JP2021110699A - Device, system, and method for generating recommended walking information and computer program - Google Patents

Abstract

To give a support to a user so that the user can walk properly when the user is not wearing a sensor.SOLUTION: A recommended walking information generation device includes: a proper walking amount storing unit for storing proper walking amount information showing a walking amount per day recommended to improve health, in relation to personal attributes; and a personal proper walking amount estimation unit for estimating recommended walking amount information showing a walking amount per day recommended to improve the health of the user on the basis of the proper walking information related to a personal attribute responding to the personal attribute of the user.SELECTED DRAWING: Figure 1

Description

The present invention relates to a recommended walking information generator, a recommended walking information providing system, a recommended walking information generation method, and a computer program.

Conventionally, for example, Patent Documents 1 and 2 are known as techniques for supporting a person's walking movement. In the prior art described in Patent Document 1, the walking information of a pedestrian is measured by a sensor attached to the waist or abdomen of the pedestrian, and the measured walking information acts on the pedestrian's arm so as to approach a target value. Controls the equipment to be worn. In the prior art described in Patent Document 2, the walking speed and heart rate of the user are acquired by the acceleration sensor and the heart rate sensor attached to the user, and the walking speed and the heart rate are used to obtain the user. Estimates the maximum oxygen uptake of.

Japanese Unexamined Patent Publication No. 2019-107471 Japanese Unexamined Patent Publication No. 2018-158087

However, the above-mentioned conventional device has a problem that the user has to wear the sensor and it is difficult for the person who finds it troublesome to wear the sensor to use the device.

The present invention has been made in consideration of such circumstances, and an object of the present invention is to provide the user with appropriate walking movement support even if the user does not wear a sensor. ..

(1) One aspect of the present invention is an appropriate walking amount storage unit that stores appropriate walking amount information indicating the daily walking amount recommended for health promotion in association with personal attributes, and an individual user. Based on the appropriate walking amount information associated with the personal attribute corresponding to the attribute, the personal appropriate walking amount that estimates the recommended walking amount information indicating the daily walking amount recommended for improving the health of the user. It is a recommended walking information generator including an estimation unit.
(2) One aspect of the present invention is the recommended walking information generator according to (1) above, wherein the personal attribute includes at least one of walking speed and walking posture.
(3) In one aspect of the present invention, the appropriate walking amount storage unit stores the appropriate walking amount information for each road attribute, and the personal appropriate walking amount estimating unit stores the recommended walking amount information for each road attribute. It is a recommended walking information generator according to any one of (1) and (2) above.
(4) One aspect of the present invention is based on a road information storage unit that stores road information including road attributes of each road, road attributes of candidate roads on which the user walks, and the recommended walking amount information. The recommended walking information generation device according to the above (3) further includes a route guide unit that generates recommended walking route information indicating a walking route recommended to the user.
(5) One aspect of the present invention is a collaborator sensor information storage unit that stores position information, acceleration information, and vital information acquired by a sensor carried by a data collection collaborator in association with the acquisition time, and the collaborator sensor. An exercise load estimation unit that estimates the exercise load of the data collection collaborator based on the information stored in the information storage unit, and a personal attribute storage that stores collaborator personal attribute information indicating the personal attributes of the data collection collaborator. A unit and an appropriate walking amount calculation unit that calculates the daily walking amount recommended for health promotion for each individual attribute based on the personal attributes and exercise load of the data collection collaborator are further provided. This is the recommended walking information generator according to either (1) or (2) above.
(6) One aspect of the present invention is a collaborator sensor information storage unit that stores position information, acceleration information, and vital information acquired by a sensor carried by a data collection collaborator in association with the acquisition time, and the collaborator sensor. An exercise load estimation unit that estimates the exercise load of the data collection collaborator based on the information stored in the information storage unit, and a personal attribute storage that stores collaborator personal attribute information indicating the personal attributes of the data collection collaborator. Based on the personal attributes of the department and the data collection collaborators, the road attributes of the roads used, and the exercise load, the recommended daily walking amount for health promotion is calculated for each personal attribute and each road attribute. The recommended walking information generation device according to any one of (3) or (4) above, further comprising an appropriate walking amount calculation unit.
(7) One aspect of the present invention pays the data collection cooperator according to at least one of the disclosure level of the personal attribute of the data collection cooperator and the walking amount of the data collection cooperator carrying the sensor. The recommended walking information generation device according to any one of (5) or (6) above, further comprising a consideration calculation unit for calculating consideration.

(8) One aspect of the present invention includes the recommended walking information generator according to any one of (5) to (7) above, and various sensors for acquiring position information, acceleration information, and vital information, and the sensors acquire the information. A user of a data collection collaborator's mobile communication terminal that transmits the position information, acceleration information, and vital information to the recommended walking information generator and a recommended walking information providing service that receives recommended walking information from the recommended walking information generator. It is a recommended walking information providing system equipped with a communication terminal of.

(9) In one aspect of the present invention, the recommended walking information generator converts appropriate walking amount information indicating the daily walking amount recommended for health promotion into an appropriate walking amount storage unit in association with personal attributes. The appropriate walking amount storage step to be stored and the recommended walking information generator are recommended for improving the health of the user based on the appropriate walking amount information associated with the personal attribute corresponding to the user's personal attribute. It is a recommended walking information generation method including a personal appropriate walking amount estimation step for estimating recommended walking amount information indicating the walking amount per day to be performed.

