for the nursing care record information, the doctor report information, and the family report information, the control unit 11 may generate the report information when the generation timing arrives, and steps S46 to S48 are performed. Either one or a plurality of them may be executed at an appropriate creation timing. Also, the timing of creating each report information may be set for each person to be monitored. For example, the timing of creating report information to the doctor may be changed according to the condition of the monitoring subject, etc., and the timing of creating the report information to the monitoring subject's family depends on the frequency requested by the family. May be changed. In addition, the report information is not limited to being created on a regular basis. It becomes possible to

In this embodiment, in addition to the configuration for summarizing the conversation text using the learning model and specifying the content of nursing care provided by the nursing care staff, the learning model is used to extract nursing care record information, doctor report information, It may be configured to create family report information. In this case, for example, a learning model for nursing care records that is trained to output nursing care record information (text data) generated by summarizing the input text data, for example, by inputting text data of a conversation uttered by a care staff. may be used to create care record information. In addition, using a learning model for doctor reports that has been trained to output doctor report information (text data) generated by summarizing the input text data with text data of conversations uttered by care staff as input. may be used to generate physician report information. In addition, a learning model for family reports is used, which is trained to output family report information (text data) generated by summarizing the input text data from text data of conversations uttered by nursing care staff. may create family report information. When such a learning model is used, nursing care record information, doctor report information, and family report information can be created from the conversation data of the care staff, thereby reducing the work load of the care staff.

In this embodiment, the same effects as those of the above-described embodiments can be obtained. Further, in this embodiment, based on the text data of the contents of conversations of the care staff, stored in association with each event by the server 10, care record information, report information to the doctor, and report information to the monitoring subject's family are generated. can be created automatically. As a result, it is possible to reduce the work load of the care staff when creating these report information. The configuration of this embodiment can be applied to the information processing systems of the first and second embodiments described above, and similar effects can be obtained even when applied to the information processing systems of the first and second embodiments. Also in this embodiment, it is possible to apply the modified examples appropriately described in each of the above-described embodiments.

(Embodiment 4)
An information processing system that includes a nurse call system and stores information on conversations between a person to be monitored and a care staff using the nurse call system will be described. FIG. 11 is an explanatory diagram showing a configuration example of an information processing system according to the fourth embodiment.

The information processing system of this embodiment includes a server 10, a staff terminal 30, a parent device 40 and a child device 50 in a nurse call system, etc., and these devices are connected via a network N for communication. For example, instead of being connected to the network N, the child device 50 may be connected to the master device 40 via a dedicated communication line or wireless communication. Although not shown in FIG. 11, the information processing system of the present embodiment includes, in addition to the configuration shown in FIG. 11, a sensor I/F device 20 and various sensors 21 to 26 ( (See FIG. 1). Further, the child device 50 of the nurse call system may be provided in the room of the person to be monitored instead of the call button 26 . In the present embodiment, the server 10 and the staff terminal 30 are the same devices as the server 10 and the staff terminal 30 in the information processing system of the first embodiment, so description thereof will be omitted.

The nurse call system includes a handset 50 used as a calling device and a master set 40 used as a response device for responding to calls from the handset 50 . The child device 50 is installed, for example, in each room and shared space of the person to be monitored, and the master device 40 is installed, for example, in a room (staff room) where care staff resides, an office of a care facility, or the like. The staff terminal 30 carried by the care staff may be configured to be used as a response device for the nurse call system.

The child device 50 has a communication unit for communicating with the parent device via the network N, a call button 51 operated (depressed) by the monitored person, a microphone 52, a speaker 53, and the like. The parent device 40 includes a lamp 41 provided in association with each child device 50, a release button 42 for canceling lighting of the lamp 41, a speaker 43, a receiver 44, a control section for controlling these sections, and the like. Lamps 41 and release buttons 42 are provided in the same number as the handsets 50, and receivers 44 have microphones and speakers.

