JP2021163006A - Sleep health level determination program - Google Patents

Abstract

To accurately and automatically determine a sleep health level without manual intervention.SOLUTION: A sleep health level determination program for determining a sleep health level in sleep health level determination causes a computer to execute: an information acquisition step for acquiring heart rate data obtained by imaging teeth of a subject; and a determination step which determines a sleep health level on the basis of reference heart rate data in accordance with the heart rate data acquired in the information acquisition step, by using three or more stages of associations between the reference heart rate data of the teeth captured in the past and the sleep health level.SELECTED DRAWING: Figure 3

Description

The present invention relates to a sleep health degree determination program for determining the health degree during sleep.

Sleep disorders lead to a considerable annual medical cost burden, more than half of which are said to be associated with sleep apnea syndrome. It has been pointed out that sleep apnea syndrome not only causes sleep disorders, but is also associated with so-called adult diseases such as diabetes, cardiovascular disease, and depression, and modern diseases. For this reason, improving health during sleep has become extremely important in modern disease management.

For this reason, there has been an increasing social demand for improving the accuracy of sleep health judgment by obtaining assistance from artificial intelligence and for general users to be able to perform self-diagnosis to some extent.

Therefore, the present invention has been devised in view of the above-mentioned problems, and an object of the present invention is a sleep health degree determination program capable of automatically determining the health degree during sleep with high accuracy. Is to provide.

The sleep health determination program according to the present invention is an information acquisition that acquires time-series heart rate data detected from the body of a sleeping subject in a sleep health determination program that determines the health during sleep. The steps were acquired in the above information acquisition step by referring to the time-series reference heart rate data detected from the body of the subject during sleep in the past and the degree of association with the sleep health level in three or more stages. It is characterized in that a computer is made to perform a discrimination step for discriminating sleep health based on heart rate data.

Even if you do not have any special skills or experience, you can automatically determine the degree of health during sleep with high accuracy. As a result, users who do not have time to go to the clinic can have AI automatically determine their sleep health level at home, and perform self-diagnosis before having them diagnosed at the hospital. You can do it, and you can know in advance the urgency of going to the hospital.

It is a block diagram which shows the whole structure of the system to which this invention is applied. It is a figure which shows the specific configuration example of a search device. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention.

Hereinafter, the sleep health determination program to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing an overall configuration of a sleep health determination system 1 to which a sleep health determination program to which the present invention is applied is implemented. The sleep health degree discrimination system 1 includes an information acquisition unit 9, a discrimination device 2 connected to the information acquisition unit 9, and a database 3 connected to the discrimination device 2.

The information acquisition unit 9 is a device for a person who uses this system to input various commands and information, and specifically, is composed of a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an image pickup device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper-based document. Further, the information acquisition unit 9 may be integrated with the discrimination device 2 described later. The information acquisition unit 9 outputs the detected information to the determination device 2. Further, the information acquisition unit 9 may be configured by means for specifying the position information by scanning the map information. Further, the information acquisition unit 9 may be composed of an illuminance sensor for measuring a temperature sensor, a humidity sensor, and a wind direction sensor. Further, the information acquisition unit 9 may be composed of a communication interface for acquiring data on the weather from the Japan Meteorological Agency or a private weather forecast company. Further, the information acquisition unit 9 may be composed of a body sensor that is attached to the body to detect body data, and this body sensor detects, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. It may be composed of a sensor for the purpose. Further, the body sensor may acquire biological data of animals as well as humans. Further, the information acquisition unit 9 may be configured as a device that acquires information such as drawings by scanning or reading it from a database. In addition to these, the information acquisition unit 9 may be configured by an odor sensor that detects an odor or scent. The information acquisition unit 9 may be composed of a CT camera, a camera that captures an X-ray image, a spectrum image, or the like.

Database 3 stores various information necessary for determining sleep health. Information necessary for determining sleep health includes time-series reference heart rate data detected from the body of a past subject during sleep, and detection from the body of a past subject during sleep. Reference blood oxygen concentration data, reference voice data detected from the body during sleep of the past subject, reference movement data that detected the movement of the past subject during sleep in chronological order , Reference sleep time series data consisting of continuous sleep time and awakening time when the past subject sleeps intermittently, Time series reference room temperature data in the room where the past subject sleeps, Time-series reference body temperature data detected from the body during sleep of past subjects, reference bath data indicating the presence or absence of bathing before acquiring the above reference heart rate data of past subjects, Reference sleep time matching degree data showing the degree of sleep time matching when sleeping in the same room as a past subject's cohabitant, reference treatment history data regarding the past subject's treatment history, past subject Reference treatment history data related to the treatment history of the above, reference attribute data of past subjects, etc. are accumulated as output data in relation to the state of sleep health.

That is, in the database 3, such reference heart rate data, reference blood oxygen concentration data, reference voice data, reference movement data, reference sleep time series data, reference room temperature data, and reference body temperature data are stored. , Reference bath data, reference sleep time matching degree data, reference treatment history data, reference treatment history data, reference attribute data, and sleep health degree are stored in association with each other.

The discrimination device 2 is composed of, for example, an electronic device such as a personal computer (PC), but is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., in addition to the PC. It may be converted. The user can obtain a search solution by the discriminating device 2.

FIG. 2 shows a specific configuration example of the discrimination device 2. The discrimination device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire discrimination device 2 and an operation unit 25 for inputting various control commands via an operation button, a keyboard, or the like. A communication unit 26 for the purpose, a determination unit 27 for making various determinations, and a storage unit 28 for storing a program for performing a search to be executed represented by a hard disk or the like are connected to the internal bus 21, respectively. .. Further, a display unit 23 as a monitor that actually displays information is connected to the internal bus 21.

The control unit 24 is a so-called central control unit for controlling each component mounted in the discrimination device 2 by transmitting a control signal via the internal bus 21. Further, the control unit 24 transmits various control commands via the internal bus 21 in response to the operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input by the user, the operation unit 25 notifies the control unit 24 of the execution command. Upon receiving this notification, the control unit 24, including the determination unit 27, executes a desired processing operation in cooperation with each component. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The determination unit 27 determines the search solution. The discriminating unit 27 reads out various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the discriminating operation. The discriminating unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any well-known artificial intelligence technique.

The display unit 23 is composed of a graphic controller that creates a display image based on the control by the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is composed of a hard disk, predetermined information is written to each address based on the control by the control unit 24, and is read out as needed. Further, the storage unit 28 stores a program for executing the present invention. This program is read and executed by the control unit 24.

