JP7803052B2 - Data conversion method, care information conversion device, and program for causing a computer to execute the data conversion method - Google Patents

Description

This disclosure relates to providing information, and more particularly to technology for converting information acquired in a care facility into a format compatible with an external system.

As the number of people using nursing care services increases, the burden on nursing care staff to record the condition of nursing care facility residents (those receiving care) is increasing, and systems are being introduced to reduce this burden.

For example, Japanese Patent Application Laid-Open Publication No. 2020-135734 (Patent Document 1) discloses "a care record program that enables centralized management of information about care services for multiple care recipients on a single screen" (see [Abstract]).

In order to realize "scientific care" that is proven to be effective in supporting independence and preventing the condition from worsening, it is necessary to accumulate evidence and analyze that evidence to provide justification for the care services provided to care recipients, and systems for collecting evidence (such as LIFE (Long-term care Information For Evidence)) are in operation.

Japanese Patent Application Laid-Open No. 2020-135734

However, the types and amounts of data stored in systems used in nursing care facilities are diverse, which increases the burden of inputting this data into external systems. Therefore, there is a need for technology that can reduce the burden of inputting data stored in the system into external systems.

This disclosure has been made in light of the above-mentioned background, and in accordance with one embodiment, discloses technology that reduces the burden of inputting nursing care record data into an external system.

(1) According to one embodiment, a computer-implemented data conversion method for outputting data is provided. The data conversion method includes the steps of accessing one or more pieces of data indicating the status of a resident, converting the format of the one or more pieces of data into a data format required by a system other than a computer, and outputting the data in the converted format.

(2) In one aspect, the one or more data indicating the resident's condition includes data acquired from a sensor installed in the resident's room. The data required by the system includes data that qualitatively indicates the resident's condition. The converting step includes converting the acquired data into qualitatively indicating data.

(3) In a data conversion method according to a certain aspect, the data acquired from the sensor includes image data, trajectory data of the resident in the room, and sleep data of the resident.

(4) In a certain aspect, the one or more data indicating the resident's status include character information determined to be relevant from character information prepared in advance as information indicating the resident's status. The data required by the system includes data that qualitatively indicates the resident's status. The converting step includes converting the character information into data that qualitatively indicates the status.

(5) In one aspect, the one or more data indicating the resident's condition include care records describing the resident's condition. The data required by the system includes data qualitatively indicating the resident's condition. The converting step includes extracting words from the care records and generating data indicating whether the extracted words correspond to keywords predefined in the system.

(6) A data conversion method according to one aspect further includes the steps of outputting a message to a mobile device capable of communicating with a computer prompting the user to input a care record for the resident, and receiving the care record input in response to the message from the mobile device. The converting step includes converting the format of the data for the items included in the received care record into a format predefined for the item in the system.

(7) In one aspect, the one or more data indicating the resident's condition include data acquired at a first time period from a sensor installed in the resident's room and data acquired at a second time period after the first time period. The data required by the system includes data indicating whether or not the resident's condition has changed. The converting step includes generating data qualitatively indicating the resident's condition based on the change from the data acquired at the first time period to the data acquired at the second time period.

(8) In one aspect, the converting step includes converting quantitative data into qualitative data for one or more data.

(9) According to another embodiment, a care information conversion device is provided. The care information conversion device includes access means for accessing a storage device that stores one or more data items indicating the condition of a resident, conversion means for converting the format of the one or more data items into a data format required by a system other than the care information conversion device, and output means for outputting the data in the converted format.

(10) In one aspect, the one or more data indicating the resident's condition includes data acquired from a sensor installed in the resident's room. The data required by the system includes data that qualitatively indicates the resident's condition. The conversion means converts the acquired data into qualitatively indicating data.

(11) In a care information conversion device according to a certain aspect, the data acquired from the sensor includes image data, trajectory data of the resident in the room, and sleep data of the resident.

(12) In a certain aspect, one or more data items indicating the resident's status include character information determined to be relevant from character information prepared in advance as information indicating the resident's status. The data required by the system includes data that qualitatively indicates the resident's status. The conversion means converts the character information into data that qualitatively indicates the status.

(13) In one aspect, the one or more data indicating the resident's condition include a care record describing the resident's condition. The data required by the system includes data qualitatively indicating the resident's condition. The conversion means extracts words from the care record and generates data indicating whether the extracted words correspond to keywords predefined in the system.

(14) In one aspect, the care information conversion device further includes a receiving means for receiving, from the mobile terminal, a care record entered in response to a message prompting the entry of a care record for the resident. The conversion means converts the data format of the items included in the received care record into a format predefined for the item in the system.

(15) In one aspect, the one or more data indicating the resident's condition include data acquired at a first time period from a sensor installed in the resident's room and data acquired at a second time period after the first time period. The data required by the system includes data indicating whether or not the resident's condition has changed. The conversion means generates data qualitatively indicating the resident's condition based on the change from the data acquired at the first time period to the data acquired at the second time period.

(16) In one aspect, the conversion means converts quantitative data into qualitative data for one or more pieces of data.

(17) According to yet another embodiment, a program for causing a computer to execute any of the above methods is provided.

According to one embodiment, the data format of the care records is converted into a format compatible with the external system, thereby reducing the burden of inputting data into the external system.

The above and other objects, features, aspects and advantages of the present invention will become apparent from the following detailed description of the invention taken in conjunction with the accompanying drawings.

FIG. 1 is a diagram showing the flow of nursing care work before and after the introduction of LIFE. FIG. 1 illustrates an example of a configuration of a system 100 according to an embodiment. FIG. 1 is a block diagram showing an outline of the configuration of a system 100. FIG. 1 is a diagram showing an outline of a system 100 using a sensor box 119. FIG. 4 is a block diagram showing the hardware configuration of a computer system 400. FIG. 2 is a block diagram for explaining the configuration of a system 60. FIG. 1 is a diagram representing the data items acquired by the system used in the facility and entered into the scientific care database. FIG. 10 is a diagram showing an example in which data acquired by the sensor box 119 is converted into data compatible with the external systems 630 and 640. 10 is a flowchart illustrating an example of processing executed by a CPU 1 of the care record linking server 600. FIG. 10 is a diagram illustrating an example of how data stored on a hard disk 5 is converted into a format compatible with the format of an external system. 10 is a flowchart showing a part of the processing executed by the care record linking server 600. FIG. 6 shows how information recorded by care staff is converted into a format compatible with external systems 630 and 640. 10 is a flowchart showing a part of the processing executed by a CPU 1 of the care record linking server 600. FIG. 6 shows how information recorded by care staff is converted into a format compatible with external systems 630 and 640. 10 is a flowchart showing a part of the processing executed by a CPU 1 of the care record linking server 600. FIG. 1 illustrates an example of text mining according to an embodiment. 10 is a diagram showing the transition of screens displayed on a display 226 of a mobile terminal 220 used by a care staff member. 10 is a flowchart showing a part of a process executed by a control device 221 of a mobile terminal 220.

Embodiments of the present invention will now be described with reference to the drawings. In the following description, identical components are designated by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions of them will not be repeated.

First, we will explain information collection and utilization using the scientific nursing care information system LIFE, with reference to Figure 1. Figure 1 shows the flow of nursing care work before and after the introduction of LIFE. Figure 1(A) shows the flow of nursing care work before the introduction of LIFE. Figure 1(B) shows the flow of nursing care work after the introduction of LIFE.

As shown in Figure 1 (A), before LIFE is introduced, a care plan/rehabilitation (hereinafter referred to as "rehabilitation") implementation plan is created in step S110. Care/rehabilitation is implemented in step S120. Care records/rehabilitation implementation records are entered into the system in step S130. Nursing care fee claims are processed in step S170.

Referring to Figure 1(B), after LIFE is introduced, in step S110, a care plan/rehabilitation implementation plan is created. In step S120, care/rehabilitation is implemented. In step S130, nursing care records/rehabilitation implementation records are entered into the system.

Then, in step S140, information is collected. In step S150, the collected information is entered into the system (LIFE). In step S160, the data is sent.

In step S170, the nursing care fee claim process is carried out. In step S180, the nursing care records, rehabilitation implementation records, and nursing care fee analysis results are downloaded. In step S190, the analysis results are fed back into the creation of the care plan/rehabilitation implementation plan (step S110).

