Information processing method, program, and information processing device

Abstract

To provide an information processing method and the like capable of automatically determining a status of a calling operation (nurse call) on the basis of sensor information obtained by a sensor for monitoring a target person.SOLUTION: An information processing method acquires operation information indicating that a call button is operated by a target person, acquires sensor information obtained by a sensor that monitors the target person in association with the acquisition of the operation information, and determines a status of the call operation on the basis of the acquired sensor information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In recent years, there has been active development of nurse call systems that support the monitoring of patients in medical institutions or nursing care insurance facilities. For example, Patent Document 1 discloses a nurse call determination device that determines a method of responding to a nurse call and a nurse to respond to the nurse call based on the urgency of the nurse call determined based on treatment information related to the treatment to be performed on the patient (patient) and care recipient information related to the patient. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-170929 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the invention of Patent Document 1 has the problem that it requires the collection of treatment information and care recipient information, as it determines the urgency of a nurse call based on the care recipient's treatment information (e.g., treatment details such as intravenous drip, event details, and expected time of the event) and care recipient information.

[0005] One aspect of the present invention is to provide an information processing method etc. that can automatically determine the status of a call operation (nurse call) based on sensor information obtained by a sensor that monitors a subject. [Means for solving the problem]

[0006] An information processing method according to one aspect is characterized in that it acquires operation information indicating that a call button has been operated by a subject, acquires sensor information obtained by a sensor that monitors the subject in connection with the acquisition of the operation information, and determines the status of the call operation based on the acquired sensor information. [Effects of the Invention]

[0007] In one aspect, the status of the call operation can be automatically determined based on sensor information obtained by a sensor monitoring the subject. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram showing an overview of a nurse call system. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of a server. [Figure 3] FIG. 10 is an explanatory diagram showing an example of a record layout of a training data DB. [Figure 4] FIG. 10 is an explanatory diagram showing an example of the record layout of a target person DB and an alert notification DB. [Figure 5] 1 is a block diagram showing an example of the configuration of a nurse call device and a caregiver terminal. [Figure 6] FIG. 10 is an explanatory diagram illustrating a process of determining the status of a call operation. [Figure 7] FIG. 10 is an explanatory diagram illustrating a status determination model. [Figure 8] 10 is a flowchart showing a processing procedure for determining the status of a call operation. [Figure 9] FIG. 10 is an explanatory diagram illustrating an example of an alert notification history screen. [Figure 10] 10 is a flowchart showing a processing procedure when multiple alert notifications are output. [Figure 11] FIG. 10 is an explanatory diagram showing an example of a record layout of a training data DB in the second embodiment. [Figure 12]FIG. 10 is an explanatory diagram illustrating a status determination model in the second embodiment. [Figure 13] 10 is a flowchart showing a processing procedure for determining the status of a call operation in the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] The present invention will be described in detail below with reference to the drawings showing embodiments thereof.

[0010] (Embodiment 1) The first embodiment relates to a form in which, when a call button (nurse call button) is operated by a person being monitored or cared for, the status of the call operation is determined. Fig. 1 is an explanatory diagram showing an overview of a nurse call system. The system of this embodiment includes an information processing device 1, an information processing device 2, a bed sensor 3, an imaging device 4, and an information processing terminal 5, and each device transmits and receives information via a network N such as the Internet.

[0011] The information processing device 1 is an information processing device that processes, stores, and transmits / receives various types of information. The information processing device 1 is, for example, a server device, a personal computer, or a general-purpose tablet PC (personal computer). In this embodiment, the information processing device 1 is assumed to be a server device, and for simplicity, will be referred to as server 1 below.

[0012] The information processing device 2 is a device for the subject (care recipient) that receives operation of a call button by the subject W1 and transmits operation information indicating that the call button has been operated. The information processing device 2 is, for example, an information processing device such as a nurse call device, a smartphone, a tablet, a mobile phone, a personal computer terminal, or a wearable device such as a smart watch. For simplicity, the information processing device 2 will be referred to as the nurse call device 2 below.

[0013] The bed sensor 3 is a device used in nursing homes, hospitals, etc., that detects the breathing state, body movement, sleeping state, etc. of the subject W1 based on vibrations emitted by the subject W1. The bed sensor 3 is placed, for example, between the floor and mattress of the bed, and detects the breathing state, body movement, etc. by detecting the air pressure in the air mattress.

[0014] The imaging device 4 is an imaging device for imaging the subject W1. The imaging device 4 is installed in a location where it can capture an image of the entire subject W1 (for example, diagonally above the bed). By installing the imaging device 4 from a viewpoint that can cover the entire subject W1, it is possible to accurately record the movements or activities (behavior) of the subject W1.

[0015] The imaging device 4 of this embodiment includes a wireless communication unit. The wireless communication unit is a wireless communication module for performing communication-related processing, and transmits image data or video data of the captured subject W1 to the server 1 via a network. Note that the imaging device 4 may be replaced by a smartphone capable of capturing images, a personal computer, or a mobile surveillance robot capable of capturing images of the subject W1.

[0016] The information processing terminal 5 is a terminal device for a caregiver that receives and displays the determination result of the status of the call operation. The caregiver may be a nurse or a caregiver. The information processing terminal 5 is, for example, an information processing device such as a personal computer terminal, a smartphone, a tablet, a mobile phone, or a wearable device such as a smart watch. For simplicity, the information processing terminal 5 will be referred to as a caregiver terminal 5 below.

