Information processing system, service quality improvement support method, and control program

Abstract

To provide an information processing system, a service quality improvement support method, and a control program which support an improvement in service quality in care service of a nursing and care facility.SOLUTION: An information processing system includes: an acquisition section 111 for acquiring data on action of a staff implementing care for residents at a nursing and care facility; an index generation section 112 for generating an index indicating a service provision method of the staff from the acquired action data on the staff; and an output section 113 for outputting the generated index.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an information processing system, a business quality improvement support method, and a control program. [Background technology]

[0002] In recent years, the rise in living standards, improved sanitary conditions, and improved medical standards have resulted in a notable increase in life expectancy. This, combined with a decline in the birth rate, has led to an aging society with a high aging rate. In such an aging society, it is expected that the number of people requiring care, such as those in need of nursing care or nursing care, due to illness, injury, aging, etc., will increase.

[0003] In nursing care, various types of care recipients are targeted. In addition, the staff involved in providing care have various experiences and skills. Furthermore, the policies of the facilities where nursing care is provided are not uniform, and there are differences between facilities. In other words, nursing care sites are diverse, and it is a field in which standardization of the work is difficult. The following Patent Document 1 is an example of a technology for finding ways to improve work in such an environment. In Patent Document 1, with the aim of grasping problems and issues in nursing care work and improving nursing care work, information on the presence or movement of staff is output using nurse call history information and the like based on information on the positions of nursing care staff. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2014-215683 A Summary of the Invention [Problem to be solved by the invention]

[0005] The technology disclosed in Patent Document 1 only captures one aspect of the work, i.e., the location information of staff members. In addition, regarding areas for improvement, the decision is made by a human being by looking at the data, and specific areas for improvement are not indicated by the system.

[0006] The present invention has been made in consideration of the above circumstances, and aims to provide a system that supports improvement of the quality of nursing care work in nursing care facilities from a comprehensive perspective by analyzing data related to staff nursing care. [Means for solving the problem]

[0007] The above object of the present invention can be achieved by the following means.

[0008] (1) an acquisition unit that acquires behavioral data of staff providing care to residents of a facility; an index generating unit that generates an index representing a staff member's work execution method from the acquired staff member behavior data; and an output unit that outputs the generated index.

[0009] (2) The information processing system according to (1) above, wherein the index is an index showing the degree of variability in the time required for each task performed at the facility and / or the degree of variability in the number of tasks performed.

[0010] (3) The indicator is an indicator showing the degree of variability in the time required for each task to be performed among staff members at the facility and / or the degree of variability in the number of tasks performed. The information processing system described herein.

[0011] (4) In addition, we have a department for deriving improvement measures. the improvement measure derivation unit extracts tasks having large variation indices generated by the index generation unit, and derives improvement measures for reducing variation related to the extracted tasks; The information processing system according to (2) or (3), wherein the output unit further outputs the derived improvement measures.

[0012] (5) The information processing system according to (4) above, wherein the improvement measure deriving section derives a plurality of improvement measures.

[0013] (6) the improvement measure derivation unit further calculates an effect expected value for the derived improvement measure using an estimation model; The information processing system according to (4) above, wherein the output unit further outputs the effect likelihood value.

[0014] (7) the improvement measure deriving unit derives a plurality of improvement measure candidates; the improvement measure derivation unit selects one or more improvement measures from among a plurality of candidate improvement measures based on facility information, which is information about the facility, the index, and the effect expected value; The information processing system according to (6) above, wherein the output unit outputs the selected improvement measure.

[0015] (8) The information processing system according to (1) above, wherein the index generation unit identifies a task performed by the staff from among a plurality of tasks based on the behavioral data, and generates an index representing the method of performing the task by the staff from the identified task.

[0016] (9) An information processing system as described in (1) above, wherein the behavioral data includes detection data by a detection unit that detects human movements within the room in which the resident is present, and notification information and operation information for a staff terminal used by the staff.

[0017] (10) The information processing system according to (3) above, wherein the index generation unit identifies the staff member who performed the task from the behavioral data.

[0018] (11) A step (a) of acquiring behavioral data of staff providing care to residents of a facility at said facility; (b) generating an index representing the staff's work performance method from the acquired staff behavioral data; and (c) outputting the index generated in the step (b).

[0019] (12) The indicator is an indicator showing the degree of variation in the time required for each task to be performed and / or the number of tasks performed among staff at the facility, The method further includes a step (d) of extracting tasks having large variability indices generated in the step (b) and deriving improvement measures for reducing variability for the extracted tasks, The business quality improvement support method according to (11) above, wherein in the step (c), the improvement measures derived in the step (d) are output.

[0020] (13) Furthermore, using the estimation model, the expected effect value of the improvement measures derived above is calculated. (e) calculating The business quality improvement support method according to (12) above, wherein in the step (c), the effect expected value is further output.

[0021] (14) A control program for causing a computer to execute the business quality improvement support method according to any one of (11) to (13) above. Effect of the Invention

[0022] The information processing system according to the present invention includes an acquisition unit that acquires behavioral data of staff who care for residents in a facility, an index generation unit that generates an index representing a staff work performance method from the acquired behavioral data of the staff, and an output unit that outputs the generated index, thereby supporting improvement of the quality of care work in a nursing care facility. [Brief description of the drawings]

[0023] [Figure 1]1 is a schematic diagram showing an information processing system according to an embodiment of the present invention; [Diagram 2] 1 is a schematic diagram showing the overall configuration of a monitoring support system used in a nursing care facility. [Diagram 3] FIG. 1 is a block diagram showing a configuration of an information processing device. [Figure 4] 13 is an example of data b1 and b2 stored in the second storage unit. [Diagram 5] FIG. 13 is a diagram showing an example of a detection unit installed in a resident's room. [Figure 6] FIG. 2 is a block diagram showing a schematic configuration of a detection unit. [Figure 7] FIG. 13 is a schematic diagram showing a silhouette determined from a captured image. [Figure 8] FIG. 1 is a block diagram showing a schematic configuration of a monitoring device. [Figure 9] 10 is a flowchart showing a process for responding to an event related to a watching support service executed by the watching support system. [Figure 10] 13 is an example of an operation screen displayed on a staff terminal for responding to an event notification. [Figure 11] 13 is a flowchart showing a process of collecting and storing behavioral data and the like. [Figure 12] 13 is a flowchart showing a business quality improvement support process. [Figure 13] FIG. 11 is a diagram for explaining the identification of a business type by preprocessing. [Figure 14] FIG. 11 is a diagram illustrating an example of various generated indices. [Figure 15] This is an example of extracting staff members who deviate from the average for all staff members (improvement measures). [Figure 16] 13 is a flowchart showing a generation process of an effect estimation model. [Figure 17] This is an example of an effect estimation model. [Figure 18] 13 is a subroutine flowchart showing the process of step S25 in FIG. 12. [Figure 19]13 is a flowchart showing continuous business improvement through a business quality improvement support process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] Hereinafter, an embodiment of the present invention will be described with reference to the attached drawings. However, the scope of the present invention is not limited to the disclosed embodiment. In the description of the drawings, the same elements are given the same reference numerals, and duplicated descriptions are omitted. In addition, the dimensional ratios of the drawings are exaggerated for the convenience of explanation, and may differ from the actual ratios.

