JP7689869B2 - Cognitive function assessment system - Google Patents

Description

The present invention relates to technology for a cognitive function assessment system capable of detecting abnormalities in cognitive function.

Conventionally, technology for a cognitive function assessment system capable of detecting abnormalities in cognitive function has been publicly known. For example, it is as described in Patent Document 1.

Patent Document 1 describes a dementia risk assessment system (cognitive function assessment system) that includes a biometric data detection sensor that can detect a subject's biometric data (cerebral blood flow data, heart rate data, pulse wave data, respiratory data, body movement data, etc.) and a dementia risk assessment device that compares the subject's biometric data with data related to dementia symptoms to assess the risk of developing dementia.

The biometric data detection sensor described in Patent Document 1 is loaned to a subject for a fixed period of time, and the subject uses the biometric data detection sensor to detect biometric data by operating it himself. Specifically, the subject irradiates near-infrared light from the biometric data detection sensor onto the forehead or other area, and the biometric data is detected by the reflected waves. Based on the biometric data thus obtained, the risk of developing dementia is determined.

However, as in Patent Document 1, it is cumbersome for subjects to undergo special tests (detection of biological data) to determine their own risk of developing dementia. For this reason, it is expected that there will be a certain number of subjects who will shy away from such tests, which is undesirable from the perspective of early detection of dementia.

JP 2021-45208 A

The present invention was made in consideration of the above-mentioned circumstances, and the problem it aims to solve is to provide a cognitive function assessment system that can easily detect abnormalities in cognitive function.

The problem that the present invention aims to solve is as described above, and the means for solving this problem will be explained next.

That is, in claim 1, the present invention includes a behavior detection unit capable of detecting the behavior of the subject by detecting the usage status of a plurality of pieces of equipment provided in a building used by the subject, a cognitive function assessment unit that compares active action data relating to the behavior of the subject detected by the behavior detection unit with learned behavior data relating to the behavior of the subject that has been learned in advance to determine whether or not there is an abnormality in the cognitive function of the subject, and a notification unit that can issue a notification to a person to be notified, wherein the plurality of pieces of equipment are classified in advance according to their frequency of use in a predetermined period, and store a first piece of equipment belonging to a first classification and a second piece of equipment belonging to a second classification that is used less frequently than the first classification, and during a first period, the cognitive function assessment unit stores a first piece of equipment belonging to a first classification and a second piece of equipment belonging to a second classification that is used less frequently than the first classification, and detects whether or not there is an abnormality in the cognitive function of the subject regarding the first piece of equipment. the presence or absence of a cognitive abnormality of the subject regarding the second equipment during the second period; the number of times a cognitive abnormality is detected for each behavior of the subject regarding the first equipment during a second period that is longer than the first period; if the number of times a cognitive abnormality is detected for the first equipment during the second period is equal to or greater than a predetermined threshold, a cognitive abnormality warning is issued to the subject to be notified using the alarm unit; the presence or absence of a cognitive abnormality of the subject regarding the second equipment during the second period is determined; the number of times a cognitive abnormality is detected for each behavior of the subject regarding the second equipment during a third period that is longer than the second period; and if the number of times a cognitive abnormality is detected for the second equipment during the third period is equal to or greater than a predetermined threshold, a cognitive abnormality warning is issued to the subject to be notified using the alarm unit .

In claim 2, the cognitive function assessment unit performs an action time assessment process to determine that an abnormality has occurred in the cognitive function of the subject when the time period during which the subject performed a predetermined action differs from the learned time period by a predetermined time or more, or when the subject does not perform the learned action.

In claim 3, the cognitive function assessment unit performs a sleep time assessment process to determine that an abnormality has occurred in the cognitive function of the subject when the time period during which the subject slept differs from the time period during which the subject studied by a predetermined time or more, or when the subject has not slept.

In claim 4, the cognitive function assessment unit assesses the degree of cognitive function abnormality in the sleep time assessment process based on an increase or decrease in the subject's sleep time relative to the learned sleep time.

In claim 5, the cognitive function assessment unit performs an action count assessment process to determine that an abnormality has occurred in the cognitive function of the subject when the number of times the subject has performed a predetermined action in a predetermined period differs from the number of times learned by a predetermined number or more.

The effects of the present invention are as follows:

According to the first aspect of the present invention, it is possible to easily detect abnormalities in cognitive function, and to appropriately notify a warning to a person to be notified.

In claim 2, abnormalities in cognitive function can be easily detected.

In claim 3, abnormalities in cognitive function can be easily detected.

In claim 4, more detailed assessment of cognitive function can be performed.

In claim 5, abnormalities in cognitive function can be easily detected.

FIG. 1 is a schematic diagram showing the configuration of a cognitive function assessment system according to one embodiment of the present invention. FIG. 1 is a diagram showing an overview of a series of processes performed by the cognitive function assessment system. 11A to 11C are diagrams showing examples of learning results, detection results in daily processing, and determination results. 11 is a flowchart showing the contents of daily processing. 11 is a flowchart showing the contents of an active time period determination. 11 is a flowchart showing the contents of determining the time period from going to bed to waking up. 7 is a flowchart showing a continuation of FIG. 6 . 11 is a flowchart showing the contents of weekly processing. 13A is a flow chart showing the contents of the weekly result notification, and FIG. 13B is a flow chart showing the contents of the monthly result notification.

The following describes the configuration of a cognitive function assessment system 100 according to one embodiment of the present invention, using FIG. 1.

The cognitive function assessment system 100 is for determining whether or not there is an abnormality in the cognitive function of the subject P1. In this embodiment, as an example, it is assumed that the subject P1 is an elderly person, and the presence or absence of an abnormality in the cognitive function of the elderly person is determined. The cognitive function assessment system 100 mainly comprises a power sensor 110, a server 120, and a terminal 130.