[0017] Normally, when a person W1 who needs care makes a nurse call using the nurse call device 2, the caregiver cannot grasp the condition (status) of the person W1, and appropriate response may be delayed.

[0018] To solve this problem, the server 1 according to this embodiment acquires operation information indicating that the call button has been operated by the subject W1 from the nurse call device 2 of the subject W1. In connection with the acquisition of the operation information, the server 1 acquires sensor information monitoring the subject W1 from the bed sensor 3 or the imaging device 4. Based on the acquired sensor information, the server 1 determines the status of the call operation. The status will be described later. The server 1 transmits an alert notification including the determined status to the caregiver terminal 5.

[0019] 2 is a block diagram showing an example of the configuration of the server 1. The server 1 includes a control unit 11, a storage unit 12, a communication unit 13, a reading unit 14, and a large-capacity storage unit 15. Each component is connected by a bus B.

[0020] The control unit 11 includes an arithmetic processing device such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), or a quantum processor. The control unit 11 reads and executes a control program 1P (program product) stored in the storage unit 12, thereby performing various information processing, control processing, etc. related to the server 1.

[0021] The control program 1P can be deployed to run on a single computer, or on multiple computers located at one site, or distributed across multiple sites and interconnected by a communications network. While the control unit 11 is illustrated in FIG. 2 as a single processor, it may also be a multiprocessor.

[0022] The storage unit 12 includes memory elements such as RAM (Random Access Memory) and ROM (Read Only Memory), and stores the control program 1P or data required for the control unit 11 to execute processing. The storage unit 12 also temporarily stores data required for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing communication-related processing, and transmits and receives information to and from the nurse call device 2, bed sensor 3, imaging device 4, caregiver terminal 5, etc. via the network N.

[0023] The reading unit 14 reads a portable storage medium 1a including a CD (Compact Disc)-ROM or a DVD (Digital Versatile Disc)-ROM. The control unit 11 may read the control program 1P from the portable storage medium 1a via the reading unit 14 and store it in the mass storage unit 15. Alternatively, the control unit 11 may download the control program 1P from another computer via a network N or the like and store it in the mass storage unit 15. Furthermore, the control unit 11 may read the control program 1P from the semiconductor memory 1b.

[0024] The mass storage unit 15 includes a recording medium such as a hard disk drive (HDD) or a solid state drive (SSD). The mass storage unit 15 includes a status determination model 151, a training data database (DB) 152, a target DB 153, and an alert notification DB 154.

[0025] The status determination model 151 is an output device (estimator) that outputs information about a plurality of statuses based on first sensor information obtained through the bed sensor 3 and second sensor information obtained through the imaging device 4, and is a trained model generated by machine learning. The training data DB 152 stores training data for constructing (generating) the status determination model 151. The subject DB 153 stores information about the subject W1. The alert notification DB 154 stores the history of alert notifications to caregivers.

[0026] In this embodiment, the storage unit 12 and the large-capacity storage unit 15 may be configured as an integrated storage device. Furthermore, the large-capacity storage unit 15 may be configured by a plurality of storage devices. Furthermore, the large-capacity storage unit 15 may be an external storage device connected to the server 1.

[0027] The server 1 may execute various information processing and control processing on a single computer, or may execute the processing in a distributed manner on multiple computers. The server 1 may also be realized by multiple virtual machines provided in a single server, or may be realized by using a cloud server.

[0028] 3 is an explanatory diagram showing an example of a record layout of the training data DB 152. The training data DB 152 includes a training ID string, an input data string, and an output data string. The training ID string stores a unique ID of each training data item to identify the training data item.

[0029] When the call button is operated by the subject W1, the input data sequence stores first sensor information and second sensor information for a time period before and after the call operation. The input data sequence stores, for example, first sensor information and second sensor information, which are time-series data for a predetermined time range centered around the moment the call button is operated. The predetermined time range may be, for example, from a few seconds before to a few seconds after the call button is operated, or from a few minutes before to a few minutes after the call button is operated. The first sensor information and second sensor information may also be time-series data for a predetermined time range (for example, 60 seconds) before the call button is operated. The first sensor information and second sensor information will be described later.

[0030] The output data sequence stores the status type of the call operation, including a first status indicating an emergency, a second status indicating assistance with getting out of bed or walking, a third status indicating daily support, or a fourth status indicating psychological support.

[0031] The first status is a status requiring an emergency, such as subject W1 falling, crouching, difficulty breathing, or confusion. The second status is a status requiring assistance, such as getting out of bed (e.g., moving from the bed) or walking (e.g., returning from the toilet). The third status is a status requesting the provision of fluids, food, medicine, daily necessities, etc., or a status requesting cleaning or laundry, etc. The fourth status is a status requiring communication with a caregiver when subject W1 feels isolated or anxious.

[0032] It should be noted that the status is not limited to the first to fourth statuses described above, and for example, a fifth status requiring support such as treatment may be set.

[0033] The training data may be collected from a large amount of past performance data obtained from a questionnaire survey of the subject W1, the diagnosis or experience of a medical professional, or an electronic health record (e.g., medical record or clinical information), etc. The training data is, for example, data in which the first sensor information and the second sensor information of the subject W1 are associated with each of the first status (emergency), second status (getting out of bed or walking), third status (daily support), and fourth status (psychological support).

[0034] FIG. 4 is an explanatory diagram showing an example of the record layout of the target person DB 153 and the alert notification DB 154. As shown in FIG. The subject DB 153 includes a subject ID column, a name column, and a room number column. The subject ID column stores a unique ID of the subject W1 to identify each subject W1. The name column stores the name of the subject W1. The room number column stores the room number of the subject W1.