[0025] FIG. 1 is a schematic diagram showing an information processing system 1 and a plurality of nursing care facilities 900 connected thereto. FIG. 2 is a schematic diagram showing the overall configuration of a monitoring support system 30 used in a nursing care facility 900 (hereinafter also simply referred to as a facility). The information processing system 1 is composed of an information processing device 10. In addition to the information processing device 10, the information processing system 1 also includes a monitoring support system 30 for a nursing care facility 900. The monitoring support system 30 may further include at least one of the monitoring support system 30 and the terminal device 20. The terminal device 20 is, for example, a PC. An employee 76 (or a manager or the like 74 described later) of the service provider providing the service of the monitoring support system recognizes a problem in the nursing care facility 900 by referring to the problem extraction result (described later) displayed and output on the terminal device 20. The information processing device 10 is a server for service management operated by the service provider, and is an on-premise server installed in the service provider's building, or a cloud server using a commercial cloud service. In addition, the monitoring support system 30 is provided with a monitoring device 32, which functions as an edge server installed in each nursing care facility 900. The information processing device 10 may be provided in the building of any of the nursing care facilities 900, that is, any of the monitoring devices 32 may function as the information processing device 10.

[0026] (Behavioral Data) The monitoring device 32 generates or collects behavioral data of staff members involved in the care of residents of the facility, and periodically transfers all or part of the collected behavioral data to the information processing device 10. Details of the behavioral data will be described later.

[0027] A monitoring support system 30 is installed in each of the multiple nursing care facilities 900. The monitoring support systems 30 installed in each nursing care facility 900 have the same configuration. The monitoring support system 30 is connected to an information processing device 10 operated by a service provider via the Internet. The nursing care facility 900 is a facility that provides nursing care services to residents of the facility (also called care recipients), and is, for example, a special nursing home for the elderly, a residential type nursing home, or a group home.

[0028] (Overall configuration of monitoring support system 30) Referring to FIG. 2, the monitoring support system 30 used in the nursing care facility 900 includes a detection unit 31, a monitoring device 32, a staff terminal 34, a wireless AP (access point) 35, and a terminal device 20. The terminal device 20, the detection unit 31, the monitoring device 32, and other devices are connected to each other via a LAN. The staff terminal 34 connects to other devices via a wireless access point 35. Furthermore, each device in the nursing care facility 900 connects to an external network via an RT (router). The detection unit 31 is disposed in each room (hereinafter also referred to as a living room) of a resident 70, and detects the behavior and state of the resident 70 in the room. The staff terminal 34 is a portable terminal such as a smartphone, and is used by the staff 72 during work hours. The configuration of the staff terminal 34 is omitted, but includes a control unit, a memory unit, a communication unit, an operation display unit, and the like. Furthermore, the staff terminal 34 can acquire location information within the facility by communicating with multiple wireless APs 35 using wifi disposed within the facility. Also, the staff terminal 34 may monitor acceleration using a built-in acceleration sensor. The watching device 32 may acquire position information and acceleration information at each time, and record the information by linking it with the ID of the staff member 72 using the device. The control unit executes various programs, the communication unit communicates wirelessly, and the operation display unit displays an operation screen using a touch panel and accepts operations. Details of the detection unit 31 and the watching device 32 will be described later.

[0029] (Information processing device 10) Fig. 3 is a block diagram showing a schematic configuration of the information processing device 10. The information processing device 10 includes a control unit 110, a storage unit 120, and a communication unit 130. Although the storage unit 120 is shown as a single configuration in Fig. 3, it may be distributed and disposed in the monitoring devices 32 of multiple care facilities 900. The data stored in the storage unit 120 is information generated at each facility and stored in the storage unit 323 (Fig. 8 described later) of the monitoring device 32 of each care facility 900, which is collected and aggregated.

[0030] (Control unit 110) The control unit 110 includes a CPU, a GPU, a RAM, a ROM, etc. The control unit 110 functions as an acquisition unit 111, an index generation unit 112, a model generation unit 113, an improvement measure derivation unit 114, and an output unit 119, either alone or in cooperation with a communication unit 130.

[0031] The acquisition unit 111 acquires various types of information related to nursing care, including behavioral data of the staff 72, from the monitoring support system 30 of each nursing care facility 900. The details will be described later, but the "behavioral data" of the staff 72 includes the following. (1) The behavior of the staff member 72 determined from the detection data of the detection unit 31, or notification information based on the detection data (event notification and event notification settings, which will be described later); (2) Operation information of the staff member 72 to the staff terminal 34 in response to this notification information.

[0032] The index generating unit 112 generates a task method index (hereinafter, simply referred to as an "index") that indicates a task implementation method. For example, as an index, the index generating unit 112 has a variance in the implementation method for each task determined from the behavioral data. The variance includes the variance in the number of times that a task type, such as night patrol, moving assistance, and diaper changing, is performed in a predetermined period (for example, one shift (8 hours) or one day), and the variance in the time that the staff stays in the room (time required for the task). Here, "night patrol" refers to the staff member 72 visiting the resident's room for a short time (for example, within one minute) during the nighttime hours. This night patrol is mainly performed to confirm the safety of the resident. Moving assistance refers to the staff member 72 assisting the resident 70 when moving from the bed to the wheelchair (or vice versa) in the room. Diaper changing refers to the staff member 72 changing the resident's diaper by the staff member 72. The variation is determined by identifying the staff member 72 who performed the task, and includes the variation in the number of times each staff member performed the task and the duration of stay. Statistical information such as the average value, variance, and quartiles can be used as an index of variation. Furthermore, as a benchmark for variation, statistical information of facilities with similar facility information (same cluster group described below) among multiple nursing care facilities 900 can be used. Furthermore, if a facility is of a scale including multiple units or floors, statistical information of other units or other floors can be used as a benchmark.

[0033] The model generation unit 113 generates an estimation model (also called an effect estimation model) using behavioral data from a predetermined period of time in the past. Covariance structure analysis, multiple regression analysis, etc. are used as methods for the estimation model. For example, the model generation unit 113 creates an estimation model of an index for each task using past indicators for each staff member. For example, the estimation model describes the relationship between the number of visits and the length of stay for each task (see FIG. 17 described later). This estimation model is generated using behavioral data of staff members in multiple nursing care facilities 900 with similar facility information. The generated estimation models for each task are stored in the memory unit 120 and used by the improvement measure derivation unit 114.