The power sensor 110 detects the power consumption of various pieces of equipment used by the subject P1 (particularly equipment used in daily life). The power sensor 110 is provided in the distribution board 2 of the building (house 1) in which the subject P1 resides. The power sensor 110 can detect the power of each branch circuit of the distribution board 2. This allows the power sensor 110 to detect the usage status (whether or not the equipment is being used) of the equipment connected to each branch circuit. By detecting the usage status of the equipment, it is possible to indirectly detect the behavior of the subject P1 (which equipment is being used).

In this embodiment, examples of equipment whose power consumption is detected by the power sensor 110 include cooking appliances (induction cooker, microwave oven, etc.), refrigerators, televisions, hair dryers, vacuum cleaners, washing machines, air conditioners, heating appliances, lighting, etc. For example, when use of a cooking appliance is detected, it is indirectly detected that subject P1 has used the cooking appliance (and thus eaten a meal). Also, when use of a television is detected, it is indirectly detected that subject P1 has watched television.

The method of detecting the usage status of various equipment is not limited to the method of detecting the power of each branch circuit by the power sensor 110, and various methods can be used. For example, it is possible to detect the power (main power) of the main circuit of the distribution board 2 and analyze the waveform of that power to identify and grasp the equipment being used. Also, instead of detecting the power of the distribution board 2, it is also possible to directly detect the operating status of the various equipment itself (on/off of the power of the various equipment, power of the outlets to which the various equipment are connected, etc.). Also, if the house 1 is provided with a system (e.g., HEMS: Home Energy Management System, etc.) that grasps (manages) the usage status of the various equipment, it is also possible to use the information grasped by that system.

The server 120 performs various processes based on the detection results of the power sensor 110. The server 120 is configured, for example, by a virtual server (cloud server) provided on the cloud. The server 120 can grasp the usage status of various pieces of equipment by acquiring information from the power sensor 110. The server 120 can determine whether or not there is an abnormality in the cognitive function of the subject P1 based on the usage status of the various pieces of equipment. The server 120 can also send and receive various pieces of information to and from the terminal 130 described below.

The terminal 130 is capable of displaying various types of information. The terminal 130 is carried by a person (e.g., a family member or relative of the subject P1) who should know whether or not there is an abnormality in the cognitive function of the subject P1. In this embodiment, it is assumed that a family member P2 of the subject P1 carries the terminal 130. The terminal 130 is configured, for example, as a device (e.g., a smartphone or tablet terminal) that can be carried by the family member P2 of the subject P1. The terminal 130 can notify the family member P2 of the subject P1 of information from the server 120 by an appropriate method (display on an LCD screen, audio, etc.).

By using the cognitive function assessment system 100 configured as described above, it is possible to detect the onset and signs of dementia in the subject P1.

For example, symptoms of dementia may include memory loss, disorientation, executive dysfunction, and reversal of day and night cycles.

"Memory disorder" is a disorder that causes symptoms such as being unable to remember new things and losing memories that were previously remembered. When subject P1 develops "memory disorder," it is expected that behavioral changes (abnormalities) will occur, such as forgetting that he or she has eaten a meal and eating again, or forgetting that he or she has cleaned and cleaning again.

"Disorientation" is a disorder in which a person is unable to grasp the situation they are in, such as "when, where, who," etc. If subject P1 develops "disorientation," it is expected that this will result in behavioral changes (abnormalities) such as turning on the heater even though it is summer, becoming unable to find their way in the house and being unable to go to the bathroom or bathroom, and being unable to return home once they have gone out.

"Dysfunction of executive function" is a disorder in which a person is unable to organize or plan things and carry out things in an orderly manner. If "dysfunction of executive function" develops in subject P1, it is expected that changes in behavior (abnormalities) will occur, such as being unable to prepare meals or not knowing how to use electrical appliances.

"Day-night reversal" is a disorder in which the sleep-wake rhythm is disrupted and day and night are reversed. If subject P1 develops "day-night reversal," it is expected that behavioral changes (abnormalities) will occur, such as being active during times when one would normally be sleeping (the middle of the night).

The cognitive function assessment system 100 of this embodiment detects changes in the behavior of the subject P1 as described above, and determines whether or not there is an abnormality in the cognitive function of the subject P1 based on this change in behavior. If necessary, the family P2 of the subject P1 is notified of the abnormality in the cognitive function of the subject P1. This allows the family P2 of the subject P1 to recognize the signs and onset of dementia in the subject P1, and can take appropriate measures (treatment, etc.) early on.

The following provides an overview of the series of processes performed by this cognitive function assessment system 100.

As shown in FIG. 2, the server 120 stores various pieces of equipment installed in the house 1, categorizing them according to frequency of use. Specifically, the server 120 stores various pieces of equipment, categorizing them into equipment used daily (category (1)) and equipment used not daily but at least once a week (category (2)). For example, in the example shown in FIG. 2, cooking appliances (induction cooker, microwave), refrigerator, television, hair dryer, etc. are used daily, and therefore are classified into category (1). Vacuum cleaners, washing machines, etc. are not used daily, but are used at least once a week, and therefore are classified into category (2).

Furthermore, server 120 also stores equipment that is only used during certain seasons, classifying it into category (1) or category (2). For example, in the example shown in FIG. 2, air conditioners and heating appliances are used every day in the seasons when they are needed (summer and winter), and are therefore classified into category (1). Although FIG. 2 does not give any specific examples of category (2), for example, if a washer-dryer is only used during the rainy season, this washer-dryer can be classified into category (2).