<System Overview>
Referring to Figure 2, a system 100 capable of acquiring information related to nursing care or rehabilitation will be described. Figure 2 is a diagram showing an example of the configuration of system 100 according to an embodiment. Examples of monitored subjects are residents in each room provided in a room area of facility 180. In system 100 of Figure 2, rooms 110 and 120 are provided in the room area. Room 110 is assigned to resident 111. Room 120 is assigned to resident 121.

The system 100 includes a gateway server 130, an exchange device 135, an access point 140, a management server 200, a sensor box 119, various devices that communicate with the sensor box 119, and mobile terminals 161, 162, 163, and 164.

The gateway server 130 connects the facility 180's internal network (intranet) with the facility 180's external network 16. The external network 16 is, for example, the Internet or a public telephone network. The external network 16 is also connected to a cloud server 150, a push server 160, and a wireless base station 195.

The switching device 135 connects each device in the facility 180's internal network to one another. In some aspects, a router or a switch may be used as the switching device 135. In the example shown in FIG. 2, the number of switching devices 135 is two, but the number is not limited to this. The facility 180's internal network may be configured using a combination of multiple switching devices 135.

Access point 140 is used to connect mobile terminals 161 and 162 to the internal network of facility 180. In some aspects, a Wi-Fi (registered trademark) (Wireless Fidelity) router can be used as access point 140.

The management server 200 receives event information from the sensor box 119 in the facility 180 and manages information about the residents of each room. The management server 200 also communicates with mobile terminals 161 and 162, managing the staff who use these mobile terminals and sending various notifications to each mobile terminal. Note that the management server 200 may use an external push server 160 when sending notifications to mobile terminals 161 and 162. Furthermore, an external cloud server 150 may have some or all of the functions of the management server 200.

The sensor box 119 acquires information about the occupants 111, 121 in the rooms 110, 120 by linking with the cameras and sensors built into its housing and various other sensors in the rooms 110, 120. This information may include images showing each resident's gait, body temperature, pulse rate, and other vital signs. The sensor box 119 also transmits the acquired information about the occupants 111, 121 to the management server 200 via the internal network. Details of the sensor box 119 will be provided later.

Mobile terminals 161, 162 are used by caregivers and other staff members providing care at facility 180. Staff members can use mobile terminals 161, 162 to input care records, etc. Mobile terminals 161, 162 send the care records to management server 200. Furthermore, if a problem occurs with resident 111, 121, staff members use mobile terminals 161, 162 to receive notifications from management server 200. Mobile terminals 161, 162 are connected to access point 140 within facility 180 and communicate with management server 200 via the internal network. In the example herein, caregivers 141, 142, 143, and 144 each carry mobile terminals 161, 162, 163, and 164.

From outside the facility 180, the mobile terminals 163, 164 can communicate with the management server 200 via the gateway server 130 via a wireless base station 195 or the like. When the mobile terminals 163, 164 communicate with the management server 200 from outside the facility 180, some of the services provided by the management server 200 to the mobile terminals 163, 164 may be restricted in order to protect resident information.

Note that the number of other devices, such as mobile terminals 161 and 162, access points 140, and exchange devices 135, is not limited to the number illustrated in Figure 2.

Each of the rooms 110 and 120 includes furniture 112, a bed 113, and a toilet 114 as its facilities. Door sensors 118 are installed on the doors of the rooms 110 and 120, respectively, to detect whether the doors are open or closed. A toilet sensor 116 is installed on the door of the toilet 114, to detect whether the toilet 114 is open or closed. An odor sensor 117 is installed on the bed 113, to acquire excretion information from the resident 111. The resident 111 wears a vital sensor 290 that detects vital information from the resident 111. One example of the detected vital information is the resident's body temperature. Another example is the resident's breathing. Another example is the resident's heart rate. Yet another example is two or more of these types of information. In the room 110, the resident 111 can operate the care call handset 115. When the resident 111 operates the care call handset 115, the care call handset 115 transmits a call signal, which is received by the sensor box 119. The sensor box 119 transmits the received call signal to the management server 200. The management server 200 transmits a signal to the mobile terminal 220 notifying it that a call from the resident 111 has been received.

The sensor box 119 has built-in sensors for detecting the behavior of objects in the rooms 110 and 120. One example of a sensor is a Doppler sensor for detecting the movement of objects. Another example is a camera. Still other examples are the care call handset 115, door sensor 118, toilet sensor 116, odor sensor 117, or vital sign sensor 290. The sensor box 119 may include at least one of these sensors.

The configuration of system 100 will be described with reference to Figure 3. Figure 3 is a block diagram showing an overview of the configuration of system 100.

[Sensor box 119]
The sensor box 119 includes a control device 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a communication interface 104, a camera 105, a Doppler sensor 106, a wireless communication device 107, and a storage device 108.

The control device 101 controls the sensor box 119. The control device 101 is composed of, for example, at least one integrated circuit. The integrated circuit is composed of, for example, at least one CPU (Central Processing Unit), MPU (Micro Processing Unit) or other processor, at least one ASIC (Application Specific Integrated Circuit), at least one FPGA (Field Programmable Gate Array), or a combination of these.

An antenna (not shown) and the like are connected to the communication interface 104. The sensor box 119 exchanges data with external communication devices via the antenna. External communication devices include, for example, the management server 200, mobile terminals 161, 162, 163, 164 and other terminals, the access point 140, the cloud server 150, and other communication terminals.

In one implementation, camera 105 is a near-infrared camera. The near-infrared camera includes an IR (Infrared) projector that projects near-infrared light. By using a near-infrared camera, images showing the interior of rooms 110 and 120 can be captured even at night. In another implementation, camera 105 is a surveillance camera that receives only visible light. In yet another implementation, camera 105 may be a 3D sensor or a thermographic camera. The sensor box 119 and camera 105 may be configured as an integrated unit, or may be configured as a combination of separate devices.

The Doppler sensor 106 functions as a body movement sensor. The Doppler sensor 106 emits and receives microwaves, ultrasound, and other radio waves to detect the behavior (movement) of objects (e.g., resident 111, care staff, etc.) in the rooms 110, 120. This allows the biometric information of the residents 111, 121 in the rooms 110, 120 to be detected.

More specifically, the Doppler sensor 106 is connected to the control device 101 and, under the control of the control device 101, measures the movement of the chest surface associated with the breathing of the resident 111. The Doppler sensor 106 transmits microwaves or ultrasound waves (hereinafter also referred to as "transmitted waves"), receives microwaves or ultrasound waves reflected by an object (i.e., "reflected waves"), and outputs a Doppler signal of Doppler frequency components based on the transmitted and reflected waves. When an object is moving, the frequency of the reflected wave shifts in proportion to the object's moving speed due to the so-called Doppler effect. This results in a difference (Doppler frequency component) between the frequency of the transmitted wave and the frequency of the reflected wave. The Doppler sensor 106 generates a signal of this Doppler frequency component as a Doppler signal at a predetermined sampling rate and outputs the Doppler signal to the control device 101. When the control device 101 receives the Doppler signal from the Doppler sensor 106, it stores the received Doppler signal in chronological order in the memory device 108. When microwaves are used as transmission waves, the microwaves pass through clothing and are reflected by the surface of the resident's 111 body. Therefore, body surface movements can be detected even if the resident 111 is wearing clothes.

In one example, each Doppler sensor 106 emits microwaves in the 24 GHz band toward the bed 113 in each room 110, 120 and receives reflected waves reflected by the occupants 111, 121, etc. The reflected waves are Doppler shifted by the movements of the occupants 111, 121. The Doppler sensor 106 can detect the breathing state and heart rate of the occupants 111, 121 from the reflected waves.

The wireless communication device 107 receives signals from the care call handset 115, door sensor 118, toilet sensor 116, odor sensor 117, and vital sensor 290, and transmits these signals to the control device 101. The care call handset 115 has a care call button 241. When the care call button 241 is operated, the care call handset 115 transmits a signal (e.g., a call signal) indicating that the operation has been performed. The transmitted signal is received by the wireless communication device 107. When the door sensor 118, toilet sensor 116, odor sensor 117, and vital sensor 290 transmit their respective detection results, the transmitted signals are received by the wireless communication device 107.

The storage device 108 is a recording medium, such as a fixed storage device such as a flash memory or a hard disk, or an external storage device. The storage device 108 stores programs executed by the control device 101 and various data used to execute the programs. The various data may include behavioral information of the residents 111, 121. Details of the behavioral information will be described later.

