JP7579111B2 - Health Management Device - Google Patents

Description

The present invention relates to a health management device that predicts a user's health condition.

Patent Document 1 provides a comprehensive health management system that obtains information about the start of a woman's menstruation and physical discomfort from voice input, and also obtains weather data to calculate an individual's menstrual cycle, the probability that menstruation will start on that day, the probability of discomfort due to the menstrual cycle, and the individual's sensitivity to drops in air pressure, and issues advance warning of physical discomfort.

JP 2018-195000 A

However, it has been difficult to make detailed predictions of each individual's menstrual symptoms using only an individual's menstrual cycle and weather data.

Therefore, in order to solve the above-mentioned problems, the present invention aims to provide a health management device that can accurately predict each symptom associated with health conditions such as menstruation for each individual user.

The health management device of the present invention includes a storage unit that stores life log data, which is information that affects the physical health of multiple users, and a symptom prediction unit that predicts symptoms of a user's health condition during a peripheral period at a specified reference time based on the life log data.

This configuration makes it possible to accurately and easily predict symptoms in the peripheral period of a user's health condition at a specified reference time based on the user's life log data.

According to the present invention, by using each user's life log data, it is possible to accurately predict peripheral symptoms of the user's health condition at a specified baseline time.

1 is a diagram illustrating a system configuration of a health management system according to the present disclosure. FIG. 2 is a block diagram showing the functional configuration of the measurement value transfer device 30. FIG. 2 is a block diagram showing a functional configuration of a physical condition registration device 40. 2 is a block diagram showing the functional configuration of a basic constitution registration device 50. [0033] FIG. FIG. 2 is a block diagram showing the functional configuration of the menstrual information registration device 60. FIG. 2 is a block diagram showing the functional configuration of a weather information acquisition device 70. FIG. 2 is a block diagram showing the functional configuration of the data collection and analysis device 100. 11 is a diagram showing a specific example of a database stored in the data storage function 120. FIG. 13 is a flowchart showing a prediction model generation process in the data collection and analysis device 100. 13 is a flowchart showing the process of generating an onset date prediction model by an onset date prediction model generating function 130. 13 is a flowchart showing a process of predicting the onset date of any one symptom by the onset date prediction function 140. 13 is a flowchart showing a process for generating an onset cycle prediction model. FIG. 11 is a diagram for explaining a frequency analysis process. 13 is a flowchart showing a process of predicting the onset cycle of a symptom by the onset cycle prediction function 145. 13 is a flowchart showing a process for generating a severity prediction model by a severity prediction model generating function 150. 13 is a flowchart showing a process of predicting the severity of a symptom by the severity prediction function 160. 13 is a flowchart showing a maximum severity day prediction model generation process of the maximum severity day prediction model generation function 155. 13 is a flowchart showing a process of predicting the day (maximum day) when the severity of a symptom will be maximum, performed by the maximum severity day prediction function 165. FIG. 1 is a diagram illustrating an example of a hardware configuration of a data collection and analysis device 100 according to an embodiment of the present disclosure.

Embodiments of the present disclosure will be described with reference to the accompanying drawings. Where possible, identical parts will be designated by the same reference numerals, and duplicate descriptions will be omitted.

Figure 1 is a diagram showing the system configuration of the health management system in the present disclosure. As shown in Figure 1, the health management system is configured to include a measurement device 20, a measurement value transfer device 30, a physical condition registration device 40, a basic constitution registration device 50, a menstrual information registration device 60, a weather information acquisition device 70, and a data collection and analysis device 100 (health management device). This data collection and analysis device 100 collects and analyzes the user's life log data from the measurement device 20, the physical condition registration device 40, the basic constitution registration device 50, the menstrual information registration device 60, and the weather information acquisition device 70. As described later, the life log data is data indicating the physical health condition of each individual user and/or data that affects the health, and is information indicating the user's daily life. The life log data includes measurement values that are objective information of the user's body, physical condition data related to the user's physical condition, basic constitution data indicating the user's basic constitution, the user's menstruation start date, menstrual data related to other symptoms, and other weather information. Weather data indicates the weather in the user's place of residence and is information that affects the user's health depending on the weather.

The measuring device 20 is a part that directly measures measurements, which are a type of life log data, from the user. In this disclosure, the measuring device 20 includes at least one of a blood pressure monitor, a weight scale, an activity meter, and a thermometer, and measures objective physical data such as the user's blood pressure, weight, heart rate, calories burned, and body temperature.

The measurement value transfer device 30 is a device that transfers the measurement values, which are a type of life log data, measured by the measuring device 20 together with the measurement date to the data collection and analysis device 100 via the network 90.

The health registration device 40 accepts user operation, receives the registration date (corresponding to the onset date) and health data, and stores this in the data collection and analysis device 100. The health data indicates the amount of sleep and whether or not medication was taken, but may also include other information such as the content or amount of food eaten and satisfaction with the food. In addition to the amount of sleep, it may also include satisfaction with sleep. The health data is information related to the user's lifestyle habits.