[0034] The improvement measure derivation unit 114 derives the type of work, or the type of work and the target staff (staff to be improved) based on the index generated by the index generation unit 112. For example, it determines whether the index of variation is large for each work, and derives the work with large variation as the work type to be targeted for improvement measures. In addition, the improvement measure derivation unit 114 uses an estimation model to calculate an expected effect value when improvement measures are implemented and the index improves from the current value to a certain value.

[0035] The output unit 119 outputs business quality improvement support information consisting of the calculated or derived indexes, improvement measures, and / or effect expected values. More specifically, the output unit 119 outputs the indexes calculated by the index generating unit 112, or together with the indexes, the improvement measures derived by the improvement measure derivation unit 114, and the effect expected value. As the output, for example, the information is transmitted to the terminal device 20.

[0036] The memory unit 120 stores (a1) multiple effect estimation models, (b1) staff terminal operation logs, (b2) system detection and alert logs, (b3) care performance (care records), and (b4) care facility information.

[0037] The effect estimation model a1 is an effect estimation model related to index values ​​for each task, and is generated by the model generation unit 113. b1 to b3 are generated or acquired by the watching support system 30 based on the detection data of the detection unit 31 or the operation input of the staff terminal 34.

[0038] Fig. 4 shows examples of b1 and b2 (various logs). In the facility, the monitoring support system 30 detects a specific behavior of the care recipient (called an event) and records a response log when an alert (notification) is issued to the staff 72 via the staff terminal 34. The procedure for determining an event as shown in Fig. 4 and acquiring the corresponding response log will be described later (Fig. 9, etc.).

[0039] b3 is actual nursing care data recorded by the operation of staff 72 on staff terminal 34, and records whether or not meal care, bathing care, excretion care, morning care (MC), evening care (EC), etc. were performed, as well as the amount of care provided and the condition of the resident at that time.

[0040] The nursing care facility information in b4 includes attributes of the nursing care facility, staff composition of the nursing care facility, and resident attributes of the nursing care facility. The facility attributes include the facility type, capacity, location (prefecture), and occupancy rate (number of residents / capacity). There are eight general facility classifications (facility types), each with its own characteristics and the trends in resident profiles or facility management characteristics change. Private facilities include nursing care homes, residential nursing homes, serviced housing for the elderly, and group homes, while public facilities include care houses, special nursing homes, nursing care health facilities, and nursing care hospitals. The staff composition is the number of people for each occupation, such as care, nursing, and management. The resident attributes are the number of people for each level of care required. This nursing care facility information can be collected by referring to the facility information, resident list, and staff list (all of which will be described later) recorded in the memory unit 323 of the monitoring device 32 of each facility.

[0041] (Monitoring Support System 30) Hereinafter, the watching support system 30 and a procedure for generating various log data including staff behavior data by the watching support system 30 will be described with reference to Figs.

[0042] (Detection unit 31) FIG. 5 is a diagram showing an example of a detection unit 31 installed in a room of a resident of the facility, and FIG. 6 is a block diagram showing a schematic configuration of the detection unit 31. As shown in FIG.

[0043] The detection unit 31 is also called a sensor box or a monitoring support sensor, and is disposed in each room so as to observe or monitor the room of the resident 70, which is the observation area. The detection unit 31 includes various sensors as described later, and generates sensing information from the output of the sensors. The sensing information includes not only the signals of each sensor, but also, for example, the determination result of the movement of a person determined by image processing from a video signal (an event described later), and a care call signal from the care call unit 315 (described later).

[0044] As shown in FIG. 6, the detection unit 31 includes a control unit 311, a communication unit 312, a camera 313, a body movement sensor 314, and a care call unit 315, which are connected to each other via a bus or short-range wireless communication.

[0045] The control unit 311 has a CPU, RAM, ROM, etc., as a configuration similar to that of the control unit 110. The control unit 311 may also have a HDD. The control unit 311 controls each unit of the detection unit 31 and performs calculation processing according to a program. The control unit 311 functions as an event determination unit 31a.

[0046] The communication unit 312 is an interface circuit (eg, a LAN card, a wireless communication circuit, etc.) for communicating with other devices such as the monitoring device 32 via a LAN.

[0047] The camera 313 is placed, for example, on the ceiling or upper part of a wall of the room, captures the bed 60 of the resident 70 directly below as an observation area, and outputs the captured image (image data). This captured image includes still images and videos. The camera 313 is a near-infrared camera, but a visible light camera may be used instead, or both may be used in combination. The camera 313 outputs an image signal as sensing information acquired by the imaging sensor.

[0048] The body movement sensor 314 is a Doppler shift type sensor that transmits and receives microwaves to and from the bed 60 and detects a Doppler shift of the microwaves caused by body movement (e.g., breathing) of the resident 70. This body movement sensor 314 detects chest body movement (up and down movement of the chest) caused by the breathing of the resident 70. If this sensor detects a disruption in the period of the chest body movement or an amplitude of the chest body movement that is equal to or smaller than a preset threshold, the control unit 311 determines that there is an abnormality in the slight body movement (e.g., due to cardiac arrest).

[0049] The care call unit 315 includes a push button switch, and detects a care call (also called a nurse call) when the resident 70 operates this switch. Instead of a push button switch, a care call may be detected by an audio microphone. When the switch of the care call unit 315 is pressed, that is, when a care call is detected, the control unit 311 transmits a notification that a care call has been made to the watching device 32, etc., via the communication unit 312 and the LAN.

[0050] FIG. 7 is a schematic diagram showing a silhouette determined from a captured image. FIG. 7 shows a part of a captured image i1 captured by a camera 313. The event determination unit 31a of the control unit 311 detects a whole-body silhouette 1A of a resident 70 (hereinafter referred to as a "human silhouette") from a plurality of captured images (moving images). A head silhouette (not shown) may be used together with or instead of the human silhouette 1A. The human silhouette 1A may be detected, for example, by extracting a range of pixels with a relatively large difference by a time difference that subtracts images captured before and after. The human silhouette 1A may also be detected by a background difference method that subtracts a background image from a captured image.

[0051] Whether the event is getting up, getting out of bed, falling or falling down is determined by the event determination unit 31a based on the posture of the resident 70 (e.g., standing, sitting, lying, etc.) from the detected human silhouette 1A and the relative position to objects in the room such as the bed 60. For example, getting up can be recognized when the width of the human silhouette 1A crossing any side of a preset rectangle viewed from above, with vertices at the four corners of the bed 60, increases to 20 cm or more. Also, getting out of bed can be recognized when the ratio of the area of ​​the human silhouette 1A outside the rectangle to the area inside the rectangle increases to 80% or more.