At least one of the above programs and data may be stored in a storage device other than storage device 108 (for example, a storage area of control device 101 (e.g., cache memory, etc.), ROM 102, RAM 103, or an external device (e.g., management server 200 or mobile terminals 161, 162, 163, 164, etc.)) as long as the storage device is accessible by control device 101.

[Behavioral Information]
Next, the behavior information in this embodiment will be described. The behavior information is, for example, information indicating that the resident 111, 121 has performed a predetermined behavior. In one example, the predetermined behavior includes four behaviors: "getting up" indicating that the resident 111, 121 has woken up; "getting out of bed" indicating that the resident 111, 121 has left the bed (bedding) 113; "falling down" indicating that the resident 111, 121 has fallen down from the bed (bedding) 113; and "falling down" indicating that the resident 111, 121 has collapsed.

Furthermore, the behavioral information may include actions taken by the resident to refuse to receive care. For example, the behavioral information may include actions such as shaking off the caregiver with the hands, trying to kick the caregiver with the legs, clinging to the bed 113 and refusing to be changed, etc.

In one embodiment, the control device 101 generates behavioral information for each resident 111, 121 associated with each room 110, 120 based on images captured by cameras 105 installed in each room 110, 120. For example, the control device 101 detects the heads of the residents 111, 121 from the images, and based on changes in the size of the detected heads of the residents 111, 121 over time, detects information such as "refusal of care" in addition to the usual information such as "getting up," "getting out of bed," "falling," and "falling down" for the residents 111, 121. A specific example of generating behavioral information is described in more detail below.

First, the storage device 108 stores the location area of each bed 113 in the rooms 110, 120, a first threshold value Th1, a second threshold value Th2, and a third threshold value Th3. The first threshold value Th1 distinguishes between the size of the resident's head when lying down and when sitting up within the area where the bed 113 is located. The second threshold value Th2 distinguishes whether the resident is standing or not based on the size of the resident's head within the rooms 110, 120 excluding the area where the bed 113 is located. The third threshold value Th3 distinguishes whether the resident is lying down or not based on the size of the resident's head within the rooms 110, 120 excluding the area where the bed 113 is located.

The control device 101 extracts moving object regions from the target image as regions of the occupants 111, 121, for example, using background subtraction or frame subtraction. The control device 101 then extracts the head regions of the occupants 111, 121 from the extracted moving object regions using, for example, a circular or elliptical Hough transform, pattern matching using a pre-prepared head model, and a threshold derived by a neural network trained for head detection. The control device 101 detects "getting up," "getting out of bed," "falling," and "falling off" from the position and size of the extracted head.

The control device 101 may determine that the behavior "getting up" has occurred when the position of the head extracted as described above is within the location area of the bed 113 and when it detects that the size of the head extracted as described above has changed from the size of a lying position to the size of a sitting position using the first threshold value Th1.

When the head position extracted as described above moves from within the area where the bed 113 is located to outside the area where the bed 113 is located, the control device 101 may apply the second threshold value Th2 to the size of the head extracted as described above, and when it detects that the head has changed from a certain size to the size of an upright position, determine that the behavior "leaving bed" has occurred.

When the position of the head extracted as described above moves from within the area where the bed 113 is located to outside the area where the bed 113 is located, the control device 101 may apply a third threshold value Th3 to the size of the head extracted as described above, and when it detects that the head has changed from a certain size to the size of a recumbent position, determine that the behavior of "falling" has occurred.

The control device 101 may determine that the behavior "fall" has occurred if the head position extracted as described above is located within the room 110, 120 excluding the area where the bed 113 is located, and if it detects that the size of the extracted head has changed from a certain size to the size of a lying position by using the third threshold value Th3.

Furthermore, the control device 101 detects the caregiver in addition to the resident from the image data and estimates the distance between the resident and the caregiver. If the control device estimates that the distance is shorter than a predetermined normal distance, it can determine that care refusal behavior is occurring. Furthermore, if the control device 101 determines that the resident's movements are abnormal, it can determine that the resident is exhibiting care refusal behavior toward the caregiver.

In this manner, in one specific example, the control device 101 of the sensor box 119 generates behavioral information for each of the residents 111 and 121. Note that in other aspects of the system 100, an element other than the control device 101 (e.g., a cloud server 150) may generate behavioral information for the residents 111 and 121 using images of the interior of the rooms 110 and 120.

[Mobile terminal 220]
Mobile terminal 220 includes control device 221, ROM 222, RAM 223, communication interface 224, display 226, storage device 228, and input device 229. In one aspect, mobile terminals 161, 162, 163, and 164 are realized as, for example, smartphones, tablet terminals, wristwatch-type terminals, or other wearable devices.

The control device 221 controls the mobile terminals 161, 162, 163, and 164. The control device 221 is, for example, composed of at least one integrated circuit. The integrated circuit is, for example, composed of at least one CPU, at least one ASIC, at least one FPGA, or a combination thereof.

An antenna (not shown) and other devices are connected to the communication interface 224. The mobile terminals 161, 162, 163, and 164 exchange data with external communication devices via the antenna and the access point 140. Examples of external communication devices include the sensor box 119 and the management server 200.

The display 226 is realized, for example, by an organic EL (Electro Luminescence) display, a liquid crystal display, or the like. The input device 229 is realized, for example, by a touch sensor provided on the display 226. The touch sensor accepts touch operations on the mobile terminals 161, 162, 163, and 164, and outputs a signal corresponding to the touch operation to the control device 221.

Storage device 228 may be realized, for example, by flash memory, a hard disk, or other fixed storage device, or a removable data recording medium.

In one aspect, the control device 101 distinguishes between going to bed, lying down, getting up, getting out of bed, falling, tipping over, and abnormal micro-movements, for example, as follows. Note that the area in the target image where the bed 113 is located (the area where the bed 113 is located) is pre-stored in ROM 102 as one of various data. Furthermore, each threshold value and continuation determination time is appropriately set from multiple samples, and is pre-stored in ROM 102 as one of various data.

[Admission to bed]
In determining whether to admit to bed, the control device 101 provisionally determines that the person has admitted to bed if the previous state variable (variable that stores the behavior determination result) was "out of bed" and the person area extracted this time from the target image acquired from the camera 105, for example by background subtraction, completely overlaps the area where the bed 113 is located (if the person area is completely within the area where the bed 113 is located), and if the duration of this complete overlap state continues beyond the continued admission to bed determination time, the control device 101 finally determines that the person has admitted to bed and detects admission to bed. The control device 101 updates the state variable to "in bed." The continued admission to bed determination time is used as a threshold for finally determining that the person has admitted to bed, which was provisionally determined based on the complete overlap between the extracted person area and the area where the bed 113 is located.

[Lying down]
"Lying in bed" refers to a state in which a resident (subject to monitoring) is lying down in bed 113. For example, when the area occupied by the resident in the image is included in the area of bed 113 and the amount of movement of the resident is equal to or less than a predetermined amount, the control device 101 detects "lying in bed" as the behavior information of the resident.

[Wake up]
In determining whether or not a person has woken up, the control device 101 provisionally determines that the person has woken up if the previous state variable was "lying down" and the area of the person area extracted from the target image acquired from the camera 105 this time that extends beyond the area where the bed 113 is located is equal to or greater than the wake-up determination threshold and less than the bed-leaving determination threshold. The control device 101 finally determines that the person has woken up and detects the person having woken up if the duration of the area in which the area is equal to or greater than the wake-up determination threshold and less than the bed-leaving determination threshold exceeds a continued wake-up determination time. The control device 101 updates the state variable to "wake-up." The wake-up determination threshold is used to determine whether or not a person has woken up based on the size of the area. The bed-leaving determination threshold is used to determine whether or not a person has woken up based on the size of the area. The bed-leaving determination threshold is set to a value greater than the wake-up determination threshold. The continued wake-up determination time is used as a threshold for finally determining that a person has woken up, which was provisionally determined by comparing the area with the wake-up determination threshold.

[Getting out of bed]
In determining whether or not a person has left bed, the control device 101 provisionally determines that the person has left bed if the previous state variable was either "in bed" or "wake up" and the area of the person area extracted from the target image acquired this time from the camera 105 that extends beyond the area where the bed 113 is located is equal to or greater than the bed exit determination threshold. If the duration of time that this area remains equal to or greater than the bed exit determination threshold exceeds the continued bed exit determination time, the control device 101 finally determines that the person has left bed and detects the person having left bed. The control device 101 updates the state variable to "out of bed". The continued bed exit determination time is used as a threshold for finally determining that the person has left bed, which was provisionally determined by comparing this area with the bed exit determination threshold.