The basic constitution registration device 50 is a device that accepts user operations, receives basic constitution data, and registers it in the data collection and analysis device 100. The basic constitution data is information indicating age, BMI (Body Mass Index), birth history, medical history, etc. The basic constitution data is data indicating the user's medical history, information that is updated about once a year, and physical information that is generally unlikely to change significantly within a year.

The menstrual information registration device 60 is a device that accepts user operations, receives menstrual data, and registers it in the data collection and analysis device 100. Menstrual data is information (hereinafter referred to as symptom information) indicating the onset date of menstruation and various symptoms during the peri-menstrual phase (a specified period before and after menstruation). The various symptoms are symptoms that occur in relation to the menstrual cycle, and indicate symptoms that occur during at least one of the follicular phase, ovulation phase, luteal phase, or menstruation phase. Specifically, the various symptoms indicate at least one of lower back pain, headache, abdominal pain, discomfort, irritability, the presence or absence of bleeding, breast swelling, the presence or absence of vaginal discharge, skin condition, or fatigue.

The weather information acquisition device 70 is a device that acquires weather data (temperature, weather, air pressure, humidity, etc.) for the area where the user lives from a weather database owned by the Japan Meteorological Agency or the like.

The data collection and analysis device 100 stores the data collected from each device, and generates prediction models for the onset date, onset end date, onset cycle, severity, and maximum severity date of peripheral symptoms using machine learning (any machine learning method can be used; for example, a classical linear model, a nonlinear model such as XGBoost or LightGBM, or deep learning such as DNN can be used) based on that data. These prediction models are then used to predict the onset date, onset end date, onset cycle, severity, and maximum severity date of peripheral symptoms.

In the above explanation, life log data is accepted and registered through user operation, but this is not limited to this. The user may operate the user terminal to transmit various types of life log data from the user terminal to each device and register them.

These devices are described below. Figure 2 is a block diagram showing the functional configuration of the measurement value transfer device 30. As shown in the figure, the measurement value transfer device 30 has a data acquisition function 31, a data transfer function 32, a measurement device authentication function 33, and a user authentication function 34.

The data acquisition function 31 is a function that acquires the measurement values and measurement dates measured by the measuring device 20.

The data transfer function 32 is a function that transfers the acquired measurement values and measurement dates to the data collection and analysis device 100.

The measurement device authentication function 33 is a function that performs authentication processing of the measurement device 20 when acquiring a measurement value from the measurement device 20. The authentication processing is a known authentication processing, for example, a processing for matching the identification information of the measurement device 20.

The user authentication function 34 is a function that performs authentication processing of the user when acquiring a measurement value from the measuring device 20. The authentication processing is a well-known authentication processing, for example, a processing of matching the user's identification information and his/her password.

Figure 3 is a block diagram showing the functional configuration of the health registration device 40. The health registration device 40 includes a data registration function 41, a data transfer function 42, and a user authentication function 43.

The data registration function 41 has a section for accepting user operations, and is a function for accepting physical condition data and the date of registration thereof in accordance with the operations.

The data transfer function 42 is a function that transfers physical condition data and the registration date to the data collection and analysis device 100.

The user authentication function 43 is a function that performs authentication processing of the user when the data registration function 41 accepts physical condition data. The authentication processing is a well-known authentication processing, for example, a processing of matching the user's identification information and password.

Figure 4 is a block diagram showing the functional configuration of the basic constitution registration device 50. The basic constitution registration device 50 has a data registration function 51 and a data transfer function 52.

The data registration function 51 has a section for accepting user operations, and is a function for accepting basic constitution data and the date of registration thereof in accordance with the operations.

The data transfer function 52 is a function that transfers basic constitution data and the registration date to the data collection and analysis device 100.

Figure 5 is a block diagram showing the functional configuration of the menstrual information registration device 60. The menstrual information registration device 60 has a data registration function 61 and a data transfer function 62.

The data registration function 61 has a section for accepting user operations and is a function for accepting menstrual data in accordance with those operations.

The data transfer function 52 is a function that transfers menstrual data to the data collection and analysis device 100.

Figure 6 is a block diagram showing the functional configuration of the weather information acquisition device 70.

The weather information acquisition device 70 has a data acquisition function 71 and a data transfer function 72.

The data acquisition function 71 is a function that periodically or when the data collection and analysis device 100 generates an estimation model, accesses the weather information database to acquire weather information corresponding to the user's location or place of residence and the registration date (or measurement date) of the various pieces of information described above. The user's location or place of residence is information that is registered in advance, but it may also be a location obtained using GPS or the like.

The data transfer function 72 is a function that transfers weather information for each user to the data collection and analysis device 100.

7 is a block diagram showing the functional configuration of the data collection and analysis device 100. As shown in the figure, the data collection and analysis device 100 includes a data acquisition function 110, a data storage function 120, an onset date prediction model generation function 130, an onset cycle prediction model generation function 135, an onset date prediction function 140, an onset cycle prediction function 145, a severity prediction model generation function 150, a maximum severity day prediction model generation function 155, a severity prediction function 160, a maximum severity day prediction function 165, and a result notification function 170.
The data collection and analysis device 100 has multiple prediction functions and multiple prediction model functions, but is not limited thereto. One or several prediction models that output the onset date, onset end date, onset cycle, severity, and maximum severity date for the life log data may be learned and used. In addition, in the description below, each prediction model generation function generates a respective prediction model (onset date prediction model, onset cycle prediction model, severity prediction model, maximum severity date prediction model) for all symptoms, but one or several prediction models that output a prediction value for each symptom may be generated.