[0052] (Monitoring device 32) Fig. 8 is a block diagram showing a schematic configuration of the monitoring device 32. The monitoring device 32 includes a control unit 321, a communication unit 322, and a storage unit 323. The monitoring device 32 is a server (edge ​​server) and works in cooperation with the information processing device 10 to collect various information including behavioral data of staff members. Note that the device configuration shown in Fig. 8 and other figures is merely an example, and A part of the functions of the device 32 may be performed on the information processing device 10 side, or conversely, a part of the functions of the information processing device 10 side may be performed on the watching device 32 side.

[0053] (Control unit 321) The control unit 321 includes a CPU, a RAM, a ROM, and the like. The control unit 321 functions as a behavioral data generating unit 32a and a facility information receiving unit 32b. The facility information receiving unit 32b receives input of facility information of the nursing care facility 900 to which the monitoring device 32 provides services from the manager, etc. 74, and stores it in the memory unit 323. The control unit 321 also functions as a notifying unit, and notifies the staff terminal 34 of the event determined by the detection unit 31, etc. (S850 described later). In addition, the notification setting for the staff terminal 34 may be individually set by input setting through the terminal device 20, etc. of the user (hereinafter, referred to as event notification setting). For example, whether or not to notify the staff terminal 34 of the event determined by the detection unit 31 can be set for each resident 70 or for each type of event. For example, for a resident 70 who is at high risk of falling according to physical function and level of care, notifications for all types of events are enabled. Conversely, if the resident 70 has a high degree of independence, it is deemed that care for the event of getting out of bed is not necessary, and notification of the event of getting out of bed to this resident 70 is disabled.

[0054] (Communication unit 322) The communication unit 322 is an interface circuit (for example, a LAN card, a wireless communication circuit, etc.) for communicating with other devices such as the detection unit 31 via a LAN.

[0055] (Storage unit 323) The memory unit 323 stores a resident list, a staff list, an event list, nursing care records (care records), shift information, and facility information.

[0056] The "resident list" and the "staff list" include personal IDs (name, number), room numbers, staff names, units, etc., related to the residents 70 and staff 72. The "resident list" also includes information on the physical condition of the residents 70, such as the level of care required, height, weight, age, medical history, and dementia level. A unit (also called a responsible group) is a resident unit to which multiple residents who are in a common area, such as the same floor in the facility, belong, and a group to which multiple staff members responsible for these resident units belong. The "event list" includes event information and response status. The "shift information" is the working hours or working period of each staff member 72, and is recorded corresponding to the login / logoff time described later. The "care record" includes a care record sheet, a nursing record sheet (medical chart, life record), and a diagnostic chart, which record the care given to these residents 70 by the staff member 72 (caregiver, nurse, etc.). Some of the care records are input by the staff member 72 through the staff terminal 34.

[0057] (Event handling) Fig. 9 is a flowchart showing a process for responding to an event related to the monitoring support service executed by the monitoring support system 30. By the process in Fig. 9, (b1) the staff terminal operation log and (b2) the system detection and alert log as shown in Fig. 4 are generated by the behavior data generating unit 32a and recorded as an event list in the storage unit 323. The recorded event lists in each of the monitoring devices 32 in each care facility 900 are periodically collected and aggregated by the information processing device 10.

[0058] (Step S800) Here, a login authentication process is performed. The staff member 72 inputs a staff ID and a password via a touch panel (not shown) of the staff terminal 34, and transmits them to the monitoring device 32. The monitoring device 32 checks the authentication information stored in the storage unit 323 and The authentication result according to the staff's authority is transmitted to the staff terminal 34.

[0059] (Step S810) The detection unit 31 monitors the observation area with a camera 313 .

[0060] (Steps S820, S830) The detection unit 31 detects an event from the movement of the resident 70 in the observation area. The detection unit 31 also detects an event through an operation of the care call unit 315. Then, the communication unit 312 of the watching device 32 acquires event information of the event detected by the detection unit 31.

[0061] (Step S840) The monitoring device 32 updates the event list with the event information acquired in step S830. Events included in the event list include getting up, getting out of bed, falling, falling over, and care calls (also referred to as care call events) as described above. The latest detected event is added to the end of the event list. Each event includes data on "event information" and "response status." The event information includes an event ID that is an automatically assigned primary key, a room number, a care recipient ID (target person ID), an event type, an occurrence date and time (time), and image data information. The image data (photographed image) included in the event information is still image data obtained by photographing the event by the detection unit 31 when the event occurred, which was transmitted in step S830. The "response status" includes the status, the staff member who responded, the response date and time (time), and whether or not a live image (hereinafter also simply referred to as a video) was viewed (use of the photographed image) (hereinafter referred to as viewing of a live image). In addition, the information may include whether or not there is a conversation between the staff 72 and the resident 70 by the care call unit 315 (audio microphone) through the staff terminal 34 (hereinafter referred to as audio conversation). In addition, the information may also include whether or not the staff 72 has visited the room. The responding staff is a staff member who has taken the initiative in the processing of step S880 described below and has become responsible for the room. Here, "visiting the room" refers to the act of the staff 72 visiting the resident 70's room. When multiple people are recognized in the room at the same time by image processing of the captured image, the event determination unit 31a determines that there has been a visit. When the monitoring device 32 detects a visit within a predetermined time from the occurrence of an event, it links the visit to the event.

[0062] (Step S850) Here, the monitoring device 32 notifies one or more staff members 72 of the event information newly acquired in step S820. More specifically, based on the event information, a broadcast notification is performed to simultaneously notify the staff terminals 34 of all logged-in staff members 72 belonging to the unit in charge of the resident 70. Note that Fig. 9 only shows the processing of one staff terminal 34 used by one staff member 72 out of the multiple staff terminals 34. Furthermore, when making this notification, if the notification based on the settings for each resident and each event type is disabled by the above-mentioned event notification setting, the notification may be omitted.

[0063] (Step S860) Each staff member 72 checks the event that has occurred through the staff terminal 34. Fig. 10 shows examples of operation screens d1 and d2 for responding to an event notification (broadcast notification) displayed on the display unit of the staff terminal 34. The operation screen d1 shown in the figure is a screen that displays a list of events. The displayed events can be scrolled up and down by a flick operation.

