Computer program, care needlessness index estimation device, and care needlessness index estimation method

Abstract

To provide a computer program, a care needlessness index estimation device, and a care needlessness index estimation method which can estimate whether or not a person cared in a residential place will not need care in the residence place in the future.SOLUTION: The computer program causes a computer to execute processing of acquiring time-series relevant data relevant to a life of a care-receiver cared in a residential place and estimating a future care needlessness index of the care-receiver on the basis of the acquired relevant data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a computer program, a care need index estimating device, and a care need index estimating method. [Background technology]

[0002] In recent years, the average life expectancy has increased, leading to an aging society and an increase in the number of nuclear families. In an aging society, various problems such as an increase in the number of people requiring care, the aging of caregivers, and an increase in the care burden on caregivers have become prominent, and it is important to consider how to support the elderly.

[0003] Patent document 1 discloses an in-house care system that sets up a day service facility on the company's premises that can be used by family members of employees who need care, and that can set and manage the usage times of the day service in accordance with employees' arrival and departure times for work. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-185206 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, although the system of Patent Document 1 can reduce the burden of care on the family, it does not take into consideration the reduction of the burden on the caregivers engaged in care. The nursing care industry has a problem of labor shortage, and caregivers have problems such as a large physical burden. On the other hand, those who need care, such as the elderly, wish to stop living in facilities and live at home if possible.

[0006] The present invention has been made in consideration of such circumstances, and aims to provide a computer program, a care no-need-to-reach index estimation device, and a care no-need-to-reach index estimation method that can estimate whether a care recipient who is cared for at their residence will no longer need care at their residence in the future. [Means for solving the problem]

[0007] The present application includes multiple means for solving the above-mentioned problems. As one example, a computer program causes a computer to execute a process of acquiring time-series relevant data related to the life of a care recipient receiving care at their residence, and estimating a future care-requiring indicator for the care recipient based on the acquired relevant data. Effect of the Invention

[0008] According to the present invention, it is possible to estimate whether a care recipient who is receiving care at his / her residence will no longer require care at his / her residence in the future. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating an example of the configuration of a care need index estimation system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of subject data stored in a subject DB. [Diagram 3] FIG. 1 is a diagram showing an example of a portion of a layout in a care facility. [Figure 4] FIG. 13 is a diagram illustrating an example of a method for estimating a degree of return to home by a server. [Diagram 5] 4A to 4C are diagrams illustrating examples of activity data, sleep data, care records, and biological data. [Figure 6] FIG. 13 is a diagram illustrating a relationship between activity data, sleep data, care records, and biological data and mobility ease. [Figure 7] FIG. 13 is a diagram showing an example of a transition in mobility ease. [Figure 8] FIG. 11 is a diagram showing a first example of a process for estimating a return-to-home degree using a learning model. [Figure 9]FIG. 13 is a diagram showing a second example of a process for estimating the degree of return to home using a learning model. [Figure 10] FIG. 13 is a diagram illustrating an example of a rule-based method for estimating a degree of return to home. [Figure 11] FIG. 13 is a diagram illustrating an example of an output of an estimation result of a degree of return to home. [Figure 12] FIG. 13 is a diagram showing examples of places of residence and corresponding levels of care need. [Figure 13] FIG. 13 is a diagram illustrating an example of a process of estimating the degree of need for care by a server. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing an example of the configuration of a care-required index estimation system of this embodiment. The care-required index estimation system includes a server 50 as a care-required index estimation device. The care-required index estimation system may include a plurality of sensors 10, 11, 12, ... 1N and a relay device 20. A care recipient DB (database) 61 is connected to the server 50. The server 50 is connected to the relay device 20, a data server 100, and a terminal device 40 via a communication network 1. A plurality of sensors 10, 11, 12, ... 1N are connected to the relay device 20. The care recipient DB 61 may be a data server. In this embodiment, a care facility is taken as an example of a residence where a care recipient lives.