[0035] The alert notification DB 154 includes an alert ID column, a target ID column, a status type column, a status name column, a notification date and time column, and a reading status column. The alert ID column stores a unique ID of the alert notification to identify each alert notification. The target ID column stores a target ID to identify the target W1.

[0036] The status type column stores the type of status of the determined call operation (first status, second status, third status, or fourth status). The status name column stores the name of the status of the call operation. For example, the name of the first status is "emergency." The name of the second status is "getting out of bed assistance" or "walking assistance." The name of the third status is "daily support." The name of the fourth status is "psychological support."

[0037] The notification date and time column stores the date and time when the caregiver was notified. The read status column stores the read status of the alert notification (for example, "unread" or "read").

[0038] The storage format of each DB described above is an example, and other storage formats may be used as long as the relationships between the data are maintained.

[0039] FIG. 5 is a block diagram showing an example of the configuration of the nurse call device 2 and the caregiver terminal 5. As shown in FIG. The nurse call device 2 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, a display unit 25, and a call button 26.

[0040] The control unit 21 includes an arithmetic processing unit such as a CPU or an MPU, and performs various information processing and control processing related to the nurse call device 2 by reading and executing a control program 2P (program product) stored in the storage unit 22.

[0041] 5, the control unit 21 is described as a single processor, but it may be a multi-processor. The control unit 21 may execute various information processing or control processes by the same processor within the nurse call device 2, or may execute various information processing or control processes by different processors within the nurse call device 2.

[0042] The storage unit 22 includes memory elements such as RAM or ROM, and stores the control program 2P or data required for the control unit 21 to execute processing. The storage unit 22 also temporarily stores data required for the control unit 21 to execute arithmetic processing.

[0043] The communication unit 23 is a communication module for performing communication-related processing, and transmits and receives information to and from the server 1, etc., via the network N. The input unit 24 may be a keyboard, a mouse, or a touch panel integrated with the display unit 25. The display unit 25 is a liquid crystal display, an organic EL (electroluminescence) display, or the like, and displays various information in accordance with instructions from the control unit 21. Note that the call button in this embodiment may be a physical button provided on the input unit 24, or may be a button displayed by the display unit 25.

[0044] The call button 26 is a button that accepts a call operation by the target person W1. The call button 26 may be provided on the display unit 25 or may be provided as a physical button on the nurse call device 2.

[0045] The caregiver terminal 5 includes a control unit 51, a memory unit 52, a communication unit 53, an input unit 54, a display unit 55, and a speaker 56. Note that the control unit 51, the memory unit 52, the communication unit 53, the input unit 54, and the display unit 55 are similar to the control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the display unit 25 of the nurse call device 2, and therefore their description will be omitted. The speaker 56 is a device that converts an electrical signal into sound.

[0046] 6 is an explanatory diagram illustrating the process of determining the status of a call operation. The nurse call device 2 accepts a touch (click) operation of the call button 26 by the subject W1. The nurse call device 2 transmits operation information indicating that the call button 26 has been operated to the server 1. The operation information includes the subject ID and information indicating that the call button 26 has been pressed (for example, a button ID). The server 1 receives the operation information transmitted from the nurse call device 2.

[0047] It should be noted that a nurse call handset line installed in a medical institution or a nursing care insurance facility may be used instead of the nurse call device 2. For example, linking information that associates a handset ID for identifying a nurse call handset with the subject ID of the subject W1 who will use the nurse call handset is registered (stored) in advance in the memory unit 12 or the mass memory unit 15 of the server 1.

[0048] When the nurse call handset accepts a call operation from the subject W1, it transmits the nurse call handset ID to the server 1. The server 1 acquires the subject ID of the subject W1 by identifying the subject W1 based on the handset ID transmitted from the nurse call handset and on information linking the handset ID and the subject W1 registered in advance.

[0049] The server 1 identifies the sensor monitoring the subject W1 based on the subject ID included in the received operation information. The sensor includes a bed sensor 3 and an imaging device 4. The server 1 acquires first sensor information of the subject W1 from the identified bed sensor 3. The first sensor information is time-series data including the heart rate, respiratory rate, body movement amount, etc. within a predetermined time range (for example, from a few minutes before to a few minutes after the call button is operated).

[0050] The heart rate is a value indicating how many times the subject W1's heart beats per minute. The respiratory rate is a value indicating how many times the subject W1 breathes per minute. The amount of body movement is an index indicating how much the subject W1 moves their body while sleeping (the number of times they turn over in bed, the speed or strength of the turning, etc.). The bed sensor 3 detects minute vibrations while the subject W1 is lying in bed. The bed sensor 3 calculates the heart rate, respiratory rate or amount of body movement by analyzing the detected vibration data.

[0051] The first sensor information may include the time of getting into bed, the time of getting out of bed, the time of waking up mid-sleep, the length of sleep, or the quality of sleep of the subject W1 on the day the call button was operated or the day before.

[0052] The time of getting into bed is the time when the subject W1 gets into bed and lies down to sleep. The time of getting out of bed is the time when the subject W1 gets up from the bed. The time of getting into bed and the time of getting out of bed can be obtained, for example, by the bed sensor 3 detecting the weight or body movement of the subject W1.