[0064] Areas e10 to e12 of the operation screen d1 are events of log IDs 3836977 to 3836980 that occurred after log ID 3836973 in FIG. 4. Area e10 displays an icon indicating that log ID 3836977 is a care call, and an icon indicating that the call has been dealt with. In the area e11, an icon indicating that the event is a wake-up event and that the event has been dealt with are displayed for log ID 3836978. In the area e12, icons indicating that the event is a wake-up event and that the event has been dealt with are displayed for log IDs 3836979 and 3836980, and that the event has not yet been dealt with are displayed for log IDs 3836979 and 3836980. These two events are related to the same resident 70 (Mr. C), so they are displayed together in the same area. Also, because they have not yet been dealt with, a thumbnail image related to the latest event (ID 3836980) is displayed in the area e13. By operating the area e13, text messages can be exchanged with other staff members 72 who are logged in. By clicking the area e12 on the operation screen d1, the staff member 72 transitions to the operation screen d2 for confirming the next content.

[0065] (Step S870) The staff 72 checks the details of the event on the operation screen d2 displayed on the staff terminal 34. In the operation screen d2, the name of the resident (Mr. C) who caused (determined) the event and the name of the staff (Staff 03) who uses the staff terminal 34 are displayed in the area e20. The time elapsed from the time the event occurred is displayed in the area e21. The elapsed time ("1 minute passed") shown in the area e21 is the time elapsed (rounded down to the nearest minute) since the latest event was determined to have occurred. The area e21 also displays a thumbnail image (still image) of the image taken at the time of the event (getting out of bed). When the staff 72 feels that the thumbnail image is insufficient information and wants to check the status of the resident 70 who caused the get out of bed or get up event, he operates the "talk" button and the "view" button in the areas e23 and e24 below. By operating the "talk" button, he can talk to the resident 70 (Mr. C) through the microphone and speaker of the care call unit 315. By operating the "Watch" button, a display request is sent to the monitoring device 32, and in response, live images (real-time captured images (video)) captured by the camera 313 can be viewed by streaming playback on the operation screen d2. When the "Watch" button is operated, as shown in the video viewing column of the event list in FIG. 4, video viewing "yes" is recorded for this event (hereinafter also referred to as use of the "live video function"). At this time, the video viewing time and the number of calls / call time via the "Talk" button may be recorded in association with the event.

[0066] The staff member 72 (for example, staff member 03) wishes to take the initiative in taking charge of the wake-up and get-out events (ID012, 013) displayed by operating the "response" button (hereinafter also referred to as "request for responsibility") in the area e22. If the staff member does not wish to take charge, the staff member operates the back button (triangle icon) in the bottom column to return to the previous operation screen d1 showing the event list. Note that while a certain staff member 72 is displaying the operation screen d2 shown in FIG. 10 and checking the status of the event, a prohibition process is performed on the other staff members 72 under the control of the monitoring device 32. For example, when a certain staff member 72 is checking the status of the event of the resident 70 (Mr. C), another staff member 72 selects the same event (ID3836980). In this case, the words "checking status" are displayed on the operation screen d1 of the other staff member 72, and the "response" button is not displayed or cannot be selected even if the operation screen d2 is transitioned to.

[0067] (Steps S880, S890) When staff member 03 wishes to take the initiative and take charge of an event, he or she operates the "take charge" button (presses the take charge button). In response to staff member 03, who is the terminal user, operating the "take charge" button, staff terminal 34 transmits a request to take charge of the selected event to the monitoring device 32. In response, the monitoring device 32 returns an approval notice. Upon approval, staff member 03 who sent the request becomes responsible for the event, checks the status of the event through staff terminal 34, and rushes to the event to take charge (visit the room), etc., if necessary.

[0068] (Step S900) The monitoring device 32 updates the event list in response to the process of step S880. Specifically, the status of the event list (ID3836979-3836980: getting out of bed, etc.) is changed to "handled". In this embodiment, the status is changed to "handled" in response to the staff member 72 selecting an event and operating the above-mentioned "handle" button for the event displayed on the operation screen d2. That is, by operating the "handle" button, the handling status of "handled", which is information indicating confirmation, is input, and the handling date and time are recorded assuming that the staff member 72 who operated the button handled the event. More specifically, in the event list as shown in FIG. 4, the time when the process of step S880 or S990 was performed is recorded in the handling date and time column. In this case, the handling may be ended without rushing to the event by checking the thumbnail image on the operation screen d2 or talking to the resident 70. However, the present invention is not limited to this, and the response date and time may be recorded in the response date and time field as the time when the staff member 72 rushes to the room of the resident 70 who has caused an event such as a fall, a trip, or a nurse call and determines that the staff member 72 has visited the room (step S920 described below). As another example, the response may be completed by inputting the response result on a separate operation screen, and the input time may be recorded in the response date and time field. In addition, in response to updating the event list, the monitoring device 32 broadcasts the updated event list to all staff members who are currently logged in.

[0069] (Step S910) Here, an example will be described in which a staff member 72 in charge of the event rushes to the room of the resident 70 who caused the event to respond to the emergency.

[0070] (Step S920) It is detected that the staff member 72 has visited (entered) the room. This visit is determined by activating a sensor at the entrance of the room, for example, by holding the staff terminal 34 over an NFC tag (near field communication tag) placed at the entrance. Alternatively, the detection unit 31 (event determination unit 31a) of the room determines the visit by detecting a third party other than the resident 70 based on an image captured by the camera 313, that is, by detecting the presence of multiple people. In the latter case, if there is a visit to the room where the event occurred within a predetermined time (for example, within 10 to 15 minutes) from the request to respond to the event (S880), it may be deemed that there was a visit by the staff member 72 (staff member D) who made the response request.

[0071] (Step S930) The detection unit 31 transmits information about the staff's visit to the monitoring device 32. The visit information includes the resident's 70 ID number.

[0072] (Step S940) The watching device 32 records the visit information received in step S930 in association with an event for which the status of the resident 70 corresponding to the ID number is "already handled" and which has the latest handled date and time.

[0073] (Step S950) When the staff member 72 finishes working, the staff member 72 logs out by operating an "end of work" button (not shown) on the staff terminal 34. The logout time is recorded in the storage unit 323 as shift information.

[0074] (Collection, storage and processing of behavioral data, etc.) 11 is a flowchart showing the process of collecting and storing behavioral data, etc. The information processing device 10 collects and stores behavioral data, etc., from the monitoring support system 30 of a plurality of nursing care facilities 900 for a predetermined period, for example, every day. We collect various information such as behavioral data.

[0075] (Steps S101 to S103) The acquisition unit 111 of the information processing device 10 acquires the above-mentioned data b1 to b3 from each of the monitoring support systems 30 of the multiple care facilities 900. More specifically, the acquisition unit 111 acquires the data b1 to b4 stored in the memory unit 323 of the monitoring device 32 of the care facility 900, and accumulates it in the memory unit 120 for each facility. Here, the data b1 to b4 are as follows: (b1) staff terminal operation log, (b2) system detection and alert log, (b3) care performance (care record).