When the call button 51 is operated by the person to be monitored, the slave device 50 transmits a call signal including information for identifying itself (for example, slave device ID) to the master device 40 by the communication unit. Thereby, the master device 40 is notified of the information of the slave device 50 whose call button 51 has been operated. When receiving a call signal from one of the child devices 50 , the master device 40 identifies the room number corresponding to the received child device ID, lights or blinks the lamp 41 of the identified room number, and emits a ringing sound from the speaker 43 . Or output a call message by voice. As a result, the room number of the child device 50 whose call button 51 has been operated and the person to be monitored can be notified to the nursing care staff near the master device 40 . When the care staff picks up the handset 44, conversation (phone call) becomes possible between the handset 50 that has transmitted the call signal and the base unit 40. - 特許庁

The server 10 of the present embodiment treats the operation of the call button 51 of the child device 50 as one of the events occurring in the monitored person, and when detecting the call of the parent device 40 by the child device 50, the event information is , a nurse call is stored in the event DB 13c. For example, the server 10 stores the current date and time, "call", and "nurse call" in the date and time column, event item column, and event content column of the event DB 13c. In addition, the server 10 acquires conversational voices exchanged between the parent device 40 and the child device 50, converts the acquired conversational voices into text data, converts the conversational voices and conversational texts into conversational voice strings and conversational texts in the event DB 13c. stored in each column. Therefore, in the present embodiment, when a call is made using the child device 50, the text and voice regarding the conversation exchanged between the monitored person and the care staff via the child device 50 and the parent device 40 are transmitted. , is stored in the event DB 13c.

Processing performed by the server 10 when a nurse call is made using the child device 50 in the information processing system of the present embodiment will be described below. FIG. 12 is a flow chart showing an example of a processing procedure by the server 10 of the fourth embodiment. The following processing is executed by the control section 11 according to the program 13P stored in the auxiliary storage section 13 of the server 10. FIG. It should be noted that the server 10 of the present embodiment performs the following processes while performing the processes shown in FIGS.

The control unit 11 of the server 10 determines whether or not a nurse call has been made by any of the child devices 50 (S51). For example, control unit 11 may be configured to be notified of reception of a call signal from master device 40 when master device 40 receives a call signal from any of slave devices 50 . Further, the control unit 11 may be configured to be notified from the master device 40 of the start of communication when the master device 40 starts communication of the conversation voice with any of the slave devices 50 . The control unit 11 can determine that a nurse call has been made based on such notification from the master device 40 . If it is determined that a nurse call has not been made (S51: NO), the control unit 11 waits while performing other processes.

If it is determined that a nurse call has been made (S51: YES), the control unit 11 identifies the person to be monitored who made the call (S52). For example, the control unit 11 may acquire the information of the monitored person who made the call by a notification from the base unit 40, and based on the call signal transmitted from the slave unit 50, the monitored person who made the call. may be specified. The control unit 11 stores the event information of the nurse call call in the event DB 13c of the identified monitoring subject (S53).

Next, the control unit 11 determines whether or not the voice data of the conversation transmitted and received between the child device 50 that made the nurse call and the master device 40 has been acquired (S54). The control unit 11 acquires audio data transmitted from the slave device 50 to the master device 40 via the network N, and audio data transmitted from the master device 40 to the slave device 50, for example. Note that the control unit 11 may acquire voice data transmitted and received between the slave device 50 and the master device 40 from the master device 40 together with information indicating the speaker (person to be monitored or care staff).

When the control unit 11 determines that the voice data of the conversation has been acquired (S54: YES), it identifies the speaker of the acquired voice data (S55). For example, when voice data transmitted from the slave device 50 to the master device 40 is acquired, the control unit 11 selects the monitored person corresponding to the slave device 50 (monitored person specified in step S52) as the speaker of the voice data. ) is specified, and voice data to be transmitted from the master device 40 to the slave device 50 is acquired, the care staff is specified as the speaker of the voice data. When a call from the child device 50 is answered using one of the staff terminals 30, the control unit 11 determines that the speaker of the voice data transmitted from the staff terminal 30 to the child device 50 is: The care staff who is the user of the staff terminal 30 can be identified.

The control unit 11 converts the acquired voice data into text data, and generates text data of conversation voice of the care staff or the monitored person (S56). Then, the control unit 11 stores the text data generated in step S56 and the voice data of the acquired conversation in the event DB 13c of the person to be monitored identified in step S52 (S57). Specifically, the control unit 11 associates information indicating whether the speaker is a person to be monitored or a nursing care staff, the reception date and time of the voice data, and the text data of the generated conversation voice to create a conversation text. The information of the speaker, the reception date and time of the voice data, and the acquired voice data are associated with each other and stored in the conversation voice string. Thereby, the control unit 11 can store the text data and voice data of the conversation between the monitored person and the care staff via the nurse call system in the event DB 13c of the monitored person.