The operation in the sleep health degree determination system 1 having the above-described configuration will be described.

In the sleep health degree determination system 1, for example, as shown in FIG. 3, it is premised that three or more levels of association between the reference heart rate data and the sleep health degree are preset. The reference heart rate data is time-series heart rate data during sleep measured for a past subject. The heart rate data can be acquired through a sensor that measures the heart rate, and the sensor that measures the heart rate is based on a well-known optical method, electrocardiographic method, or the like. This reference heart rate data can be obtained by the subject detecting the heart rate during sleep through such a sensor. As the heart rate measuring means, any well-known device, sensor, or means other than the above-mentioned sensor may be used.

This reference heart rate data is acquired as time-series heart rate data, but the acquisition period of the data is not only the time-series data of the total sleep time but also a part of the time. It may be composed of time-series data in the band.

The sleep health level may be displayed in two simple stages of "healthy" and "unhealthy". In addition to whether your sleep condition is healthy or slightly healthy, what kind of improvement is possible, whether you need to consult a doctor immediately, whether your eating habits should be ●●, and whether you should play sports moderately. It is also possible to show the judgment result about the future policy such as bathing and drinking. This sleep health degree may be quantitatively expressed by a frequency called sleep health degree, and may be 1000 points if it is healthy and close to 0 points if it becomes unhealthy. This sleep health evaluation may be based on what doctors and insurance institutions have evaluated based on heart rate data in the past, but it is not limited to this, and private companies or various organizations Furthermore, an individual may independently evaluate the degree of health based on these reference heart rate data, and if necessary, evaluate the score as described above.

Furthermore, sleep health may be judged based on the previous experience of specialists, or the level may be evaluated by multiple specialists and doctors by actually reading the materials of past medical cases. However, they may be statistically analyzed to determine sleep health.

In the example of FIG. 3, it is assumed that the input data is, for example, reference heart rate data P01 to P03. Reference heart rate data P01 to P03 as such input data are linked to sleep health as output. In this output, specific examples of sleep health degrees A to D as output solutions are shown. The sleep health levels A to D may be displayed as sleep health levels of 591 points, 306 points, 603 points, and the like.

The reference heart rate data are associated with each other through three or more levels of association with the sleep health levels A to D as the output solution. Reference heart rate data is arranged on the left side via this degree of association, and each sleep health degree is arranged on the right side via this degree of association. The degree of association indicates which sleep health degree is highly related to the reference heart rate data arranged on the left side. In other words, this degree of association is an indicator of what sleep health level each reference heart rate data is likely to be associated with, and the most probable sleep health level is selected from the reference heart rate data. It shows the accuracy in doing so. In the example of FIG. 3, w13 to w19 are shown as the degree of association. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the sleep health as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the price as an output.

The discriminating device 2 acquires in advance the degree of association w13 to w19 of three or more stages shown in FIG. That is, the discriminating device 2 accumulates a past data set as to which of the reference heart rate data and the sleep health degree in that case is adopted and evaluated in discriminating the actual search solution, and these By analyzing and analyzing, the degree of association shown in FIG. 3 is created.

For example, it is assumed that sleep health level A (health) is highly evaluated as the sleep health level for reference heart rate data acquired in the past. By collecting and analyzing such a data set, the degree of association with the reference heart rate data is strengthened.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of reference heart rate data P01, analysis is performed from various data as a result of past evaluation of sleep health. If there are many cases of sleep health level A (health) in the case of reference heart rate data P01, the degree of association that leads to the evaluation of this sleep health level is set higher, and sleep health level B (slightly health level) is set. If there are many cases (there is room for improvement), set a higher degree of association that leads to this evaluation of sleep health. For example, in the example of the reference heart rate data P01, the sleep health level A and the sleep health level C (diagnosis by a doctor is required) are linked. At 7 points, the degree of association of w14, which leads to sleep health C, is set at 2 points.

Further, the degree of association shown in FIG. 3 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.
In such a case, as shown in FIG. 4, reference heart rate data is input as input data, sleep health is output as output data, and at least one or more hidden layers are provided between the input node and the output node. It may be made to be machine-learned. The above-mentioned degree of association is set in either one or both of the input node and the hidden layer node, and this is the weight of each node, and the output is selected based on this. Then, when the degree of association exceeds a certain threshold value, the output may be selected.

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data through a data set of reference heart rate data based on heart rate data acquired from previous subjects and sleep health that was actually discriminated and evaluated, it will actually be new from now on. In determining the sleep health level, the sleep health level is searched for by using the above-mentioned learned data. In such a case, time-series heart rate data is acquired from the body of the sleeping subject who actually measures the sleep health level. The newly acquired heart rate data is input by the above-mentioned information acquisition unit 9. The acquisition of the heart rate data may be performed by the same method as the reference heart rate data described above. By the way, the subject who acquires the heart rate data may be the same as the subject who acquired the reference heart rate data, but may not be the same, and the data of an unspecified number of others is used for reference. The judgment may be made based on what has been learned as heart rate data.

Based on the heart rate data newly acquired in this way, the sleep health degree is determined. In such a case, the degree of association shown in FIG. 3 (Table 1) acquired in advance is referred to. For example, when the newly acquired heart rate data is the same as or similar to P02, the sleep health degree B is associated with the association degree w15 and the sleep health degree C is associated with the association degree w16 through the association degree. .. In such a case, the sleep health degree B having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree C, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In this way, the most suitable sleep health level can be searched for and displayed to the user from the newly acquired heart rate data. By looking at the search results, it is possible to determine the degree of sleep health and the like, and it is possible to quickly shift to measures for ensuring sleep health.

In the example of FIG. 5, the degree of association between the reference heart rate data and the reference treatment history data data is formed. The reference treatment history data is related to the treatment history related to the past sleep in obtaining the reference heart rate data. The past treatment history includes the specific contents of the treatment, if the patient has undergone a medical examination and has been treated before. This reference treatment history data is, for example, the content and progress information of the surgical operation if it was performed before, the content and history of the mouthpiece, etc., and CPAP therapy (nasal positive airway pressure). If you are performing continuous positive airway pressure), the contents and history. It is possible to improve the discrimination accuracy by making a judgment in combination with such a treatment history. Therefore, in addition to the reference heart rate data, the reference treatment history data is combined to form the above-mentioned degree of association.

