JP2006244018A - Individual health promotion support method, and system therefor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an individual health promotion support method capable of exhibiting inherent nutritional care information and health food suitable for a system user, based on medical examination information of the system user and nutrition ingestion information analyzed automatically, and capable of confirming consecutively an effect in execution of health promotion based on the nutritional care information and the health food, and a system therefor. <P>SOLUTION: This method is an individual health promotion support method capable of exhibiting the nutritional care information and the health food suitable for a person of executing the health promotion, based on the medical examination information of the person of executing the health promotion and meal ingestion information thereof. The meal ingestion information is transmitted to a nutrition care server as an image with a meal content photographed by a mobile terminal such as a cellular phone provided with a photographing means, via the Internet, nutrients are analyzed automatically, and the effect of executing the health promotion based on the exhibited nutritional care information and the health food is consecutively confirmed by data-analyzing time-serially daily health information in the person of executing the health promotion. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a health promotion support method and system for presenting nutritional management information and health food useful for the system user to promote health based on health diagnosis information and meal intake information of the system user.

  Despite being the most fundamental and important factor in promoting personal health, there are surprisingly few occasions where proper nutritional management is performed in daily diets except in hospitals and other facilities. The reason is that it has become difficult to judge how much nutrients are necessary to maintain and improve health due to the variety of recent meal menus. Under such circumstances, many health foods called so-called supplements are on the market, and there are cases where they are consumed without the information necessary for daily nutritional management of individuals.

    On the other hand, information on personal health can be obtained through regular health checkups and medical checkups, but it cannot be said that such information is also utilized in daily life. Therefore, recently, a system that supports daily health management of individuals and a system that supports nutrition management have been proposed. For example, in Non-Patent Document 1, when dietary content of a person who is worried about diabetes is photographed with a camera of a portable terminal and the video data is transmitted to a service site via the Internet, a dietitian determines the content of the diet and the user of the system A service that advises is disclosed.

“A trial of image analysis of food consumption using a portable information terminal with a camera” Diabetes, Vol. 46, No. 2, p.168, 2003

  However, the amount of necessary nutrients is considered to vary from individual to individual depending on the living environment and constitution, and as a nutrition management support service, it is necessary to present nutrition management information and health food suitable for each individual. In addition, food intake requires information over a period of time as a lifestyle habit, and as the number of users of the system increases, there is a limit to manual analysis. Furthermore, when the system user intends to promote health based on the presentation of nutritional management information and health food, it is considered that the willingness of the system user to promote health is enhanced by continuously confirming the implementation effect.

  Accordingly, the problem of the present invention is to present unique nutrition management information and health food suitable for the system user from the system user's health diagnosis information and automatically analyzed nutrition intake information. To provide an individual health promotion support method and system capable of continuously confirming the effect of health promotion based on the presentation of health foods.

  The personal health promotion support method and system according to the present invention made to solve the above-described problems are nutrition management information suitable for a person who performs health promotion based on health diagnosis information and dietary intake information of the person who performs health promotion. And a personal health promotion support method for presenting health foods, wherein the meal intake information is transmitted to the nutrition management server via the Internet as an image of meal contents taken by a portable terminal such as a mobile phone equipped with a photographing means, The nutrient amount is automatically analyzed by a computer, and further provided with means for continuously confirming the effect of health promotion based on the presented nutrition management information and health food from the daily health information of the person who performs the health promotion. And

  By using the personal health promotion support method and system according to the present invention, the system user can know nutritional management information and health foods suitable for his / her living environment and constitution, and health based on such information. The effect of the promotion can be confirmed continuously.

  FIG. 1 is a diagram showing the concept of the personal health promotion support method and system of the present invention. Users of this system first entrust the management of their own health check data to a service provider who operates the system. The system user's health checkup data is stored in a health checkup database of the nutrition management server, and is referred to in order to find out nutrition management information and health food suitable for the system user from the system user's meal intake information.