If the control unit 11 determines that the voice data of the conversation has not been acquired (S54: NO), it skips the processing of steps S55 to S57. The control unit 11 determines whether or not the conversation via the parent device 40 and the child device 50 has ended (S58). For example, the control unit 11 determines that the conversation has ended when the transmission and reception of voice data between the parent device 40 and the child device 50 have ended. Further, the control unit 11 may be notified by the master device 40 of the end of communication between the master device 40 and the slave device 50 . If it is determined that the conversation via the parent device 40 and the child device 50 has not ended (S58: NO), the control unit 11 returns to the process of step S54, and starts the conversation via the parent device 40 and the child device 50. The processing of steps S55 to S57 is repeated each time voice data is acquired. If it is determined that the conversation has ended (S58: YES), the control section 11 ends the series of processes. At this time, the control unit 11 may store "completed" indicating the end of nursing care in the progress information column of the event DB 13c.

By the above-described processing, the server 10 can accumulate text data and voice data of the conversation between the monitored person and the care staff using the nurse call system. Also in this embodiment, the text data of the conversation stored in the server 10 can be viewed using the staff terminal 30 or another terminal, and a screen such as that shown in FIG. 7A can be generated. For example, in the screen shown in FIG. 7A , the information of the monitored person who made the nurse call, the fact that the nurse call was made, and the date and time are displayed in the thick line display frame at the top. In the display frame, the text data of the content of the conversation uttered by the care staff or the person to be monitored is displayed together with the date and time of the utterance.

In this embodiment, the same effects as those of the above-described embodiments can be obtained. In addition, in this embodiment, text data and voice data of conversation between the monitored person and the care staff can be stored using the nurse call system. Therefore, based on the accumulated data, it is possible to confirm at a later date how the nursing care staff responded to the monitored person's call for a nurse call (response to the nurse call). 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.

(Embodiment 5)
Information for extracting similar cases from the information accumulated in the event DB 13c by the server 10 when an event to be notified occurs in a person to be monitored, and presenting nursing care performed in the extracted similar cases to the nursing care staff as advice. A processing system 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. In this embodiment, attribute information including age and gender of each monitored subject, medical history, treatment history, history of taking medicine, current diagnosis and symptoms, blood test and urine test are stored in the monitored subject DB 13a. It is assumed that medical records including various test results such as are stored. The medical record of the monitoring subject may be stored in the monitoring subject DB 13a, or may be obtained from another server that stores electronic medical records including medical records.

FIG. 13 is a flowchart illustrating an example of a processing procedure in the information processing system according to the fifth embodiment; The process shown in FIG. 13 is obtained by adding steps S71 to S73 between YES in step S16 and step S17 in the processes shown in FIGS. Description of the same steps as in FIGS. 4 and 5 will be omitted. Also, in FIG. 13, illustration of each step in FIG. 5 is omitted.

The server 10 and staff terminal 30 of this embodiment perform the same processing as steps S11 to S16 in FIGS. Accordingly, the server 10 detects the occurrence of an event for each person to be monitored based on the signals from the sensors 21 to 25 and the call button 26 acquired via each sensor I/F device 20 . When the control unit 11 of the server 10 determines that the event specified in step S14 is an event to be notified to the care staff (S16: YES), a case similar to the specified event is sent to each monitoring subject. It is extracted from the storage contents of the event DB 13c. Specifically, the control unit 11 selects the monitoring target person identified in step S12 from the attributes and medical records of each monitoring target person stored in the monitoring target person DB 13a, and the monitoring target person having similar attributes, symptoms, etc. is extracted (S71). For example, the control unit 11 can identify monitoring targets with the same diagnosis, similar disease types or progressing conditions, monitoring targets taking the same medicine, and the Extract monitoring targets, etc. The control unit 11 extracts a predetermined number (for example, 5) of persons to be monitored whose attributes and medical record contents are more similar.

Next, the control unit 11 extracts an event (similar case) similar to the event identified in step S14 from the information of each event stored in the event DB 13c of the extracted monitored person (S72). For example, the control unit 11 extracts events having the same event item and event content, events having the same event item and event content, and having similar occurrence time zones. The control unit 11 extracts a predetermined number (for example, 1 or 2) of events that are more similar in event content, occurrence time period, and the like.