[0011] The multiple sensors 10 to 1N are installed in the nursing facility and include a mat sensor laid on a bed or the like, a door sensor that detects the opening and closing of a door, a human presence sensor that detects the presence or absence of a person and the movement of the person, etc. The sensor data detected by the multiple sensors 10 to 1N is transmitted to the relay device 20 together with a sensor ID. Note that the sensors are not limited to the above-mentioned examples, and may include, for example, a camera that can capture video.

[0012] The relay device 20 includes a memory, a communication module, etc., temporarily stores sensor data from the multiple sensors 10 to 1N, and transmits the stored sensor data to the server 50. The relay device can identify which of the multiple care recipients the sensor data belongs to based on the sensor data from the multiple sensors 10 to 1N, and classify the sensor data for each care recipient. For example, sensor data detecting a series of actions in which a care recipient leaves a bedroom, goes to a toilet, and returns to the bedroom can identify the care recipient based on the ID of the sensor in the bedroom, and can identify that the sensor data detects a series of actions of the identified care recipient by arranging the data detected by each sensor in chronological order. The relay device 20 collects sensor data for each care recipient ID and transmits it to the server 50. The server 50 may classify the sensor data for each care recipient.

[0013] The terminal device 40 is a terminal device used by a person in charge of the care need index estimation system (such as an administrator or operator), and is configured as a portable PC, a desktop PC, a tablet terminal, or a smartphone.

[0014] The data server 100 is a database that records the care records and biometric data of each of a plurality of care recipients. The care records are information recorded by the caregiver throughout the daily life of the care recipient, and are recorded in chronological order on a daily basis. For example, the care records include the walking distance that the care recipient was able to walk in one training session, the number of steps per unit time, and the time it took to transfer from a wheelchair to a bed or a toilet seat. The biometric data are data measured by a medical professional throughout the daily life of the care recipient, and are recorded in chronological order on a daily basis. For example, the biometric data include blood pressure, heart rate, body temperature, and blood oxygen concentration.

[0015] The server 50 includes a control unit 51 that controls the entire server 50, a communication unit 52, a memory 53, an interface unit 54, and a storage unit 55. The server 50 may be configured by a computer. The functions of the server 50 may be shared among a plurality of servers.

[0016] The control unit 51 may be configured by incorporating a required number of central processing units (CPUs), micro-processing units (MPUs), graphics processing units (GPUs), etc. The control unit 51 may also be configured by combining digital signal processors (DSPs), field-programmable gate arrays (FPGAs), etc.

[0017] The interface unit 54 has an interface function with an external device. The interface unit 54 has a function for accessing the care recipient DB 61. The interface unit 54 can write data to the care recipient DB 61 and read data from the care recipient DB 61.

[0018] The communication unit 52 includes a communication module and has a function of communicating with the relay device 20, the data server 100, and the terminal device 40 via the communication network 1. Under the control of the control unit 51, the communication unit 52 acquires (receives) sensor data of the multiple sensors 10 to 1N of the care recipient from the relay device 20. Note that the communication unit 52 may acquire (receive) sensor data of the multiple sensors 10 to 1N, and the control unit 51 may compile the sensor data for each care recipient. Furthermore, under the control of the control unit 51, the communication unit 52 acquires (receives) care records and biological data of the care recipient from the data server 100.

[0019] The storage unit 55 can be configured with a hard disk or a semiconductor memory, and stores a computer program 56 (program product), a learning model 57, and required information.

[0020] The computer program 56 is an application program of the care-need-not-be-needed index estimation service that runs on the server 50. The computer program 56 may be downloaded from an external device via the communication unit 52 and stored in the storage unit 55. The computer program 56 recorded on a recording medium (for example, an optically readable disk storage medium such as a CD-ROM) may be read by a recording medium reading unit and stored in the storage unit 55. The computer program 56 may be deployed to be executed on a single computer, or on multiple computers located at one site, or distributed across multiple sites and interconnected by a communication network.

[0021] The memory 53 can be configured with a semiconductor memory such as a static random access memory (SRAM), a dynamic random access memory (DRAM), a flash memory, etc. A computer program 56 can be loaded into the memory 53, and the control unit 51 can execute the computer program 56. The control unit 51 can execute processing defined by the computer program 56. The processing by the control unit 51 is also processing by the computer program 56.

[0022] The care recipient DB 61 stores care recipient data.