(10) One aspect of the present invention is an appropriate walking in which an appropriate walking amount information indicating the daily walking amount recommended for health promotion is stored in an appropriate walking amount storage unit in association with personal attributes. Based on the amount storage step and the appropriate walking amount information associated with the personal attribute corresponding to the user's personal attribute, the recommended walking indicating the recommended daily walking amount for improving the health of the user. It is a computer program for executing a personal appropriate walking amount estimation step for estimating amount information.

According to the present invention, it is possible to obtain the effect of providing the user with appropriate walking motion support even if the user does not wear the sensor.

It is a block diagram which shows the configuration example of the recommended walking information provision system which concerns on one Embodiment. It is a figure which shows the structural example of the appropriate walking amount storage part which concerns on one Embodiment. It is a flow chart for demonstrating Example 1 of the appropriate walking amount calculation part which concerns on one Embodiment. It is a flow chart for demonstrating Example 1 of the appropriate walking amount calculation part which concerns on one Embodiment. It is a flow chart for demonstrating Example 2 of the appropriate walking amount calculation part which concerns on one Embodiment. It is a flow chart for demonstrating Example 2 of the appropriate walking amount calculation part which concerns on one Embodiment. It is a flow chart which shows the example of the procedure of the recommended walking information generation method which concerns on one Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a configuration example of a recommended walking information providing system according to an embodiment. The recommended walking information providing system 1 shown in FIG. 1 includes a collaborator terminal group 10, a user terminal group 20, and a recommended walking information generation device 30. The recommended walking information providing system 1 provides recommended walking information to a user of the recommended walking information providing service (hereinafter, simply referred to as a user). The recommended walking information is information related to walking and is recommended information for improving the health of the user.

[Cooperator terminal]
The collaborator terminal group 10 is composed of a mobile communication terminal (hereinafter, referred to as a collaborator terminal) such as a smartphone carried by a data collection collaborator. The collaborator terminal includes a position sensor 110, an acceleration sensor 111, and a vital sensor 112. The position sensor 110 acquires position information indicating the current position by using a positioning system such as GPS (Global Positioning System). The acceleration sensor 111 detects the left-right and front-back tilts and acquires the detected value (acceleration information). Acceleration information is used to measure the number of steps and walking posture of data collection cooperators. The vital sensor 112 measures the biological information of the data collection collaborator. The biological information is, for example, body temperature, blood pressure, heart rate, and the like. The vital sensor 112 is, for example, a heart rate sensor and measures a heart rate.

The collaborator terminal performs wireless communication with the recommended walking information generator 30. The collaborator terminal transmits the position information, acceleration information, and vital information acquired by each of the sensors 110, 111, and 112 to the recommended walking information generation device 30 together with the acquisition time of the information.

The collaborator terminal is, for example, a wristwatch-type mobile communication terminal having sensors 110, 111, 112 built-in, and the wristwatch-type mobile communication terminal may be worn on the arm of a data collection collaborator. .. The sensors 110, 111, 112 may be built in the main body of the cooperator terminal, or may be sensors attached to the main body of the cooperator terminal.

The data collection collaborator is a person who has consented to provide his / her own predetermined information (individual attribute (individual attribute), position information, acceleration information, vital information, etc.) to the recommended walking information providing system 1.

Data collection collaborators are categorized by personal attributes. Personal attributes include, for example, gender, age, physique, occupation, athletic ability, and health status. In the example of FIG. 1, the data collection collaborators 11-1 to m are in their thirties, their occupation is a salaryman, and their gender is male. Data collection collaborators 12-1 to n are teenagers, occupations are students, and genders are women. Data collection collaborators 13-1 to o are in their 70s, unemployed, and male in gender. The state of health is a state related to health and includes, for example, a medical condition.

[User terminal]
The user terminal group 20 is composed of communication terminals (hereinafter, referred to as user terminals) used by the user. The user terminal communicates with the recommended walking information generator 30. The user terminal may be, for example, a mobile communication terminal such as a smartphone, which performs wireless communication with the recommended walking information generation device 30. The user terminal is a terminal for receiving recommended walking information from the recommended walking information generator 30 and presenting the received recommended walking information to the user.

As an example of this embodiment, the user terminal is a mobile communication terminal such as a smartphone carried by the user, and includes a position sensor 210, an acceleration sensor 211, a destination input unit 212, and a route display unit 213. The position sensor 210 acquires position information indicating the current position by using a positioning system such as GPS. The acceleration sensor 211 detects the left-right and front-back tilts and acquires the detected value (acceleration information). Acceleration information is used to measure the number of steps and walking posture of the user. The user terminal transmits the position information and acceleration information acquired by the sensors 210 and 211 to the recommended walking information generation device 30 together with the acquisition time of the information.

In this embodiment, the position sensor 210 and the acceleration sensor 211 are not essential. Therefore, the user terminal does not have to include the position sensor 210 and the acceleration sensor 211. That is, the user does not have to wear a sensor such as a position sensor, an acceleration sensor, or a vital sensor.