The server 120 can learn the detection results of the power sensor 110 in advance and classify the various pieces of equipment based on the learning results. That is, it can determine the frequency with which the various pieces of equipment are used in a specified period of time and classify them into category (1) or (2) based on this frequency. Also, instead of using the learning results, the manufacturer/seller or user of the cognitive function assessment system 100 can arbitrarily determine the classification.

The server 120 performs appropriate processing for each classified piece of equipment to determine whether or not the subject P1 has an abnormality in cognitive function, and notifies the subject P1's family member P2 of the abnormality in cognitive function as necessary.

Specifically, the server 120 detects the daily (every day) usage status (and thus the behavior of the subject P1) of the equipment classified as category (1), and performs processing to determine the presence or absence of abnormalities in the cognitive function of the subject P1 based on the detection results. Hereinafter, this processing is referred to as "daily processing." In daily processing, the server 120 stores the behavior that was the subject of the judgment, the presence or absence of abnormalities, and the reason for the judgment, linking them to each other.

The server 120 also calculates the number of times an abnormality is detected for each behavior during the week by the daily processing. For behaviors for which an abnormality is detected a predetermined number of times or more, an alert (warning) is issued using the terminal 130. Hereinafter, this processing is referred to as "weekly result notification." The weekly result notification enables the family member P2 of the subject P1 who possesses the terminal 130 to know that an abnormality has occurred in a specific behavior of the subject P1, and thus that there is a risk of cognitive function decline.

Meanwhile, the server 120 detects the weekly (every week) usage status (and thus the behavior of the subject P1) of the equipment classified as category (2), and performs a process to determine whether or not there is an abnormality in the cognitive function of the subject P1 based on the detection results. Hereinafter, this process is referred to as "weekly processing." In the weekly processing, the server 120 stores the behavior that was the subject of the judgment, the presence or absence of an abnormality, and the reason for the judgment, linking them together.

The server 120 also calculates the number of times an abnormality is detected for each behavior during the month by the weekly processing. Then, for behaviors in which an abnormality is detected a predetermined number of times or more, an alert is issued using the terminal 130. Hereinafter, this processing is referred to as "monthly result notification." This allows the family member P2 of the subject P1 who possesses the terminal 130 to understand that an abnormality has occurred in the behavior of the subject P1, and thus that there is a risk of cognitive function decline.

In this way, the cognitive function assessment system 100 performs various processes according to the equipment with different usage frequencies (categories (1) and (2)), thereby determining whether or not there is an abnormality in the cognitive function of the subject P1 and issuing an alert to the family member P2 of the subject P1.

The following provides a detailed explanation of the processing contents (daily processing, weekly processing, weekly result notification, and monthly result notification) of the cognitive function assessment system 100 described above.

As a prerequisite for the various processes, the server 120 detects the usage status of various facilities in the house 1 over a predetermined period (e.g., about two weeks to one month) in advance (before performing the above-mentioned daily processing, etc.), thereby learning the behavioral tendencies of the subject P1, and stores this information (learned behavior data). Specifically, the server 120 detects the actions and time periods that the subject P1 performs throughout his or her day based on the detection results of the power sensor 110, and keeps track of the actions that the subject P1 performs for each time period. An example is shown in the "Learning Results" table in Figure 3.

For example, when the server 120 detects that a cooking appliance (induction heater, microwave oven) has been used, it learns the time period during which it was used. This is repeated for a predetermined period of time to understand the behavior of the subject P1, including the time period during which the subject P1 usually uses cooking appliances. The server 120 also indirectly detects that the subject P1 has gone to bed when the lights in the house 1 are turned off, for example, and learns the sleeping hours of the subject P1.

The behavior of subject P1 changes according to the season, for example, air conditioners and heating appliances are only used in seasons when they are needed (summer and winter). Therefore, server 120 learns the behavioral tendencies of subject P1 for each season, and when performing daily processing, etc., as described below, uses the learning results according to the season at that time.

In addition, during the period covered by the daily processing and other processes, the server 120 constantly detects the usage status of the various facilities in the house 1 (and thus the behavior of the subject P1) and stores the information (actual behavior data). More specifically, the server 120 stores what actions the subject P1 actually performed during what time periods. An example is shown in the "Detection Results" table in Figure 3.

First, we will explain the daily processing using Figures 4 to 7.

The server 120 performs daily processing at a predetermined time every day. Note that since the server 120 needs to determine whether the subject P1 is sleeping properly at night, it is not preferable to perform daily processing during the time period when the subject P1 is likely to be asleep. Therefore, the server 120 according to this embodiment performs daily processing during the time period when the subject P1 is likely to be awake (e.g., 10:00 a.m., etc.).

In step S101, the server 120 extracts the behavior of the subject P1 from the stored behaviors (for example, when daily processing is performed at 10:00 AM, from 9:00 AM of the previous day to 9:00 AM of the current day). These 24 hours are the period that is the subject of judgment by daily processing. Hereinafter, this period is referred to as the "period subject to daily processing". After performing the processing of step S101, the server 120 proceeds to step S102.

In step S102, the server 120 checks the time of each behavior extracted in step S101, and determines whether a predetermined time (X1 hours) has passed since the subject P1 was last detected to have performed the behavior. In other words, if more than X1 hours have passed since the subject P1 last performed the behavior, it means that the behavior of the subject P1 has not been detected for more than X1 hours. In other words, in this case, there is a possibility that some kind of emergency has occurred, such as the subject P1 having collapsed. Note that the value of the predetermined time (X1 hours) can be set arbitrarily, but it is particularly desirable to set it to a time (e.g., 12 hours, 24 hours, etc.) that can be inferred to be occurring in an emergency for the subject P1.

If the server 120 determines that X1 hours or more have passed since the subject P1 last performed an action, the process proceeds to step S103. On the other hand, if the server 120 determines that X1 hours or more have not passed since the subject P1 last performed an action, the process proceeds to step S104.