[0023] 2 is a diagram showing an example of the configuration of care recipient data stored in the care recipient DB 61. The care recipient data is composed of the care recipient ID, name, date of birth, sex, family address, etc. The care recipient data is registered when the care recipient enters a care facility.

[0024] FIG. 3 is a diagram showing an example of a part of the layout in a care facility. FIG. 3 shows a part of the layout related to the range of movement of the care recipient (particularly the range of movement at night). The layout includes the care recipient's bedroom and toilet, separated by a corridor (passageway). A bed is installed in the bedroom. A mat sensor laid on the bed, a bedroom door sensor, and the like are installed in the bedroom. A human sensor, a toilet door sensor, and the like are installed in the toilet. These sensors are the sensors 10 to 1N described above. Note that the layout of the care facility is one example and is not limited to the example in FIG. 3.

[0025] The index of no need for care is an index for evaluating a state in which no care is required, and may be expressed, for example, by a numerical value, by a rank, or by a binary choice such as whether or not care is required. In the following, an example will be described in which the degree of no need for care (evaluated by a numerical value) is used as the index of no need for care. Next, a method for estimating the degree of return to home (index of return to home) as the degree of no need for care of a care recipient will be described. The index of return to home is an index for evaluating a state in which no care is required and the care recipient can return to home, and may be expressed, for example, by a numerical value, by a rank, or by a binary choice such as whether or not the care recipient can return to home. The degree of return to home is a numerical representation of the index of return to home, similar to the degree of no need for care. The degree of no need for care is a judgment index for judging the boundary between whether or not care is required. The degree of return to home, which is a sub-concept of the degree of no need for care, is a judgment index for judging the degree to which a care recipient living in a care facility can leave the care facility and return to life at home. The degree of return to home can be expressed, for example, in the range of 0 to 100%, and if the degree of return to home is 75% or more, the person can return to living at home. Note that the degree of return to home is not limited to an example expressed as a numerical range such as 0 to 100%, and may be expressed, for example, in five stages from 1 to 5. In this case, for example, if the degree of return to home is 4 or more, the person can return to living at home.

[0026] FIG. 4 is a diagram showing an example of a method for estimating the degree of return to home by the server 50. As shown in FIG. 4, the control unit 51 has a state identification processing function, a mobility ease estimation processing function, and a weighting processing function. The control unit 51 acquires time-series related data related to the life of the care recipient via the communication unit 52. The related data includes sensor data detected by a plurality of sensors for detecting the behavior of the care recipient. In the example of FIG. 4, the plurality of sensors are the bedroom mat sensor, the bedroom door sensor, the toilet door sensor, and the toilet human sensor exemplified in FIG. 3. In addition, the related data includes at least one of the care record and the biological data of the care recipient.

[0027] The control unit 51 identifies at least one of the activity data and the sleep data of the care recipient based on the sensor data detected by the multiple sensors. In the example of Fig. 4, the control unit 51 identifies the activity data and the sleep data. The activity data and the sleep data will be described later.

[0028] The control unit 51 calculates mobility as an evaluation index for evaluating the mobility of the care recipient based on at least one of the identified activity data and sleep data. Mobility is an index for evaluating how much the care recipient can walk (move) alone, and is an index for estimating whether the care recipient can live, for example, at home while receiving nursing care services without needing nursing care at a nursing facility. Mobility can be classified into mobility from each evaluation axis by classifying the condition of the care recipient according to multiple evaluation axes. Mobility can be quantified, for example, in the range of 0 to 100%.

[0029] In the example of Fig. 4, the control unit 51 calculates mobility A of the evaluation axis A based on the activity data, and calculates mobility B of the evaluation axis B based on the sleep data. The control unit 51 may also calculate an evaluation index for evaluating the mobility of the care recipient based on at least one of the care records and the biological data. In the example of Fig. 4, the control unit 51 calculates mobility C of the evaluation axis C based on the care records, and calculates mobility D of the evaluation axis D based on the biological data.