The destination input unit 212 inputs a destination that the user plans to go by walking. The destination input unit 212 includes an input interface for the user to input the destination. In addition, the destination input unit 212 may input the departure place where the user starts walking. For example, the destination input unit 212 is provided with an input interface for the user to input the departure place, or the departure place setting unit sets the current position indicated in the position information acquired by the position sensor 210 as the departure place. May be provided. The destination input unit 212 notifies the recommended walking information generator 30 of the destination and the departure place.

The route display unit 213 displays the recommended walking information distributed from the recommended walking information generation device 30 to the user terminal on the display screen of the user terminal. The recommended walking information is, for example, recommended walking amount information, recommended walking route information, and the like. The recommended walking amount information is information indicating the daily walking amount recommended for improving the health of the user. The recommended walking route information is information indicating a walking route recommended to the user.

Users are categorized by personal attributes, similar to data collection collaborators. In the example of FIG. 1, the users 21-1 to p are in their thirties, their occupation is a salaryman, and their gender is male. Users 22-1 to q are teenagers, occupations are students, and genders are women. Users 23-1 to r are in their 70s, unemployed, and male in gender.

[Recommended walking information generator]
The recommended walking information generation device 30 includes a collaborator sensor information storage unit 301, a road estimation unit 302 used, an exercise load estimation unit 303, a personal attribute storage unit 304, a road information storage unit 305, and an appropriate walking amount calculation unit. It includes a 306, an appropriate walking amount storage unit 307, a consideration calculation unit 308, a user sensor information storage unit 309, a personal appropriate walking amount estimation unit 310, and a route guidance unit 311.

Each function of the recommended walking information generating device 30 is realized by executing a computer program by a CPU (Central Processing Unit) included in the recommended walking information generating device 30. The recommended walking information generation device 30 may be configured by using a general-purpose computer device, or may be configured as a dedicated hardware device. For example, the recommended walking information generator 30 may be configured by using a server computer connected to a communication network such as the Internet. Further, each function of the recommended walking information generation device 30 may be realized by cloud computing. Further, as the recommended walking information generation device 30, for example, a WWW system or the like may be used to establish a website.

The collaborator sensor information storage unit 301 uses the position information, acceleration information, and vital information received by the recommended walking information generator 30 from each collaborator terminal of the collaborator terminal group 10 as the collaborator terminal (terminal identification information of the collaborator terminal). For each (cooperator terminal ID), the information is stored in association with the acquisition time.

The road estimation unit 302 compares the position information stored in the collaborator sensor information storage unit 301 with the preset map information for each collaborator terminal to perform map matching. The road estimation unit 302 estimates the road (road used) used by the data collection collaborators based on the result of map matching. The map matching is a process of correcting the position information obtained by GPS, which may contain an error, so as to indicate the position on the road by using the map information. Map matching is used, for example, in car navigation systems.

In the road estimation unit 302, the collaborator terminal whose average value of the distance traveled per unit time is less than a predetermined threshold value is a collaborator terminal or the like in a building along the road, and the value is less than the threshold value. It may be determined that the road is not used for a certain period of time.

Further, the road estimation unit 302 determines, based on the moving speed of the cooperator terminal, whether the means of movement of the cooperator terminal using the road is walking or a vehicle such as a bicycle or a car. May be good.

The exercise load estimation unit 303 estimates the exercise load related to walking of the data collection collaborator based on the information (position information, acceleration information, vital information, acquisition time) stored in the collaborator sensor information storage unit 301. The method for estimating the exercise load related to walking (exercise load estimation calculation formula) is set in advance.
Generally, for the exercise load, for example, a method using the difference between the resting heart rate and the maximum heart rate (preliminary heart rate, Heart Rate Reserved) is known. As the exercise load, the calculation formula of the exercise load (%) when the exercise load in the exercise state which is the resting heart rate is set to 0% and the exercise load in the exercise state which is the maximum heart rate is set to 100% is It is represented by the equation (1).
Exercise load (%) = (heart rate-resting heart rate) ÷ (maximum heart rate-resting heart rate) x 100 ... (1)
In equation (1), it is not easy to measure the maximum heart rate, so an estimated value "220-age" is generally used for the maximum heart rate.
In equation (1), the exercise load (%) corresponding to each person's walking speed can be obtained by measuring the relationship between each person's walking speed (number of steps per minute) and heart rate. Then, by using health examination data and evaluating the relationship between maintenance and improvement of health and the total exercise load per week, the walking speed and the number of steps per week required for maintenance and improvement of health are evaluated. Is required.
In addition, as another method for estimating exercise load related to walking, the research result "Walking cadence (steps / min) and intensity in 21-40 year olds: CADENCE-adults" by the University of Massachusetts Amherst et al. It describes a method of calculating Mets from the number of steps per minute using METs (METs: Metabolic Equivalents), which is an index of energy consumption. In this method, it is derived that the exercise load reaches 3 METs in 100 steps per minute, and then the exercise load increases by 1 METs for every 10 steps increased in the number of steps per minute. This research result is an index that integrates 10 males and 10 females (76 in total) for the age group of 5 years from 21 to 40 years. On the other hand, in the present embodiment, the relationship between the number of steps per minute and the exercise load is personalized for each individual attribute by constantly measuring data for a large number of data collection collaborators with different personal attributes. There is expected. In addition, the "Physical Activity Standards for Health Promotion 2013" issued by the Ministry of Health, Labor and Welfare indicates the amount of physical activity required for people aged 18 to 64 to reduce the risk of developing lifestyle-related diseases. According to this, it is shown that it is desirable that the total of physical activity of 3 METs or more is "METs x exercise time (h) = 23 or more" per week. It is expected that this index will also be personalized for each individual attribute in this embodiment.