[0053] The time of awakening during the night is the time when the subject W1 wakes up during the night. The bed sensor 3 detects the body movement of the subject W1 based on the change in pressure on the mattress caused by the subject W1 turning over during sleep, etc. When the bed sensor 3 detects the body movement of the subject W1, it records the time of awakening during the night. Note that the heart rate increases when waking up, so the bed sensor 3 detects the time of awakening during the night based on the change in heart rate. The time of awakening during sleep may also be recorded.

[0054] The sleep time is the time that the subject W1 actually sleeps during the night, calculated by subtracting the time of awakening during the night from the time between the time of getting into bed and the time of getting out of bed. For example, the bed sensor 3 measures body movement or heart rate during sleep and calculates the time period when body movement increases or the time period when the heart rate increases as the time of awakening during the night. The bed sensor 3 calculates the sleep time by subtracting the calculated time of awakening during the night from the time between the time of getting into bed and the time of getting out of bed.

[0055] Sleep quality is an index that represents the depth of sleep (sleep depth). Sleep quality includes, for example, light sleep, deep sleep, and wakefulness. For example, when time-series data including heart rate, respiratory rate, or body movement (e.g., turning over in sleep) is input, the server 1 inputs the time-series data including the heart rate, respiratory rate, or body movement of the subject W1 into a learning model that has been trained to output a recognition result that recognizes the sleep quality, and outputs the sleep quality of the subject W1.

[0056] The server 1 acquires second sensor information of the subject W1 from the identified imaging device 4. The second sensor information is audio data, image data, video data, or activity information related to the activity (physical activity) of the subject W1 within a predetermined time range (for example, from a few minutes before to a few minutes after the call button is operated). The audio data is time-series audio data that records the speech of the subject W1. The image data is time-series image data that records the activity of the subject W1. The video data is video data that records the activity of the subject W1. The activity information is time-series data including the amount of activity of the subject W1, the distribution of activity time, or activity pattern, etc.

[0057] The activity amount is data indicating the physical activity of the subject W1 (e.g., stride length, walking speed, standing up or sitting down), etc. The activity amount includes, for example, the activity amount before a fall occurs, the activity amount before a slip and fall occurs, the activity amount before lying down occurs, the activity amount before getting up, the activity amount before a boundary position (sitting on the edge of bed) occurs, the activity amount indoors, or the activity amount before getting out of bed.

[0058] The amount of activity before a fall occurs is the amount of bodily movement or activity of the subject W1 immediately before the subject W1 falls when standing up from the bed. For example, this is time series data such as the speed or smoothness of the movement when standing up from the bed, or the distance traveled, speed, or walking pattern after standing up from the bed. The amount of activity before a slip-off occurs is the amount of bodily movement or activity of the subject W1 immediately before the subject W1 slips off the bed. For example, this is time series data such as the movement or change in body position while sitting before the subject W1 slips off the bed.

[0059] The amount of activity before lying down is the amount of bodily movement or activity immediately before the subject W1 lies down. For example, it is time series data of movements while standing or walking before lying down on the bed. The amount of activity before getting up is the amount of bodily movement or activity immediately before the subject W1 stands up from a sitting or lying state. For example, it is time series data of movements or changes in body position while sitting before getting up from the bed.

[0060] The amount of activity before the occurrence of the boundary position is the amount of body movement or activity immediately before the subject W1 transitions to the edge-sitting position (sitting on the edge of the seating space). For example, it is time-series data such as the standing state, movement while walking, and the speed or smoothness of the sitting motion before transitioning to the edge-sitting position, or the movement distance, speed, or change in body position after transitioning to the edge-sitting position.

[0061] The amount of indoor activity is the overall amount of physical movement or activity performed by the subject W1 indoors. For example, it is time-series data such as the distance traveled indoors, the time spent standing, or the time spent sitting. The amount of activity before getting out of bed is the amount of physical movement or activity immediately before the subject W1 gets out of bed. For example, it is time-series data such as the movement or change in body position while lying down before getting out of bed.

[0062] The activity time distribution is data showing the frequency of individual activities over a specific period of time, such as the time periods during which subject W1's physical activities (such as lying on the floor or getting up from bed) are performed. Activity patterns include, for example, falling on the floor, lying on the floor, getting up from bed, boundary position movements, sliding off the bed, or getting out of bed.

[0063] For example, the image capturing device 4 monitors the movement or posture of the subject W1 (for example, lying on the floor, getting up from the bed, or falling), and acquires activity data of the subject W1. The image capturing device 4 analyzes the acquired activity data to calculate the activity time distribution of the subject W1 (a distribution indicating whether the subject W1 is active during a given time period).

[0064] For example, when the imaging device 4 inputs the acquired activity data of the subject W1, it inputs the activity data of the subject W1 into an activity pattern identification model that has been trained to output a recognition result that identifies the activity pattern of the subject W1, and outputs the activity pattern of the subject W1.

[0065] The second sensor information may include a recognition result of emotion, posture, etc. based on voice data, image data, or video data. For example, the server 1 inputs voice data, image data, or video data of the subject W1 captured by the imaging device 4 into a learning model that has been trained to output emotion information (e.g., pain) and posture information (e.g., falling) of the subject W1 when voice data, image data, or video data is input, and outputs the emotion information and posture information of the subject W1.

[0066] The server 1 inputs the acquired first sensor information and second sensor information to a status determination model 151, and outputs the status of the call operation including the first status (emergency), the second status (getting out of bed or walking), the third status (daily support), or the fourth status (psychological support). The status determination model 151 will be described later.