[0030] 5 is a diagram showing an example of activity data, sleep data, care records, and biological data. Activity data is data indicating the amount of activity of the care recipient, and includes, for example, travel time (total travel time in a day, average travel time per unit time, etc.), number of trips (for example, number of trips from one place to another per day or per unit time, etc.). If the travel time or number of trips increases, it can be estimated that the ease of movement (walking) of the care recipient has improved.

[0031] The sleep data is data that indicates the sleep state of the care recipient, and includes, for example, the sleep duration (average sleep duration per day, etc.), the number of awakenings during sleep (e.g., the number of times the care recipient got out of bed during sleep, etc.). If the sleep duration is within a predetermined time range (e.g., 6 to 8 hours per day), the sleep state can be estimated to be good. Also, the fewer the number of awakenings during sleep, the better the sleep state can be estimated. If the sleep state is good, it can be estimated that the care recipient's health and motor skills are being maintained in good condition, and it can be indirectly estimated that the ease of movement (walking) of the care recipient has improved.

[0032] Nursing records are recorded daily by caregivers who care for the care recipients. Nursing records include, for example, walking distance (e.g., distance walked in one day's walking training), transfer time, number of steps (e.g., number of steps walked in one day's walking training), etc. Nursing records also include whether or not a wheelchair or walker is needed. If the walking distance or number of steps increases, it can be assumed that the care recipient's mobility (walking) has improved. If the transfer time decreases, it can be assumed that the care recipient's mobility (walking) has improved.

[0033] The biological data includes the blood pressure, heart rate, etc. of the care recipient. If the biological data is within the standard value, it can be assumed that the care recipient's health condition is being maintained in good condition, and indirectly, it can be assumed that the ease of movement (walking) of the care recipient has improved.

[0034] FIG. 6 is a diagram showing a schematic relationship between activity data, sleep data, nursing records, and biological data and mobility ease. In FIG. 6, evaluation axes A to D are activity data, sleep data, nursing records, and biological data. FIG. 6A shows a schematic relationship between activity data (e.g., average travel time) and mobility ease A. As shown in FIG. 6A, there is a tendency that mobility ease increases as the average travel time decreases. It can also be seen that the rate of change in mobility ease relative to activity data is relatively large. This indicates that mobility ease will also improve significantly as activity data improves.

[0035] FIG. 6B shows a schematic diagram of the relationship between sleep data (e.g., average sleep time) and mobility B. As shown in FIG. 6B, as the average sleep time increases, mobility tends to gradually increase. It can also be seen that the rate of change in mobility relative to sleep data is relatively small. This indicates that as sleep data improves, mobility also improves indirectly.

[0036] FIG. 6C shows a schematic diagram of the relationship between the care record (e.g., average walking distance) and mobility C. As shown in FIG. 6C, the longer the average walking distance, the greater the mobility tends to be. It can also be seen that the rate of change in mobility relative to the data in the care record is relatively large. This indicates that the mobility improves significantly as the data in the care record improves.

[0037] FIG. 6D is a schematic diagram showing the relationship between biometric data (e.g., mean blood pressure) and mobility D. As shown in FIG. 6D, if the mean blood pressure is within the standard range, mobility tends to improve slightly. This indicates that if biometric data improves, mobility will also indirectly improve.

[0038] FIG. 7 is a diagram showing an example of the transition of mobility. In FIG. 7, the vertical axis indicates mobility, and the horizontal axis indicates time. The graph in FIG. 7 shows the transition of mobility in the past and the transition of mobility in the future, with the present as the center. In the example of FIG. 7, patterns 1, 2, and 3 are shown as examples of past transitions. The transition of the mobility of the care recipient may gradually increase or decrease, or may not change much, depending on its nature. Pattern 1 shows an example in which mobility gradually increases with the passage of time (month and day). In the case of pattern 1, it can be estimated that mobility gradually increases from the present to the future. Pattern 2 shows an example in which mobility gradually decreases with the passage of time (month and day). In the case of pattern 2, it can be estimated that mobility gradually decreases from the present to the future. Pattern 3 shows an example in which mobility does not change much with the passage of time (month and day). In the case of pattern 3, it can be estimated that mobility does not change much from the present to the future. The transition of mobility as shown in Fig. 7 can be obtained by collecting data on the mobility of many care recipients on a daily basis, and classifying the collected data, for example. Note that the transition of mobility is only an example, and is not limited to the example of Fig. 7.