The data acquisition function 110 is a function that acquires various information from the measurement value transfer device 30, the physical condition registration device 40, the basic constitution registration device 50, the menstrual information registration device 60, and the weather information acquisition device 70.

The data storage function 120 is a function that stores various information acquired by the data acquisition function 110, and is a so-called storage unit. Figure 8 is a diagram showing a specific example of a database stored by the data storage function 120. As shown in the diagram, measurement data, menstrual data, physical condition data, basic constitution data, and weather data are stored in association with each user ID. Each of these data is associated with the registration date (or measurement date).

Measurement data is information that associates body temperature, weight, activity level (heart rate), etc. with the registration date.

The physical condition data is information that associates sleep time and whether or not medication is taken with the registration date.

The menstrual data is the start date of menstruation, the end date of menstruation, or perimenstrual symptoms and the date of their registration. The perimenstrual symptoms are at least one of the following: the presence or absence or severity of abdominal pain, the presence or absence or severity of headache, the presence or absence or severity of lower back pain, the presence or absence or severity of mood discomfort, the presence or absence or severity of irritability, the presence or absence or severity of bleeding, the presence or severity of breast bloating, the presence or absence or amount of vaginal discharge, the condition of the skin, and the presence or absence or severity of fatigue.

Basic physical constitution data is information that correlates age, BMI, whether or not a person has given birth, and the date of registration.

Weather data is information that associates temperature, weather, humidity, and air pressure with the registration date.

In FIG. 8, the data storage function 120 stores the above-mentioned various information only for user A, but it stores the above-mentioned various information for all users other than user A.

The data extraction function 125 is a function that extracts various data stored in the data storage function 120 in order to generate each predictive model. For example, the data extraction function 125 extracts life log data of a user who has registered data for a specified period of time that is useful for generating a predictive model.

The onset date prediction model generation function 130 is a function that generates a prediction model (onset date prediction model) for predicting the onset date and onset end date during the perimenstrual period. This onset date prediction model generation function 130 generates an onset date prediction model for predicting the onset date and onset end date of perimenstrual symptoms using the measurement data, menstrual data, physical condition data, basic constitution data, and weather data extracted by the data extraction function 125 as feature quantities (explanatory variables) and the difference between the menstruation start date and onset date as the objective variable. Details will be described later. The onset date prediction model may output either the onset date or the onset end date.

The onset cycle prediction model generation function 135 is a function that generates a prediction model (onset cycle prediction model) for predicting onset cycles. This onset cycle prediction model generation function 135 generates an onset cycle prediction model for predicting the onset cycle of perimenstrual symptoms using the measurement data, menstrual data, physical condition data, basic constitution data, and weather data extracted by the data extraction function 125 as feature quantities (explanatory variables) and the cycle of onset days as the objective variable. Details will be described later.

The onset date prediction function 140 stores the onset date prediction model generated by the onset date prediction model generation function 130, and uses this to predict the onset date and end date of each perimenstrual symptom. The onset date prediction function 140 predicts the onset date and end date of each perimenstrual symptom by inputting life log data such as the user's measurement value data, menstrual data, basic constitution data, and weather data at the time of prediction.

The onset cycle prediction function 145 stores the onset cycle prediction model generated by the onset cycle prediction model generation function 135, and uses this to predict the onset cycle of each perimenstrual symptom. The onset cycle prediction function 145 predicts the cycle of each perimenstrual symptom by inputting life log data such as the user's measurement value data, menstrual data, basic constitution data, and weather data at the time of prediction.

The severity prediction model generation function 150 is a function that generates a severity prediction model for predicting the severity of each symptom during the perimenstrual period. This severity prediction model generation function 150 uses the measurement data, menstrual data, physical condition data, basic constitution data, and weather data extracted by the data extraction function 125 as feature quantities (explanatory variables) and the severity at which the symptom is at its maximum as the objective variable to generate a severity prediction model for predicting the maximum severity of perimenstrual symptoms. Details will be described later.

The maximum severity day prediction model generation function 155 is a function that generates a maximum severity day prediction model for predicting the day when the severity of each symptom during the perimenstrual period will be at its maximum (maximum severity day). This maximum severity day prediction model generation function 155 uses the measurement data, menstrual data, physical condition data, basic constitution data, and weather data extracted by the data extraction function 125 as feature quantities (explanatory variables) and the day when the symptom severity will be at its maximum as the objective variable to generate a maximum severity day prediction model for predicting the day when the perimenstrual symptoms will be at their maximum severity. Details will be described later.

The severity prediction function 160 stores the severity prediction model generated by the severity prediction model generation function 150, and uses this to predict the severity of each symptom that occurs during the perimenstrual period.

The maximum severity day prediction function 165 stores the maximum severity day prediction model generated by the maximum severity day prediction model generation function 155, and uses this to predict the day on which the severity of each symptom occurring during the perimenstrual period will be at its maximum.