The personal attribute storage unit 304 stores collaborator personal attribute information indicating the personal attributes of the data collection collaborator. The collaborator's personal attribute information is registered in the recommended walking information generation device 30 in advance. In addition, the personal attribute storage unit 304 stores user personal attribute information indicating the user's personal attribute. The user personal attribute information is registered in the recommended walking information generation device 30 in advance.

The road information storage unit 305 stores road information including the locus of each road and road attributes. The locus of a road is geographic information (for example, latitude, longitude) indicating a start point, a passing point, and an end point of the road. The road attribute is an attribute of the road, which may affect the exercise load of a person's walking. Road attributes include, for example, the altitude and slope of the road, the structure, and the road surface condition.

The appropriate walking amount calculation unit 306 calculates the daily walking amount (number of steps) recommended for health promotion for each individual attribute based on the individual attribute and exercise load of the data collection collaborator. Furthermore, the appropriate walking amount calculation unit 306 is recommended for health promotion for each individual attribute and each road attribute based on the individual attribute of the data collection collaborator, the road attribute of the road used, and the exercise load. The amount of walking (number of steps) per day may be calculated. The appropriate walking amount calculation unit 306 outputs and stores the appropriate walking amount information indicating the daily walking amount of the calculation result in the appropriate walking amount storage unit 307 together with the personal attribute and the road attribute. The details of the appropriate walking amount calculation unit 306 will be described later.

The appropriate walking amount storage unit 307 stores appropriate walking amount information indicating the daily walking amount recommended for health promotion in association with personal attributes. Further, the appropriate walking amount storage unit 307 stores appropriate walking amount information for each road attribute. FIG. 2 shows a configuration example of an appropriate walking amount storage unit according to the present embodiment. In the example shown in FIG. 2, the appropriate walking amount storage unit 307 stores appropriate walking amount information for each individual attribute and for each road attribute.

The consideration calculation unit 308 responds to at least one of the disclosure level of the personal attributes of the data collection collaborator and the walking amount of the data collection collaborator carrying the collaborator terminals (including sensors 110, 111, 112). Calculate the consideration to be paid to the data collection collaborator. The consideration may be money, or may be something other than money such as privilege points that can be used for discounting the purchase price of goods or services.

The user sensor information storage unit 309 uses the position information and acceleration information received by the recommended walking information generator 30 from each user terminal of the user terminal group 20 as the user terminal (terminal identification information of the user terminal (user). Each terminal ID) is stored in association with the acquisition time of the information.

The personal appropriate walking amount estimation unit 310 is based on the appropriate walking amount information associated with the personal attribute corresponding to the personal attribute of the user, and the walking amount per day recommended for improving the health of the user (the walking amount per day ( Estimate the recommended walking amount information indicating the number of steps). Further, the personal appropriate walking amount estimation unit 310 may estimate the recommended walking amount information for each road attribute.

The appropriate walking amount information is associated with the personal attribute in the appropriate walking amount storage unit 307. The personal appropriate walking amount estimation unit 310 matches the personal attribute of the user personal attribute information stored in the personal attribute storage unit 304 with the personal attribute (matching target personal attribute) included in the appropriate walking amount storage unit 307. .. The personal appropriate walking amount estimation unit 310 estimates the recommended walking amount information based on the appropriate walking amount information associated with the matching target personal attribute having the highest degree of matching of the individual attributes.

Further, as illustrated in FIG. 2, when the appropriate walking amount information is associated with the personal attribute and the road attribute in the appropriate walking amount storage unit 307, the personal appropriate walking amount estimating unit 310 is an individual for each road attribute. The recommended walking amount information is estimated based on the appropriate walking amount information associated with the matching target individual attribute having the highest degree of attribute matching.

The route guidance unit 311 indicates recommended walking that indicates a recommended walking route for the user based on the road attributes of the candidate roads on which the user walks and the recommended walking amount information estimated for the user. Generate route information. The destination of the walking route is notified from the user terminal to the recommended walking information generator 30. When the recommended walking information generator 30 is notified from the user terminal, the starting point of the walking route uses the notified starting point. When the departure place is not notified from the user terminal to the recommended walking information generator 30, the position indicated by the latest position information of the user terminal stored in the user sensor information storage unit 309 is used as the departure place.

The route guidance unit 311 extracts road candidates from the starting point to the destination of the walking route based on the road locus included in the road information of the road information storage unit 305. The route guidance unit 311 acquires the road attributes of the extracted road candidates from the road information of the road information storage unit 305.