[0039] Returning to Fig. 4, the control unit 51 estimates the future degree of need for care of the care recipient based on the calculated evaluation index. In the example of Fig. 4, the control unit 41 calculates the degree of home return of the care recipient based on the calculated mobility A to D. In this case, the statistical values ​​(e.g., average value, median, etc.) of the mobility A to D are calculated as the degree of home return. For example, if the mobility A to D are 80%, 85%, 75%, and 90%, respectively, the degree of home return is 82.5% (=[80+85+75+90] / 4).

[0040] If the guideline (threshold) for permitting a care recipient to return home is, for example, 80%, then if the degree of return to home is 82.5%, the care recipient is permitted to return home.

[0041] 4, the control unit 51 may weight each of the calculated mobility eases A to D (evaluation indexes) and estimate the future degree of return to home of the care recipient based on the weighted mobility eases (evaluation indexes). For example, if the weighting coefficients of the mobility eases A to D are a, b, c, and d, respectively, the degree of return to home can be estimated by the formula: a×mobility ease A+b×mobility ease B+c×mobility ease C+d×mobility ease D.

[0042] As described above, the control unit 51 estimates the current or future degree of need for care of the care recipient based on the acquired related data. This makes it possible to estimate whether a care recipient who is cared for at a residence such as a care facility will no longer need care at the residence or will no longer need care at the residence in the future.

[0043] The degree to which the care recipient is able to return home may be estimated using a learning model 57.

[0044] FIG. 8 is a diagram showing a first example of a process of estimating the degree of return to home by the learning model 57. The learning model 57 can use a method such as a deep learning network such as a recurrent neural network (RNN), a long short term memory (LSTM) network, a support vector machine (SVM), or a random forest. As shown in FIG. 8, the learning model 57 receives time-series sensor data (associated data) of the care recipient detected by a plurality of sensors such as a bedroom mat sensor, a bedroom door sensor, a toilet door sensor, and a toilet motion sensor. The input sensor data can be data within a predetermined period from the present to the past. The predetermined period can be, for example, the past one month, the past two months, or the like.

[0045] The learning model 57 outputs the degree of return to home (degree of need for care) of the care recipient at present. The learning model 57 may also output the degree of return to home of the care recipient at a future time point. The future time point can be set appropriately, for example, one month or two months from the present.

[0046] The learning model 57 can be learned (generated) by machine learning using time-series sensor data of many care recipients that have been converted into big data. Specifically, time-series sensor data (related data) related to the lives of multiple care recipients and training data including the degree of return to home of multiple care recipients based on the results of care for the multiple care recipients are collected. The control unit 51 acquires the training data, and generates (learns) the learning model 57 so as to output an estimated value of the degree of return to home when time-series sensor data is input based on the acquired training data. The estimated value of the degree of return to home may be annotated in association with the sensor data. Note that the learning model 57 may be learned (generated) by using a learning server different from the server 50, and the learning model 57 generated by the learning server may be acquired from the learning server.

[0047] Fig. 9 is a diagram showing a second example of the process of estimating the degree of return to home using the learning model 57. The difference from the first example shown in Fig. 8 is that the input data includes nursing record data and biological data.

[0048] In the second example, the learning model 57 can also be trained (generated) by machine learning using time-series sensor data of many care recipients that have been converted into big data. Specifically, training data including time-series sensor data, care record data, and biological data (associated data) related to the lives of multiple care recipients, and the degree of return to home of multiple care recipients based on the results of care for the multiple care recipients is collected. The control unit 51 acquires the training data, and generates (trains) the learning model 57 so as to output an estimated value of the degree of return to home when the time-series sensor data, care record data, and biological data (associated data) are input based on the acquired training data. The estimated value of the degree of return to home may be annotated in association with the sensor data, the care record data, and the biological data. The learning model 57 may be trained (generated) using a learning server different from the server 50, and the learning model 57 generated by the learning server may be acquired from the learning server.