In step S103, the server 120 issues a predetermined alert using the terminal 130. Upon receiving this alert, the family member P2 can recognize that an emergency has occurred for the subject P1, and can take action such as heading to the residence 1 of the subject P1.

The processes of steps S101 to S103 are processes that can confirm that an emergency has occurred for the subject P1, so they may be executed continuously, rather than being executed only once a day (at 10:00 a.m.). This allows for a more rapid response to an emergency for the subject P1. After executing the process of step S103, the server 120 proceeds to step S104.

In step S104, the server 120 determines whether or not there is an abnormality in the behavior of the subject P1 based on the subject P1's behavior during his/her active time period (the time period when he/she is awake and active). Hereinafter, this process will be referred to as "active time period determination." Below, the active time period determination will be explained using FIG. 5.

The server 120 repeats the process from step S201 to step S204 in FIG. 5 for each behavior of the subject P1 classified into category (1). In addition, for behaviors that are performed multiple times a day (e.g., using cooking appliances (IH, microwave oven), watching television, etc.), the process is performed the same number of times. Each process from step S201 to step S204 is described below.

In step S201, the server 120 determines whether or not the behavior to be judged has been detected during the daily processing period. Specifically, the server 120 determines whether or not the behavior that has been learned as the behavior of the subject P1 (e.g., the use of cooking appliances (IH, microwave) shown in FIG. 3) has been detected during the daily processing period.

If the server 120 detects a behavior that is the subject of judgment, the process proceeds to step S202. On the other hand, if the server 120 does not detect a behavior that is the subject of judgment, the process proceeds to step S204.

In step S202, the server 120 judges whether the time difference between the time periods of the detected behavior of the subject P1 is within a predetermined time (X2 hours) based on the learning result. The method of calculating the time difference is not particularly limited, and any method capable of determining whether the time periods of both (the learned behavior and the detected behavior) have changed may be used. For example, a method of calculating the difference by adding up the time during which the two behaviors do not overlap, or a method of calculating the difference by adding up the difference between the start times and the difference between the end times of the two behaviors, etc., can be considered. The value of the predetermined time (X2 hours) can be set arbitrarily, but it is particularly desirable to set a time (e.g., 1 hour, 2 hours, etc.) that can be used to infer that the subject P1 is showing symptoms of dementia.

If the difference between the time period of the behavior of the subject P1 and the learning result is within X2 hours, the server 120 proceeds to step S203. On the other hand, if the difference between the time period of the behavior of the subject P1 and the learning result is greater than X2 hours, the server 120 proceeds to step S204.

In step S203, the server 120 determines that the behavior that was the subject of the judgment is normal. The server 120 stores the behavior that was the subject of the judgment, the presence or absence of an abnormality, and the reason for the judgment, in association with each other. For example, the server 120 stores the information "television," "no abnormality," and "the timing difference is within X2 hours" in association with each other.

On the other hand, in step S204, which is entered from step S201 or step S202, the server 120 determines that the behavior that is the subject of the determination is abnormal.

Here, transition from step S201 to step S204 (NO in step S201) indicates that the subject P1 has not performed an action that he/she is supposed to perform every day even once during one day (daily processing target period). In this case, it is presumed that the subject P1 has developed some kind of dementia symptom, such as memory disorder, disorientation, or executive function disorder. The server 120 stores the action that was the subject of the judgment, the presence or absence of an abnormality, and the reason for the judgment, linking them together. For example, the server 120 stores information such as "cooking appliance (induction, microwave)", "abnormal", and "not performed today" linking them together.

In addition, when the process moves from step S202 to step S204 (NO in step S202), this indicates that subject P1 is performing a specific behavior at a time different from normal. In this case, it is presumed that subject P1 is suffering from some kind of dementia symptom, such as memory impairment, disorientation, impaired executive function, or day-night reversal. Server 120 stores the behavior that was the subject of the judgment, the presence or absence of an abnormality, and the reason for the judgment, linking them together. For example, server 120 stores the information "washing machine," "abnormality," and "the timing difference is greater than X2 hours" linking them together.

The server 120 repeats the processes from step S201 to step S204 for each behavior of the subject P1 and the number of times. This allows the server 120 to determine whether or not an abnormality has occurred for each behavior of the subject P1 and each time. The server 120 then proceeds to step S105 in FIG. 4.

In step S105 of FIG. 4, the server 120 determines whether or not there is something abnormal in the behavior of the subject P1 based on the subject P1's behavior during the time period from when the subject P1 goes to sleep until when the subject P1 wakes up. Hereinafter, this process will be referred to as "sleep-wake-up time period determination." Below, the sleep-wake-up time period determination will be explained using FIG. 6 and FIG. 7.

In step S301 of FIG. 6, the server 120 determines the time period from when the subject P1 goes to bed to when he or she wakes up based on the stored behavior of the subject P1. After performing the process of step S301, the server 120 proceeds to step S302.

In step S302, the server 120 determines whether the deviation of the time period (sleep time period) from when the detected subject P1 goes to bed to when he wakes up is within a predetermined time (X3 hours) based on the learning result. There is no particular limitation on the method of calculating the deviation of the time period, and it can be calculated using the method exemplified in step S202. Note that the value of the predetermined time period (X3 hours) can be set arbitrarily, but it is particularly desirable to set it to a time period (e.g., 1 hour, 2 hours) that can be inferred to indicate that the subject P1 is exhibiting symptoms of dementia.

If the server 120 determines that the deviation in the sleep time zone of the subject P1 from the learning result is within X3 hours, it proceeds to step S308 in FIG. 7. On the other hand, if the server 120 determines that the deviation in the sleep time zone of the subject P1 from the learning result is greater than X3 hours, it proceeds to step S303.