[0076] (Step S104) Furthermore, the acquisition unit 111 of the information processing device 10 acquires the above-mentioned nursing care facility information when new information is input, when information is updated, or when an input instruction is given by an administrator or the like. The information processing device 10 accumulates the collected information in the storage unit 120 as (b4) nursing care facility information. This ends the processing of FIG. 11.

[0077] (Business quality improvement support processing) Next, the business quality improvement support process by the information processing system 1 according to this embodiment will be described with reference to Fig. 12 to Fig. 16. Fig. 12 is a flowchart showing the business quality improvement support process. In response to receiving an execution start instruction for a target facility from a user such as an employee 76 via the terminal device 20, the information processing device 10 starts execution of the business quality improvement support process shown in Fig. 12.

[0078] (Business quality improvement support processing) (Step S21) The acquisition unit 111 acquires the behavior data of the target facility. This behavior data is acquired in FIG.

[0079] (Step S22) The index generating unit 112 performs preprocessing on the behavioral data. In this preprocessing, the index generating unit 112 identifies (estimates) the type of work (work content). In particular, the index generating unit 112 identifies the type of work related to care such as patrol and diaper changing (also called room care) performed by staff in the room of the resident 70. In addition, the index generating unit 112 identifies and links the staff 72 engaged in the estimated type of work.

[0080] The index generating unit 112 uses the following (1) to (6) to identify the type of work performed by the staff from among multiple types of work. Also, the index generating unit 112 uses the following (1) to (8) to identify the type of work and the staff who performed that work. (1) The time of day when each event occurred (night, daytime), (2) Type of event; (3) Event and log order, (4) Event,log time interval, (5) Duration of the log (span), (6) The type of work recorded in the nursing care record, the time of recording, and the recorder (staff member in charge), (7) Position information and acceleration information of staff member 72 acquired from staff terminal 34 (8) Shift information.

[0081] For example, the index generating unit 112 can identify that the type of work is indirect work, ie, record entry, and the staff member who performed this, based on the input time of the nursing care record (6). Using the data (7) alone or in combination with the data (6), the unit 112 can identify the type of work as food assistance, data entry assistance, or other indirect work, and identify the staff member who performed it.

[0082] The business type can be specified by referring to the following concrete examples. Fig. 13 is a diagram for explaining the specification of the business type by pre-processing. The specified business type is written in the tag column of each list in Fig. 13.

[0083] In the example shown in Fig. 13(a), the room visit event surrounded by the dashed line has no corresponding past events within a predetermined time, and the span is also within a predetermined time range (less than one minute). From these conditions, the index generating unit 112 identifies the type of work as a "night patrol" such as a wait-and-see operation.

[0084] In the example shown in Fig. 13(b), the visiting event surrounded by the dashed line has no corresponding past events within a predetermined time period, as in Fig. 13(a), but the span is within a predetermined time range (3 minutes or more). From these conditions, the index generating unit 112 identifies the task type as "diaper changing".

[0085] In the example shown in Fig. 13(c), for the visit event surrounded by the dashed line, there is a notification (care call) event as a corresponding past event within a predetermined time. Although not shown in Fig. 13(a), the terminal operation log records the use of the Live video function (see Fig. 4, for example), so the indicator generating unit 112 identifies the business type as a visit to a room in response to a notification (with LIVE confirmation).

[0086] (Step S23) Based on the behavioral data preprocessed in step S22, the index generating unit 112 generates an index representing the work implementation method of the staff 72. FIG. 14 is a diagram showing an example of various generated indexes. As shown in FIG. 14, the index generating unit 112 calculates various indexes as indexes representing the work implementation method of the staff 72. The index generating unit 112 calculates variation indexes regarding the number of notifications handled, the number of visits, and the length of stay by time period, by work type, and by staff. As shown in FIG. 14, the indexes include indexes by room (by resident), by work type, by staff, and by time period (by time period), or by combinations of these. The various variation indexes may be a distribution diagram or a bar graph so that the distribution and amount can be seen, as shown in FIG. 14. Alternatively, the various variation indexes may be the number (or percentage) of staff members that are included or not included within the standard deviation, the interquartile range, or the average value ±x%.

[0087] By being presented with such indicators, users can understand the types of work that vary widely, and can also understand that certain staff members are outside the distribution of the entire staff.

[0088] (Step S24) The improvement measure derivation unit 114 derives one or more improvement measures using the various indices for each task type calculated in step S23. Specifically, the improvement measure derivation unit extracts tasks that vary widely and can be improved, and the staff members who are eligible for improvement. The extraction methods include the following. (1) Set a threshold for the variability index (standard deviation, quartile), and extract tasks that fall outside the threshold. Also, extract tasks that are in the top x or bottom y positions. (2) Also, extract staff members who deviate from the average for all staff members. (2.1) Extract staff members who are more than x% off the average in absolute value, who are outside the quartile range, or who are in the top z position in absolute value of the difference from the average. Figure 15 is an example of an improvement measure. As shown in this figure, for each task (code 0 to code 45) of the number of visits and the length of stay, ,Staff members that deviate from the average are extracted.,The indicators enclosed in a square in Figure 15 are such,indicators. (2.2) If the absolute value of the variability is equal to or less than a threshold, the number of staff members to be extracted may be reduced (may be zero). (2.3) From the effect estimation model (see, for example, Figure 17 below), extract staff whose estimated values ​​deviate significantly from the estimates, i.e., whose tendencies are different from those of other staff.

[0089] (Improvement measures) As improvement measures, examples of past efforts in other facilities (facilities with similar facility information) may be used. For example, the following (1) to (4) are included. An improvement measure table describing the correspondence between the target business of the improvement measures and the improvement measures may be stored in advance in the storage unit 120. (1) If reducing the variation in the number of night-time patrols is identified as an issue, the improvement measure will be to strictly enforce the rules regarding patrol times. (2) If reducing the variability in the time it takes to change a diaper is identified as an issue, lectures on diaper changing techniques will be given to staff with low skills. (3) If reducing the variability in the frequency of diaper changes is identified as an issue, improvement measures will include reviewing the diaper material, for example, changing to a thicker diaper with a higher absorption capacity. (4) If reducing the variation in notification response visits is identified as an issue, improvement measures include (a) thoroughly enforcing notification response rules or (b) reviewing event notification settings. Here, (a) notification response rules mean, for example, in the case of a resident with a high degree of independence, the staff member 72 does not visit the room immediately after receiving a notification, but rather monitors the resident using a live image viewing or voice conversation function, or uses these functions to confirm the situation before visiting the room. (b) To review event notification settings, notifications are disabled for each resident and for each event type individually. For example, bed leaving notifications for a resident 70 with a high degree of independence are set to disabled (OFF).