The result notification function 170 is a function that notifies the user of the onset date, onset end date, onset cycle, severity, and the day when the severity is at its maximum (day of maximum severity) of each symptom that occurs around the menstrual period, as predicted using the onset date prediction model, cycle prediction model, severity prediction model, and maximum severity day prediction model.

The above prediction model generation process is performed periodically or at random. In addition, the prediction process and notification process are performed periodically or at the user's discretion.

Next, the operation of the data collection and analysis device 100 of the present disclosure will be described. FIG. 9 is a flowchart showing the prediction model generation process in the data collection and analysis device 100. The data acquisition function 110 acquires various data (life log data) from all or part of each device, and the data storage function 120 stores it (S100). The data storage function 120 detects and removes outliers and interpolates missing values from the stored life log data (S101).

The data extraction function 125 extracts users who have stored life log data a certain number of times or more for the past three months or more (S102). Note that this is not limited to three months, and may be a certain number of times or more in a specified period.

The onset date prediction model generation function 130 generates an onset date prediction model using the life log data stored in the data storage function 120 (S103). This onset date prediction model is generated for each symptom, such as headache or abdominal pain, that occurs during the perimenstrual period. The onset date prediction function 140 uses the onset date prediction model to predict the onset date and end date of the next and subsequent perimenstrual symptoms (S104).

Furthermore, the onset cycle prediction model generation function 135 generates an onset cycle prediction model using the life log data (S105). This onset cycle prediction model is generated for each symptom, such as headache or abdominal pain, that occurs during the perimenstrual period. The onset cycle prediction function 145 uses the onset cycle prediction model to predict the onset cycle of perimenstrual symptoms from the next period onwards (S106).

The severity prediction model generation function 150 also generates a severity prediction model using the life log data stored in the data storage function 120 (S107). This severity prediction model is generated for each symptom. The severity prediction function 160 uses the severity prediction model to predict the severity from the next time onwards (S108).

The maximum severity day prediction model generation function 155 uses the life log data to generate a maximum severity day model (S109). This maximum severity day prediction model is generated for each symptom. The maximum severity day prediction function 165 uses the maximum severity day prediction model to predict the day on which the severity will be maximum from the next time onwards (S110).

The result notification function 170 notifies the user of the onset date, onset end date, onset cycle, severity, and the date when the severity will be at its maximum for each symptom predicted by the onset date prediction function 140, onset cycle prediction function 145, severity prediction function 160, and maximum severity date prediction function 165 (S111).

The above prediction processes S104, S106, S108, and S110 are not limited to being executed after each prediction model is generated, and only the prediction processes may be executed at any timing.

Next, the detailed processing of step S103 will be described. FIG. 10 is a flowchart showing the process of generating an onset date prediction model by the onset date prediction model generation function 130.

The onset date prediction model generation function 130 extracts the menstrual start date of each user based on the extracted menstrual data of each user. Then, it calculates the menstrual cycle of each user (S103-1). If there are three or more menstrual start dates, the average of these is used as the menstrual cycle of that user.

The onset date prediction model generation function 130 runs a processing loop for each perimenstrual symptom (S103-2, S103-3). That is, the onset date prediction model generation function 130 extracts life log data of users who have developed the symptom for each symptom from the menstrual data stored in the data storage function 120 (S103-3). The symptoms are headache, abdominal pain, etc., and some users may develop both headache and abdominal pain, or may develop headache but not abdominal pain. In the present disclosure, life log data of users who have developed the symptom for each symptom, such as users who have developed headache and users who have developed abdominal pain, is collected. Therefore, the same life log data may be handled in duplicate. Note that the physical condition data in FIG. 8 is represented by the severity of the symptom. In the physical condition data, 0 is added if there is no symptom. Note that if the severity of the symptom is extremely low, the symptom may be treated as not being present.

The onset date prediction model generation function 130 calculates the difference in number of days D1 between the menstruation start date and the first day of onset that is closest to the menstruation start date for each user (S103-4). The symptoms continue to occur, and the first day of onset refers to the first day of onset. The process here finds the day that is closest to the first day of menstruation.

The onset date prediction model generation function 130 uses physical condition data, basic constitution data, weather data, menstruation start date, and menstrual cycle as feature quantities (explanatory variables) and the difference in number of days D1 as a target variable, and uses any machine learning method to generate an onset date prediction model for predicting the menstruation start date and the closest first day of onset of the symptom from the menstruation start date. This onset date prediction model is a prediction model that predicts the onset date of the symptom determined in S103-2, etc.

The onset date prediction model generation function 130 performs these processes for all symptoms (headache, stomachache, etc.) and generates onset date prediction models for all symptoms (S103-6).
For convenience of explanation, the generation process of the onset date prediction model has been described with a focus on the onset date, but this onset date prediction model is similarly trained for the onset end date. That is, the onset date prediction model generation function 130 calculates the difference in number of days between the onset end date, which is paired with the onset first day, and the menstruation start date, and learns the onset date prediction model for the onset end date based on the difference in number of days.