In the example shown in FIG. 6, the deviation of the sleeping hours of the subject P1 from the learning results is determined, but it is also possible to determine, for example, whether the subject P1 is sleeping during the daily processing target period. For example, if the subject P1 is not sleeping at all, the process may proceed to step S303.

In step S303, the server 120 determines whether the sleeping time of the subject P1 has become longer than the sleeping time previously learned. If the server 120 determines that the sleeping time of the subject P1 has not become longer, the server 120 proceeds to step S304. On the other hand, if the server 120 determines that the sleeping time of the subject P1 has become longer, the server 120 proceeds to step S305.

In step S304, the server 120 determines that the behavior (sleep) of the subject P1 during the sleep time period is abnormal. In other words, if the deviation in the time period has become large even though the sleep time has not become longer (NO in step S302 and NO in step S303), it is presumed that the subject P1 has developed some kind of dementia symptom, such as executive dysfunction, disorientation, or day-night reversal. The server 120 stores the behavior (sleep) that is the subject of the determination, the presence or absence of an abnormality, and the reason for the determination, in association with each other. For example, the server 120 stores the information "sleep", "abnormal", and "deviation in timing of execution is greater than X3 hours" in association with each other.

After performing the process of step S304, the server 120 proceeds to step S308 in FIG. 7.

On the other hand, in step S305, which is entered after step S303, the server 120 determines that attention is required for the behavior of the subject P1 during his/her sleep hours. Here, the determination that attention (is required) is not "normal," but is a determination that the degree of abnormality is less severe (slight) than the determination of "abnormal" in step S304.

When moving from step S303 to step S305 (YES in step S303), since the sleeping time of the subject P1 has become longer, it is possible that the cognitive function of the subject P1 is not declining, but the subject P1 is simply tired. Therefore, in this embodiment, in step S305, a judgment of "Caution", which is less severe than "Abnormal", is made. The server 120 stores the behavior (sleep) that was the subject of this judgment, the presence or absence of abnormality, and the reason for the judgment, linking them together. For example, the server 120 stores the information "sleep", "attention required", and "the timing difference is greater than X3 hours and the sleeping time has become longer" linking them together. After performing the process of step S305, the server 120 moves to step S306.

In step S306, the server 120 determines whether or not the shift in the sleep time of the subject P1 has reduced the active time period (time period other than the subject's normal sleep time period) and affected the detected behavior of the subject P1. For example, if the time period during which a behavior (see step S204) determined to be abnormal in the active time period determination (see FIG. 5) would normally be performed overlaps with the detected sleeping time of the subject P1, the server 120 can determine that the behavior is affected by the shift in the sleep time of the subject P1 (the behavior is determined to be abnormal due to the shift in the sleep time period).

If the server 120 determines that the detected behavior of the subject P1 is affected by a shift in the subject P1's sleep time zone, the process proceeds to step S307. On the other hand, if the server 120 determines that the detected behavior of the subject P1 is not affected by a shift in the subject P1's sleep time zone, the process proceeds to step S308 in FIG. 7.

In step S307, the server 120 changes the judgment result of step S305 from "Caution" to "Abnormal." In this way, if the subject P1's behavior that should be performed is being affected due to the increased sleep time (YES in step S303) (YES in step S306), the server 120 assumes that this is an unfavorable situation for the subject P1, and therefore increases the degree of abnormality of the judgment result from "Caution" to "Abnormal." After performing the process of step S307, the server 120 proceeds to step S308 in FIG. 7.

In step S308 of FIG. 7, the server 120 determines whether or not it has detected behavior (behavior other than sleeping) of the subject P1 during the time period from when the subject P1 goes to bed until he or she wakes up (sleeping time period, see step S301). If the server 120 determines that it has not detected behavior of the subject P1 during the sleeping time period, it proceeds to step S309. On the other hand, if the server 120 determines that it has detected behavior of the subject P1 during the sleeping time period, it proceeds to step S310.

In step S309, the server 120 determines that the behavior of the subject P1 during the sleep hours is normal. The server 120 stores the behavior that was the subject of this determination, the presence or absence of abnormality, and the reason for the determination, in association with each other. For example, the server 120 stores the information "sleep," "no abnormality," and "no behavior detected during sleep hours," in association with each other. After performing the processing of step S309, the server 120 ends the daily processing (see FIG. 4).

On the other hand, in step S310, which is entered after step S308, the server 120 determines whether or not the behavior of the subject P1 detected during the sleeping hours included any behavior other than going to the toilet and related behavior.

Specifically, when going to the toilet during sleep hours, it is expected that some kind of behavior will be performed related to going to the toilet. For example, when going to the toilet, subject P1 is expected to not only turn on the toilet light, but also turn on the lights in the bedroom, hallway, etc. to ensure visibility when going to the toilet. The server 120 determines whether or not there has been any behavior other than such behavior related to going to the toilet (necessary behavior). The type of behavior related to the toilet can be learned by the server 120 or can be determined by the manufacturer/seller of the cognitive function assessment system 100, the user, etc.

If the server 120 determines that there has been a behavior other than toilet and related behavior, it proceeds to step S311. On the other hand, if the server 120 determines that there has been no behavior other than toilet and related behavior, it proceeds to step S312.

In step S311, the server 120 determines that the behavior of the subject P1 during the sleeping hours is abnormal. In other words, if the subject P1 exhibits behavior other than toilet-related behavior during the sleeping hours (YES in step S310), it is presumed that the subject P1 is suffering from some kind of dementia symptom, such as executive dysfunction, disorientation, or day-night reversal. The server 120 stores the behavior (sleep) that was the subject of the determination, the presence or absence of an abnormality, and the reason for the determination, in association with each other. For example, the server 120 stores the information "sleep", "abnormal", and "behavior detected during sleep", in association with each other. After performing the process of step S311, the server 120 ends the daily process (see FIG. 4).