Here, a case where the recommended walking amount information is estimated for each road attribute will be described. The route guidance unit 311 matches the road attributes of the road candidates with the road attributes of the estimation target (matching target road attributes) of the recommended walking amount information for each road candidate. The route guidance unit 311 selects the recommended walking amount information of the matching target road attribute having the highest degree of matching of the road attributes for each road candidate. The route guidance unit 311 determines the road candidates to be adopted for the walking route based on the recommended walking amount information selected for each road candidate. For example, a road candidate whose walking distance satisfies the walking amount of the recommended walking amount information is a predetermined value (for example, 80%) or more is adopted as the walking route. The route guidance unit 311 generates recommended walking route information indicating a walking route that passes through a road candidate determined to be adopted as a walking route. The correspondence (conversion method) between the walking distance and the walking amount (number of steps) is set in advance. For example, the walking distance and the walking amount may be converted based on the default value of the stride length. Furthermore, the stride length may be corrected based on the personal attributes of the user.

When the recommended walking amount information is not estimated for each road attribute, the route guidance unit 311 acquires the road attribute of the road candidate for each road candidate from the road information of the road information storage unit 305. Predetermined weighting corresponding to the road attribute is performed on the recommended walking amount information of the user. The route guidance unit 311 determines the road candidates to be adopted for the walking route based on the recommended walking amount information after weighting each road candidate. For example, a road candidate whose walking distance satisfies the walking amount of the weighted recommended walking amount information is a predetermined value (for example, 80%) or more is adopted as the walking route. The route guidance unit 311 generates recommended walking route information indicating a walking route that passes through a road candidate determined to be adopted as a walking route.

Further, when the destination of the walking route is not notified from the user terminal to the recommended walking information generation device 30, the route guidance unit 311 may determine an arbitrary walking route based on the recommended walking amount information. For example, an arbitrary walking route is determined so that the ratio of satisfying the walking amount of the recommended walking amount information is a predetermined value (for example, 80%) or more.

The route guidance unit 311 transmits recommended walking information including recommended walking route information to the user terminal. The route guidance unit 311 may include the recommended walking route information and the recommended walking amount information in the recommended walking information. The recommended walking information may not include the recommended walking route information and may include the recommended walking amount information.

The route display unit 213 of the user terminal displays the recommended walking information distributed from the recommended walking information generation device 30 to the user terminal on the display screen of the user terminal. For example, the walking route indicated by the recommended walking route information is shown on the map displayed on the display screen of the user terminal. For example, the daily walking amount indicated by the recommended walking amount information is displayed on the display screen of the user terminal. Further, the walking amount for today's shortage may be calculated by the user terminal and displayed on the display screen of the user terminal with respect to the walking amount per day indicated by the recommended walking amount information.

[Appropriate walking amount calculation unit]
The appropriate walking amount calculation unit 306 will be described. In the present embodiment, an appropriate walking amount is calculated by using a machine learning model in which the relationship between individual attributes and exercise load is learned by machine learning. Furthermore, an appropriate amount of walking may be calculated using a machine learning model in which the relationship between individual attributes, road attributes, and exercise load is learned by machine learning. Hereinafter, Examples 1 and 2 of the appropriate walking amount calculation unit will be described.

[Example 1 of appropriate walking amount calculation unit]
3 and 4 are flow charts for explaining Example 1 of the appropriate walking amount calculation unit. First, the learning stage of Example 1 of the appropriate walking amount calculation unit will be described with reference to FIG. This learning stage is a stage of learning the machine learning model 3061 used in the appropriate walking amount calculation stage described later. The appropriate walking amount calculation unit 306 includes a machine learning model 3061.

(Step S101) The appropriate walking amount calculation unit 306 inputs the personal attributes of the data collection collaborators stored in the personal attribute storage unit 304 into the machine learning model 3061 as learning data.

(Step S102) As a result of inputting the personal attributes of the data collection cooperator into the machine learning model 3061, the exercise load for the personal attributes of the data collection cooperator is output from the machine learning model 3061.

(Step S103) The appropriate walking amount calculation unit 306 verifies the exercise load output from the machine learning model 3061 by using the exercise load estimated value of the data collection collaborator as teacher data (correct answer value). The exercise load estimation value of the data collection collaborator is the result estimated by the exercise load estimation unit 303. The appropriate walking amount calculation unit 306 reflects the result of the verification in the machine learning model 3061. Machine learning of the machine learning model 3061 is repeated until the result of the verification satisfies a predetermined learning end condition. The predetermined learning end condition is, for example, satisfying a predetermined correct answer rate or more or a predetermined incorrect answer rate or less, or satisfying both a predetermined correct answer rate or more and a predetermined incorrect answer rate or less. Alternatively, the predetermined learning end condition is that the number of repetitions of machine learning of the machine learning model 3061 has reached a predetermined number of times.

Next, the appropriate walking amount calculation stage of Example 1 of the appropriate walking amount calculation unit will be described with reference to FIG.
This appropriate walking amount calculation step is a step of calculating an appropriate walking amount for each individual attribute using the machine learning model 3061 that has been learned by the learning step described above. The appropriate amount of walking is the amount of walking (number of steps) per day recommended for improving health.

(Step S201) The appropriate walking amount calculation unit 306 inputs the individual attribute of the target for calculating the appropriate walking amount (hereinafter, referred to as the appropriate walking amount target individual attribute) into the machine learning model 3061. The appropriate walking amount target personal attribute is arbitrarily set in advance.