[Fall]
In determining whether a fall has occurred, the control device 101 determines that a fall has occurred and detects a fall if the size of the head region of the person region extracted from the target image acquired this time from the camera 105 is equal to or smaller than the lying posture determination threshold, the rate of change in the size of the head region is equal to or greater than the fall determination speed threshold, and the person region is within a fall determination region set around the area where the bed 113 is located. The lying posture determination threshold is used to determine whether the size of the head region is in a lying posture. Whether the posture is lying or sitting is determined based on the size of the head region. The fall determination speed threshold is used to determine whether a fall has occurred based on the rate of change in the size of the head region.

[fall down]
In determining whether a fall has occurred, the control device 101 determines that a fall has occurred and detects a fall if the size of the head region of the person region extracted from the target image acquired this time from the camera 105 is equal to or smaller than the recumbent posture determination threshold, the rate of change in the size of the head region is equal to or greater than the fall determination speed threshold, and the person region is located in an area excluding the area where the bed 113 is located and the fall determination area. The fall determination speed threshold is used to determine whether or not a fall has occurred based on the rate of change in the size of the head region.

[Microbody abnormality]
Micro-movement abnormalities are detected based on the Doppler signal output from the Doppler sensor 106. More specifically, the control device 101 performs, for example, a fast Fourier transform (FFT) on the Doppler signals measured within a predetermined time period from the time of measurement to the past, and calculates the average amplitude in a frequency band corresponding to the typical breathing frequency from the spectrum obtained by this FFT. The control device 101 compares this average value with a threshold value for determining whether or not micro-movement abnormalities exist. If the average value is equal to or less than the threshold value, the control device 101 provisionally determines that micro-movement abnormalities exist. If the duration of the state in which the average value is equal to or less than the threshold value exceeds a predetermined determination time, the control device 101 finally determines that micro-movement abnormalities exist, thereby detecting micro-movement abnormalities. The control device 101 updates the state variable with "micro-movement abnormality." The determination time is used as a threshold for finally determining that a micro-movement abnormality provisionally determined by comparing the calculated average value with the micro-movement abnormality determination threshold is a micro-movement abnormality.

When the control device 101 detects the predetermined behavior from the resident's actions in this way, it transmits an event notification signal containing event information indicating the content of the specified event related to the resident to the management server 200 via the communication interface 104. More specifically, the control device 101 transmits an event notification signal containing the sensor ID (Identification) of the sensor box 119, event information indicating the content of the event, and the target image used when detecting entering bed, getting up, getting out of bed, falling, and tipping over to the management server 200 via the communication interface 104.

In one embodiment, the event information includes one or more of: going to bed, lying down, getting up, getting out of bed, falling, tipping over, abnormal micro-movements, and care calls. Here, the control device 101 includes one or more of the detected going to bed, getting up, getting out of bed, falling, tipping over, and abnormal micro-movements as event information in the event notification signal. The images may include at least one of still images and videos. In one embodiment, as described below, for example, still images may first be sent from the sensor box 119 to the management server 200, and videos may then be distributed in response to a request from a user (e.g., a caregiver, administrator, doctor, or other staff member). Note that in other aspects, videos may be distributed first. Alternatively, still images and videos may be sent to the management server 200, and the mobile device 220 may display the still images or videos on the display 226 in a split-screen format based on a signal sent from the management server 200.

When the care call handset 115 receives a nurse call, the control device 101 transmits an event notification signal to the management server 200 indicating this as another example of a predetermined event, and then uses a speaker (not shown) or the like to establish a voice call with the mobile terminal 220. More specifically, when the care call button 241 is operated, a signal corresponding to the operation is received by the wireless communication device 107. The sensor box 119 generates an event notification signal including its sensor ID and a nurse call as event information, and transmits the event notification signal to the management server 200 via the communication interface 104. The control device 101 then establishes a voice call, for example, via VoIP (Voice over Internet Protocol), between the microphone (not shown) and speaker (not shown) of the care call handset 115 and the mobile terminal 220 via the wireless communication device 107.

When the control device 101 receives a request for video distribution from an image display device such as the management server 200, cloud server 150, or mobile terminal 220 via the communication interface 104, it responds to the request by streaming video (e.g., live video) captured by the camera 105 and distributing the video to the image display device.

[Overview of monitoring]
The monitoring using the system 100 will be described with reference to Fig. 4. Fig. 4 is a diagram showing an outline of the system 100 using a sensor box 119.

System 100 is used to monitor occupants 111, 121 and other occupants who are the targets of monitoring (surveillance). A sensor box 119 is attached to the ceiling of room 110. Similar sensor boxes 119 are attached to other rooms.

Range 31 represents the detection range of sensor box 119. If sensor box 119 has the aforementioned Doppler sensor, the Doppler sensor detects human behavior occurring within range 31. If sensor box 119 has a camera as a sensor, the camera captures images within range 31.

The sensor box 119 is installed, for example, in nursing homes, medical facilities, homes, etc. In the example of Figure 4, the sensor box 119 is attached to the ceiling and captures images of the resident 111 and bed 113 from the ceiling. The sensor box 119 does not have to be attached to the ceiling, but may also be attached to the side wall of the room 110.

The system 100 detects danger to the resident 111 based on a series of images (i.e., video) obtained from the camera 105. As an example, detectable dangers include the resident 111 falling or the resident 111 being in a dangerous location (e.g., a bed rail).

When the system 100 detects that the resident 111 is in danger, it notifies the caregivers 141, 142, etc. As an example of a notification method, the system 100 notifies the mobile devices 161, 162 of the caregivers 141, 142 of the danger to the resident 111. When the mobile devices 161, 162 receive the notification, they notify the caregivers 141, 142 of the danger to the resident 111 by message, sound, vibration, etc. This allows the caregivers 141, 142 to immediately know that the resident 111 is in danger and to quickly rush to the resident 111's aid.

Furthermore, the system 100 can also notify the mobile devices 163, 164 of caregivers 143, 144 outside the facility of the danger via the wireless base station 195.

Note that while Figure 4 shows an example in which system 100 includes one sensor box 119, in other aspects, system 100 may include multiple sensor boxes 119. Note that while Figure 4 shows an example in which system 100 includes multiple mobile terminals 161, 162, in other aspects, system 100 may also be realized with a single mobile terminal.

[Computer system configuration]
The configuration of a computer system 400, which is one aspect of an information processing device, will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the hardware configuration of computer system 400. Computer system 400 functions as gateway server 130, cloud server 150, push server 160, or management server 200.

Computer system 400 mainly comprises the following components: CPU 1, which executes programs; mouse 2 and keyboard 3, which receive instructions input by the user of computer system 400; RAM 4, which volatilely stores data generated by program execution by CPU 1 or data input via mouse 2 or keyboard 3; hard disk 5, which nonvolatilely stores data; optical disk drive 6; communication interface (I/F) 7; and monitor 8. Each component is interconnected by a data bus. A CD-ROM 9 or other optical disk is inserted into optical disk drive 6.

Processing in computer system 400 is realized by software executed by each piece of hardware and CPU 1. Such software may be pre-stored on hard disk 5. Alternatively, the software may be stored on CD-ROM 9 or other recording medium and distributed as a computer program. Alternatively, the software may be provided as a downloadable application program by an information provider connected to the Internet. Such software is read from the recording medium by optical disk drive 6 or other reading device, or downloaded via communication interface 7, and then temporarily stored on hard disk 5. The software is read from hard disk 5 by CPU 1 and stored in RAM 4 in the form of an executable program. CPU 1 executes the program.

The components constituting computer system 400 shown in FIG. 5 are common. Therefore, one essential part of the technical concept of the present disclosure can be said to be software stored in RAM 4, hard disk 5, CD-ROM 9, or other recording media, or software that can be downloaded via a network. Recording media may include non-transitory computer-readable data recording media. Note that the operation of each piece of hardware in computer system 400 is well known, so a detailed description will not be repeated.

Note that recording media are not limited to CD-ROMs, FDs (Flexible Disks), and hard disks, but may also include media that permanently carry programs, such as magnetic tape, cassette tapes, optical disks (MOs (Magnetic Optical Discs)/MDs (Mini Discs)/DVDs (Digital Versatile Discs)), IC (Integrated Circuit) cards (including memory cards), optical cards, mask ROMs, EPROMs (Electronically Programmable Read-Only Memory), EEPROMs (Electronically Erasable Programmable Read-Only Memory), flash ROMs, and other semiconductor memories.