  The system user captures the contents of daily meals with a mobile phone camera and transmits it to the nutrition management server as video data. At this time, one or more reference objects having known sizes, colors, and shapes are simultaneously photographed (see FIG. 2). The video data of these reference objects serves as a reference for estimating the name of the food and its quantity by extracting features such as the size, color, and shape of the subject from the meal content video. When a system user captures meal contents with a camera of a mobile terminal such as a mobile phone, the distance to the subject, the angle, the amount of light, etc. are not constant, and it is difficult to estimate the food name and its amount without a reference object. Once the name of the food and its amount are estimated, the amount of nutrients consumed can be calculated based on that. The analysis of the nutrient amount from the meal intake information is performed for a certain period, and the information is accumulated in the nutrient intake database of the nutrition management server.

  As the next step, the system user's nutrition intake data accumulated in the nutrition intake database is collated with the system user's health diagnosis data accumulated in the medical examination database, so that the system user can improve their health. Nutritional management information and health foods are determined and stored in the nutritional management information / health food database. Such information is notified to a portable terminal such as a cellular phone of the system user.

  When a system user implements health promotion based on this information, the system user confirms the effect by ingesting one or more health data items representing the biometric information of the system user and the presented health food. Daily health information consisting of one or more life data items representing life information including health promotion implementation items, etc. is transmitted to a health management server using a mobile terminal such as a mobile phone. These pieces of information are stored in the health / life database and analyzed by the following algorithm (see FIG. 3).

Let p _n be the data on day _n of a health data item and e _{i be the} data on day _i of a life data item. The data of some days before n days and i days before is defined as p _m , e _j , for example, and the following quantities are defined.
Δp _nm = p _n -p _m (1)
e ^t _ij = e _i + e _i-1 + ・ ・ ・ + e _j (2)
e _ij = (e _i + e _i-1 + ... + e _j ) / (i-j + 1) (3)
Here, Δp _nm is a change in health data in an arbitrary period. Dividing this by any given period gives the rate of change in health data. e ^t _ij is an addition (simple addition) value of life data in an arbitrary period, and e _ij is an average (simple average) value of life data in an arbitrary period.
The days n and i are generally not the same day, but a delay period s is defined as shown in FIG. Further, the arbitrary periods nm and ij are not necessarily the same period. Next, using arbitrary periods nm and ij and delay period s as parameters, changing n and i based on a large amount of time-series data, the time-series correlation between Δp _nm and e ^t _ij or e _ij is observed. (See scatter diagram in FIG. 3). Here, e ^t _ij is the case with the meaning of some days of the addition of life data item, when the average of several days has a meaning, to adopt the e _ij. At this time, the correlation coefficient changes depending on the values of the arbitrary period nm, ij, and delay period s, so find the combination of nm, ij, s that shows the maximum correlation (nm) _max , (ij) _max , s _max . The larger the (nm) _max and (ij) _max , the longer the long-term data of the life data item will have a greater effect on the current value of the health data item, and the smaller the data in the short term of the life data item, the health data. This will greatly affect the current value of the item. In addition, the larger the s _max , the later the influence of the life data item appears in the health data item data, and the smaller the s _max , the sooner the influence of the life data item is reflected in the health data item data. Next, based on the values of (ij) _max and s _max , e ^t _ij or e _ij is calculated for one or more life data items, these are used as input variables, and p _n is used as a target variable, and a decision tree generation algorithm To generate a decision tree. Furthermore, based on this decision tree, a correlation rule between health data items and life data items is extracted. Here, the life data items include health promotion implementation items such as the intake of health food presented from the nutrition management server, and the effect of the health promotion implementation is expressed as a correlation rule with the health data items.

  Here, life data items are not limited to health promotion implementation items based on presentation of nutrition management information and health foods suitable for system users. This is because it is necessary to extract the correlation between health data items and life data items comprehensively.