Meanwhile, in step S312, which is entered after step S310, the server 120 determines that the behavior of the subject P1 during the sleep hours is normal. The server 120 stores the behavior that was the subject of this determination (sleep), the presence or absence of abnormality, and the reason for the determination, linking them together. For example, the server 120 stores the information "sleep," "no abnormality," and "no behavior detected during sleep hours" linking them together.

In this embodiment, it is determined that the result is normal in step S312, but it is also possible to compare the learned number of times that subject P1 goes to the toilet with the detected number of times that he or she goes to the toilet, and determine that a "warning" is required if the number of times has increased. This can also alert the user to the increased number of times that he or she goes to the toilet.

After performing step S312, the server 120 ends the daily processing (see FIG. 4).

Next, we will explain weekly processing using Figure 8.

The server 120 performs weekly processing once a week at a specified date and time. For example, the weekly processing is performed once a week at the same time as the daily processing (e.g., 10:00 a.m.).

The server 120 repeats the process from step S401 to step S403 in FIG. 8 for each behavior of the subject P1 classified into category (2). Each process from step S401 to step S403 is described below.

In step S401, the server 120 determines whether the number of actions of the detected subject P1 has increased or decreased by a predetermined number (Y1 times) or more based on the learning result. The value of the predetermined number (Y1 times) can be set arbitrarily. If the server 120 determines that the number of actions of the detected subject P1 has increased or decreased by Y1 times or more, it proceeds to step S402. On the other hand, if the server 120 determines that the number of actions of the detected subject P1 has not increased or decreased by Y1 times or more, it proceeds to step S403.

In step S402, the server 120 determines that the behavior that is the subject of the judgment is abnormal. In other words, if the number of behaviors increases or decreases by Y1 or more times, it is inferred that the subject P1 is suffering from some kind of dementia symptom, such as memory impairment, disorientation, or executive function disorder. The server 120 stores the behavior that is the subject of the judgment, the presence or absence of an abnormality, and the reason for the judgment, linking them together. For example, the server 120 stores the information "vacuum cleaner," "abnormal," and "decreasing behavior" linking them together.

Meanwhile, in step S403, which is entered after step S401, the server 120 determines that the behavior that was the subject of the judgment is normal. In other words, if the number of behaviors has not increased or decreased by Y1 or more times, it is presumed that there has been no particular change in the behavior of the subject P1 and that the symptoms of dementia have not developed. The server 120 stores the behavior that was the subject of the judgment, the presence or absence of abnormality, and the reason for the judgment, linking them together. For example, the server 120 stores the information "vacuum cleaner," "no abnormality," and "no increase or decrease in behavior" linking them together.

The server 120 repeats the processes from step S401 to step S403 for each behavior of the subject P1. This allows the server 120 to determine whether or not an abnormality has occurred for each behavior of the subject P1. The server 120 then ends the weekly process.

Next, we will explain the weekly result notification using Figure 9 (a).

The server 120 notifies the weekly results once a week at a specified date and time. For example, the server 120 notifies the weekly results once a week at the same time as the daily processing (e.g., 10:00 a.m.).

In step S501, the server 120 determines whether or not there is any behavior that has been repeatedly judged as a warning or abnormal a predetermined number of times (Y2 times) or more during the week among the behaviors that have been the subject of daily processing. The value of the predetermined number of times (Y2 times) can be set arbitrarily, but it is preferable to set it to a value of 2 or more in order to determine whether an abnormality or other judgment has been repeated. If the server 120 determines that there is any behavior that has been repeatedly judged as a warning or abnormal a predetermined number of times (Y2 times) or more, it proceeds to step S502. On the other hand, if the server 120 determines that there is no behavior that has been repeatedly judged as a warning or abnormal a predetermined number of times (Y2 times) or more, it ends the weekly result notification.

In step S502, the server 120 issues an alert (cognitive function abnormality warning) using the terminal 130. Specifically, the server 120 notifies family member P2 using the terminal 130 of behaviors that have been judged as requiring caution or abnormal a predetermined number of times or more, and the reason for the judgment. Examples of the notification method include displaying the information on the LCD screen of the terminal 130, or issuing a sound from the terminal 130.

In this way, the server 120 notifies family member P2 of behaviors in which abnormalities have been detected repeatedly (Y2 times or more), since it is considered highly likely that an abnormality in cognitive function has occurred. This allows family member P2 to take appropriate action (treatment, etc.). In other words, the server 120 does not notify family member P2 of behaviors that have been determined to be abnormal, etc. less than a predetermined number of times (Y2 times). This makes it possible to prevent family member P2 from being notified of behaviors that are determined to be abnormal, etc. (false detection of abnormality) when the subject P1's behavior happens to be different from usual, regardless of the subject P1's cognitive function.

After performing the processing of step S502, the server 120 ends the weekly result notification.

Next, we will explain monthly result notification using Figure 9 (b).

The server 120 notifies the monthly result at a specified date and time once a month. For example, the server 120 notifies the monthly result at the same time as the weekly result notification (e.g., 10:00 a.m.) once a month.

In step S601, the server 120 determines whether or not there is any behavior that has been repeatedly judged as a warning or abnormal a predetermined number of times (Y3 times) or more among the behaviors that have been subject to weekly processing during the month. The value of the predetermined number of times (Y3 times) can be set arbitrarily, but it is preferable to set it to a value of 2 or more in order to determine whether an abnormality or other judgment has been repeated. If the server 120 determines that there is any behavior that has been repeatedly judged as a warning or abnormal a predetermined number of times (Y3 times) or more, it proceeds to step S602. On the other hand, if the server 120 determines that there is no behavior that has been repeatedly judged as a warning or abnormal a predetermined number of times (Y3 times) or more, it ends the monthly result notification.