[0090] (Step S25) Here, the improvement measure derivation unit 114 uses an effect estimation model stored in the storage unit 120 to calculate an effect expectation value for each of the one or more improvement measures extracted in step S24.

[0091] The processing here will be described below with reference to Fig. 16 to Fig. 18. Fig. 16 is a flowchart showing the generation processing of the effect estimation model. First, with reference to Fig. 16, the effect estimation model used in step S25 will be described.

[0092] (Effect estimation model) (Step S301) The index generating unit 112 generates a past work method index for each staff member. The staff behavior data used for this generation may be data of the target facility, or may be more limited and generated using behavior data of staff members belonging to the same unit. Alternatively, in a broader range, behavior data of staff members of multiple facilities belonging to the same cluster group may be used for each facility cluster to which the target facility belongs. The facility cluster is a clustering of the nursing care facility 900 based on the facility information. More specifically, the facility cluster is a clustering of similar facilities by determining the similarity in terms of facility attributes, staff composition, and resident attributes. More specifically, the facility cluster is a clustering of similar facilities by determining the similarity in terms of facility attributes, staff composition, and resident attributes included in the facility information.

[0093] (Step S302) The model generation unit 113 generates an effect estimation model for each task using the past task policy index generated by the index generation unit 112. FIG. 17 is an example of the effect estimation model. Six types of tasks, code 0 to 5, are targeted as tasks. The effect estimation model shown in FIG. 17 is the average number of visits (per day or per shift) and average visit time (per visit (minutes)) for each staff member for each month, calculated based on past behavioral data spanning multiple months. The horizontal axis is the average number of visits (per day) for each staff member, and the vertical axis is the average visit time (time (minutes) per day). The effect estimation model generated in this manner is stored in the storage unit 120.

[0094] The effect estimation model reveals the following. Code 0 (nighttime inspections) and code 2 (diaper changes) have a large variability between staff, and even for the same staff, there is a large difference from month to month. On the other hand, there is relatively little variability in visits made in response to notifications of codes 3 to 5. For this reason, equalizing codes 0 and 2 is more effective in improving the variability in visit time and frequency.

[0095] As another example, if there is a correlation between indicators of care methods, such as a reduction in the number of diaper changes resulting in an increase in visits to the room in response to notifications, these indicators may also be reflected in the effect indicator model.

[0096] (Step S25: Calculation of expected value) FIG. 18 is a subroutine flowchart showing the process of step S25.

[0097] (Step S401) The improvement measure derivation unit 114 selects an improvement measure to be a target for calculating an expected value. This improvement measure is selected from the multiple improvement measures derived in step S24. For example, the improvement measure derivation unit 114 selects, as the improvement measure, improvement of the variation in the number of diaper changes for code2 (diaper changes) in FIG. 17. For example, if the number of diaper changes for staff member u001 deviates from that of other staff members, this staff member u001 becomes the target of the improvement measure.

[0098] (Step S402) The improvement measure derivation unit 114 acquires the current index value x0 of the staff member who is the target of the measure. For example, if the number of diaper changes (number of visits) of code2 of the staff member u001 is the target, the number of visits becomes the index value x0.

[0099] (Step S403) The improvement measure derivation unit 114 uses an estimation model to calculate the index x0 and its improved index value x1 (prospective index value) as index values ​​y0 and y1 for the entire facility. The index values ​​y0 and y1 may be index values ​​y0 and y1 for a smaller unit rather than for the entire facility. The improved index value x1 may be, for example, an average value for staff in the facility or unit, or a predetermined value. The number of target staff members is not limited to one, and may be multiple. For example, multiple staff members who deviate greatly from the distribution of index values.

[0100] (Current index value y0) For example, in the case where the improvement measure derivation unit 114 is targeting the number of diaper changes (number of visits) of code2 by staff member 001, this number of visits becomes the index value x0. For the index value y0 of the entire facility when staff member 001's index value is x0, the current value of the facility can be used. Alternatively, the index value y0 can be calculated by multiplying the average number of visits in the entire facility by the average visiting time. Alternatively, the index value y0 can use the variance statistics between staff members for the current total visiting time per day.

[0101] (Improved expected index value y1) For example, the improvement measure derivation unit 114 assumes that the number of diaper changes (number of visits) for code2 of staff member 001 has improved from index value x0 to index value x1. In this case, the average value for the entire facility becomes slightly smaller due to the decrease in index value from x0 to index value x1. Then, by calculating the variation index for index value x1, index value y1 is obtained by the following procedure 1 or procedure 2.

[0102] In the following, a is the time spent visiting a room, X is the number of visits per day, and the estimation model for the total visiting time is fa(X):=a*X+b. (Step 1) When x0 or x1 is the number of visits, the total visit time fa(x1) can be calculated by substituting x1 into the estimation model. For staff 001, this total visit time fa(x1) is used to calculate the variance index y1 (the variance index of total visit time between staff) in the same way as for x0. Here, the total visit time for staff other than staff 001 is calculated using the actual results for a specified past period, for example the actual value for the previous month. (Step 2) When x0 or x1 is the visit time per visit, only when calculating the total visit time for staff member 001, the total visit time for x1 (fx1(X)) can be calculated by replacing the coefficient a corresponding to the "visit time per visit" in the estimation model with x1 (fa → fx1). In this case, the number of times X substituted into the estimation model is, for example, the actual value for staff member 001 from the previous month. After that, y1 is calculated in the same way as in step 1.

[0103] (Step S404) The improvement measure derivation unit 114 calculates the difference between the current index value y0 and the index value y1 after the expected improvement in the variation, thereby calculating the expected effect value. Then, the subroutine process in Fig. 18 is terminated, and the process returns to the process in Fig. 12, and the process from step S25 onwards is performed.

[0104] (Step S26) The output unit 119 outputs the derived business quality improvement data. The business quality improvement data includes the indicators, improvement measures, and effect expectation values ​​calculated or derived in steps S23 to S25. For example, the information processing device 10 transmits and presents this information to the terminal device 20 that has received the execution start instruction.

[0105] In this manner, the information processing system according to the present embodiment includes an acquisition unit that acquires behavioral data of staff who care for residents at the facility, an index generation unit that generates an index representing the staff's work implementation method from the acquired behavioral data of the staff, and an output unit that outputs the generated index. This allows users such as employees 76 and managers 74 to easily grasp the issues with the facility. In particular, by calculating and outputting the work method index of the staff at the facility, the user can grasp the status of the staff's work method. Furthermore, by deriving and outputting improvement measures, the user can specifically grasp everything from the staff's status to the improvement measures. Furthermore, by presenting the expected effect value, the user can receive support in making a decision on which improvement measure to prioritize from among multiple improvement measures.