Next, a prediction process using the onset date prediction model will be described. FIG. 11 is a flowchart showing the process of predicting the onset date of any one symptom by the onset date prediction function 140. The onset date prediction function 140 applies the life log data of one user to the onset date prediction model corresponding to one symptom to calculate a predicted value (S104-1). The onset date prediction function 140 converts the predicted value into an onset date (S104-2). This predicted value is the difference in number of days between the menstruation start date and the first day of onset of the symptom closest to the menstruation start date. The onset date prediction function 140 predicts the next menstruation start date from the registered menstruation start date and the menstrual cycle calculated from the menstruation start date, and can use this to find the onset date of the symptom. The result notification function 170 notifies the one user of the predicted onset date of the symptom (S104-3). This is the onset date notification process for one symptom. These processes are repeated for all symptoms. Additionally, the user may specify any symptom and have the onset date of that symptom predicted.

Next, process S105 will be described. FIG. 12 is a flowchart showing the process of generating an onset cycle prediction model. The onset cycle prediction model generation function 135 extracts the menstruation start date of each user based on the extracted menstrual data of each user. Then, the menstrual cycle of each user is calculated (S105-1). If there are three or more menstruation start dates, the average value is used as the menstrual cycle of that user.

The onset cycle prediction model generation function 135 runs a processing loop for each perimenstrual symptom (S105-2, S105-3). That is, the onset cycle prediction model generation function 135 extracts, for each symptom, life log data of users who have developed that symptom from the menstrual data stored in the data storage function 120 (S105-3). Symptoms include headaches, abdominal pain, etc., and some users may develop both headaches and abdominal pain, or may develop headaches but no abdominal pain. Therefore, life log data may be used in duplicate.

The onset cycle prediction model generation function 135 calculates the onset cycle Y of perimenstrual symptoms using frequency analysis or any regression analysis based on the onset date of the target symptom (S105-4).

Here, the calculation process of the onset cycle Y will be described. FIG. 13 is a diagram for explaining the frequency analysis process. Frequency analysis is a method for deriving the periodicity of time series data and analyzing its characteristics. In this disclosure, the horizontal axis (time axis) of the time series data is the number of days going back from the start date of menstruation, and the vertical axis (amplitude) is the registration rate for the entire symptom.

In FIG. 13, the dotted line is a graph of the registration rate of users who registered symptom a on days going back from the start of menstruation. The registration rate is the ratio of the number of users who registered that they had developed symptom a to the total number of users, and is calculated for each day going back from the start of menstruation. These values are connected to form graph G1, represented by a dotted line. Note that instead of the registration rate on the vertical axis, the severity of the symptom may be used. For example, users may be asked to enter numerical information on the severity of their headache or stomachache, and the average may be taken.

The onset cycle prediction model generation function 135 can extract the fluctuation pattern (periodicity) shown in the solid line graph G2 by performing frequency analysis on the dotted line graph G1.

The onset cycle prediction model generation function 135 can detect peaks in the amplitude of this solid line graph G2 to calculate the number of days between peaks, i.e., the cycle Y of symptom a. This symptom a is each symptom of the perimenstrual period, such as headache, abdominal pain, etc.

The onset cycle prediction model generation function 135 uses physical condition data, basic constitution data, weather data, menstruation start date, and menstrual cycle as feature quantities, and onset cycle Y as a target variable, and generates an onset cycle prediction model for predicting onset cycles using any machine learning method. This onset cycle prediction model is a prediction model that predicts the onset cycle of the symptoms determined in S105-2.

The onset cycle prediction model generation function 135 performs these processes for all symptoms (headache, stomachache, etc.) and generates onset cycle prediction models for all symptoms (S105-6).

Next, the prediction process using the onset cycle prediction model will be described. FIG. 14 is a flowchart showing the prediction process of the onset cycle of one symptom by the onset cycle prediction function 145. The onset cycle prediction function 145 applies the life log data of one user to the onset cycle prediction model corresponding to one symptom to predict the onset cycle of the one symptom (S106-1). The result notification function 170 notifies the one user of the onset cycle of the one symptom (S106-2). This is the notification process of the onset date for one symptom. These processes are repeated for all symptoms. Note that one user may specify any symptom and predict the onset cycle, etc. of only that symptom.

Next, the detailed processing of step S107 will be described. FIG. 15 is a flowchart showing the process of generating a severity prediction model by the severity prediction model generation function 150.

The severity prediction model generation function 150 extracts the menstrual start date of each user based on the extracted menstrual data of each user. Then, it calculates the menstrual cycle of each user (S107-1). If there are three or more menstrual start dates, the average of these is used as the menstrual cycle of that user.

The severity prediction model generation function 150 runs a processing loop for each perimenstrual symptom (S107-2). In other words, the onset date prediction model generation function 130 determines one perimenstrual symptom.

Then, the severity prediction model generation function 150 extracts the menstruation start date and the severity L of the symptom closest to the menstruation start date from the life log data of the user who has the perimenstrual symptom (S107-3). That is, the severity prediction model generation function 150 extracts the severity L of the day closest to the menstruation start date from among several onset dates at which the severity peaks. This is performed for each user's life log data. For women who do not have the perimenstrual symptom, the severity is calculated as 0.