[0049] As described above, the control unit 51 acquires training data including time-series associated data related to the lives of multiple care recipients and the degree of return-home of multiple care recipients (degree of need for care) based on the results of care given to the multiple care recipients, and inputs the acquired associated data into a learning model 57 that outputs an estimated value of the degree of return-home when time-series associated data is input, based on the acquired training data, to estimate the current or future degree of return-home of the care recipient.

[0050] This makes it possible to estimate whether a person receiving care at a residence such as a care facility will no longer require care at their residence, or whether they will no longer require care at their residence in the future.

[0051] A rule-based method may be used to estimate the degree of return to home. The rule-based estimation method will be described below.

[0052] Fig. 10 is a diagram showing an example of a rule-based method for estimating the degree of return to home. The rule base performs judgment according to rules written by humans, and specifically, the control unit 51 performs estimation processing of the degree of return to home according to the rules written by humans. The example of Fig. 10 shows an overview of the rule base for convenience, but an actual rule base will have many more branches.

[0053] As shown in Fig. 10, data input to the rule-based algorithm includes time-series sensor data, care records, and biometric data detected for the care recipient. According to the rules (branches) shown in Fig. 10, for example, it is determined whether the care recipient has moved from the bed to the toilet, and if so, it is determined whether the movement time is △△ or less, and if it is △△ or less, it is determined whether there is an abnormality in the biometric data, and if there is no abnormality, it is determined that the care recipient can return home (the degree of return to home is equal to or greater than a threshold).

[0054] In addition, if the travel time is not △△ or less, it is determined whether the number of trips per day is 〇× or more, and if it is not 〇× or more, it is determined that the person is not able to return home (the degree of return to home is less than the threshold value).

[0055] Also, as shown in FIG. 10, if the patient does not move from the bed to the toilet, it is determined whether the walking distance in one day is XX or more, and if the walking distance is XX or more, it is determined whether the transfer time is XX or less, and if the transfer time is XX or less, it is determined whether there are any abnormalities in the biometric data, and if there are no abnormalities, it is determined that the patient can return home (the degree of return to home is above a threshold value).

[0056] As described above, the control unit 51 can acquire time-series related data relating to the life of the care recipient, and estimate the future care-needlessness index of the care recipient using a rule base based on the acquired related data.

[0057] FIG. 11 is a diagram showing an example of an output of an estimation result of a degree of home return. In the figure, the vertical axis indicates the degree of home return as a degree of need for care, and is expressed, for example, in a range of 0 to 100%. The horizontal axis indicates time, and for example, indicates a period from the past to the present and from the present to the future in units of one day. In FIG. 11, the degree of home return from the past to the present is expressed by a solid line, and the estimated degree of home return from the present to the future is expressed by a dashed line. For example, an estimation result of the degree of home return one month later is output based on related data (sensor data, care records, biological data, etc.) from the past one month or the past two months. When the estimated degree of home return is equal to or greater than a threshold value (threshold value for allowing home return), the control unit 51 outputs a notice to the terminal device 40 that home return is possible. The estimation result as shown in FIG. 11 can be output for each care recipient receiving care at a care facility. In addition, the estimation result as shown in FIG. 11 can be output on a daily basis.

[0058] In the above example, a care facility has been described as an example of a residence where a care recipient lives, but the residence is not limited to a care facility, as described below.

[0059] FIG. 12 is a diagram showing an example of a place of residence and the corresponding degree of need for care. As shown in FIG. 12, the place of residence can be a hospital facility, a home where the care recipient lives alone (a home where the care recipient lives alone), etc., in addition to a care facility. When the place of residence is a hospital facility, the control unit 51 can calculate the ease of movement as an evaluation index and estimate the discharge possibility (discharge possibility index) as the degree of need for care. The calculation of the ease of movement and the estimation of the discharge possibility are the same as in the case of a care facility. The discharge possibility index is an index for evaluating the state in which care is not required and the patient can be discharged from the hospital, and may be expressed, for example, by a numerical value, a rank, or a binary choice such as discharge possible or not possible. The discharge possibility index is a numerical value that represents the discharge possibility index, similar to the degree of need for care.