  Examples of the present invention will be described below. It was pointed out that the system user in the present example was anemic at the time of the medical examination and the blood pressure was slightly high. The meal contents taken by the mobile phone camera for about one month were transmitted as an image to the nutrition management server, and the image data was analyzed. Here, in the meal content image transmitted from the system user, three cubes each having a side length of 2 cm and having three primary colors of red, blue, and green are simultaneously photographed as reference objects. These reference objects are distributed to system users in advance by the system service provider. Here, the video data of the meal content was analyzed by referring to the video data of the reference object and judging the distance to the subject (meal content), the angle, the color and shape of the subject. For the analysis of specific video data to estimate the food name, color analysis and texture analysis are performed from many video data with known food names, and the neural network using the color feature and texture feature as learning data The method of was used. As a result of the analysis, iron was slightly lacking as a nutrient, but no factor was found to increase blood pressure. Therefore, the intake of foods containing a lot of iron and supplements that have the effect of lowering blood pressure were presented on the mobile phone of system users as health promotion items.

System users have started taking foods that contain high amounts of iron and supplements that are considered to have antihypertensive effects to improve health. In this embodiment, in order to confirm the effect of supplement intake, which can be said to be relatively expensive, the system user uses blood pressure as a health data item, supplement intake as a life data item, calories consumed by exercise, alcohol intake, sleep Time, depth of sleep, and stress were selected, and daily data was sent from the mobile phone to the health management server and stored in the health / life database.

From the health / life database, data for about 3 months of system users' minimum blood pressure, supplement intake, calories consumed by exercise, alcohol intake, sleep time, depth of sleep, and stress is taken into the health management server, A decision tree is generated by time series data analysis by algorithm. Here, a decision tree was generated with supplement intake representing life information, calorie consumption due to exercise, alcohol intake, sleep time, and stress as input variable items, and minimum blood pressure representing biological information as target variable items. Since the minimum blood pressure is numerical data, the target variable is divided into three symbol values of “high”, “intermediate”, and “low” depending on the size of the data value of the minimum blood pressure. The input variables actually used are as follows. The depth of sleep was treated as a data item that weights sleep time.

(1) Supplement intake:
The simple addition value of the data from the day before the blood pressure measurement day to 5 days before showed the maximum correlation with the minimum blood pressure. This 5-day simple addition value was displayed as supplement intake 5 and used as an input variable.
(2) Calories burned by exercise:
The simple addition value of the data on the day before and 2 days before the blood pressure measurement day showed the maximum correlation with the minimum blood pressure value. This added value was displayed as total calorie consumption 2 and used as an input variable.

(3) Alcohol intake:
The added value of the data 2 days before and 3 days before the blood pressure measurement day showed the maximum correlation with the minimum blood pressure value. In this example, the alcohol intake is expressed by symbol values of five levels of 1 to 5 (1 is the largest and 5 is the smallest), so the reciprocal of the number representing the level is used as data. For example, when 2 days are 3 and 4, the alcohol intake is 1/3 + 1/4 = 0.58. This added value was displayed as alcohol intake 2 and used as an input variable.

(4) Sleep time:
The weighted addition value of the data from the day before the blood pressure measurement day to 5 days before showed the maximum correlation with the minimum blood pressure value. The weight here is due to the depth of sleep. In this example, the depth of sleep is expressed by three levels of symbol values from 1 to 3 (1. sound, 2. slightly shallow, 3. couldn't sleep well). Weighted. Specifically, the sleep time of the day was divided by the square root of the number indicating the depth of sleep. For example, if the sleep time is 7 hours but the sleep is slightly shallow, it is set to 7 / √2 hours. This 5-day weighted addition value was displayed as sleep time 5 and used as an input variable.

(5) Stress:
The reciprocal of the average value of the data from the previous day to the third day before the blood pressure measurement day showed the maximum correlation with the minimum blood pressure value. In this example, the stress is expressed by symbol values in three stages (1 is high, 2. normal, 3. low) as specified by the system user, so the inverse of the average value is taken. For example, when 3 days is (2. normal, 3. less, 3. less), stress = 1 / ((2 + 3 + 3) / 3) = 0.38. This value was displayed as stress 3 and used as an input variable.