[0067] The server 1 transmits an alert notification including the alert ID and the determined status of the call operation to the caregiver terminal 5. The server 1 stores the alert notification to the caregiver in the alert notification DB 154. Specifically, the server 1 stores the target person ID, the type of status (e.g., first status), the name of the status, the notification date and time, and the read status of "unread" as one record in association with the alert ID in the alert notification DB 154.

[0068] The caregiver terminal 5 receives the alert notification sent from the server 1. The caregiver terminal 5 displays an alert display screen including an alert display field 91. The alert display field 91 is a display field that displays the alert notification to the caregiver. The caregiver terminal 5 changes the display mode of the alert display field 91 depending on the status of the call operation included in the received alert notification. The display mode may be a change of the diagram or picture drawn in the alert display field 91, a change of color or pattern, or a change of the text displayed on the alert display field 91.

[0069] The displayed text is set according to the status of the call button. For example, the displayed text may be "Call button pressed," "Important! Call button pressed," or "Confirm! Call button pressed." The displayed text may include the name and room number of the caregiver W1. The caregiver terminal 5 uses TTS (Text-To-Speech) technology to output audio data of the displayed text through the speaker 56.

[0070] The caregiver terminal 5 displays the alert notification transmitted from the server 1, and then transmits the read status of "read" to the server 1 in association with the alert ID. The server 1 receives the alert ID and the read status transmitted from the server 1. The server 1 updates the read status in the alert notification DB 154 to "read" in association with the received alert ID.

[0071] 7 is an explanatory diagram illustrating the status determination model 151. When the call button is operated by the subject W1, the status of the call operation can be output by inputting first sensor information and second sensor information of the time period before and after the call operation into the status determination model 151. The time period before and after the call operation may be, for example, from several seconds before to several seconds after the call button is operated, or from several minutes before to several minutes after the call button is operated.

[0072] The status determination model 151 is used as a program module that is part of artificial intelligence software. The status determination model 151 is an output device constructed by machine learning that receives first sensor information and second sensor information when the call button is operated by the subject W1 as input and outputs the status of the call operation.

[0073] The status determination model 151 is constructed by, for example, a support vector machine (SVM). The server 1 acquires training data used for learning the status determination model 151 from the training data DB 152.

[0074] The training data is a dataset that has a target variable (label) and explanatory variables (features). The target variable (output data) is an object to be estimated (predicted) or classified, such as a label indicating the type of status. For example, the label could be "1st status," "2nd status (getting out of bed assistance)," "2nd status (walking assistance)," "3rd status," or "4th status."

[0075] The explanatory variables (input data) are input data used to estimate or classify the objective variables, and are data that represent the state before and after the occurrence of an incident (body movement, getting out of bed, walking, etc.). The input data includes first sensor information of the subject W1 obtained through the bed sensor 3 and second sensor information of the subject W1 obtained through the imaging device 4.

[0076] The first sensor information is time-series data including a heart rate, a respiratory rate, an amount of body movement, etc., or a combination of these. The first sensor information may also include time getting into bed, time getting out of bed, time waking up during the night, sleep duration, sleep quality, body temperature, blood pressure, etc. The second sensor information is time-series data including image data, video data, activity amount, activity time distribution, activity pattern, etc., of the subject W1, or a combination of these.

[0077] The server 1 uses the acquired objective variables and explanatory variables to construct a status determination model 151. Specifically, the server 1 binarizes each objective variable and converts it into a value of "0" or "1" that indicates whether an incident has occurred. For example, if an incident has occurred, the value may be 1, and if not, the value may be 0.

[0078] The server 1 finds a decision boundary (hyperplane) that best divides the data using the binarized objective variable and each explanatory variable (first sensor information and second sensor information) before and after the incident. The server 1 trains the status determination model 151 by finding a decision boundary that maximizes the margin, which is the distance from the decision boundary to the nearest data point (support vector).

[0079] In this embodiment, the status determination model 151 is described as being an SVM. However, the status determination model 151 is not limited to an SVM, and may be, for example, a random forest, an isolation forest, a decision tree, or an SVR (Support Vector Machine). Neural networks related to Regression, LOF (Local Outlier Factor), Bayesian networks, regression trees, LTSM (Long-Short Term Memory), Transformers, CNNs (Convolutional Neural Networks), or RNNs (Recurrent Neural Networks) may also be used.

[0080] When the server 1 acquires the first sensor information and the second sensor information in the time period before and after the call operation by the subject W1, the server 1 inputs the acquired first sensor information and the second sensor information into the trained status determination model 151 and outputs the determination result of the status of the call operation. As shown in the figure, the estimated result of "second status (assistance in getting out of bed)" is output.

[0081] In the present embodiment, an example of a process for determining the status of a call operation based on combined data of the first sensor information and the second sensor information has been described, but the present invention is not limited to this. For example, the status of a call operation may be determined based on only one of the first sensor information and the second sensor information.

[0082] In the present embodiment, an example has been described in which the algorithm for determining the status of a call operation is the status determination model 151, but this is not limiting. The algorithm for determining the status of a call operation may be, for example, rule-based.

[0083] The rule base is a rule (criteria for determining the status) for detecting the status of the call operation when a specific condition is satisfied. For example, the server 1 may determine the status of the call operation by comparing the values ​​of various sensor data with predetermined thresholds in the time series data of the first sensor information of the subject W1 obtained by the bed sensor 3 and the time series data of the second sensor information obtained by the imaging device 4.