Then, the control unit 11 generates advice based on the content of nursing care provided by the nursing care staff in the extracted similar cases (S73). For example, the control unit 11 reads the conversation text stored in association with the extracted event (similar case) from the event DB 13c, and extracts from the read conversation text words related to the nursing care provided by the care staff. Then, the control unit 11 generates advice using the extracted wording regarding the content of nursing care. For example, in response to an event in which a person to be monitored with dementia has left the room and is wandering outside the room, the conversation text will say, "Your family will be coming to pick you up soon, so let's wait in the room." When the content of nursing care such as "I did" is extracted, the control unit 11 generates the advice "Please say, 'Your family will come to pick you up soon, so let's wait in the room.'". Further, when the nursing care content "I feel calmer after taking a walk outdoors" is extracted from the conversation text, the control unit 11 generates the advice "Try taking a walk outdoors". It should be noted that the process of extracting words related to the nursing care provided by the nursing care staff from the conversation text stored in the event DB 13c may be performed in advance at an appropriate timing and stored in the event DB 13c. In this case, when generating advice in step S73, the control unit 11 can generate the advice using the pre-extracted wording, so the processing can be simplified.

The control unit 11 generates alert information to be notified to the care staff, including the advice generated in step S73 (S17). The alert information here includes the details of the event, information about the person to be monitored for whom the event has occurred, and advice on the content of nursing care that the nursing care staff should provide in response to the event. For example, in the case of an event in which a person to be monitored with dementia has left the bed and is wandering outside the living room, the control unit 11 outputs the room number and name of the person to be monitored, and a message indicating that the person to be monitored is wandering. and advice proposing the details of nursing care are generated. Specifically, it generates alert information such as "Room 503, Mr. Taro Yamada, is wandering outside his room. Please take a walk outside." After that, the control unit 11 and the control unit 31 of the staff terminal 30 execute the processes after step S18. Therefore, the staff terminal 30 outputs the alert information received from the server 10 by voice, thereby providing the information of the monitored person for whom the event has occurred, the content of the event, and the content of nursing care to be provided by the nursing care staff. can be notified to Note that the alert information may be text data or image data, and if the staff terminal 30 has a display unit, the alert information may be displayed on the display unit and notified to the care staff.

With the above-described processing, when an event to be notified occurs in a person to be monitored, it is possible not only to notify the care staff of the occurrence of the event, but also to advise the care staff on possible care details based on past similar cases. can. In the process described above, when an event occurs, advice regarding the content of nursing care is generated and presented to the nursing staff, but the configuration is not limited to this. For example, after notifying the care staff of the occurrence of an event for the person to be monitored, while the care staff are having a conversation using the staff terminal 30, advice regarding the content of care care is generated and presented to the care staff. let's In this case, in addition to the information of the person to be monitored and the contents of the event, it is possible to give advice on the contents of nursing care that the nursing staff should perform, taking into account the nursing care contents that the nursing staff has provided so far.

In this embodiment, when extracting a similar case, a monitoring subject having similar attributes and symptoms may include a monitoring subject whose event is occurring. In this case, it is possible to present advice based on the content of nursing care provided by the nursing care staff in similar events that occurred in the past for the same monitored person.

In this embodiment, when an event occurs in one of the monitored persons, the monitored persons with similar attributes and symptoms are specified from the information stored in the monitored person DB 13a, and similar events are identified from the stored contents of the event DB 13c. It is not limited to any particular configuration. For example, with respect to a case (event) to be used for advice, the attributes and medical records of the monitoring subject, the content of the event, and the content of nursing care provided by the care staff are extracted in advance from the monitoring subject DB 13a and the event DB 13c. , is accumulated in the DB for advice. Then, the server 10 identifies, from the contents stored in the advice DB, a monitoring subject similar to the attributes and symptoms of the monitoring subject in which the event occurred, and a similar event, and stores them in association with the specific contents. The contents of a certain nursing care may be obtained. With such a configuration, similar cases to be used for advice can be retrieved in a short period of time, and appropriate advice can be provided by registering appropriate details of nursing care. Furthermore, such an advice DB is set for each facility, and by updating it periodically, it is possible to customize the contents according to the conditions of persons to be monitored in the facility. Suitable advice can be generated.

In this embodiment, the same effects as those of the above-described embodiments can be obtained. In addition, in this embodiment, when notifying the care staff of the occurrence of an event for the person being monitored, it is possible to advise the care staff about possible care details. As a result, even nursing staff with little skill, knowledge, or experience can provide appropriate nursing care according to advice. Therefore, even if there are few nursing staff, such as at night, it is possible to allocate nursing staff with little skill, knowledge, or experience. In addition, since the care staff can receive support by advice, it is possible to reduce anxiety about work, and it is expected that the turnover rate will decrease and the shortage of human resources will be resolved. The configuration of this embodiment can be applied to the information processing systems of the first to fourth embodiments described above, and similar effects can be obtained even when applied to the information processing systems of the first to fourth embodiments. Also in this embodiment, it is possible to apply the modified examples appropriately described in each of the above-described embodiments.