The severity prediction model generation function 150 uses the physical condition data, basic constitution data, weather data, menstruation start date, and menstrual cycle as feature quantities (explanatory variables) and the severity L as the objective variable, and uses any machine learning method to generate a severity prediction model for predicting the menstruation start date and severity L of the day closest to the menstruation start date among several days when the severity peaks. This severity prediction model is a prediction model that predicts the severity of one symptom determined in S107-2.

The severity prediction model generation function 150 performs these processes for all symptoms (headache, stomachache, etc.) and generates a severity prediction model for all symptoms (S107-5).

Next, the prediction process using the severity prediction model will be described. Figure 16 is a flowchart showing the process of predicting the severity of one symptom by the severity prediction function 160. The severity prediction function 160 applies the life log data to the severity prediction model corresponding to one symptom to calculate the maximum severity (S108-1). The result notification function 170 notifies the user of the severity of that one symptom (S108-2). This is the process of notifying the severity of one symptom. These processes are repeated for all symptoms. Note that the user may specify any symptom to have the severity of only that symptom predicted.

Next, the process of generating a maximum severity day prediction model for predicting the onset date when the severity will be at its maximum will be described. FIG. 17 is a flowchart showing the maximum severity day prediction model generation process of the maximum severity day prediction model generation function 155.

The severity maximum day prediction model generation function 155 extracts the menstrual start date of each user based on the extracted menstrual data of each user. Then, it calculates the menstrual cycle of each user (S109-1). If there are three or more menstrual start dates, the average of these is used as the menstrual cycle of that user.

The maximum severity day prediction model generation function 155 runs a processing loop for each perimenstrual symptom (S109-2, S109-3). That is, the maximum severity day prediction model generation function 155 extracts, for each symptom, life log data of users who have developed that symptom from the menstrual data stored in the data storage function 120 (S109-3). Symptoms include headaches, abdominal pain, etc., and some users may develop both headaches and abdominal pain, or may develop headaches but no abdominal pain.

The maximum severity day prediction model generation function 155 calculates, for each user, the difference in number of days D2 between the menstrual start date and the onset date with the maximum severity closest to the menstrual start date (S109-4).

The maximum severity day prediction model generation function 155 uses physical condition data, basic constitution data, weather data, menstruation start date, and menstrual cycle as feature quantities, and the difference in number of days D2 as the objective variable, and uses any machine learning method to generate an onset date prediction model for predicting the difference in number of days between the start of menstruation and the onset date closest to the menstruation start date when the severity of the symptom will be at its maximum. This maximum severity day prediction model is a prediction model that predicts the day when the severity of the symptom determined in S109-2 will be at its maximum.

The maximum severity day prediction model generation function 155 performs this processing for all symptoms (headache, stomachache, etc.) and generates a maximum severity day prediction model for all symptoms (S109-6).

Next, a prediction process using the maximum severity day prediction model will be described. FIG. 18 is a flowchart showing the prediction process of the day when the severity of one symptom is at its maximum (maximum severity day) by the maximum severity day prediction function 165. The maximum severity day prediction function 165 applies the life log data of one user to the maximum severity day prediction model corresponding to one symptom to calculate a prediction value (S110-1). The maximum severity day prediction function 165 converts the prediction value into the onset date (S110-2). This prediction value is the difference between the menstruation start date and the day when the severity is at its maximum, which is closest to the menstruation start date. The maximum severity day prediction function 165 predicts the menstruation start date from the registered menstruation start date and the menstrual cycle calculated from the menstruation start date, and can use this to find the day when the severity of the symptom is at its maximum. The result notification function 170 notifies the user of the day when the severity of the symptom is at its maximum (S110-3). This is a notification process of the day when the severity of one symptom is at its maximum. This process is repeated for all symptoms. The user may also specify any symptom and have the system predict the day when the severity of that symptom alone will be at its maximum.

Next, the effects of the data collection and analysis device 100 of the present disclosure will be described. The data collection and analysis device 100 of the present disclosure includes a data storage function 120 that functions as a memory unit that stores life log data, which is information about the physical health condition of a user and information that affects the health, and a prediction function that functions as a symptom prediction unit that predicts symptoms of a user's health condition at a specific reference time based on the life log data.

This prediction function is at least one of the onset date prediction function 140, the onset cycle prediction function 145, the severity prediction function 160, or the maximum severity date prediction function 165.

With this configuration, it is possible to accurately and easily predict symptoms in a peripheral period of a user's health condition at a specified reference time based on the user's life log data. The life log data is information that affects the user's health condition and health, for example, information about the body of an individual user or information that affects the body, so that it is possible to accurately predict symptoms in that peripheral period according to the user's characteristics. This life log data includes at least one of the user's blood pressure, weight, activity level, body temperature, sleep time, medication data (whether or not the user is taking medication), menstruation start date, and place of residence. By using this information about the body or information that affects the body, it is possible to predict symptoms in the peripheral period of an individual user's health condition at a specified reference time.

In addition, in the present disclosure, peripheral symptoms at a specific reference time of health status are peripheral symptoms at the start of menstruation. While the cycle of the menstrual start date, etc. does not vary much from person to person and is easy to understand, symptoms in the peripheral period do vary from person to person, and there is a demand to know these in advance.