In the example of FIG. 5, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference treatment history data P14 to 17. The intermediate node shown in FIG. 5 is a combination of the reference heart rate data and the reference treatment history data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference treatment history data is associated with each other through three or more levels of association with sleep health as this output solution. Reference heart rate data and reference treatment history data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference treatment history data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference treatment history data are likely to be associated with, and is a reference heart rate data and reference. It shows the accuracy in selecting the most probable sleep health level from the treatment history data. Therefore, the optimum sleep health level is searched for by combining the reference heart rate data and the reference treatment history data.

In the example of FIG. 5, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the discriminating device 2 accumulates past data as to which of the reference heart rate data, the reference treatment history data, and the sleep health level in that case is suitable for discriminating the actual search solution. By analyzing and analyzing these, the degree of association shown in FIG. 5 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference heart rate data P01 and the reference treatment history data P16, the sleep health degree is analyzed from the past data. When there are many cases of sleep health level A, the degree of association leading to this sleep health level A is set higher, and when there are many cases of sleep health level B and there are few cases of sleep health level A, sleep The degree of association that leads to health level B is increased, and the degree of association that leads to sleep health level A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and quality B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and w14 connected to sleep health degree B. The degree of association is set to 2 points.

Further, the degree of association shown in FIG. 5 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence. Other than that, the configuration related to artificial intelligence is the same as the description in FIG.

In the example of the degree of association shown in FIG. 5, the node 61b is a node in which the reference heart rate data P01 is combined with the reference treatment history data P14, the degree of association of the sleep health degree C is w15, and the degree of sleep health is w15. The degree of association of E is w16. The node 61c is a node in which the reference treatment history data P15 and P17 are combined with the reference heart rate data P02, and the degree of association of the sleep health degree B is w17 and the degree of association of the sleep health degree D is w18. ing.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually determining the sleep health degree from now on, the above-mentioned learned data will be used. In such a case, the heart rate data and the treatment history data of the subject are input or selected from the subject who actually wants to determine the sleep health level. The treatment history data may be manually entered by the hospital from the patient's chart or extracted from the database. The subject may also manually enter his / her treatment history.

Based on the newly acquired heart rate data and treatment history data in this way, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 5 (Table 1) acquired in advance is referred to. For example, when the newly acquired heart rate data is the same as or similar to P02 and the treatment history data is P17, the node 61d is associated via the degree of association. The node 61d is associated with a sleep health degree C of w19 and a sleep health degree D of association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In addition, Table 2 below shows examples of the degrees of association w1 to w12 extending from the input.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

In FIG. 6, in addition to the above-mentioned reference heart rate data, a combination with the reference subjective symptom data instead of the above-mentioned reference treatment history data and a degree of association of three or more levels of sleep health with the combination are set. An example is shown.

This reference subjective symptom data, which is added as an explanatory variable instead of the reference treatment history data, is all information about the subject's subjective symptoms in the reference heart rate data. The reference subjective symptom data includes all subjective symptoms such as "severe drowsiness after lunch", "lack of appetite", "anemia", and "a lot of yawning in the morning". Such reference subjective symptom data may be the one that the doctor hears from the subject and is input to the medical record or the like, or may be the one that the subject himself / herself input. In actually implementing this program, it is premised that these reference subjective symptom data are converted into electronic data.

Since such subjective symptoms also affect the sleep health level, the discrimination accuracy can be improved by combining the reference heart rate data and discriminating the sleep health level through the degree of association.

In the example of FIG. 6, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference subjective symptom data P18 to 21. The intermediate node shown in FIG. 6 is a combination of the reference heart rate data and the reference subjective symptom data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference subjective symptom data is associated with each other through three or more levels of association with sleep health as this output solution. Reference heart rate data and reference subjective symptom data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference subjective symptom data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference subjective symptom data are likely to be associated with, and is a reference heart rate data and reference. It shows the accuracy in selecting the most probable sleep health level from subjective symptom data.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the discriminating device 2 determines the reference heart rate data, the reference subjective symptom data obtained when the reference heart rate data is acquired, and the sleep health degree in that case in discriminating the actual search solution. Past data is accumulated to determine which is more suitable, and by analyzing and analyzing these, the degree of association shown in FIG. 6 is created.

For example, at the time of evaluating the actual sleep health level in the past, it is assumed that the reference subjective symptom data is "severe sleepiness after lunch" with respect to a certain reference heart rate data. In such a case, if there are many cases where the sleep health degree is determined to be A, these are learned as a data set and defined in the form of the above-mentioned association degree.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the reference heart rate data P01 is the reference subjective symptom data P20, the sleep health degree is analyzed from the past data. When there are many cases of sleep health A, the degree of association that this sleep health leads to A is set higher, and when there are many cases of sleep health B and few cases of sleep health A, , The degree of association that sleep health leads to B is increased, and the degree of association that sleep health leads to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and sleep health degree B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and it is set to sleep health degree B. The degree of association of the connected w14 is set to 2 points.

Further, the degree of association shown in FIG. 6 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence. Other than that, the configuration related to artificial intelligence is the same as the description in FIG.

In the example of the degree of association shown in FIG. 6, the node 61b is a node in which the reference heart rate data P01 is combined with the reference subjective symptom data P18, the sleep health degree C is associated with w15, and the sleep health degree E is The degree of association is w16. The node 61c is a node that is a combination of the reference subjective symptom data P19 and P21 with respect to the reference heart rate data P02, and the degree of association of the sleep health degree B is w17 and the degree of association of the sleep health degree D is w18. ing.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for sleep health from now on, the above-mentioned learned data will be used. In such a case, the heart rate data of the sleep health degree discrimination target and the subjective symptom data are actually acquired. Here, the subjective symptom data is newly acquired for the subject of the heart rate data when the sleep health degree is newly determined, and the acquisition method is the same as the above-mentioned reference subjective symptom data.

Based on the heart rate data newly acquired in this way and the subjective symptom data, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 6 (Table 1) acquired in advance is referred to. For example, when the newly acquired heart rate data is the same as or similar to P02 and the subjective symptom data is the same as or similar to P21, the node 61d is associated via the degree of association. In this node 61d, the sleep health degree C is associated with w19, and the sleep health degree D is associated with the association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

FIG. 7 shows a combination of the above-mentioned reference heart rate data and the reference blood oxygen concentration data instead of the above-mentioned reference treatment history data, and the degree of association between the sleep health degree and the sleep health level of the combination in three or more stages. Shows an example in which is set.