The term "program" here refers not only to programs that can be executed directly by a CPU, but also to programs in source program format, compressed programs, encrypted programs, etc.

The system 60 according to this embodiment will be described with reference to Figure 6. Figure 6 is a block diagram illustrating the configuration of the system 60. The system 60 includes a care record linking server 600, a sensor 610, a mobile terminal 220, and external systems 630 and 640.

Sensor 610 detects the status of each resident. Sensor 610 is realized, for example, as sensor box 119.

The mobile device 220 is used by each staff member to accept input of each resident's condition and transmit data indicating that condition to the care record linking server 600.

The care record linking server 600 is realized by a computer device having a well-known configuration. In one aspect, the care record linking server 600 is realized in the cloud server 150 or the management server 200. The care record linking server 600 includes a control unit 611, a memory unit 620, a display unit 621, and an output unit 622. The control unit 611 includes an access unit 612, a counting unit 613, a comparison unit 614, and a data format conversion unit 615.

The control unit 611 uses the data received by the care record linkage server 600 and the data stored in the management server 200 to generate data compatible with the external system 630 or the external system 640. In one aspect, the control unit 611 is realized by a CPU or other processor.

More specifically, the access unit 612 reads data stored in the memory unit 620. The stored data includes data acquired by the sensor box 119 and data entered by the care staff into the mobile terminal 220.

At a certain stage, the aggregation unit 613 aggregates the data obtained for each resident using data stored in the memory unit 620.

In certain situations, the comparison unit 614, based on a comparison instruction, compares the most recent value obtained for a specified item for each resident with values obtained in the past to detect changes in the resident's condition. Here, the past may mean, for example, one month ago, three months ago, or six months ago, but this can be arbitrarily specified by the user of the care record linkage server 600 (such as an administrator or care staff member) or selected from pre-prepared candidates.

The data format conversion unit 615 converts the data formats acquired by the sensor box 119, text information and other data input to the mobile terminal 220, and other data managed by the management server 200 into formats compatible with the data formats of the external systems 630 and 640. More specifically, data items stored in the management server 200 may include data items used in the external systems 630 and 640, but the data formats may be different. Therefore, the data format conversion unit 615 pre-sets the data format required by the external systems 630 and 640 as the data format at the time of output. The data format at the time of output is stored in the memory unit 620 or is incorporated into the program executed by the control unit 611.

More specifically, when the management server 200 holds quantitative information about a resident, the external systems 630 and 640 may request qualitative information indicating changes in the activity status of that resident. In this case, the data format conversion unit 615 converts the quantitative data stored in the management server 200 to generate the qualitative data requested by the external systems 630 and 640.

As an example, the management server 200 stores quantitative information about residents, such as active time, sleeping time, time in the room, and time away from home. On the other hand, the external systems 630, 640 request qualitative information about the residents' activity status, such as data on whether they are going out more or less than before. The data format conversion unit 615 then calculates the increase or decrease in the time equivalent to going out for each resident, compares this increase or decrease with a preset threshold, and if it determines that the time equivalent to going out has increased, it generates qualitative data indicating that going out has increased. On the other hand, if the data format conversion unit 615 determines that the time equivalent to going out for a certain resident has decreased compared to before, it generates qualitative data indicating that the resident is going out less.

As another example, the management server 200 stores data acquired by the sensor box 119 regarding the daily status of each resident. This data may indicate, for example, whether the resident is asleep, awake, indoor active, or absent. If the external systems 630, 640 request qualitative data indicating whether the resident has a tendency to become isolated, the data format conversion unit 615 converts the data stored in the management server 200 into the qualitative data. For example, if a resident's indoor time is longer than a predetermined reference time, or if the resident's indoor time has increased compared to before, the data format conversion unit 615 generates data (e.g., 1) indicating that the resident has a tendency to become isolated. On the other hand, if another resident's indoor time is shorter than the reference time, or if the resident's indoor time has decreased compared to before, the data format conversion unit 615 generates data (e.g., 0) indicating that the other resident does not have a tendency to become isolated.

The data format conversion unit 615 may output the generated data. The output data is input to a separate system, such as external systems 630 and 640, used by an organization separate from the facility using management server 200. External systems 630 and 640 may use the input data to extract qualitative information such as trends in similar types of facilities. Qualitative information is data indicating, for example, whether a condition has improved or whether a specified action can be performed.

The display unit 621 displays a screen according to the data output by the control unit 611. The display unit 621 is realized as an LCD monitor device or other display device.

The output unit 622 outputs the data generated by the data format conversion unit 615 to the external system 630 or the external system 640. The output unit 622 is realized by a well-known interface for communicating with other systems.

[Input items to the system and information that can be supplemented by individual systems]
The data items entered into the scientific care database will be described with reference to Figure 7. Figure 7 is a diagram showing the data items acquired by the system used in the facility and the data items entered into the scientific care database.

Table 710 is managed in the scientific care database. Table 710 includes a sheet name 711, a first item 712, a second item 713, a third item 714, and a total 715.

Sheet name 711 represents the report data containing each piece of information. Item 1 712 is an item that must be submitted to LIFE or other systems. Item 2 713 is an item that can be submitted voluntarily depending on the purpose. For example, if a facility wishes to receive a supplement to its nursing care fees, it must enter the information corresponding to item 2 713 into LIFE or other systems. Item 3 is other items. Total 715 represents the sum of items 1 712 to 3 714.

In the example shown in FIG. 7, 594 items can be entered into LIFE or other systems. For example, the first item 712 includes 16 items related to user information, 64 items related to nutritional management header detail information, 27 items related to dementia information, and 25 items related to basic item information. Furthermore, the first item 712 includes 16 items related to medical history information, 14 items related to medication information, and 23 items related to roommate information.

Table 720 is maintained in another system, for example, a system managed and operated by a facility. Table 720 includes a record item 721, an understanding item 722, and an image evaluation item 723.

Record items 721 are acquired for each resident at the facility. For example, record items 721 are acquired by a sensor box 119 installed in each resident's room. Information acquired as record items 721 includes, for example, sleeping time in the room, movement time, wake-up time, time getting out of bed, whether or not a fall occurred, whether or not a fall occurred, etc.

The items to be grasped 722 are items that are grasped by the staff at the care site in the facility. The items to be grasped 722 are, for example, activities of daily living, and include information that the staff understands about daily living activities, transferring, moving, eating, changing clothes, washing, bathing, and grooming. This information includes, for example, whether the patient can perform daily living activities by themselves, whether they can feed themselves, whether the amount of food they eat has changed, etc.

The image evaluation items 723 include items that can be evaluated using images obtained by a camera or other imaging device included in the sensor box 119. As an example, the image evaluation items 723 include whether or not the resident is wandering around their room, and the extent of the wandering.

Record item 721 contains 12 items related to nutrition management header detail information. Therefore, these 12 items can be used for any of the 64 items included in the nutrition management header detail information sheet required in table 710.

Additionally, the grasp item 722 includes 25 items related to nutrition management header detail information. Therefore, these 25 items can be used for any of the 64 items included in the nutrition management header detail information sheet required in table 710.

Furthermore, image evaluation item 723 includes four items related to nutritional management header detail information. Therefore, these four items can be used for any of the 64 items included in the nutritional management header detail information sheet required in table 710.

[Convert sensor data into system items]
Detection of a resident's condition of being locked inside will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example in which data acquired by the sensor box 119 is converted into data compatible with the external systems 630 and 640.

At one stage, the hard disk 5 stores a table 800 for each resident of the facility, which is acquired by the sensor box 119 installed in the resident's room. The example in Figure 8 shows a portion of the daily data acquired for the resident with the identification number 001. Similarly, the hard disk 5 stores tables consisting of similar data for the other residents.

Table 800 includes image data acquired about the resident, trajectory data within the room, and sleep data (based on data obtained from the Doppler sensor).

The care record linking server 600 converts this data into a format compatible with the external systems 630, 640. For example, the care record linking server 600 generates data from table 800 indicating whether the resident in question tends to become housebound.

As an example, the CPU 1 of the care record linkage server 600 tallies the time classified as absent 840 and calculates the time the resident is not in the room. The remaining time, i.e., the sum of sleep 810, wakefulness 820, and indoor activity 830, is the time the resident is estimated to be in the room. When the CPU 1 detects that the proportion of time spent in the room per day exceeds a preset reference value, it determines that the resident is prone to becoming isolated, and displays a message or other notification to the care staff urging them to develop rehabilitation or a care plan to increase the resident's time outdoors.