In step S602, the server 120 issues an alert (cognitive function abnormality warning) using the terminal 130. Specifically, the server 120 notifies family member P2 using the terminal 130 of behaviors that have been judged as requiring caution or abnormal a predetermined number of times or more, and the reasons for the judgment. In this way, the server 120 does not notify family member P2 of behaviors that have been judged as abnormal or the like less than the predetermined number of times (Y3 times).

After performing the processing of step S602, the server 120 ends the monthly result notification.

The cognitive function assessment system 100 performs the above-mentioned processes (daily process, weekly process, weekly result notification, and monthly result notification) to detect abnormalities in the cognitive function of the subject P1 and notify the family P2. For example, FIG. 3 shows the results of the daily process. In the example shown in FIG. 3, the learning results show that the subject P1 should use a hair dryer at 9 p.m., but the actual detection results show that the hair dryer was not used (see step S201), so the server 120 judges the abnormality as "abnormal." After 10 p.m., the subject P1 sleeps, but for some reason (such as the subject's sleep time becoming longer (see step S303)), the server 120 judges the abnormality as "caution." If the server 120 detects an abnormality in this way and if it is repeated several times, it judges that there is a high possibility that the subject P1 has an abnormality in his/her cognitive function and notifies the family P2 (see FIG. 9).

In this way, by using the cognitive function assessment system 100, it is possible to detect abnormalities in cognitive function based on the behavior of the subject P1 in his/her daily life. This makes it possible to easily detect abnormalities in cognitive function without requiring the subject P1 to undergo special tests, etc.

As described above, the cognitive function assessment system 100 according to this embodiment has the following features:
A power sensor 110 (behavior detection unit) capable of detecting the behavior of a subject P1 by detecting the usage status of equipment installed in a building (house 1) used by the subject P1;
A server 120 (cognitive function assessment unit) that compares the action data regarding the action of the subject P1 detected by the power sensor 110 with the learned action data regarding the action of the subject P1 that has been learned in advance to determine whether or not the subject P1 has an abnormality in cognitive function;
It is equipped with the following.

This configuration makes it possible to easily detect abnormalities in cognitive function. In other words, the behavior of subject P1 can be detected and the presence or absence of abnormalities in cognitive function can be determined by subject P1 simply living his or her daily life as usual. This makes it possible to detect abnormalities in cognitive function without subject P1 having to undergo special tests.

In addition, the server 120
If the time period during which the subject P1 performed a specified behavior differs from the learned time period by more than a specified amount of time, or if the subject does not perform the learned behavior (NO in step S201 or step S202), an activity time determination process (active time period determination) is performed to determine that an abnormality has occurred in the subject's cognitive function (step S204).

By configuring in this way, abnormalities in cognitive function can be easily detected. In other words, if there is a discrepancy between the time period in which subject P1 acts and the time period in which he/she learns, or if the action is not performed at all, it is presumed that subject P1 is experiencing some symptoms of dementia (such as executive function disorder). Therefore, by detecting a discrepancy between the two time periods, abnormalities in cognitive function can be easily detected.

In addition, the server 120
If the period during which the subject P1 slept differs from the period during which the subject P1 studied by more than a predetermined time, or if the subject P1 did not sleep (NO in step S302), it is determined that an abnormality has occurred in the cognitive function of the subject P1 (step S304 or step S305), and a sleep time determination process (determination of the period from going to bed to waking up) is performed.

By configuring in this way, abnormalities in cognitive function can be easily detected. In other words, if there is a discrepancy between the sleeping hours of subject P1 and the learned sleeping hours, or if subject P1 is not sleeping at all, it is presumed that some symptom of dementia (executive function disorder, etc.) is occurring in subject P1. Therefore, by detecting a discrepancy between the two time periods, abnormalities in cognitive function can be easily detected.

In addition, the server 120, in determining the sleep-wake time period,
The degree of cognitive abnormality is determined based on the increase or decrease in the subject P1's sleep time relative to the learned sleep time (steps S303 to S305).

By configuring in this way, it is possible to perform a more detailed assessment of cognitive function. That is, as illustrated in this embodiment, when the sleeping hours are long, it is possible that the subject P1 is simply tired and there is no abnormality in cognitive function. Therefore, in such a case, the degree (level) of abnormality in cognitive function is lowered and it is determined that "attention is required," making it possible to differentiate the degree of abnormality assessment and perform a detailed assessment.

In addition, the server 120
If the number of times that the subject P1 performs a predetermined behavior in a specified period differs from the number of times that it has learned by a specified number or more (step S401), a behavior count determination process (weekly processing) is performed to determine that an abnormality has occurred in the subject's cognitive function (step S402).

By configuring in this way, abnormalities in cognitive function can be easily detected. In other words, if there is a difference between the number of times that subject P1 has acted and the number of times that he has learned, it is presumed that subject P1 is experiencing some kind of symptom of dementia (such as executive dysfunction). Therefore, by detecting the difference between the number of times, abnormalities in cognitive function can be easily detected.

In addition, the cognitive function assessment system 100 includes:
The device further includes a terminal 130 (notification unit) capable of notifying a family member P2 (a person to be notified),
The server 120 includes:
During the first period, the subject's cognitive function is evaluated for abnormalities (daily and weekly treatments),
Calculate the number of times that cognitive function abnormalities are detected for each behavior of the subject during a second period that is longer than the first period (steps S501 and S601);
When the number of times that cognitive function abnormalities are detected during the second period reaches or exceeds a predetermined threshold, the notification unit issues a cognitive function abnormality warning to the person to be notified (steps S502 and S602).