[0060] Furthermore, when the residence is a home where the person lives alone, the control unit 51 can calculate the ease of movement as an evaluation index and estimate the possibility of living alone (indicator of possibility of living alone) as the degree of need for nursing care. The possibility of living alone is a judgment index for judging the degree to which a person living alone at home can continue living alone while receiving nursing care services. The calculation of the ease of movement and the estimation of the possibility of living alone are the same as in the case of a nursing facility. The indicator of possibility of living alone is an index for evaluating the state in which the person does not need nursing care at the nursing facility and can live alone, and may be expressed, for example, as a numerical value, as a rank, or as a binary choice such as possible or impossible to live alone. The possibility of living alone, like the degree of need for nursing care, is a numerical representation of the indicator of possibility of living alone.

[0061] As described above, according to the server 50 of the present embodiment, in addition to the degree of return to home as a degree of need for nursing care, the degree of possibility of being discharged from hospital and the degree of possibility of living alone can be estimated.

[0062] FIG. 13 is a diagram showing an example of a process of estimating the degree of need for care by the server 50. The control unit 51 acquires time-series related data of the care recipient within a predetermined period in the past (S11). The predetermined period can be, for example, one month. The related data includes sensor data detected by a plurality of sensors for detecting the behavior of the care recipient. The related data also includes at least one of the care record and biological data of the care recipient.

[0063] The control unit 51 calculates an evaluation index (ease of movement) for a plurality of evaluation axes based on the acquired related data (S12). The plurality of evaluation axes can be, for example, four evaluation axes: behavior data, sleep data, care records, and biological data. The control unit 51 weights the evaluation index (ease of movement) for each evaluation axis (S13).

[0064] The control unit 51 estimates the degree of need for care after a predetermined time point based on the weighted evaluation index (S14), and outputs the estimation result (S15). After the predetermined time point may be a future time point or the present time. The control unit 51 determines whether or not to end the process (S16), and if the process is not to be ended (NO in S16), determines whether or not it is time to estimate (S17). The estimation timing may be, for example, once a day.

[0065] If it is not the estimated timing (NO in S17), the control unit 51 continues the process of step S17. If it is the estimated timing (YES in S17), the control unit 51 continues the process of step S11 and after. If the process is to end (YES in S16), the control unit 51 ends the process.

[0066] (Additional Note 1) The computer program causes a computer to execute a process of acquiring time-series relevant data related to the life of a care recipient who is receiving care at his or her residence, and estimating an indicator of the care recipient's future need for care based on the acquired relevant data.

[0067] (Appendix 2) The computer program in Appendix 1 causes a computer to execute a process of inputting the acquired related data into a learning model that outputs a care-elimination indicator when time-series related data is input, and acquiring a future care-elimination indicator for the care recipient.

[0068] (Supplementary Note 3) In the computer program according to Supplementary Note 1 or 2, the associated data includes sensor data detected by a plurality of sensors for detecting behavior of the care recipient.

[0069] (Supplementary Note 4) In the computer program according to any one of Supplementary Note 1 to Supplementary Note 3, the related data includes at least one of a care record and biometric data of the care recipient.

[0070] (Supplementary Note 5) The computer program according to Supplementary Note 3 causes a computer to execute a process of identifying at least one of activity data and sleep data of the care recipient based on sensor data detected by the plurality of sensors.

[0071] (Appendix 6) In Appendix 5, the computer program causes a computer to execute a process of calculating an evaluation index for evaluating the mobility of the care recipient based on at least one of the activity data and the sleep data, and estimating a future care-requiredness index for the care recipient based on the calculated evaluation index.

[0072] (Appendix 7) In Appendix 4, the computer program causes a computer to execute a process of calculating an evaluation index for evaluating the mobility of the care recipient based on at least one of the care records and the biometric data, and estimating a future care-requiredness index for the care recipient based on the calculated evaluation index.

[0073] (Supplementary Note 8) The computer program causes a computer to execute a process of weighting each of the calculated evaluation indexes in Supplementary Note 6 or Supplementary Note 7, and estimating a future care-needlessness index of the care recipient based on the weighted evaluation indexes.