This reference blood oxygen concentration data, which is added as an explanatory variable instead of the reference treatment history data, is all information about the blood oxygen concentration of the reference heart rate data. The reference blood oxygen concentration data can be detected by a well-known blood oxygen concentration measuring device and a blood oxygen concentration measuring sensor. As the reference blood oxygen concentration data, the data detected for the subject in the hospital and input to the medical record or the like may be used, or the data measured by the subject himself or herself may be input. good. In actually implementing this program, it is premised that these reference blood oxygen concentration data are converted into electronic data.
The reference blood oxygen concentration data may be measured before going to bed or may be used during sleep. As the reference blood oxygen concentration data, data during sleep may be continuously measured in chronological order.

Since such subjective symptoms also affect the sleep health level, the discrimination accuracy can be improved by combining the reference heart rate data and discriminating the sleep health level through the degree of association.

In the example of FIG. 7, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference blood oxygen concentration data P18 to 21. The intermediate node shown in FIG. 7 is a combination of the reference heart rate data and the reference blood oxygen concentration data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference blood oxygen concentration data is associated with each other through three or more levels of association with sleep health as this output solution. Reference heart rate data and reference blood oxygen concentration data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference blood oxygen concentration data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference blood oxygen concentration data are likely to be associated with, and is a reference heart rate data. It shows the accuracy in selecting the most probable sleep health level from the reference blood oxygen concentration data.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. 7. That is, the discrimination device 2 discriminates the actual search solution, the reference heart rate data, the reference blood oxygen concentration data obtained when the reference heart rate data is acquired, and the sleep health in that case. The past data on which degree was suitable is accumulated, and the degree of association shown in FIG. 7 is created by analyzing and analyzing these data.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the reference heart rate data P01 is the reference blood oxygen concentration data P20, the sleep health degree is analyzed from the past data. When there are many cases of sleep health A, the degree of association that this sleep health leads to A is set higher, and when there are many cases of sleep health B and few cases of sleep health A, , The degree of association that sleep health leads to B is increased, and the degree of association that sleep health leads to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and sleep health degree B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and it is set to sleep health degree B. The degree of association of the connected w14 is set to 2 points.

Further, the degree of association shown in FIG. 7 may be composed of the nodes of the neural network in artificial intelligence.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for sleep health from now on, the above-mentioned learned data will be used. In such a case, the heart rate data of the sleep health degree discrimination target and the blood oxygen concentration data are actually acquired. Here, the blood oxygen concentration data is newly acquired for the subject of the heart rate data when the sleep health level is newly determined, and the acquisition method is the same as the reference blood oxygen concentration data described above. be.

Based on the heart rate data newly acquired in this way and the blood oxygen concentration data, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 6 (Table 1) acquired in advance is referred to. For example, when the newly acquired heart rate data is the same as or similar to P02 and the blood oxygen concentration data is the same as or similar to P21, the node 61d via the degree of association. Is associated with this node 61d, the sleep health degree C is associated with w19, and the sleep health degree D is associated with the association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In FIG. 8, in addition to the above-mentioned reference heart rate data, a combination with the above-mentioned reference voice data instead of the above-mentioned reference treatment history data, and a degree of association of three or more levels of association with the sleep health degree for the combination are set. An example is shown.

This reference voice data, which is added as an explanatory variable instead of the reference treatment history data, is the time-series voice data of the subject during sleep in the past, and the reference voice data is a well-known voice measuring device and voice. It can be detected by a measurement sensor. This audio data includes all audio emitted from the subject's body, such as snoring and growling. As the reference voice data, the voice of the sleeping subject may be continuously measured in time series and used as data.

Since such subjective symptoms also affect the sleep health level, the discrimination accuracy can be improved by combining the reference heart rate data and discriminating the sleep health level through the degree of association.

In the example of FIG. 8, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference voice data P18 to 21. The intermediate node is a combination of the reference heart rate data and the reference voice data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference voice data is associated with each other through three or more levels of association with the sleep health level as this output solution. Reference heart rate data and reference voice data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference voice data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference voice data are likely to be associated with, and is a reference heart rate data and reference voice. It shows the accuracy in selecting the most probable sleep health level from the data.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, in determining the actual search solution, the discrimination device 2 determines which of the reference heart rate data, the reference voice data obtained when acquiring the reference heart rate data, and the sleep health level in that case. Was suitable, or the past data is accumulated, and the degree of association is created by analyzing and analyzing these.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference heart rate data P01 and the reference voice data P20, the sleep health degree is analyzed from the past data. When there are many cases of sleep health A, the degree of association that this sleep health leads to A is set higher, and when there are many cases of sleep health B and few cases of sleep health A, , The degree of association that sleep health leads to B is increased, and the degree of association that sleep health leads to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and sleep health degree B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and it is set to sleep health degree B. The degree of association of the connected w14 is set to 2 points.

Further, the degree of association shown in FIG. 8 may be composed of the nodes of the neural network in artificial intelligence.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for sleep health from now on, the above-mentioned learned data will be used. In such a case, the heart rate data of the sleep health degree determination target and the voice data are actually acquired. Here, the voice data is newly acquired for the subject of the heart rate data when the sleep health degree is newly determined, and the acquisition method is the same as the reference voice data described above.

Based on the newly acquired heart rate data and voice data in this way, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 8 (Table 1) acquired in advance is referred to. For example, if the newly acquired heart rate data is the same as or similar to P02 and the audio data is the same as or similar to P21, the node 61d is associated via the degree of association. The node 61d is associated with a sleep health degree C of w19 and a sleep health degree D of association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In FIG. 9, in addition to the above-mentioned reference heart rate data, a combination with the reference movement data instead of the above-mentioned reference treatment history data and a degree of association of three or more levels of the sleep health degree with respect to the combination are set. An example is shown.

This reference movement data, which is added as an explanatory variable instead of the reference treatment history data, is data obtained by detecting the movements of the subject during sleep in the past in chronological order. The reference motion data can be detected by an image taken by a camera capable of detecting the motion or by a well-known weight sensor installed on a mattress or a bed. When this motion data is acquired by an image taken by a camera, the image analysis may be performed by using a deep learning technique, if necessary, to determine the type of motion. Reference motion data may be obtained by automatically discriminating based on the feature amount of the analysis image and converting it into data. As the reference movement data, data obtained by continuously measuring the movement of the subject during sleep in a time series may be used.

Since such subjective symptoms also affect the sleep health level, the discrimination accuracy can be improved by combining the reference heart rate data and discriminating the sleep health level through the degree of association.