This configuration allows for an appropriate warning to be issued to family member P2. In other words, by issuing a warning only when a certain number of cognitive function abnormality detections have been made, it is possible to prevent a cognitive function abnormality warning from being issued even when a cognitive function abnormality happens to be detected (such as when a false positive occurs).

The house 1 according to this embodiment is one embodiment of a building according to the present invention.
Moreover, the power sensor 110 according to this embodiment is one embodiment of a behavior detection unit according to the present invention.
Moreover, the server 120 according to this embodiment is one embodiment of a cognitive function assessment unit according to the present invention.
The activity time period determination according to this embodiment is one embodiment of the behavior time determination process according to the present invention.
The sleep-to-wake-up time period determination according to this embodiment is one embodiment of the sleep time determination process according to the present invention.
The weekly process according to the present embodiment is one embodiment of the behavior count determination process according to the present invention.
Moreover, the terminal 130 according to this embodiment is one embodiment of a notification unit according to the present invention.
Moreover, the family member P2 according to this embodiment is one embodiment of a notification target according to the present invention.

Although the embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and appropriate modifications are possible within the scope of the technical concept of the invention described in the claims.

For example, the cognitive function assessment system 100 according to this embodiment has been described with an example in which the subject P1 is an elderly person, but the present invention is not limited to elderly people, and various people can be the subject P1.

In addition, in this embodiment, the power sensor 110 (behavior detection unit) is installed in the house 1, but the present invention is not limited to this, and it can also be installed in various buildings used by the subject P1. In other words, it is possible to detect abnormalities in cognitive function not only in the house 1, but also in various other buildings, facilities, etc.

In addition, in this embodiment, an example is shown in which the server 120 (such as a virtual server installed on the cloud) performs various processes, but the present invention is not limited to this, and the entity that performs the various processes can be changed as desired. For example, the processes can also be performed by a home server, a personal computer, a mobile terminal, etc. installed in the house 1.

In addition, in this embodiment, an example has been shown in which if an abnormality in the cognitive function of the subject P1 is detected, the terminal 130 is notified of this fact, but it is also possible for a family member P2 or the like to confirm the abnormality and, if they determine that there is no problem (that there is no abnormality), to communicate this fact to the server 120 using the terminal 130 or the like. In this way, by having the family member P2 or the like confirm the presence or absence of an abnormality and provide feedback to the server 120, the server 120 can learn the behavior of the subject P1 more accurately. This allows for more accurate detection of abnormalities in cognitive function.

In addition, in this embodiment, an example is shown in which if the behavior of the subject P1 is repeatedly determined to be abnormal, etc., the family P2 is notified of this fact (see Figure 9), but the present invention is not limited to this, and for example, if the behavior of the subject P1 is determined to be abnormal, etc. even once, it is also possible to immediately notify the family P2.

The period covered by each process exemplified in this embodiment (daily process, weekly process, weekly result notification, and monthly result notification) can also be changed as desired.

100 Cognitive function assessment system 110 Power sensor 120 Server 130 Terminal

Claims (5)

A behavior detection unit capable of detecting the behavior of a subject by detecting the usage status of a plurality of facilities installed in a building used by the subject;
a cognitive function assessment unit that compares action data regarding the behavior of the subject detected by the action detection unit with learned action data regarding the behavior of the subject that has been learned in advance to determine whether or not the subject has an abnormality in cognitive function;
A notification unit capable of notifying a notification target person;
Equipped with
The cognitive function assessment unit includes:
The plurality of pieces of equipment are classified in advance according to their frequency of use in a predetermined period, and a first piece of equipment belonging to a first classification and a second piece of equipment belonging to a second classification that is used less frequently than the first classification are stored;
During a first period, determining whether or not there is an abnormality in the subject's cognitive function regarding the first equipment;
Calculating the number of times that cognitive abnormalities are detected for each behavior of the subject regarding the first equipment during a second period that is longer than the first period;
When the number of times that an abnormality in a cognitive function related to the first equipment is detected during the second period is equal to or greater than a predetermined threshold, a cognitive abnormality warning is issued to the notification target using the notification unit,
During the second period, determining whether or not there is an abnormality in the subject's cognitive function regarding the second equipment;
Calculating the number of times that cognitive function abnormalities are detected for each behavior of the subject regarding the second equipment during a third period that is longer than the second period;
When the number of times that an abnormality in cognitive function related to the second equipment is detected during the third period is equal to or greater than a predetermined threshold, a cognitive abnormality warning is issued to the notification target using the notification unit.
Cognitive function assessment system. The cognitive function assessment unit includes:
performing an action time determination process for determining that an abnormality has occurred in the cognitive function of the subject when a time period during which the subject performed a predetermined action differs from a time period during which the subject performed the learned action by a predetermined time or more, or when the subject does not perform the learned action;
The cognitive function assessment system according to claim 1 . The cognitive function assessment unit includes:
performing a sleep time determination process for determining that an abnormality has occurred in the cognitive function of the subject when the time period during which the subject slept differs from the time period during which the subject studied by a predetermined time or more, or when the subject has not slept;
The cognitive function assessment system according to claim 1 or 2. The cognitive function assessment unit, in the sleep time determination process,
The degree of cognitive abnormality is determined according to an increase or decrease in the subject's sleep time relative to the learned sleep time.
The cognitive function assessment system according to claim 3. The cognitive function assessment unit includes:
performing a behavior count determination process for determining that an abnormality has occurred in the cognitive function of the subject when the number of times the subject has performed a predetermined behavior in a predetermined period differs from the number of times the subject has learned the behavior by a predetermined number or more;
The cognitive function assessment system according to any one of claims 1 to 4.

Images