Furthermore, if the CPU 1 of the care record linking server 600 determines that the resident has a tendency to become socially isolated, it converts the result of this determination into a data format (e.g., "1") that can be input into the external systems 630, 640. As a result, if the external systems 630, 640 request input of the socially isolated status of each resident, the CPU 1 of the care record linking server 600 converts the data (socially isolated status of each resident) into a format acceptable to the external systems 630, 640. One example of this format is the CSV (Comma Separated Value) format, but other formats may also be used. It is sufficient that at least the data format required by the external systems 630, 640 with which the care record linking server 600 links is registered in advance in the care record linking server 600.

This eliminates the need for users of the care record linkage server 600 (care staff, etc.) to convert data into a format compatible with the external systems 630, 640, thereby reducing the workload of care staff, etc.

While FIG. 8 illustrates an example of binary information indicating whether a resident is confined to their home, the care record linking server 600 may convert the data acquired at the facility into a form other than binary information. For example, instead of indicating whether a resident is confined to their home, the data may be converted into an absolute value of the time corresponding to confinement or into the percentage of that time per day. As one example, the care record linking server 600 may calculate the time corresponding to confinement by calculating the average time per day from the sum of sleep 810, wakefulness 820, and indoor activity 830 for each resident over a week. In another aspect, if the external system 630, 640 requests the percentage of time spent indoors per day as an indicator of confinement, the care record linking server 600 may calculate the percentage as follows: percentage (%) = time corresponding to confinement ÷ 24 × 100.

[Control Structure]
Next, a control structure of the care record linking server 600 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing an example of processing executed by the CPU 1 of the care record linking server 600.

In step S910, the CPU 1 accesses the image data history. The history is acquired for each room and stored, for example, on the hard disk 5 of the management server 200.

In step S920, CPU 1 accesses the history of trajectory data within the room. This history includes data acquired at regular intervals for each resident.

In step S930, CPU 1 accesses the sleep data history acquired from the Doppler sensor. The sleep data is acquired for each resident.

In step S940, CPU 1 tallies the amount of time each resident spends in their room.

In step S950, CPU 1 uses the counting results to determine whether the resident is in a confined state. For example, if the time the resident spends in the room exceeds a preset time, CPU 1 determines that the resident is in a confined state. In other situations, CPU 1 may also determine that the resident is in a confined state if the proportion of time the resident spends in the room exceeds a certain proportion.

In step S960, CPU 1 converts the data format indicating the confined state into a data format for the external system. For example, CPU 1 converts an absolute quantity, such as the time spent in a room, into qualitative data (e.g., 1 or 0) indicating whether the resident is confined or not.

In step S970, the CPU 1 outputs the converted data to the external systems 630, 640. By receiving qualitative data, the external systems 630, 640 can determine whether the resident is in a state of confinement.

[Visualization of changes]
The visualization of changes will be described with reference to Figures 10 and 11. Figure 10 is a diagram illustrating an example of how data stored on the hard disk 5 is converted into a format compatible with the format of an external system. Figure 11 is a flowchart showing part of the processing executed by the care record linking server 600.

As shown in FIG. 10, the hard disk 5 stores table 1000. Table 1000 stores areas 1001 to 1009. Area 1001 stores the resident ID. Area 1002 stores the date the data for the record was acquired. Area 1003 stores the daytime activity time. Area 1004 stores the nighttime activity time. Area 1005 stores the daytime movement speed. Area 1006 stores the nighttime movement speed. Area 1007 stores the daytime sleeping time. Area 1008 stores the nighttime sleeping time. Area 1009 stores nursing care record data.

In one aspect, table 1000 stores data obtained for each resident. The storage period may be the entire period, a period specified by law or regulation if such period exists, or a period according to individual settings for storage if such settings exist.

In one aspect, when the care record linking server 600 receives an external instruction to extract indicators indicating changes in a resident's condition, it determines whether there has been a change in the item specified as that condition. For example, the CPU 1 of the care record linking server 600 calculates the difference between the latest data for daytime activity time (area 1003) and preset past data (e.g., data from six months ago), and if the difference is a positive value, it determines that the resident is going out more compared to six months ago. On the other hand, if the daytime activity time for another resident has decreased compared to six months ago, the CPU 1 may determine that the other resident is going out less compared to six months ago.

CPU 1 uses the data in table 1000 to determine whether each resident is out more than they were six months ago, and writes the result to RAM 4. RAM 4 temporarily stores table 1010. Table 1010 includes areas 1011 and 1012. Area 1011 stores the resident ID. Area 1012 stores binary data indicating whether the resident is out more than they were six months ago. For example, a resident with resident ID 001 is determined to be less out than they were six months ago, so binary data (0) is stored. On the other hand, a resident with resident ID 000 is determined to be out more than they were six months ago, so binary data (1) is stored.

If the external systems 630, 640 are adapted to accept data formats such as those shown in area 1012 regarding resident outing status, the CPU 1 may output the derived binary data to the external systems 630, 640, for example, in CSV format.

Note that detecting changes in a resident's condition is not limited to comparing daytime activity time with that six months ago. It may also be compared with daytime activity time one month ago or one year ago.

Referring to FIG. 11 , in step S1110, CPU 1 accesses the sensor and care record history. In step S1120, CPU 1 reads the most recent daytime activity time from the history data. In step S1130, CPU 1 reads the daytime activity time from a certain period of time ago (e.g., one month ago, six months ago, one year ago, etc.) from the history data.

In step S1140, CPU 1 calculates the difference in daytime activity time and determines the outing status. For example, if CPU 1 detects that the recent daytime activity time has increased compared to the previous daytime activity time, it determines that the resident is going out more. Conversely, if CPU 1 detects that the recent daytime activity time has decreased compared to the previous daytime activity time, it determines that the resident is going out less.

In step S1150, CPU 1 converts the determination results into a data format compatible with external systems 630, 640. For example, if external systems 630, 640 accept binary information regarding the resident's outing status, indicating whether the resident is going out more or less, CPU 1 replaces the determination results for each resident with binary information 0 (= not going out more) or 1 (= going out more).

In step S1160, CPU 1 outputs the data converted into a predetermined format accepted by external systems 630 and 640.

[Interest table data integration]
The data linkage of resident interests will be described with reference to Figures 12 and 13. Figure 12 shows how information recorded by care staff is converted into a format compatible with external systems 630 and 640.

As shown in FIG. 12(A), the display 226 of the mobile terminal 220 used by the care staff displays a screen on which the care staff can record the resident's condition for each care item. The screen displays multiple icons. When the care staff taps icon 1210, the mobile terminal 220 switches screens, as shown in FIG. 12(B), and the display 226 displays screen 1220 for entering observation records related to meals.

Screen 1220 displays multiple care items prepared in advance for meals. When the care staff checks the blank box to the right of each care item, the mobile terminal 220 determines that the care item applies and sends data identifying the applicable care item to the management server 200. The CPU 1 of the management server 200 stores each received data on the hard disk 5 and reads each data item from the hard disk 5 in response to a data extraction command.

For example, as shown in FIG. 12(C), CPU 1 writes table 1230 to RAM 4. Table 1230 includes areas 1231, 1232, 1233, and 1234. Area 1231 stores identification data for the resident. Area 1232 stores binary data indicating whether the resident is looking forward to eating. Area 1233 stores binary data indicating whether the resident is concentrating on eating. Area 1234 stores binary data indicating whether the resident sometimes chokes on liquids.

For resident ID 001, the resident is looking forward to meals, is concentrating on eating, and sometimes chokes on water, so binary data (=1) is stored in all of areas 1232, 1233, and 1234. On the other hand, for resident ID 001, the resident is looking forward to meals, is concentrating on eating, and sometimes chokes on water, so binary data (=1) is stored in all of areas 1232, 1233, and 1234. On the other hand, for resident ID 002, it is recorded that the resident is looking forward to meals, is unable to concentrate on eating, and does not choke on water, so binary data (=1) is stored in area 1232, and binary data (=0) is stored in areas 1233 and 1234.

Therefore, if the external systems 630, 640 request information as binary data on the resident's care items, such as whether the resident is enjoying their meal, whether they are concentrating on their meal, and whether they choke on water, the care record linking server 600 can convert the contents of the care items stored on the hard disk 5 into a format compatible with the binary data format and output the converted data.