In the example of FIG. 9, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference motion data P18 to 21. The intermediate node is a combination of the reference heart rate data and the reference motion data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference movement data is associated with each other through three or more levels of association with the sleep health level as this output solution. Reference heart rate data and reference movement data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference movement data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference movement data are likely to be associated with, and is a reference heart rate data and reference movement. It shows the accuracy in selecting the most probable sleep health level from the data.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, in determining the actual search solution, the discrimination device 2 determines which of the reference heart rate data, the reference movement data obtained when acquiring the reference heart rate data, and the sleep health level in that case. Was suitable, or the past data is accumulated, and the degree of association is created by analyzing and analyzing these.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference heart rate data P01 and the reference movement data P20, the sleep health degree is analyzed from the past data. When there are many cases of sleep health A, the degree of association that this sleep health leads to A is set higher, and when there are many cases of sleep health B and few cases of sleep health A, , The degree of association that sleep health leads to B is increased, and the degree of association that sleep health leads to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and sleep health degree B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and it is set to sleep health degree B. The degree of association of the connected w14 is set to 2 points.

Further, the degree of association shown in FIG. 9 may be composed of the nodes of the neural network in artificial intelligence.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for sleep health from now on, the above-mentioned learned data will be used. In such a case, the heart rate data of the sleep health degree determination target and the movement data are actually acquired. Here, the motion data is newly acquired for the subject of the heart rate data when the sleep health degree is newly determined, and the acquisition method is the same as the reference motion data described above.

Based on the heart rate data newly acquired in this way and the movement data, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 9 (Table 1) acquired in advance is referred to. For example, if the newly acquired heart rate data is the same as or similar to P02 and the motion data is the same as or similar to P21, the node 61d is associated via the degree of association. The node 61d is associated with a sleep health degree C of w19 and a sleep health degree D of association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.
In FIG. 10, in addition to the above-mentioned reference heart rate data, the combination with the reference sleep time series data instead of the above-mentioned reference treatment history data and the degree of association between the sleep health degree and the sleep health degree with respect to the combination are shown in three or more stages. An example of the settings is shown.

This reference sleep time series data, which is added as an explanatory variable instead of the reference treatment history data, shows the continuous sleep time and awakening in the case of intermittent sleep in which the subject wakes up in the middle of sleep and then re-enters sleep. Consists of time. As shown in FIG. 11, sleep started at 11:40, slept until 2:30 the next day, then woke up once, then slept again at 2:50, and woke up again at 5:34. It is assumed that he wakes up, sleeps three times at 5:49, and wakes up at 6:50. The time spent on the floor is from 11:40 to 6:50, but in reality, waking up one or more times in the middle is called intermittent sleep. Intermittent sleep is represented by continuous sleep time and awakening time as shown in FIG. The reference sleep time series data may be represented by time or time, respectively, for continuous sleep time and awakening time. The reference sleep time series data may be obtained by pressing the stopwatch each time the subject wakes up, for example, by using a smartphone or the like equipped with such a stopwatch application. You may want to do this.

Since the content of such intermittent sleep also affects the sleep health level, the discrimination accuracy can be improved by discriminating the sleep health level through the degree of association in combination with the reference heart rate data.

In the example of FIG. 10, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference sleep time series data P18 to 21. An intermediate node is a combination of reference heart rate data and reference sleep time series data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference sleep time series data is associated with each other through three or more levels of association with sleep health as this output solution. Reference heart rate data and reference sleep time series data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference sleep time series data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference sleep time series data are likely to be associated with, and is a reference heart rate data and reference. It shows the accuracy in selecting the most probable sleep health level from the sleep time series data.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the discrimination device 2 discriminates the actual search solution, the reference heart rate data, the reference sleep time series data obtained when acquiring the reference heart rate data, and the sleep health degree in that case. Accumulate past data to determine which was more suitable, and analyze and analyze these to create a degree of association.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the reference heart rate data P01 is the reference sleep time series data P20, the sleep health degree is analyzed from the past data. When there are many cases of sleep health A, the degree of association that this sleep health leads to A is set higher, and when there are many cases of sleep health B and few cases of sleep health A, , The degree of association that sleep health leads to B is increased, and the degree of association that sleep health leads to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and sleep health degree B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and it is set to sleep health degree B. The degree of association of the connected w14 is set to 2 points.

Further, the degree of association shown in FIG. 10 may be composed of the nodes of the neural network in artificial intelligence.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for sleep health from now on, the above-mentioned learned data will be used. In such a case, the heart rate data of the sleep health degree determination target and the sleep time series data are actually acquired. Here, the sleep time series data is newly acquired for the subject of the heart rate data when the sleep health degree is newly determined, and the acquisition method is the same as the above-mentioned reference sleep time series data.

Based on the heart rate data newly acquired in this way and the sleep time series data, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 10 (Table 1) acquired in advance is referred to. For example, if the newly acquired heart rate data is the same as or similar to P02, and the sleep time series data is the same as or similar to P21, the node 61d will move through the degree of association. The node 61d is associated with a sleep health degree C of w19 and a sleep health degree D of association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In FIG. 12, in addition to the above-mentioned reference heart rate data, a combination with the above-mentioned reference room temperature data instead of the above-mentioned reference treatment history data, and a degree of association of three or more levels of association with the sleep health degree for the combination are set. An example is shown.

This reference room temperature data, which is added as an explanatory variable instead of the reference treatment history data, is the data obtained by detecting the room temperature of the room in which the subject sleeps. The reference room temperature data can be detected by a thermometer or a temperature sensor installed in the room. As the reference room temperature data, changes in room temperature during sleep time may be continuously measured in time series as data.

Since such subjective symptoms also affect the sleep health level, the discrimination accuracy can be improved by combining the reference heart rate data and discriminating the sleep health level through the degree of association.

In the example of FIG. 12, it is assumed that the input data is, for example, reference heart rate data P01 to P03 and reference room temperature data P18 to 21. The intermediate node is a combination of the reference heart rate data and the reference room temperature data as such input data. Each intermediate node is further linked to the output. In this output, the sleep health level as an output solution is displayed.

Each combination (intermediate node) of the reference heart rate data and the reference room temperature data is associated with each other through three or more levels of association with sleep health as this output solution. Reference heart rate data and reference room temperature data are arranged on the left side via this degree of association, and sleep health is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the degree of sleep health with respect to the reference heart rate data and the reference room temperature data arranged on the left side. In other words, this degree of association is an index showing what kind of sleep health degree each reference heart rate data and reference room temperature data are likely to be associated with, and is a reference heart rate data and reference room temperature. It shows the accuracy in selecting the most probable sleep health level from the data.