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 Unit 12 Main Storage Unit 13 Auxiliary Storage Unit 14 Communication Unit 20 Sensor I/F Device 21 Sleep Sensor 22 Toilet Sensor 23 Door Sensor 24 Environment Sensor 25 Human Sensor 26 Call Button 30 Staff Terminal 34 Communication Unit 35 Microphone 36 Earphone 13a Monitored person DB
13b Sensor data DB
13c Event database

Claims (11)

Acquiring sensor data from a sensor that detects the state of a person to be monitored in a care facility or the state of the surroundings of the person to be monitored;
Based on the acquired sensor data, determine an event that has occurred in the monitoring target or in the surroundings of the monitoring target,
Output the occurrence of the determined event to the terminals of multiple caregivers,
Obtaining voice data spoken by the plurality of caregivers from the terminals of the plurality of caregivers,
Convert the acquired voice data into text data,
A program that causes a computer to execute a process of associating the determined event with text data converted from voice data of conversations of the plurality of caregivers regarding the event and storing the text data in a storage unit. Acquiring sensor data from multiple types of sensors,
determining the occurrence of multiple types of events based on the sensor data obtained from the multiple types of sensors;
2. The program according to claim 1, which causes the computer to execute a process of setting, for each of the monitoring target persons, an event whose occurrence is to be output to the terminals of the plurality of caregivers among the plurality of types of events. The program according to claim 1 or 2, causing the computer to execute a process of associating the identification information of the caregiver with text data converted from voice data acquired from the terminal of the caregiver and storing the data in the storage unit. . Extracting text data related to the caregiver's response from the converted text data,
The program according to any one of claims 1 to 3, which causes the computer to execute a process of associating the determined event with the extracted text data and storing them in the storage unit. 5. The program according to any one of claims 1 to 4, causing the computer to create a report containing information about the event based on the event and the text data stored in the storage unit. 6. The report includes a report for nursing care records, a report for reporting the event to medical personnel, and a report for reporting the event to the monitoring subject's family. program as described. identifying a keyword from the converted text data;
7. The program according to any one of claims 1 to 6, which causes the computer to execute a process of emphasizing the keyword in the text data. Detecting the end of the caregiver's response to the determined event,
8. The computer according to any one of claims 1 to 7, wherein when the end of the response is detected, information indicating the end of the response by the caregiver is stored in the storage unit in association with the event. program described in . Acquiring voice data uttered by the person to be monitored input via a nurse call handset associated with the person to be monitored;
Obtaining voice data spoken by the caregiver input via a nurse call parent device or a caregiver terminal for responding to a call from the nurse call slave device,
Converting the acquired voice data of the monitored person and the voice data of the caregiver into text data,
A program that causes a computer to execute a process of correlating each converted text data and storing it in the storage unit. Acquiring sensor data from a sensor that detects the state of a person to be monitored in a care facility or the state of the surroundings of the person to be monitored;
Based on the acquired sensor data, determine an event that has occurred in the monitoring target or in the surroundings of the monitoring target,
Output the occurrence of the determined event to the terminals of multiple caregivers,
Obtaining voice data spoken by the plurality of caregivers from the terminals of the plurality of caregivers,
Convert the acquired voice data into text data,
An information processing method in which a computer executes a process of associating the determined event with text data converted from voice data of conversations of the plurality of caregivers regarding the event and storing the text data in a storage unit. a sensor data acquisition unit that acquires sensor data from a sensor that detects the state of a person to be monitored in a nursing facility or the state of the surroundings of the person to be monitored;
a determination unit that determines an event that has occurred in the monitored person or in the surroundings of the monitored person based on the acquired sensor data;
an output unit that outputs the occurrence of the determined event to terminals of a plurality of caregivers;
A voice data acquisition unit that acquires voice data spoken by the plurality of caregivers from the terminals of the plurality of caregivers;
a conversion unit that converts the acquired voice data into text data;
An information processing apparatus comprising: a storage unit that associates and stores the determined event and text data converted from voice data of conversations of the plurality of caregivers regarding the event.

Images