[0074] (Supplementary Note 9) The computer program causes a computer to execute a process in which, in any one of Supplementary Note 1 to Supplementary Note 8, the place of residence includes a nursing facility, and a home return index is estimated as the nursing care unnecessary index.

[0075] (Supplementary Note 10) The computer program causes a computer to execute a process in any one of Supplementary Note 1 to Supplementary Note 9, in which the place of residence includes a hospital facility, and a dischargeability index is estimated as the no-care-required index.

[0076] (Appendix 11) The computer program causes a computer to execute a process in which, in any one of Appendices 1 to 10, the residence includes a home in which the person lives alone, and an indicator of ability to live alone is estimated as an indicator of the absence of care.

[0077] (Appendix 12) The care-neglect index estimation device is equipped with a control unit, which acquires time-series relevant data related to the life of a care recipient who is cared for at their residence, and estimates the future care-neglect index of the care recipient based on the acquired relevant data.

[0078] (Supplementary Note 13) The method for estimating a care-requiredness index acquires time-series relevant data related to the life of a care recipient who is cared for at the residence, and estimates the future care-requiredness index of the care recipient based on the acquired relevant data.

[0079] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations regardless of the citation format. Furthermore, the claims use a format in which a claim cites two or more other claims (multiple claim format), but this is not limited to this. A multiple claim (multi-multi claim) that cites at least one multiple claim may also be used. [Explanation of symbols]

[0080] 1. Communication Network 10, 11, 12, …, 1N sensors 20 Relay Device 40 Terminal Equipment 50 Servers 51 Control section 52 Communications Department 53 Memory 54 Interface section 55 Storage section 56 Computer Programs 57 Learning Model 61 Care recipient DB 100 Data Server

Claims

1. Obtaining time-series relevant data related to the life of a care recipient who is cared for at the place of residence; Estimating a future care-need-free index of the care recipient based on the acquired related data; A computer program that causes a computer to carry out processing.

2. inputting the acquired related data into a learning model that outputs a care-elimination index when time-series related data is input, and acquiring a future care-elimination index of the care recipient; 2. A computer program product according to claim 1, which causes a computer to carry out a process.

3. The related data is The sensor data includes sensor data detected by a plurality of sensors for detecting the behavior of the care recipient.

2. The computer program product of claim 1.

4. The related data is At least one of the care record and biometric data of the care recipient is included, 2. The computer program product of claim 1.

5. identifying at least one of activity data and sleep data of the care recipient based on the sensor data detected by the plurality of sensors; 4. A computer program product according to claim 3, which causes a computer to carry out a process.

6. Calculating an evaluation index for evaluating the mobility of the care recipient based on at least one of the activity data and the sleep data; Estimating a future care-need-free index of the care recipient based on the calculated evaluation index; A computer program product according to claim 5, which causes a computer to carry out the process.

7. Calculating an evaluation index for evaluating the mobility of the care recipient based on at least one of the care record and the biological data; Estimating a future care-need-free index of the care recipient based on the calculated evaluation index; A computer program according to claim 4, which causes a computer to carry out the process.

8. Each calculated evaluation index is weighted, estimating a future care-need-free index of the care recipient based on the weighted evaluation index; A computer program according to claim 6 or 7, which causes a computer to execute the process.

9. the place of residence comprises a care facility; Estimating a home return index as the nursing care unnecessary index; A computer program product according to any one of claims 1 to 5, which causes a computer to carry out a process.

10. the residence comprises a hospital facility; Estimating a discharge possibility index as the nursing care unnecessary index; A computer program product according to any one of claims 1 to 5, which causes a computer to carry out a process.

11. The place of residence includes a home where the person lives alone; Estimating an independent living index as the nursing care unnecessary index; A computer program product according to any one of claims 1 to 5, which causes a computer to carry out a process.

12. A control unit is provided, The control unit is Obtaining time-series relevant data related to the life of a care recipient who is cared for at the place of residence; Estimating a future care-need-free index of the care recipient based on the acquired related data; Nursing care unnecessary index estimation device.

13. Obtaining time-series relevant data related to the life of a care recipient who is cared for at the place of residence; Estimating a future care-need-free index of the care recipient based on the acquired related data; Method for estimating the care-free index.

Images