The discriminating device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, in determining the actual search solution, the discrimination device 2 determines which of the reference heart rate data, the reference room temperature data obtained when acquiring the reference heart rate data, and the sleep health level in that case. Was suitable, or the past data is accumulated, and the degree of association is created by analyzing and analyzing these.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the reference heart rate data P01 is the reference room temperature data P20, the sleep health degree is analyzed from the past data. When there are many cases of sleep health A, the degree of association that this sleep health leads to A is set higher, and when there are many cases of sleep health B and few cases of sleep health A, , The degree of association that sleep health leads to B is increased, and the degree of association that sleep health leads to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of sleep health degree A and sleep health degree B, but from the previous case, the degree of association of w13 connected to sleep health degree A is set to 7 points, and it is set to sleep health degree B. The degree of association of the connected w14 is set to 2 points.

Further, the degree of association shown in FIG. 12 may be composed of the nodes of the neural network in artificial intelligence.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for sleep health from now on, the above-mentioned learned data will be used. In such a case, the heart rate data of the sleep health degree discrimination target and the room temperature data are actually acquired. Here, the room temperature data is newly acquired for the subject of the heart rate data when the sleep health degree is newly determined, and the acquisition method is the same as the above-mentioned reference room temperature data.

Based on the heart rate data newly acquired in this way and the room temperature data, the optimum sleep health level is searched for. In such a case, the degree of association shown in FIG. 9 (Table 1) acquired in advance is referred to. For example, if the newly acquired heart rate data is the same as or similar to P02 and the room temperature data is the same as or similar to P21, the node 61d is associated via the degree of association. In this node 61d, the sleep health degree C is associated with w19, and the sleep health degree D is associated with the association degree w20. In such a case, the sleep health degree C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the sleep health degree D, which has the lowest degree of association but is recognized as having the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In the present invention, as an alternative to the reference room temperature data shown in FIG. 12, the reference heart rate data shown below is learned in association with the degree of association by a combination of the reference body temperature data. May be good.

The reference body temperature data is data obtained by acquiring the body temperature of the subject in time series. In this body temperature measurement, in addition to the measurement by the thermometer, the temperature distribution of the body temperature of the entire subject may be shown in time series by thermography.

In such a case, the combination of the reference heart rate data and the reference body temperature data and the degree of association with the sleep health level in three or more stages are acquired in advance. At the time of actual judgment, the body temperature data of the subject is acquired. This body temperature data corresponds to the above-mentioned reference body temperature data, but the subject who acquired the reference body temperature data and the subject who acquires the body temperature data do not have to be the same, but the acquisition method. Is similar. Then, after referring to the degree of association, the sleep health degree is determined in the same manner as described above based on the newly acquired reference heart rate data and the reference body temperature data.

In the present invention, as an alternative to the reference treatment history data shown in FIG. 5, the reference bathing data shown below is learned in association with the degree of association by a combination of reference body temperature data. May be good.

The reference bathing data is data on whether or not the subject has taken a bath. In addition to being represented by two values of whether or not bathing was performed, bathing time, weekly bathing frequency, number of baths per day, and half-body bathing or full-body bathing may also be included in this reference bathing data. .. Reference bathing data may be obtained manually through interviews with subjects.

In such a case, the combination of the reference heart rate data and the reference bathing data and the degree of association with the sleep health level of three or more levels are acquired in advance. At the time of actual judgment, bathing data of the subject is acquired. This bathing data corresponds to the above-mentioned reference bathing data, but the subject who acquired the reference bathing data and the subject who acquired the bathing data do not have to be the same, but the acquisition method. Is similar. Then, after referring to the degree of association, the sleep health degree is determined in the same manner as described above based on the newly acquired reference heart rate data and the reference bathing data.

In the present invention, as an alternative to the reference treatment history data shown in FIG. 5, the reference sleep time coincidence data shown below is learned in association with the association degree by a combination of the reference body temperature data. It may be.

The reference sleep time matching degree data indicates the matching degree of sleep time when sleeping in the same room as the subject's cohabitant (relatives, etc.). The reference sleep time agreement data is obtained by verifying that the data changes depending on whether or not the sleep time matches with the cohabitant, and adding this as an explanatory variable. The reference sleep time agreement measurement method may be the same as the above-mentioned sleep time series data measurement method. Further, the reference sleep time agreement may be obtained by manually inputting through an interview from the subject.

In such a case, the combination having the reference heart rate data and the reference sleep time agreement degree data and the degree of association with the sleep health degree at three or more levels are acquired in advance. At the time of actual determination, the sleep time agreement degree data of the subject is acquired. This sleep time match degree data corresponds to the reference sleep time match degree data described above, but the subject who acquired the reference sleep time match degree data and the reference sleep time match degree data are acquired. The subjects do not have to be the same, but the acquisition method is the same. Then, after referring to the degree of association, the sleep health degree is determined in the same manner as described above based on the newly acquired reference heart rate data and the reference sleep time agreement degree data.

In the present invention, as an alternative to the reference treatment history data shown in FIG. 5, the reference attribute data shown below is learned by being associated with the degree of association by a combination of the reference body temperature data. May be good.

Reference attribute data is any information about the subject's attributes. Reference attribute data includes the subject's age, health status, annual income, date of birth, birthplace, and family environment (whether the wife is pregnant, the family is pursuing a disability or illness, or is living with grandparents). , Whether the care recipient is at home, whether or not they are affected by the disaster, whether or not they are DV or abused, whether or not they are divorced, whether or not they are divorced, whether or not they are divorced, whether or not they have household income, whether or not they have livelihood protection, whether or not they have wives and children, and their age structure, etc. , Children's school attendance status), etc. are also included. Regarding the state of health, whether or not the individual is in perfect health or has some kind of congenital disorder and the degree of the disorder, and whether or not there is an acquired disorder after birth and the degree of the disorder. Also, whether or not you have some kind of illness after birth, whether or not the illness continues at present and its degree, allergic condition, inflammatory condition, injured condition, chronic condition, medication status, etc. , Contains all information that indicates health status. The health condition included in the reference attribute information may be derived from medical data itself such as heart rate, pulse rate, blood data, electrocardiogram data, and X-ray image. All of these may be obtained through declarations and documents submitted by each household, medical certificates of doctors, and the like. This reference attribute data is, for example, "Age 46 years old, Birthplace: Shizuoka, Annual income of ¥ 100,000, 〇 × Working at a company, Family environment: Wife and eldest son, eldest daughter's family of four, eldest son is high school, eldest daughter is Junior high school student, health condition: "Has been operated on for gastric ulcer in the past", "Age 38 years old, Birthplace: Tokyo, Annual income of ¥ 100,000, ▲ 〇 Worked at a company, Family environment: Family of three, wife and eldest daughter, eldest daughter Is an elementary school student, health condition: good "etc.