The correlation rule between the minimum blood pressure extracted from the decision tree obtained here and the life data item is shown below. Other lifestyle data items other than supplement intake are included, but all of them suggest a correlation between supplement intake and a decrease in minimum blood pressure, confirming the effect of health promotion.

(1) If the total calorie consumption 2 is 633 kcal or more and the supplement intake 5 is 6 g or more, the minimum blood pressure tends to be low.
(2) If the alcohol intake is 0.58 or less and the supplement intake 5 is 6 g or more, the minimum blood pressure tends to be low.
(3) If the sleep time 5 is 25.1 hours or more and the supplement intake 5 is 6 g or more, the minimum blood pressure tends to be low.

In this implementation, in order to confirm the effect of health promotion implementation, a decision tree is generated with health data items as target variables and life data items including health promotion implementation items as input variables. Although the association rules are extracted, it is possible to analogize the extraction of the association rules between the health data items and the life data items by time series association rule analysis using the data set of the health data items and the life data items as a time series transaction. .

It is a figure which shows the concept of the personal health improvement support method and its system of this invention. It is a figure which shows the method of the personal health improvement support method of this invention, and the method of the meal intake information acquisition in the system. It is a figure which shows the algorithm which confirms the effect of the health promotion implementation in the personal health promotion support method and its system of this invention.

Explanation of symbols

1 Personal health promotion support service provider 2 System user 3 Nutrition management server 4 Health management server 5 Health checkup database 6 Nutrition intake database 7 Nutrition management information / health food database 8 Health / life database 9 Mobile phone 10 Meal contents 11 Reference object

Claims (7)

  A personal health promotion support method and system for presenting nutritional management information and health food suitable for a person performing health promotion based on health checkup information and dietary intake information of a person performing health promotion, the dietary intake information being A personal health promotion support method and system thereof, wherein an image of meals taken by a portable terminal such as a cellular phone provided with photographing means is transmitted to the nutrition management server via the Internet.   The image of meal content captured by a portable terminal such as a mobile phone equipped with the photographing means is processed by the nutrition management server to estimate the name of the food and its amount, and the nutrients and amount contained in the meal The personal health promotion support method and system according to claim 1, wherein:   2. One or more reference objects having a known size, color, and shape are simultaneously photographed when photographing meal contents with a portable terminal such as a cellular phone equipped with the photographing means. Item 3. A personal health promotion support method and system according to Item 2. The nutrition management information and health food suitable for the person who promotes health are presented to a portable terminal such as a mobile phone of the person who performs the health promotion via the Internet. Item 4. A personal health promotion support method and system according to Item 3. The health food presenting the effect of health promotion based on the presentation of nutrition management information and health food suitable for the person performing health promotion as one or more health data items representing the biological information of the person performing health promotion The personal health promotion according to any one of claims 1 to 4, wherein the health information is extracted from daily time-series health information composed of one or more life data items representing life information including health promotion implementation items such as ingestion of food. Support method and system thereof.   The effect of the health promotion implementation represents life information including health promotion implementation items such as the intake amount of the presented health food, with one or more health data items representing the biological information of the person performing the health promotion as a target variable. By generating a decision tree using one or more life data items as input variables, the decision tree is extracted as a correlation rule between health data items and life data items including health promotion implementation items such as intake of the health food. The personal health promotion support method and system according to claim 5.   The effect of the health promotion implementation is that one or more life data representing life information including one or more health data items representing the biological information of the person who performs the health promotion and health promotion implementation items such as intake of the presented health food. By extracting a data set of data items as a time-series transaction and performing a time-series correlation rule analysis, it is extracted as a correlation rule between health data items and life data items including health promotion items such as intake of the health food. The personal health promotion support method and system according to claim 5.

Images