(Step S202) As a result of inputting the appropriate walking amount target individual attribute into the machine learning model 3061, the exercise load for the appropriate walking amount target individual attribute is output from the machine learning model 3061. The appropriate walking amount calculation unit 306 calculates the appropriate walking amount based on the exercise load output from the machine learning model 3061. For example, a default conversion formula for converting the exercise load into an appropriate walking amount is set in advance, and the appropriate walking amount is calculated from the exercise load using the default conversion formula. Furthermore, the appropriate walking amount of the conversion result may be corrected based on the individual attribute of the appropriate walking amount target.

(Step S203) The appropriate walking amount calculation unit 306 stores the appropriate walking amount information indicating the appropriate walking amount of the calculation result in the appropriate walking amount storage unit 307 in association with the appropriate walking amount target individual attribute.

[Example 2 of the appropriate walking amount calculation unit]
5 and 6 are flow charts for explaining Example 2 of the appropriate walking amount calculation unit. First, the learning stage of Example 2 of the appropriate walking amount calculation unit will be described with reference to FIG. This learning stage is a stage of learning the machine learning model 3062 used in the appropriate walking amount calculation stage described later. The appropriate walking amount calculation unit 306 includes a machine learning model 3062.

(Step S111) The appropriate walking amount calculation unit 306 uses the personal attributes of the data collection collaborator stored in the personal attribute storage unit 304 and the road attributes of the road used by the data collection collaborator as learning data, and is a machine learning model 3062. Enter in. The road used by the data collection collaborator is the result estimated by the road estimation unit 302. The road attribute of the road to be used is acquired from the road information of the road information storage unit 305.

(Step S112) As a result of inputting the personal attributes of the data collection cooperator and the road attributes of the road used into the machine learning model 3061, the exercise load on the personal attributes of the data collection cooperator and the road attributes of the road used is the machine learning model 3062. Is output from.

(Step S113) The appropriate walking amount calculation unit 306 verifies the exercise load output from the machine learning model 3062 by using the exercise load estimated value of the data collection collaborator as teacher data (correct answer value). The exercise load estimation value of the data collection collaborator is the result estimated by the exercise load estimation unit 303. The appropriate walking amount calculation unit 306 reflects the result of the verification in the machine learning model 3062. Machine learning of the machine learning model 3062 is repeated until the result of the verification satisfies a predetermined learning end condition. The predetermined learning end condition is, for example, satisfying a predetermined correct answer rate or more or a predetermined incorrect answer rate or less, or satisfying both a predetermined correct answer rate or more and a predetermined incorrect answer rate or less. Alternatively, the predetermined learning end condition is that the number of repetitions of machine learning of the machine learning model 3062 has reached a predetermined number of times.

Next, the appropriate walking amount calculation stage of Example 2 of the appropriate walking amount calculation unit will be described with reference to FIG.
This appropriate walking amount calculation step is a step of calculating an appropriate walking amount for each individual attribute and for each road attribute using the machine learning model 3062 that has been learned by the above-mentioned learning step. The appropriate amount of walking is the amount of walking (number of steps) per day recommended for improving health.

(Step S211) The appropriate walking amount calculation unit 306 uses the machine learning model 3062 to determine the individual attribute (the individual attribute subject to the appropriate walking amount) and the road attribute (hereinafter referred to as the road attribute subject to the appropriate walking amount) for calculating the appropriate walking amount. Enter in. The appropriate walking amount target individual attribute and the appropriate walking amount target road attribute are arbitrarily set in advance.

(Step S212) As a result of inputting the appropriate walking amount target individual attribute and the appropriate walking amount target road attribute into the machine learning model 3062, the exercise load for the appropriate walking amount target individual attribute and the appropriate walking amount target road attribute is the machine learning model 3062. Is output from. The appropriate walking amount calculation unit 306 calculates the appropriate walking amount based on the exercise load output from the machine learning model 3062. For example, a default conversion formula for converting the exercise load into an appropriate walking amount is set in advance, and the appropriate walking amount is calculated from the exercise load using the default conversion formula. Further, the appropriate walking amount of the conversion result may be corrected based on at least one of the appropriate walking amount target individual attribute and the appropriate walking amount target road attribute.

(Step S213) The appropriate walking amount calculation unit 306 associates the appropriate walking amount information indicating the appropriate walking amount of the calculation result with the appropriate walking amount target individual attribute and the appropriate walking amount target road attribute to the appropriate walking amount storage unit 307. Store it.

The above is the description of Examples 1 and 2 of the appropriate walking amount calculation unit.
As the machine learning models 3061 and 3062, for example, a neural network, a support vector machine (SVM), a decision tree, or the like may be applied.

Next, a recommended walking information generation method according to the present embodiment will be described with reference to FIG. 7. FIG. 7 is a flow chart showing an example of the procedure of the recommended walking information generation method according to the present embodiment.

(Step S11) The recommended walking information generation device 30 accepts the input of the user's personal information and the road candidate (road candidate) on which the user walks.

(Step S12) The recommended walking information generator 30 is recommended per day for improving the health of the user based on the appropriate walking amount information associated with the personal attribute corresponding to the personal attribute of the user. Estimate recommended walking amount information indicating the walking amount.