[0084] As an example, the server 1 determines the subject W1 as being in a first status if the subject W1's heart rate is 60 bpm or less or 100 bpm or more, the respiratory rate is 12 breaths / minute or less or 20 breaths / minute or more, and the body movement is high (e.g., 200 units or more). The server 1 determines the subject W1 as being in a second status if the subject W1's heart rate is 61 to 99 bpm, the respiratory rate is 13 to 19 breaths / minute, and the body movement is moderate (e.g., 50 to 199 units). The server 1 determines the subject W1 as being in a third status if the subject W1's heart rate is 61 to 99 bpm, the respiratory rate is 13 to 19 breaths / minute, and the body movement is low (e.g., 49 units or less). The server 1 determines the subject W1 as being in a fourth status if the subject W1's heart rate is 61 to 99 bpm, the respiratory rate is 13 to 19 breaths / minute, and the body movement is very low (e.g., 10 units or less).

[0085] 8 is a flowchart showing the processing steps for determining the status of a call operation. The control unit 21 of the nurse call device 2 receives a touch operation of the call button 26 by the subject W1 via the input unit 24 (step S201). The control unit 21 transmits operation information indicating that the call button 26 has been operated to the server 1 via the communication unit 23 (step S202). The operation information includes the subject ID, information indicating that the call button 26 has been pressed, and the like.

[0086] The control unit 11 of the server 1 receives operation information transmitted from the nurse call device 2 via the communication unit 13 (step S101). The control unit 11 identifies the bed sensor 3 and the imaging device 4 that monitor the subject W1 based on the subject ID included in the received operation information (step S102). The control unit 11 acquires first sensor information of the subject W1 (including the time of getting into bed, the time of getting out of bed, the time of waking up mid-sleep, the heart rate, the respiratory rate, the amount of body movement, the sleep duration, or the quality of sleep, etc.) from the identified bed sensor 3 via the communication unit 13 (step S103).

[0087] The control unit 11 acquires second sensor information (audio data, image data, video data, activity amount, activity time distribution, activity pattern, etc.) of the subject W1 from the identified imaging device 4 via the communication unit 13 (step S104). The control unit 11 inputs the acquired sensor information (first sensor information and second sensor information) to the status determination model 151 (step S105), and outputs the status of the call operation (step S106).

[0088] The control unit 11 transmits an alert notification including the alert ID and the determined status of the call operation to the caregiver terminal 5 via the communication unit 13 (step S107). The control unit 11 stores the alert notification to the caregiver in the alert notification DB 154 of the mass storage unit 15 (step S108). Specifically, the control unit 11 stores the target person ID, the type of status, the name of the status, the notification date and time, and the read status of "unread" as one record in the alert notification DB 154 in association with the alert ID.

[0089] The control unit 51 of the caregiver terminal 5 receives the alert notification transmitted from the server 1 via the communication unit 53 (step S501). The control unit 51 changes the display mode (display text, color, pattern or design, etc.) of the alert corresponding to the call button 26 (for example, the alert display field 91 in FIG. 6 ) according to the status of the call operation included in the received alert notification (step S502).

[0090] The control unit 51 uses, for example, TTS technology to output voice data in which the displayed characters are read aloud from the speaker 56 (step S503). The control unit 51 then transmits the read status, which is "read", to the server 1 via the communication unit 53 in association with the alert ID (step S504).

[0091] The control unit 11 of the server 1 receives the alert ID and the read status transmitted from the caregiver terminal 5 via the communication unit 13 (step S109). The control unit 11 updates the read status to "read" in the alert notification DB 154 in association with the received alert ID (step S110). The control unit 11 ends the process.

[0092] Next, a process of outputting multiple alert notifications to the caregiver terminal 5 will be described on an alert notification history screen (FIG. 9) described later. Based on the alert ID, the server 1 acquires an alert notification corresponding to each subject W1 from the alert notification history DB 153. The alert notification includes identification information (such as name or room number) that identifies the subject W1 who operated the call button 26, the name of the determined status of the call operation, and the read status of the alert corresponding to the call button 26 ("read" or "unread"), etc.

[0093] The server 1 transmits the acquired multiple alert notifications to each caregiver terminal 5. Each caregiver terminal 5 receives the multiple alert notifications transmitted from the server 1. Each caregiver terminal 5 displays a list of the received multiple alert notifications on the screen.

[0094] 9 is an explanatory diagram showing an example of an alert notification history screen. The screen includes multiple alert notification display fields 11a. The alert notification display fields 11a are display fields that display alert notifications for each target person W1. Each alert notification display field 11a includes a status icon 11b, a status display field 11c, a target person information display field 11d, a notification date and time display field 11e, and a reading status icon 11f.

[0095] The status icon 11b is an icon that indicates the status of the call operation. The status display field 11c is a display field that displays the type and name of the status. The subject information display field 11d is a display field that displays the room number and name of the subject W1. The notification date and time display field 11e is a display field that displays the date and time when the alert notification was sent to the caregiver terminal 5. The status icon 11f is an icon that indicates the reading status of the alert notification.

[0096] The caregiver terminal 5 receives the plurality of alert notifications transmitted from the server 1 and displays the received plurality of alert notifications on the screen. Specifically, the caregiver terminal 5 displays the type of status (first status, second status, third status, or fourth status) and the name (emergency, getting out of bed support, walking support, daily support, or psychological support) of the call operation for each subject W1 in the status display field 11c.