Further, the attribute data may be obtained by manually inputting through an interview from the subject.

In such a case, the combination of the reference heart rate data and the reference attribute data and the degree of association with the sleep health level in three or more stages are acquired in advance. At the time of actual judgment, the attribute data of the subject is acquired. This attribute data corresponds to the above-mentioned reference attribute data, but the subject who acquired the attribute data and the subject who acquires the reference attribute data do not have to be the same, but the acquisition method. Is similar. Then, after referring to the degree of association, the sleep health degree is determined in the same manner as described above based on the newly acquired reference heart rate data and the reference attribute data.

In addition to heart rate data, blood oxygen concentration data, voice data, movement data, sleep time series data, room temperature data, body temperature data, bathing data, sleep time matching degree data, treatment history data, treatment history data, attributes When any two or more of the data, etc. are acquired, two or more reference information (reference blood oxygen concentration data, reference audio data, reference motion data, etc., according to the two or more information to be acquired, Reference sleep time series data, reference room temperature data, reference body temperature data, reference bathing data, reference sleep time agreement data, reference treatment history data, reference treatment history data, reference attribute data, etc.) and reference By creating learning data consisting of three or more levels of association between the combination with the heart rate data and the sleep health level for the combination, it is possible to search for a solution of the credit rating in the same manner.

In addition to heart rate data, blood oxygen concentration data, voice data, movement data, sleep time series data, room temperature data, body temperature data, bathing data, sleep time matching degree data, treatment history data, treatment history data, attributes In addition to any one or more of the data, etc., when other information is acquired, the reference information (reference blood oxygen concentration data, reference audio data, reference movement) according to the acquired information is also obtained. Data, reference sleep time series data, reference room temperature data, reference body temperature data, reference bathing data, reference sleep time agreement data, reference treatment history data, reference treatment history data, reference attribute data, etc.) By creating learning data consisting of a combination of reference heart rate data and reference information according to other acquired information, and three or more levels of association with the sleep health level for the combination. A solution search can be performed in the same way.

Further, according to the present invention, heart rate data, blood oxygen concentration data, voice data, movement data, sleep time series data, room temperature data, body temperature data, bathing data, sleep time matching degree data, treatment history data, treatment history data. , Attribute data, etc., when acquiring any two or more, two or more reference information (reference heart rate data, reference blood oxygen concentration data, reference voice) according to the two or more information to be acquired. Data, reference movement data, reference sleep time series data, reference room temperature data, reference body temperature data, reference bathing data, reference sleep time agreement data, reference treatment history data, reference treatment history data, reference By creating learning data consisting of a combination of (attribute data, etc.) and the degree of association between the sleep health level and the sleep health level of the combination, it is possible to search for a solution of the credit rating in the same manner.

Further, as shown in FIG. 9, the present invention determines each sleep health degree based on the degree of association between two or more types of information, reference information U and reference information V. This reference information U is reference heart rate data, and reference information V is other reference information (reference blood oxygen concentration data, reference voice data, reference movement data, reference sleep time series data, etc. Reference room temperature data, reference body temperature data, reference bathing data, reference sleep time agreement data, reference treatment history data, reference treatment history data, reference attribute data, etc.).

At this time, as shown in FIG. 9, the output obtained for the reference information U may be used as the input data as it is, and may be associated with the output via the intermediate node 61 in combination with the reference information V. For example, for the reference information U, after the output solution is output, this may be used as an input as it is, and the output may be searched by using the degree of association with other reference information V.

In the above-mentioned degree of association, the degree of association is expressed by a 10-step evaluation, but it is not limited to this, and it may be expressed by a degree of association of 3 or more levels, and conversely, it may be expressed by 3 or more levels. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include those expressed in two stages, that is, whether or not they are related to each other, either 1 or 0.

According to the present invention having the above-described configuration, anyone can easily determine and search the sleep health level without any special skill or experience. Further, according to the present invention, it is possible to determine the search solution with higher accuracy than that performed by a human being. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

Since the above-mentioned input data and output data often do not exist exactly the same in the process of learning, the input data and the output data may be classified by type. That is, the information P01, P02, ... P15, 16, ... That constitute the input data are classified according to the criteria classified in advance on the system side or the user side according to the content of the information, and the classified inputs. A data set may be created between the data and the output data and trained.

In the above-mentioned degree of association, the case where the data is composed of any of the reference treatment history data, the reference filling information, and the reference subjective symptom data in addition to the reference heart rate data has been described as an example. , Not limited to this. That is, the degree of association may be composed of a combination of any two or more of the reference treatment history data, the reference filling information, and the reference subjective symptom data in addition to the reference heart rate data. In addition to the reference heart rate data, the degree of association is formed by adding any one or more of the reference treatment history data, the reference filling information, and the reference subjective symptom data, and other factors to this combination. It may have been done.

In either case, data is input according to the reference information of the degree of association, and the degree of sleep health is obtained using the degree of association.

Further, as shown in FIG. 8, the present invention determines the sleep health degree based on the degree of association between two or more types of information, the reference information U and the reference information V. It is assumed that the reference information Y is the reference heart rate data, and the reference information V is any of the reference treatment history data, the reference filling information, and the reference subjective symptom data.

At this time, as shown in FIG. 8, the output obtained for the reference information U is used as input data as it is, and is associated with the output (sleep health level) via the intermediate node 61 in combination with the reference information V. May be good. For example, for reference information U (reference heart rate data), after an output solution is output as shown in FIG. 3, this is used as an input as it is, and the degree of association with other reference information V is used. , The output (sleep health) may be searched.

Further, according to the present invention, instead of obtaining the sleep health degree as an output solution, the alert information such as an alarm and an alarm based on the sleep health degree may be transmitted. The higher the degree of sleep health, the higher the degree of alerting of the alerting information. As a result, it is possible to efficiently call attention to the outside that the tooth is in a dangerous state.

Further, according to the present invention, there is a feature that an optimum solution search is performed through the degree of association set in three or more stages. The degree of association can be described by, for example, a numerical value from 0 to 100% in addition to the above-mentioned 10 steps, but the degree of association is not limited to this, and any step can be described as long as it can be described by a numerical value of 3 or more steps. It may be configured.