(Step S13) The recommended walking information generation device 30 is recommended to the user based on the road attributes of the candidate roads on which the user walks and the recommended walking amount information estimated for the user. Generate recommended walking route information indicating the walking route.

(Step S14) The recommended walking information generation device 30 transmits recommended walking information including recommended walking route information to the user terminal. The recommended walking information generation device 30 may include the recommended walking route information and the recommended walking amount information in the recommended walking information. The recommended walking information may not include the recommended walking route information and may include the recommended walking amount information.

Next, another embodiment according to the present embodiment will be described.

(Example 1)
The personal attribute may include at least one of walking speed and walking posture. This is because even people with the same gender, age, and physique among individual attributes are considered to have different exercise loads if their walking speed and walking posture are different. Therefore, the machine learning models 3061 and 3062 are made to execute machine learning that reflects the walking speed and the walking posture as individual attributes. This makes it possible to estimate recommended walking amount information based on the walking speed and walking posture of the user.

The appropriate walking amount calculation unit 306 sets the walking speed of the data collection cooperator and the walking speed of the data collection cooperator based on the position information and acceleration information of the data collection cooperator stored in the collaborator sensor information storage unit 301 and the acquisition time of the information. The walking posture may be determined. Further, the personal appropriate walking amount estimation unit 310 determines the walking speed and walking posture of the user based on the user's position information and acceleration information stored in the user sensor information storage unit 309 and the acquisition time of the information. You may judge.

(Example 2)
The appropriate walking amount calculation unit 306 may estimate the daily walking amount (number of steps) that is unlikely to cause illness for each individual attribute by using the individual's medical history, weight change, and health diagnosis result. The appropriate walking amount calculation unit 306 is based on the user's position information of the user sensor information storage unit 309 and the acquisition time of the information, and the personal appropriate walking amount estimation unit 310 recommends the walking amount information to the user for one day. It is determined whether or not the user complies with the amount of walking (number of steps) per walk. The appropriate walking amount calculation unit 306 is based on the determination result and the medical history, weight change, and health diagnosis result of the user, and the effectiveness of the recommended walking amount information for the user by the personal appropriate walking amount estimation unit 310 ( Whether it helped to improve health) is judged. The appropriate walking amount calculation unit 306 uses the determination result of the validity of the recommended walking amount information for the learning data of the machine learning models 3061 and 3062 together with the personal attributes of the user. The user's medical history, weight change, and health diagnosis result are periodically registered in the personal attribute storage unit 304.

(Example 3)
The route guidance unit 311 calculates the degree of achievement of today's walking amount with respect to the daily walking amount indicated by the recommended walking amount information based on the actual data of today's walking amount of the user, and calculates today's walking. The walking route may be determined according to the degree of achievement of the amount. For example, if it is determined that the degree of achievement of today's walking amount is insufficient, today's shortage of walking amount can be supplemented with respect to the daily walking amount indicated by the recommended walking amount information. As such, the walking route may be determined. The actual data of the walking amount of the user today is transmitted from the user terminal to the recommended walking information generator 30.

(Example 4)
The route guidance unit 311 determines today's shortage of walking amount with respect to the daily walking amount indicated by the recommended walking amount information based on the user's daily activity history, and today's shortage of the judgment result. The walking route may be determined so that the walking amount can be supplemented. The daily activity history of the user is transmitted from the user terminal to the recommended walking information generator 30.

(Example 5)
The route guidance unit 311 contains vital information of the data collection cooperator of the collaborator sensor information storage unit 301, the road used by the data collection cooperator estimated by the road estimation unit 302, and the road information of the road information storage unit 305. Based on the road attributes, the appropriate road attributes may be determined so that the person can comfortably stabilize the mind and carry out the walking exercise, and the walking route may be determined based on the road attributes of the judgment result. The value of vital information (hereinafter, referred to as a reference vital value) indicating a state in which a person feels comfortable and has stabilized his / her mind is preset. The route guidance unit 311 acquires the road attribute of the road used by the data collection cooperator from which the vital information of the data collection cooperator corresponding to the reference vital value is acquired from the road information of the road information storage unit 305. The route guidance unit 311 uses the road corresponding to the acquired road attribute for the walking route.

As described above, according to the present embodiment, the recommended walking amount information for the user can be generated without the user wearing a sensor such as a position sensor, an acceleration sensor, or a vital sensor. The effect of providing appropriate walking exercise support can be obtained.

Although the embodiments of the present invention have been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like within a range not deviating from the gist of the present invention are also included.

For example, in the above-described embodiment, it is applied to walking exercise, but the present invention is not limited to this. For example, it can be applied to cycling as well as walking exercise.
In cycling, running time is used as a basic index instead of the amount of walking (number of steps) in walking exercise. Further, the cycling device may be used to acquire information on cadence (pedal rotation speed per minute) and output (depression power), and the acquired cadence and output may be combined with the running time. This makes it possible to obtain an index that can more accurately calculate the exercise load in cycling.

Further, a computer program for realizing the functions of the above-described devices may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read by the computer system and executed. The "computer system" referred to here may include hardware such as an OS and peripheral devices.
The "computer-readable recording medium" is a writable non-volatile memory such as a flexible disk, a magneto-optical disk, a ROM, or a flash memory, a portable medium such as a DVD (Digital Versatile Disc), or a built-in computer system. A storage device such as a hard disk.