[0097] The caregiver terminal 5 displays the name of the status in different display modes depending on the type of status. As shown in the figure, the name of the first status (emergency) is displayed in large font size (e.g., 16 pt) and in bold. The name of the second status (assistance with getting out of bed or walking assistance) is displayed in normal font size (e.g., 12 pt) and in italics. The name of the third status (daily support) is displayed in normal font size and underlined. The name of the fourth status (psychological support) is displayed in normal font size.

[0098] The display mode of the status is not limited to the above-mentioned one, and the display mode may be changed by changing the color of the status name, or by changing the figure or picture drawn on the status icon 11b.

[0099] The caregiver terminal 5 displays the received room number and name of each target person W1 in the target person information display field 11d, and displays the notification date and time in the notification date and time display field 11e.

[0100] The caregiver terminal 5 acquires a corresponding status icon according to the received status of the call operation for each target person W1. The status icon may be stored in advance in the storage unit 52 of the caregiver terminal 5. The caregiver terminal 5 displays the status icon corresponding to the acquired status of each target person W1 in the status icon 11b.

[0101] The caregiver terminal 5 acquires a corresponding reading status icon according to the reading status of the received alert notification corresponding to each target person W1. The reading status icon may be stored in advance in the memory unit 52 of the caregiver terminal 5. The caregiver terminal 5 displays the reading status icon corresponding to the reading status of each acquired alert notification on the reading status icon 11f. As shown in the figure, when the reading status is "unread", the reading status icon 11f is a black reading status icon, and when the reading status is "read", the reading status icon 11f is a gray reading status icon.

[0102] When the caregiver terminal 5 receives a selection (e.g., touch) operation in an alert notification whose read status is "unread," it outputs voice data corresponding to the status of the call operation for the corresponding subject W1. The voice data includes the subject W1's room number, name, and status name. As an example, the caregiver terminal 5 may output voice data such as "XX Taro in room 501 has left bed" via the speaker 56.

[0103] The caregiver terminal 5 transmits the read status of "read" to the server 1 in association with the alert ID of the alert notification. The server 1 receives the alert ID and the read status transmitted from the caregiver terminal 5. The server 1 updates the read status of the alert notification in the alert notification history DB 153 in association with the received alert ID.

[0104] 10 is a flowchart showing the processing procedure when multiple alert notifications are output. The control unit 11 of the server 1 acquires multiple alert notifications corresponding to the target person W1 from the alert notification history DB 153 of the mass storage unit 15 based on the alert ID (step S111). The alert notification includes the name, room number, and call number of the target person W1 who operated the call button 26. The status information includes the type of status of the output operation, the name of the status, the notification date and time, or the read status of the alert.

[0105] The server 1 transmits the acquired multiple alert notifications to the caregiver terminal 5 via the communication unit 13 (step S112). The control unit 51 of the caregiver terminal 5 receives the multiple alert notifications transmitted from the server 1 via the communication unit 53 (step S511). The control unit 51 displays the received multiple alert notifications on the display unit 55 (step S512).

[0106] The control unit 51 receives a selection operation of a target alert notification by a caregiver or the like via the input unit 54 (step S513). The control unit 51 determines whether the read status of the selected alert notification is "unread" (step S514). If the read status is "read" (NO in step S514), the control unit 51 ends the process.

[0107] If the read status is "unread" (YES in step S514), the control unit 51 outputs audio data (including the room number, name, status name, etc.) corresponding to the status of the call operation for the target person W1 through the speaker 56 (step S515).

[0108] The control unit 51 transmits the read status of "read" to the server 1 via the communication unit 53 in association with the alert ID of the alert notification (step S516). The control unit 11 of the server 1 receives the alert ID and read status transmitted from the caregiver terminal 5 via the communication unit 13 (step S113). The control unit 11 updates the read status of the alert notification in the alert notification history DB 153 in association with the received alert ID (step S114). The control unit 11 ends the process.

[0109] According to this embodiment, when the call button is operated by the target person W1, it is possible to determine the status of the call operation.

[0110] According to this embodiment, the display mode of the alert corresponding to the call button is changed depending on the status of the call operation, thereby enabling the caregiver to quickly take appropriate measures.

[0111] According to this embodiment, when the call button is operated by the subject W1, voice data (voice notification) corresponding to the status of the call operation is output to attract the caregiver's attention and enable immediate response.

[0112] According to this embodiment, it is possible to output a plurality of alert notifications to the caregiver terminal 5.

[0113] (Embodiment 2) The second embodiment relates to a form in which the status of the call operation is determined based on the first sensor information, the second sensor information, and the target person information. Note that a description of the contents that overlap with the first embodiment will be omitted.

[0114] Fig. 11 is an explanatory diagram showing an example of a record layout of the training data DB 152 in embodiment 2. Note that a description of the contents that overlap with Fig. 3 will be omitted. The input data includes first sensor information, second sensor information, and subject information.

[0115] The subject information includes the gender, age, medical history, etc. of the subject W1. The medical history is a history of diseases or treatments that the subject W1 has experienced in the past. The medical history may include previously diagnosed diseases (dementia, leg fracture, mental illness, cancer, etc.), surgical history, allergic reactions, immune status (vaccination history, etc.), drug use history, or mental health condition (e.g., stress, anxiety, or depression). The subject information may also include the lifestyle of the subject W1 (drinking, smoking, or eating habits, etc.), or family history, etc.

[0116] Fig. 12 is an explanatory diagram illustrating the status determination model 151 in the second embodiment. Note that the same reference numerals are used to designate the same contents as in Fig. 7, and the description thereof will be omitted.