Figure 13 is a flowchart showing part of the processing executed by the CPU 1 of the care record linkage server 600.

In step S1310, CPU 1 detects an instruction to pop up an input screen. For example, when a care staff member taps icon 1210 on the screen of the mobile device 220 (FIG. 12(A)), the mobile device 220 displays a screen for entering details of care items (FIG. 12(B)).

In step S1320, CPU 1 displays a pop-up message on display 226 prompting the resident to enter required information. For example, CPU 1 displays the names of the required items in a color (e.g., red) different from the colors of the other items.

In step S1330, the CPU 1 accepts input for each item in the message. For example, when the care staff member taps a box field displayed on the right side of the screen, a check mark is entered in that box field in response to the tap. The care staff member switches screens on the mobile device 220 and continues making the necessary inputs.

In step S1340, CPU 1 detects the pressing of a button to confirm the registration of the input content in response to an operation on an icon (not shown) to confirm the input.

In step S1350, CPU 1 determines whether there are any other residents to be entered.

In step S1360, CPU 1 creates a table from the confirmed input contents.
In step S1370, CPU 1 converts the data format of the table into a format for the external system. For example, CPU 1 aggregates the data in the table and determines whether the total value is equal to or greater than a predetermined reference value. If the total value is equal to or greater than the reference value, CPU 1 derives data indicating that the resident applies to each item (e.g., 1) or data indicating that the resident does not apply (e.g., 0).

In step S1380, CPU 1 outputs the derived data for each item to external systems 630 and 640.

[Text mining of nursing care records]
14 to 16, other aspects will be described. The care record may be input as text information by the care staff. The text information may also be converted into a format compatible with the format required by the external systems 630 and 640.

Figure 14 shows how information recorded by care staff is converted into a format compatible with external systems 630 and 640.

As shown in Figure 14 (A), the display 226 of the mobile terminal 220 used by the care staff displays a screen on which the care staff can record the resident's condition for each care item. The screen displays multiple icons. When the care staff taps icon 1410, as shown in Figure 14 (B), the mobile terminal 220 switches screens, and the display 226 displays screen 1420 on which the care staff can input the resident's care record as text information.

Screen 1420 displays a screen on which the resident's daily care record can be entered as text. The care staff enters the care record as text information using the keyboard or voice recognition function of the mobile terminal 220. Specifically, the care staff enters the time, a summary of the actions (e.g., waking up, eating, drinking water, etc.), and the actual care record into the mobile terminal 220. After that, when the care staff confirms the content and presses a button (not shown) to register, the mobile terminal 220 sends the entered text information to the care record linking server 600. The CPU 1 of the care record linking server 600 stores each received data on the hard disk 5 and reads each data from the hard disk 5 in response to a data extraction instruction.

For example, as shown in FIG. 14 (C), the CPU 1 of the care record linkage server 600 writes table 1430 to RAM 4. Table 1430 includes areas 1431, 1432, 1433, 1434, and 1435. Area 1431 stores the identification data of the resident. Area 1432 stores binary data indicating whether the resident can get up on their own. Area 1433 stores binary data indicating whether the resident can feed themselves. Area 1434 stores binary data indicating whether the resident sometimes chokes on liquids. Area 1435 stores binary data indicating whether the resident can eat solid foods.

For the resident with resident ID 001, binary data indicating that the resident can wake up on their own, can feed themselves, chokes on water, and has difficulty chewing is stored in areas 1432, 1433, 1434, and 1435, respectively. On the other hand, for the resident with resident ID 001, binary data indicating that the resident can wake up on their own, cannot feed themselves, does not choke on water, and has no difficulty chewing is stored in areas 1432, 1433, 1434, and 1435.

Therefore, if the external systems 630, 640 request binary data on the resident's care items, such as whether the resident can wake up on their own, whether they can feed themselves, whether they choke on liquids, and whether they have difficulty chewing, the care record linking server 600 can convert the contents of the care items stored on the hard disk 5 into a format compatible with the binary data format and output the converted data.

The control structure of the care record linking server 600 will be described with reference to Figure 15. Figure 15 is a flowchart showing part of the processing executed by CPU 1 of the care record linking server 600.

In step S1510, in response to a trigger, the CPU 1 reads the text data of the care record from the hard disk 5 into the work area of the RAM 4. The trigger is, for example, an instruction to read data from the care record linkage server 600 to the external systems 630 and 640.

In step S1520, CPU 1 performs text mining on the text data to identify pre-specified keywords. Pre-specified keywords include, for example, words that describe actions such as waking up, eating, choking, and being unable to chew.

In step S1530, CPU 1 reflects the keyword acquisition results in table 1430, which has specified items.

In step S1540, CPU 1 converts the format of the data reflected in table 1430 into the data format of the external system (e.g., CSV format).

In step S1550, CPU 1 outputs to external systems 630 and 640.
[Text mining]
An example of extracting text information from care records will now be described with reference to Fig. 16. Fig. 16 is a diagram illustrating an example of text mining according to an embodiment.

As shown in FIG. 16(A), care records can be analyzed using morphological analysis and syntactic analysis. Specifically, as shown in FIG. 16(B), in certain situations, care records are analyzed using morphological analysis. In morphological analysis, for example, if the regular expression is "shoku.* kosete," "kosetare" (left) will not be extracted. The care record linking server 600 according to this embodiment registers the base part of a verb in a dictionary and extracts the base form of the conjugated form even if variations of the conjugated form are included in the care record. For example, in the care record "satsushoku ni kosete," the term "kosete" (left) 1610 is not registered as a keyword; only the base form term "kosete" (left) 1620 is registered. In this case, because the base form term is obtained, CPU 1 can extract the information "kosete" (left) from the term "kosete" 1610, even if the care record does not contain the character "kosete." Similarly, if a care record in another situation contains the text information "left behind" from the regular expression "food.*left behind" given as an example above, the care record linking server 600 will not be able to extract "left behind." However, if the base form that forms the basis of the verb conjugation form is registered, as in term 1640, the CPU 1 of the care record linking server 600 will be able to extract the information "left behind" from this registered content.

Figures 16(C) and 16(D) show examples of analyzing care records using syntactic analysis. For example, if a care staff member records "Urination occurred but urine cannot be collected," the initial and final expressions may lead to a false determination that the person was unable to urinate. Therefore, the care record linking server 600 according to this embodiment performs syntactic analysis, as shown in Figure 16(C), and can determine that "unable" is related to "urine collection" and that "urination" is not denied. Figure 16(D) is a diagram showing an example of output from care record data.

Another aspect will be described with reference to Figures 17 and 18. Figure 17 is a diagram showing the transition of screens displayed on the display 226 of the mobile terminal 220 used by the care staff. As shown in Figure 17(A), the display 226 displays a screen for entering care records for a certain resident. When the care staff performs an operation to select area 1710 to enter information about dietary care, the display 226 displays detailed items 1720 related to dietary care, as shown in Figure 17(B).

When the care staff member selects one of the items shown in the detailed items 1720, a screen for accepting care record input is displayed, as shown in FIG. 16 (C). The care staff member can input the care record as text information from this screen.

When the care staff confirms the registration of the care record, the mobile device 220 sends the care record to the care record linking server 600. The care record linking server 600 can output data related to the care record in a format compatible with the format required by the external systems 630, 640.

Referring to Figure 18, we will explain the conversion of care records input from the mobile terminal 220. Figure 18 is a flowchart showing part of the processing executed by the control device 221 of the mobile terminal 220.

In step S1810, the control device 221 displays a screen for selecting a scene (input item) on the display 226. In step S1820, the control device 221 accepts the selection of an input item. In step S1830, the control device 221 displays a screen for accepting record input for the selected input item. In step S1840, the control device 221 accepts record input by the user of the mobile terminal 220.

In step S1850, the control device 221 determines whether an instruction to confirm the input has been received. An instruction to confirm the input includes, for example, pressing an icon displayed on the display 226. If the control device 221 determines that such an instruction has been received (YES in step S1850), it switches control to step S1860. If not (NO in step S1850), the control device 221 returns control to step S1840 and waits for input from the care staff.

In step S1860, the control device 221 transmits the record data whose input has been confirmed to the care record linking server 600. Upon receiving the data, the care record linking server 600 stores it on the hard disk 5. Upon receiving a data output request to the external systems 630, 640, the care record linking server 600 compares the numerical data with a preset threshold and generates binary data according to the comparison, and extracts the textual information using the text mining described above.