In this disclosure, symptoms that occur particularly around the start of menstruation are considered to be abdominal pain, headache, back pain, feeling unwell, irritability, bleeding, breast bloating, vaginal discharge, rough skin, or fatigue. These symptoms vary from person to person, and their periodicity may not be clearly defined.

In this disclosure, it is possible to predict these symptoms from a user's life log data.

The prediction functions, onset date prediction function 140 and onset cycle prediction function 145, predict the symptom onset date, onset end date, or onset cycle from the user's life log data. In addition, the prediction functions, severity prediction function 160 and maximum severity day prediction function 165, predict the severity of the symptom or the day when the severity is at its maximum from the user's life log data.

With this configuration, it is possible to predict the onset date, end date, onset cycle, degree of severity, and date of maximum severity of abdominal pain, headache, etc. associated with menstruation from life log data.

In the data collection and analysis device 100 of the present disclosure, each prediction function (onset date prediction function 140, onset cycle prediction function 145, severity prediction function 160, and maximum severity date prediction function 165) stores a prediction model that has been trained using the user's life log data as an explanatory variable and information about peripheral symptoms at a specified reference time of the user's health condition as an objective variable. Here, the peripheral symptoms are respectively targeted by the onset date, onset end date, onset cycle, severity level, and maximum severity day.

These prediction functions can input a user's life log data into a prediction model to predict information about the user's peri-menstrual symptoms at a given baseline time point, such as symptoms at the start of menstruation.

In the present disclosure, the onset date prediction model or maximum severity date prediction model is trained using difference information between the reference time and the date and time related to the symptoms as the objective variable. In other words, the model is trained using the difference in number of days between the reference time, which is the start date of menstruation, and the date and time related to the symptoms, which is the onset date, the end date of onset, or the maximum severity date, as the objective variable.

The onset date, end date, and date of maximum severity are correlated with the start date of menstruation, and by utilizing this, it is possible to predict the onset and end date of each symptom.

Each prediction function (onset date prediction function 140, onset cycle prediction function 145, severity prediction function 160, and maximum severity day prediction function 165) stores multiple prediction models learned for each symptom. The prediction function selects a prediction model corresponding to the symptom from the multiple prediction models and makes a prediction. Providing a prediction model for each symptom enables accurate prediction.

The data collection and analysis device 100 of the present disclosure further includes a prediction model generation function that learns and generates a prediction model using the user's life log data as explanatory variables and information about peripheral symptoms at a specified reference time of the user's health condition (onset date, onset end date, onset cycle, severity, and maximum severity date) as objective variables. This prediction model generation function is at least one of an onset date prediction model generation function 130, an onset cycle prediction model generation function 135, a severity prediction model generation function 150, and a maximum severity date prediction model generation function 155.

The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and directly or indirectly connected (e.g., using wires, wirelessly, etc.). The functional blocks may be realized by combining the one device or the multiple devices with software.

Functions include, but are not limited to, judgement, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs the transmission function is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on the method of realization for either of these.

For example, the data collection and analysis device 100 according to an embodiment of the present disclosure may function as a computer that performs processing of the health management method of the present disclosure. FIG. 19 is a diagram showing an example of the hardware configuration of the data collection and analysis device 100 according to an embodiment of the present disclosure. The above-mentioned data collection and analysis device 100 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

In the following description, the term "apparatus" may be interpreted as a circuit, device, unit, etc. The hardware configuration of the data collection and analysis device 100 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

Each function of the data collection and analysis device 100 is realized by loading a specific software (program) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communications via the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned data extraction function 125, onset date prediction model generation function 130, onset date prediction function 140, etc. may be realized by the processor 1001.

The processor 1001 also reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the programs, programs that cause a computer to execute at least a part of the operations described in the above-mentioned embodiment are used. For example, the data extraction function 125, the onset date prediction model generation function 130, and the onset date prediction function 140 may be realized by a control program stored in the memory 1002 and operating in the processor 1001, and other functional blocks may be similarly realized. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and may be composed of at least one of, for example, a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), a RAM (Random Access Memory), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a health management method according to one embodiment of the present disclosure.

Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmission/reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., to realize, for example, at least one of Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, the above-mentioned data acquisition function 110 may be realized by the communication device 1004.

The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one configuration (e.g., a touch panel).

In addition, each device such as the processor 1001 and memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

The data collection and analysis device 100 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

The notification of information is not limited to the aspects/embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB))), other signals, or a combination of these. In addition, the RRC signaling may be called an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, etc.

Each aspect/embodiment described in this disclosure may be applied to at least one of systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), or other suitable systems, and next generation systems enhanced based on these. Additionally, multiple systems may be combined (for example, a combination of at least one of LTE and LTE-A with 5G, etc.).

The processing steps, sequences, flow charts, etc. of each aspect/embodiment described in this disclosure may be reordered unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

Information, etc. may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer). It may also be input/output via multiple network nodes.

The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

The determination may be based on a value represented by one bit (0 or 1), a Boolean (true or false) value, or a comparison of numerical values (e.g., with a predetermined value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or switched depending on the execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended as an illustrative example and does not have any limiting meaning on the present disclosure.

Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

Software, instructions, information, etc. may also be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and/or wireless technologies (such as infrared, microwave), then these wired and/or wireless technologies are included within the definition of a transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

Note that the terms described in this disclosure and the terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and the symbol may be a signal (signaling). Also, the signal may be a message. Also, the component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

In addition, the information, parameters, etc. described in this disclosure may be represented using absolute values, may be represented using relative values from a predetermined value, or may be represented using other corresponding information. For example, radio resources may be indicated by an index.

The names used for the above-mentioned parameters are not limiting in any way. Moreover, the formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not limiting in any way.

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Additionally, "judgment" and "decision" can include considering resolving, selecting, choosing, establishing, comparing, etc., to have been "judged" or "decided." In other words, "judgment" and "decision" can include considering some action to have been "judged" or "decided." Additionally, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using designations such as "first," "second," etc., used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must precede the second element in some way.

When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Additionally, the term "or," as used in this disclosure, is not intended to be an exclusive or.

In this disclosure, where articles have been added through translation, such as a, an, and the in English, this disclosure may include that the nouns following these articles are in the plural form.

In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

20...measuring device, 30...measurement value transfer device, 40...physical condition registration device, 50...basic constitution registration device, 60...menstrual information registration device, 70...weather information acquisition device, 100...data collection and analysis device, 90...network, 31...data acquisition function, 32...data transfer function, 33...measuring device authentication function, 34...user authentication function, 41...data registration function, 42...data transfer function, 43...user authentication function, 51...data registration function, 52...data transfer function, 61...data registration recording function, 62...data transfer function, 71...data acquisition function, 72...data transfer function, 110...data acquisition function, 120...data storage function, 130...onset date prediction model generation function, 135...onset cycle prediction model generation function, 140...onset date prediction function, 145...onset cycle prediction function, 150...severity prediction model generation function, 155...maximum severity day prediction model generation function, 160...severity prediction function, 165...maximum severity day prediction function, 170...result notification function.

Claims (4)

A storage unit that stores life log data indicating information indicating a menstrual state of a user's body or information affecting menstruation;
a prediction model storage unit that stores a prediction model learned using the user's physical condition data, the user's basic constitution data, weather data, a predetermined reference time of the user's menstrual state, and the user's menstrual cycle as explanatory variables from among the user's life log data, and using the difference in number of days between the predetermined reference time of the menstrual state and the onset date of peripheral symptoms indicating a predetermined period before and after the predetermined reference time of the user's menstrual state as an objective variable;
A symptom prediction unit that predicts an onset date of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of a menstrual state of a user based on the prediction model;
Equipped with
The symptom prediction unit inputs the life log data of the one user into the prediction model and predicts an onset date of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of the menstrual state of the one user.
Health management device. A storage unit that stores life log data indicating information indicating a menstrual state of a user's body or information affecting menstruation;
a prediction model storage unit that stores a prediction model learned using the user's physical condition data, the user's basic constitution data, weather data, a predetermined reference time of the user's menstrual state, and the user's menstrual cycle as explanatory variables, and using the difference in number of days between the end date of the peripheral symptoms at the predetermined reference time of the user's menstrual state and the predetermined reference time of the menstrual state as a response variable, from among the user's life log data;
A symptom prediction unit that predicts an end date of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of a menstrual state of a user based on the prediction model;
Equipped with
The symptom prediction unit inputs the life log data of the one user into the prediction model to predict an end date of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of the menstrual state of the one user.
Health management device. A storage unit that stores life log data indicating information indicating a menstrual state of a user's body or information affecting menstruation;
a prediction model storage unit that stores a prediction model learned using the user's physical condition data, the user's basic constitution data, weather data, a predetermined reference time of the user's menstrual state, and the user's menstrual cycle as explanatory variables and the onset cycle of symptoms in the peripheral period of the user's menstrual state at the predetermined reference time as a response variable, among the user's life log data;
A symptom prediction unit that predicts an onset cycle of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of a menstrual state of a user based on the prediction model;
Equipped with
The symptom prediction unit inputs the life log data of the one user into the prediction model and predicts an onset cycle of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of the menstrual state of the one user.
Health management device. A storage unit that stores life log data indicating information indicating a menstrual state of a user's body or information affecting menstruation;
a prediction model storage unit that stores a prediction model learned using explanatory variables including physical condition data of the user, basic constitution data of the user, weather data, a predetermined reference time of the menstrual state of the user, and the menstrual cycle of the user from among the life log data of the user, and a target variable including a difference in number of days between a predetermined reference time of the menstrual state of the user and the day closest to the reference time when the severity of symptoms is at its maximum;
A symptom prediction unit that predicts a day when the severity of a peripheral symptom, which indicates a predetermined period before and after a predetermined reference time of a menstrual state of a user, will be maximum based on the prediction model;
Equipped with
The symptom prediction unit inputs the life log data of the one user into the prediction model and predicts a day when the severity of a peripheral symptom indicating a predetermined period before and after a predetermined reference time of the menstrual state of the one user will be maximum.
Health management device.

Images