By discriminating the most probable sleep health level based on the degree of association represented by the numerical values of three or more levels, the degree of association is high under the situation where there are multiple possible candidates for the search solution. It is also possible to search and display in order. If the user can be displayed in descending order of the degree of association in this way, it is possible to preferentially display more probable search solutions.

In addition to this, according to the present invention, it is possible to judge without overlooking the discrimination result of the output having an extremely low degree of association such as 1%. It warns the user that even a judgment result with an extremely low degree of association is connected as a slight sign and may be useful as the judgment result once every tens or hundreds of times. be able to.

Further, according to the present invention, there is an advantage that the search policy can be determined by the method of setting the threshold value by performing the search based on the degree of association of three or more stages. If the threshold value is lowered, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but it is unlikely that a more appropriate discrimination result can be detected favorably, and a lot of noise may be picked up. be. On the other hand, if the threshold value is raised, there is a high possibility that the optimum search solution can be detected with a high probability. Sometimes the solution is overlooked. It is possible to decide which one to prioritize based on the ideas of the user side and the system side, but it is possible to increase the degree of freedom in selecting the points to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided via a public communication network such as the Internet. In addition, when each reference information such as reference heart rate data is acquired and knowledge, information, and data on sleep health and improvement measures are acquired, the degree of association is increased or decreased accordingly. ..

In other words, this update corresponds to learning in the sense of artificial intelligence. It can be said that it is a learning act because it acquires new data and reflects it in the learned data.

In addition, this update of the degree of association is not based on the information that can be obtained from the public communication network, but is also updated by the system side or the user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts. It may be updated artificially or automatically. Artificial intelligence may be utilized in these update processes.

Further, the process of first creating the trained model and the above-mentioned update may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning the data set of input data and output data, information corresponding to the input data is read and trained, and the degree of association related to the output data is self-formed from there. You may let it.

1 Sleep health discrimination system 2 Discrimination device 21 Internal bus 23 Display unit 24 Control unit 25 Operation unit 26 Communication unit 27 Discrimination unit 28 Storage unit 61 Node

Claims (13)

In the sleep health determination program that determines the health level during sleep,
An information acquisition step to acquire time-series heart rate data detected from the body of a sleeping subject, and
Heart rate data acquired in the above information acquisition step by referring to the time-series reference heart rate data detected from the body of the subject during sleep in the past and the degree of association with sleep health at three or more levels. A sleep health determination program characterized by having a computer perform a determination step for determining sleep health based on the above. In the above information acquisition step, blood oxygen concentration data detected from the body of the subject during sleep is further acquired.
In the above-mentioned discrimination step, a combination having the above-mentioned reference heart rate data and reference blood oxygen concentration data detected from the body during sleep of a past subject and sleep health degree are associated with three or more stages. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the blood oxygen concentration data with reference to the degree. In the above information acquisition step, the time-series voice data during sleep detected from the subject is further acquired.
In the above-mentioned discrimination step, the combination having the above-mentioned reference heart rate data and the time-series reference voice data during sleep of the past subject and the degree of association with the sleep health degree in three or more stages are referred to. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the voice data. In the above information acquisition step, motion data obtained by detecting the sleep motion of the subject in time series is further acquired.
In the discrimination step, there are three or more stages of association between the combination of the reference heart rate data and the reference movement data obtained by detecting the sleep movements of the subject in the past in a time series, and the sleep health level. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the movement data with reference to the degree. In the above information acquisition step, sleep time series data composed of continuous sleep time and awakening time in the case of intermittent sleep in which the subject wakes up in the middle of sleep and then enters sleep again is acquired.
In the discrimination step, a combination having the reference heart rate data, reference sleep time series data composed of continuous sleep time and awakening time when a past subject sleeps intermittently, and sleep health The sleep according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the sleep time series data by referring to the degree of association with the degree in three or more stages. Health judgment program. In the above information acquisition step, time-series room temperature data in the room where the subject sleeps is further acquired.
In the discrimination step, the combination of the reference heart rate data and the time-series reference room temperature data in the room where the subject sleeps in the past is referred to, and the degree of association with the sleep health level in three or more stages is referred to. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the room temperature data. In the above information acquisition step, time-series body temperature data detected from the body of the subject during sleep is further acquired.
In the discrimination step, the combination of the reference heart rate data, the time-series reference body temperature data detected from the body of the subject during sleep in the past, and the sleep health degree are associated with three or more stages. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the body temperature data with reference to the degree. In the above information acquisition step, bathing data indicating the presence or absence of bathing before acquiring the heart rate data of the subject is further acquired.
In the determination step, a combination having the reference heart rate data and the reference bath data indicating the presence or absence of bathing before acquiring the reference heart rate data of the past subject, and the sleep health degree are combined. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the bathing data with reference to three or more levels of association. In the above information acquisition step, sleep time matching degree data indicating the matching degree of sleep time when sleeping in the same room as the cohabiting person of the subject is further acquired.
In the discrimination step, a combination having the reference heart rate data and the reference sleep time match degree data indicating the degree of match of the sleep time when sleeping in the same room as the cohabitant of the past subject, and sleep health The first aspect of claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the above information acquisition step and the sleep time agreement degree data by referring to the degree of association with the degree in three or more stages. Sleep health determination program. In the above information acquisition step, further, the treatment history data regarding the treatment history related to the sleep of the subject is acquired.
In the determination step, the combination of the reference heart rate data and the reference treatment history data relating to the treatment history of the past subject and the degree of association with the sleep health level in three or more stages are referred to, and the above information is obtained. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the acquisition step and the treatment history data. In the above information acquisition step, the subjective symptom data regarding the subjective symptom related to the sleep of the subject is further acquired.
In the determination step, the combination of the reference heart rate data and the reference subjective symptom data relating to the subjective symptom of the subject in the past and the degree of association with the sleep health level in three or more stages are referred to, and the above information is obtained. The sleep health degree determination program according to claim 1, wherein the sleep health degree is determined based on the heart rate data acquired in the acquisition step and the subjective symptom data. In the above information acquisition step, the attribute data of the subject is further acquired.
In the above determination step, the combination having the reference attribute data of the past subject and the degree of association with the sleep health degree in three or more stages are referred to, and further based on the attribute data acquired in the above information acquisition step. The sleep health determination program according to claims 2 to 11, wherein the sleep health determination is performed. The sleep health determination program according to any one of claims 1 to 12, wherein in the determination step, the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence is used. ..

Images