[summary]
Some of the technical features disclosed in the above embodiments can be summarized as follows.

(1) According to one embodiment, CPU 1 accesses one or more data items indicating the status of a resident. CPU 1 converts the format of one or more data items into a data format (e.g., CSV format) required by a system other than a computer (e.g., external systems 630, 640). CPU 1 outputs the converted data to external systems 630, 640.

(2) In one aspect, the one or more data indicating the resident's condition includes data acquired from a sensor installed in the resident's room. The data required by the system includes data that qualitatively indicates the resident's condition. CPU 1 converts the acquired data into qualitative data.

(3) In a method according to a certain aspect, the data acquired from a sensor (e.g., sensor box 119) includes image data, trajectory data of the resident in the room, and sleep data of the resident.

(4) In a certain situation, one or more data items indicating the resident's status include character information determined to be relevant from character information prepared in advance as information indicating the resident's status. The data required by the system includes data qualitatively indicating the resident's status. CPU 1 converts the character information into data qualitatively indicating the status (for example, 1 if the resident's status corresponds to a predetermined status, 0 if not, etc.).

(5) In one aspect, the one or more data indicating the resident's condition include a care record describing the resident's condition. The data required by the system includes data qualitatively indicating the resident's condition. The CPU 1, for example, extracts words from the care record using text mining and generates data indicating whether the extracted words correspond to keywords predefined in the system.

(6) In a method according to one aspect, the CPU 1 causes a mobile device 220 capable of communicating with the care record linking server 600 to output a message prompting the user to enter a care record for the resident. The CPU 1 further receives the care record entered in response to the message from the mobile device 220. The CPU 1 converts the data format of the items included in the received care record into a format predefined for the item in the system.

(7) In a certain aspect, one or more data indicating the resident's condition include data acquired from a sensor (e.g., sensor box 119) installed in the resident's room at a first time point (e.g., a specified past time point, such as one week ago, one month ago, three months ago, six months ago, etc.) and data acquired at a second time point after the first time point (e.g., the current time point or the time of last acquisition). The data requested by external systems 630, 640 includes data indicating whether or not there has been a change in the resident's condition. CPU 1 generates data qualitatively indicating the resident's condition based on the change from the data acquired at the first time point to the data acquired at the second time point.

(8) In a certain situation, the CPU 1 converts quantitative data (for example, physical quantities or signals acquired by the sensor box 119) into qualitative data (such as 0 or 1 indicating whether the occupant is in a specified state) for one or more pieces of data.

(9) According to another embodiment, a care information conversion device (e.g., a care record linking server 600) is provided. The care information conversion device includes an access unit 612 for accessing a storage device that stores one or more data items indicating the condition of a resident, a data format conversion unit 615 for converting the format of the one or more data items into a data format required by a system other than the care information conversion device, and an output unit 622 for outputting the data in the converted format.

(10) According to yet another embodiment, a program is provided that causes a computer system 400 to execute any of the above methods.

According to the embodiment disclosed above, the care record linkage server 600 can convert the format of data acquired for each resident into the data format required by LIFE or other external systems 630, 640, and output the converted data. This makes it easy to prepare the data required by the external systems 630, 640, thereby reducing the burden on care staff.

The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims, not the above description, and is intended to include all modifications that are equivalent in meaning to and within the scope of the claims.

2 Mouse, 3 Keyboard, 4, 103, 223 RAM, 5 Hard disk, 6 Optical disk drive, 7, 104, 224 Communication interface, 8 Monitor, 9, 102, 222 ROM, 16 External network, 31 Range, 60, 100 System, 101, 221 Control device, 105 Camera, 106 Doppler sensor, 107 Wireless communication device, 108, 228 Storage device, 110, 120 Room, 111, 121 Resident, 112 Furniture, 113 Bed, 114 Toilet, 115 Care call handset, 116 Toilet sensor, 117, 610 Sensor, 118 Door sensor, 119 Sensor box, 130 Gateway server, 135 Exchange device, 140 Access point, 141, 142, 143, 144 Caregiver, 150 Cloud server, 160 Push server, 161, 162, 163, 164, 220 Mobile terminal, 180 Facility, 195 Wireless base station, 200 Management server, 226 Display, 229 Input device, 241 Care call button, 290 Vital sensor, 400 Computer system, 600 Care record linkage server, 611 Control unit, 612 Access unit, 613 Counting unit, 614 Comparison unit, 615 Data format conversion unit, 620 Memory unit, 621 Display unit, 622 Output unit, 630, 640 External system, 710, 720, 800, 1000, 1010, 1230, 1430 Table.

Claims (13)

1. A computer-implemented method of transforming data to output data, comprising:
accessing a plurality of data indicative of a status of each of a plurality of residents;
converting the format of each of the plurality of data into a data format compatible with a data format used in a system connected to the computer for collecting evidence;
outputting the converted format data to the system;
the plurality of data indicating the status of each of the plurality of residents is acquired from a sensor installed in the room of each of the residents and quantitatively indicates the status of the resident;
the data required by the system is data qualitatively indicating the status of each of the plurality of residents;
the converting step includes determining a state of each of the residents based on data acquired from the sensors;
converting the results of the determinations of the status of each of the residents into the qualitatively indicative data ;
The determining step includes determining that each of the residents has a tendency to become housebound based on the fact that the time spent in the resident's room per day exceeds a predetermined percentage;
The method , wherein the converting includes generating data indicative of the resident being prone to homeboundness . The data conversion method described in claim 1, further comprising the step of outputting a rehabilitation plan for the resident based on the results of the determination. The data conversion method described in claim 1 or 2, wherein the determining step includes determining the status of a single resident based on multiple quantitative data items indicating the status of the single resident. The data conversion method of claim 1, wherein the data acquired from the sensor includes image data, trajectory data of the resident in the room, and sleep data of the resident. outputting a message to prompt the entry of a care record of the resident to a mobile terminal capable of communicating with the computer;
receiving, from the mobile terminal, a care record entered in response to the message;
The data conversion method according to claim 1 , wherein the converting step includes converting the format of data of an item included in the received care record into a format predefined in the system for the item. the one or more data indicating the state of the resident include data acquired at a first time period from a sensor installed in the resident's room and data acquired at a second time period after the first time period;
the data required by the system includes data indicating whether or not there has been a change in the resident's condition;
2. The data conversion method of claim 1, wherein the converting step includes generating data qualitatively indicating the resident's condition based on changes from the data acquired at the first time period to the data acquired at the second time period. A care information conversion device,
access means for accessing a storage device storing a plurality of data indicating the status of each of a plurality of residents;
A conversion means for converting the format of each of the plurality of data into a data format compatible with a data format used in a system connected to the care information conversion device to collect evidence;
an output means for outputting data in a converted format;
the plurality of data indicating the status of each of the plurality of residents is acquired from a sensor installed in the room of each of the residents and quantitatively indicates the status of the resident;
the data required by the system is data qualitatively indicating the status of each of the plurality of residents;
The conversion means
determining a state of each of the residents based on data acquired from the sensors;
converting the results of the assessment of each of the occupants' conditions into the qualitatively indicative data ;
The determining step includes determining that each of the residents has a tendency to become housebound based on the fact that the time spent in the resident's room per day exceeds a predetermined percentage;
The converting step includes generating data indicating that the resident has a tendency to become housebound . The care information conversion device of claim 7, further comprising an output means for outputting a rehabilitation plan for the resident based on the results of the determination. The care information conversion device according to claim 7 or 8 , wherein the determining step includes determining the condition of one resident based on a plurality of quantitative data items indicating the condition of the one resident. The care information conversion device according to claim 7 , wherein the data acquired from the sensor includes image data, trajectory data of the resident in the room, and sleep data of the resident. The system further includes a receiving means for receiving, from the mobile terminal, a care record input in response to a message prompting input of a care record for the resident;
The care information conversion device according to claim 7 , wherein the conversion means converts a data format of the item included in the received care record into a format predefined in the system for the item. the one or more data indicating the state of the resident include data acquired at a first time period from a sensor installed in the resident's room and data acquired at a second time period after the first time period;
the data required by the system includes data indicating whether or not there has been a change in the resident's condition;
The nursing care information conversion device described in claim 7, wherein the conversion means generates data qualitatively indicating the condition of the resident based on changes from the data acquired at the first period to the data acquired at the second period. A program that causes a computer to execute the data conversion method according to any one of claims 1 to 6 .