[0117] The status determination model 151 is an output device constructed by machine learning that takes as input the first sensor information and second sensor information when the call button is operated by the subject W1 and the subject information of the subject W1, and outputs the status of the call operation.

[0118] The server 1 acquires training data used for learning the status determination model 151 from the training data DB 152. The training data is a data set having a response variable and an explanatory variable. Note that the response variable (output data) in this embodiment is the same as the response variable in embodiment 2, and therefore a description thereof will be omitted. The explanatory variable (input data) is input data including first sensor information, second sensor information, and subject information.

[0119] The server 1 uses the acquired objective variables and explanatory variables to construct the status determination model 151. Note that the learning process of the status determination model 151 is the same as the learning process in the second embodiment, and therefore a description thereof will be omitted.

[0120] Then, the status of the call operation can be determined using the trained status determination model 151. Specifically, the server 1 receives operation information indicating that the call button 26 has been operated from the nurse call device 2. The server 1 identifies the bed sensor 3 and the imaging device 4 that monitor the subject W1 based on the subject ID included in the received operation information.

[0121] The server 1 acquires first sensor information of the subject W1 from the identified bed sensor 3. The server 1 acquires second sensor information of the subject W1 from the identified imaging device 4. The server 1 acquires subject information (gender, age, medical history, etc.) of the subject W1. The subject information may be stored in the large-capacity storage unit 15 of the server 1, or may be stored in an external information processing device.

[0122] The server 1 inputs the acquired first sensor information, second sensor information, and subject information into the status determination model 151, and outputs the determination result of the status of the call operation. Thereafter, the server 1 transmits an alert notification including the determined status of the call operation to the caregiver terminal 5, similar to the processing in the first embodiment.

[0123] 13 is a flowchart showing the processing procedure for determining the status of a call operation in embodiment 2. Note that the same reference numerals are used to designate the same contents as in FIG. 8, and the description thereof will be omitted.

[0124] After executing the process of step S104, the control unit 11 of the server 1 acquires the subject information of the subject W1 from the mass storage unit 15 or an external information processing device (step S121). The control unit 11 inputs the acquired sensor information (first sensor information and second sensor information) and subject information to the status determination model 151 (step S122), and outputs the status of the call operation (step S123). The control unit 11 executes the process of step S107.

[0125] According to this embodiment, it is possible to improve the accuracy of determining the status of a call operation by using the status determination model 151 that has been trained by further adding target person information.

[0126] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims.

[0127] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations, regardless of the reference format. Furthermore, the claims use a format in which a claim references two or more other claims (multiple claim format), but this is not limited to this. A multiple claim (multi-multi claim) that references at least one other multiple claim may also be used. [Explanation of symbols]

[0128] 1. Information processing device (server) 11 Control section 12 Storage section 13 Communications Department 14 Reading unit 15 Mass storage 151 Status Determination Model 152 Training Data DB 153 Target Person DB 154 Alert Notification DB 1a Portable storage media 1b semiconductor memory 1P control program 2. Information processing device (nurse call device) 21 Control section 22 Memory section 23 Communications Department 24 Input section 25 Display section 26 Call button 2P control program 3 Bed Sensor 4. Imaging device 5. Information processing terminal (caregiver terminal) 51 Control section 52 Storage section 53 Communications Department 54 Input section 55 Display section 56 speakers 5P control program

Claims

1. Acquire operation information indicating that the call button has been operated by the target person; acquiring sensor information obtained by a sensor monitoring the subject in connection with the acquisition of the operation information; Determining the status of the call operation based on the acquired sensor information Information processing methods.

2. The status of the call operation is determined based on sensor information obtained through a bed sensor. The information processing method according to claim 1 .

3. The status of the call operation is determined based on sensor information obtained through an imaging device.

3. The information processing method according to claim 1 or 2.

4. The statuses include a first status requiring emergency care, a second status requiring assistance with getting out of bed or walking, and a third status requiring daily support.

3. The information processing method according to claim 1 or 2.

5. The statuses further include a fourth status of needing psychological support. The information processing method according to claim 4.

6. When first sensor information obtained through a bed sensor and second sensor information obtained through an imaging device are input, the acquired first sensor information and second sensor information are input to a learning model that has been trained to output information relating to a plurality of statuses, and a determination result of determining the status of the call operation is output. The information processing method according to claim 1 .

7. When the call button is operated, a display mode of an alert corresponding to the call button is changed according to a status of the call operation; outputting voice data corresponding to the status of the call operation; 3. The information processing method according to claim 1 or 2.

8. outputting a plurality of alert notifications each including identification information for identifying the person who operated the call button, a status of the call operation, and a read status of the alert corresponding to the call button; When a selection operation for a target alert notification is received, audio data corresponding to the status of the call operation is output.

3. The information processing method according to claim 1 or 2.

9. acquiring sensor information and subject information obtained by a sensor monitoring the subject in connection with the acquisition of the operation information; The status of the call operation is determined based on the acquired sensor information and target person information.

3. The information processing method according to claim 1 or 2.

10. Acquire operation information indicating that the call button has been operated by the target person; acquiring sensor information obtained by a sensor monitoring the subject in connection with the acquisition of the operation information; Determining the status of the call operation based on the acquired sensor information A program that causes a computer to perform a process.

11. An information processing device including a control unit, The control unit Acquire operation information indicating that the call button has been operated by the target person; acquiring sensor information obtained by a sensor monitoring the subject in connection with the acquisition of the operation information; Determining the status of the call operation based on the acquired sensor information Information processing device.

Images