Furthermore, the "computer-readable recording medium" is a volatile memory inside a computer system that serves as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line (for example, DRAM (Dynamic)). It also includes those that hold the program for a certain period of time, such as Random Access Memory)).
Further, the program may be transmitted from a computer system in which this program is stored in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting a program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
Further, the above program may be for realizing a part of the above-mentioned functions. Further, a so-called difference file (difference program) may be used, which can realize the above-mentioned functions in combination with a program already recorded in the computer system.

1 ... Recommended walking information providing system, 10 ... Collaborator terminal group, 20 ... User terminal group, 30 ... Recommended walking information generator, 301 ... Collaborator sensor information storage unit, 302 ... Used road estimation unit, 303 ... Exercise load Estimating unit, 304 ... Personal attribute storage unit, 305 ... Road information storage unit, 306 ... Appropriate walking amount calculation unit, 307 ... Appropriate walking amount storage unit, 308 ... Consideration calculation unit, 309 ... User sensor information storage unit, 310 ... Personal appropriate walking amount estimation unit, 311 ... Route guidance unit

Claims (10)

An appropriate walking amount storage unit that stores appropriate walking amount information indicating the daily walking amount recommended for health promotion in association with personal attributes, and
Based on the appropriate walking amount information associated with the personal attribute corresponding to the individual attribute of the user, the recommended walking amount information indicating the daily walking amount recommended for improving the health of the user is estimated. Personal appropriate walking amount estimation unit and
Recommended walking information generator equipped with. The personal attribute includes at least one of walking speed and walking posture.
The recommended walking information generator according to claim 1. The appropriate walking amount storage unit stores the appropriate walking amount information for each road attribute, and stores the appropriate walking amount information.
The personal appropriate walking amount estimation unit estimates the recommended walking amount information for each road attribute.
The recommended walking information generator according to any one of claims 1 or 2. A road information storage unit that stores road information including road attributes of each road,
A route guide unit that generates recommended walking route information indicating a walking route recommended for the user based on the road attributes of the candidate roads on which the user walks and the recommended walking amount information.
The recommended walking information generator according to claim 3. A collaborator sensor information storage unit that stores position information, acceleration information, and vital information acquired by a sensor carried by a data collection collaborator in association with the acquisition time.
An exercise load estimation unit that estimates the exercise load of the data collection collaborator based on the information stored in the collaborator sensor information storage unit, and an exercise load estimation unit.
A personal attribute storage unit that stores collaborator personal attribute information indicating the personal attributes of the data collection collaborator, and
An appropriate walking amount calculation unit that calculates the recommended daily walking amount for health promotion for each individual attribute based on the individual attributes and exercise load of the data collection collaborators.
The recommended walking information generator according to any one of claims 1 or 2, further comprising. A collaborator sensor information storage unit that stores position information, acceleration information, and vital information acquired by a sensor carried by a data collection collaborator in association with the acquisition time.
An exercise load estimation unit that estimates the exercise load of the data collection collaborator based on the information stored in the collaborator sensor information storage unit, and an exercise load estimation unit.
A personal attribute storage unit that stores collaborator personal attribute information indicating the personal attributes of the data collection collaborator, and
Appropriate walking that calculates the recommended daily walking amount for health promotion for each individual attribute and each road attribute based on the personal attributes of the data collection collaborators, the road attributes of the roads used, and the exercise load. Quantity calculation unit and
The recommended walking information generator according to any one of claims 3 or 4, further comprising. A consideration calculation unit that calculates the consideration to be paid to the data collection collaborator according to at least one of the disclosure level of the personal attribute of the data collection collaborator and the walking amount of the data collection collaborator carrying the sensor.
The recommended walking information generator according to any one of claims 5 or 6, further comprising. The recommended walking information generator according to any one of claims 5 to 7.
A mobile communication terminal of a data collection collaborator, which is provided with various sensors for acquiring position information, acceleration information, and vital information, and transmits the position information, acceleration information, and vital information acquired by the sensors to the recommended walking information generator.
The communication terminal of the user of the recommended walking information providing service that receives the recommended walking information from the recommended walking information generator, and
Recommended walking information providing system equipped with. An appropriate walking amount storage step in which the recommended walking information generator stores appropriate walking amount information indicating the daily walking amount recommended for health promotion in the appropriate walking amount storage unit in association with personal attributes, and
The recommended walking information generator determines the daily walking amount recommended for improving the health of the user based on the appropriate walking amount information associated with the personal attribute corresponding to the user's personal attribute. A personal appropriate gait estimation step for estimating the recommended gait information to be shown, and
Recommended walking information generation method including. On the computer
An appropriate walking amount storage step that stores appropriate walking amount information indicating the daily walking amount recommended for health promotion in the appropriate walking amount storage unit in association with personal attributes, and
Based on the appropriate walking amount information associated with the personal attribute corresponding to the individual attribute of the user, the recommended walking amount information indicating the daily walking amount recommended for improving the health of the user is estimated. Personal appropriate gait estimation step and
A computer program to run.

Images