[0106] In nursing care facilities, the skills of staff vary from facility to facility and from individual to individual. In particular, there was a large variation in skills in visiting care in residents' rooms, making it difficult to evaluate each staff member. As a result, there was little progress in standardizing staff skills. Furthermore, the actions of facility staff were often left to their own discretion, and there was no standard for evaluating whether their actions were appropriate or not, so even if staff behavior was inappropriate, it was difficult to correct it. Furthermore, even if the facility wanted to reduce the burden on individual staff members, they did not know what specific improvement measures to take or to what extent they would improve, and so were unable to make an immediate decision. As a result, the quality of care at the facility was often poor.

[0107] In the information processing system according to the present embodiment, under such circumstances, the work method index of the staff By outputting data on improving operational quality such as the above, facility users can easily understand which measures should be prioritized.

[0108] (Example) 19 is a flowchart showing continuous business improvement by the business quality improvement support process. In the following embodiment, the business quality improvement support information output by the above-mentioned process is evaluated by monitoring the transition of the index of the good item.

[0109] (Step S51) The information processing system 1 outputs the business quality improvement support information. The process here is as shown in FIG.

[0110] (Step S52) Here, the user on the facility side will understand the presented business quality improvement support information. Then, by understanding the issues, the user will select an improvement measure from among the measures. When selecting an improvement measure, the user can refer to the expected effect value to support decision-making when making the selection.

[0111] (Step S53) The facility side executes the selected measure. The timing at which the measure is started is input to the information processing system 1.

[0112] (Step S54) The information processing system 1 executes the process of step S52 after a predetermined period of time has elapsed, for example, after one month or two weeks have elapsed. The information processing system 1 calculates or derives business quality improvement support information based on the behavioral data acquired after the start of step S62, and outputs the information. The process here is as shown in FIG. 12. For example, when the information processing system 1 is continuously performed once a month, it outputs business quality improvement support information generated based on the behavioral data from the previous month of one month. At this time, the information processing support system may also calculate and output the comparison data (difference or ratio) of a and b below. (a) Business quality improvement support information obtained before starting the measures in step S53 (output in step S51); (b) Comparison data with information on business quality improvement support obtained from behavioral data for the period after the start of the measures. (Steps S55 and S56) Here, the facility side grasps the presented business quality improvement support information, and checks the effect of the measures that have been started in step S53.

[0113] In addition, users can understand the remaining issues by being presented with new improvement measures. If necessary, they can select and implement improvement measures from among the remaining issues. In this way, the facility can easily understand the effects of the improvement measures.

[0114] The above-described configuration of the information processing system 1 is a main configuration described in order to explain the features of the above-described embodiment, but is not limited to the above-described configuration and may be modified in various ways within the scope of the claims. In addition, the configuration of a general information processing device 10 is not excluded.

[0115] For example, the improvement measures output in step S26 in FIG. 12 may be some optimal improvement measures selected from a plurality of improvement measures. This selection may be, for example, improvement measures with a predicted effect value of a predetermined value or more, and may be selected from the improvement measure table of the same cluster group from the facility information. Alternatively, the remedial measures for which there is a problem may be selected.

[0116] The means and methods for performing various processes in the information processing device 10 or the information processing system 1 according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The above-mentioned program may be provided by a computer-readable recording medium such as a USB memory or a DVD (Digital Versatile Disc)-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded in the computer-readable recording medium is usually transferred to and stored in a storage unit such as a hard disk. The above-mentioned program may be provided as a standalone application software, or may be incorporated into the software of the device as one of its functions. [Explanation of symbols]

[0117] 1. Information Processing Systems 10. Information processing device 110 Control section 111 Acquisition Department 112 Index generation section 113 Model Generation Unit 114 Improvement measure derivation department 119 Output section 120 Storage section 130 Communications Department 20 Terminal Equipment 30 Monitoring support system 31 Detection unit 32 Monitoring Device 34 Staff terminal

Claims

1. An acquisition unit that acquires behavioral data of staff providing care to residents of the facility at the facility; an index generating unit that generates an index representing a staff member's work execution method from the acquired staff member behavior data; and an output unit that outputs the generated index.

2. The information processing system according to claim 1 , wherein the index indicates a degree of variation in the time required for each task performed at the facility and / or a degree of variation in the number of tasks performed.

3. The information processing system according to claim 2 , wherein the index indicates a degree of variation in the time required for one task to be performed among staff members at the facility and / or a degree of variation in the number of times the task is performed.

4. In addition, we have an improvement measure derivation department, the improvement measure derivation unit extracts tasks having large variation indices generated by the index generation unit, and derives improvement measures for reducing variation related to the extracted tasks; The information processing system according to claim 2 , wherein the output unit further outputs the derived improvement measures.

5. The information processing system according to claim 4 , wherein the improvement measure deriving section derives a plurality of improvement measures.

6. The improvement measure derivation unit further calculates an effect expected value for the derived improvement measure using an estimation model, The information processing system according to claim 4 , wherein the output unit further outputs the effect expected value.

7. the improvement measure derivation unit derives a plurality of improvement measure candidates; the improvement measure derivation unit selects one or more improvement measures from among a plurality of candidate improvement measures based on facility information, which is information about the facility, the index, and the effect expected value; The information processing system according to claim 6 , wherein the output unit outputs the selected improvement measure.

8. The information processing system according to claim 1 , wherein the index generating unit identifies an operation performed by the staff member from among a plurality of operations based on the behavioral data, and generates an index representing a method of performing the operation by the staff member from the identified operation.

9. The information processing system according to claim 1 , wherein the behavioral data includes detection data obtained by a detection unit that detects human movement within the room in which the resident is present, and notification information and operation information for a staff terminal used by the staff.

10. The information processing system according to claim 3 , wherein the indicator generating unit identifies a staff member who performed a task from the behavioral data.

11. (a) acquiring behavioral data of staff providing care to residents of a facility at said facility; (b) generating an index representing a staff member's work execution method from the acquired staff member behavior data; and (c) outputting the index generated in the step (b). A method to support the improvement of business quality.

12. The index is an index indicating the degree of variation in the time required for one task to be performed among staff members at the facility and / or the degree of variation in the number of tasks performed; The method further includes a step (d) of extracting tasks having large variability indices generated in the step (b) and deriving improvement measures for reducing variability for the extracted tasks, 12. The method for supporting improvement of business quality according to claim 11, wherein said step (c) further comprises outputting the improvement measures derived in step (d).

13. The method further includes a step (e) of calculating an expected effect value for the derived improvement measure using an estimation model, 13. The method for supporting improvement of business quality according to claim 12, wherein said step (c) further comprises outputting said effect expectation value.

14. A control program for causing a computer to execute the business quality improvement support method according to any one of claims 11 to 13.

Images