Mental and physical health support system

Abstract

To provide a mental and physical health support system that allows a user to know whether or not the user is mentally and physically healthy compared with all users and whether or not the user is mentally and physically healthy compared with users with an attribute similar to that of the user based on feedback from the users.SOLUTION: In a mental and physical health support system 1, when information on a periodical food index, a step count, sleep hours, and working hours is input to a server device 5, a first machine learning unit 53 estimates whether or not a user subject to determination is mentally and physically healthy using a relation analyzed for all users. In addition, when an input of a determination result of a user himself / herself is performed many times and the amount of data of the determination result of the user himself / herself exceeds a reference data amount for a part of users, a second machine learning unit 56 estimates whether or not the user subject to determination is mentally and physically healthy using a relation analyzed for the part of users.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a mind and body health support system having a function for supporting the mind and body health of a user. [Background technology]

[0002] Conventionally, a device has been proposed that generates and provides more comprehensive information related to a user's life based on amounts related to a plurality of life-related items including the user's meals (see, for example, Patent Document 1). The conventional device has a function of determining a meal-related amount including an amount related to the user's chewing from the output of an electromyographic sensor on the user's head, determining one or both of a sleep-related amount including an amount related to the user's going to bed and / or waking up and an exercise-related amount including an amount related to the user's number of steps and / or activity intensity from the output of an activity meter worn by the user, and generating or selecting and providing one or both of information related to the user's life related to meals and sleep and information related to the user's life related to meals and exercise based on the determined meal-related amount and the determined sleep-related amount and / or exercise-related amount. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-189513 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, remote work has become more common. However, while there are concerns that long working hours and lack of exercise can lead to poor health, there is also the problem that communication between employees is done through screens, or communication between employees is greatly reduced, making it difficult to grasp whether employees are in good physical and mental health.

[0005] In order to address these issues, there is a need for a system that allows users to know whether they are mentally and physically healthy in comparison with all other users, and also to know whether they are mentally and physically healthy in comparison with users with similar attributes based on feedback from the users. However, no such system has been proposed to date.

[0006] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a mind and body health support system that enables a user to know whether or not his or her own mental and physical health is in comparison with all other users, and also enables a user to know whether or not his or her own mental and physical health is in comparison with users with similar attributes based on feedback from the user. [Means for solving the problem]

[0007] The mental and physical health support system of the present invention comprises a first user device owned by a user who is a target of mental and physical health support, a second user device worn by the user, a third user device operated by the user during work, and a server device communicably connected to the first user device and the third user device, wherein the first user device comprises a meal information input unit that inputs information about a meal ingested by the user when the user ingests a meal, and a first information transmission unit that transmits information about an input time when the information about the meal ingested by the user was input by the user to the server device, the second user device comprises a step count measurement unit that measures the number of steps of the user when the user walks, a sleep time measurement unit that measures the amount of sleep of the user when the user sleeps, and a second information transmission unit that transmits information about the number of steps of the user and information about the amount of sleep of the user to the server device via the first user device, and the third user device determines a time from the start of work of the user to the start of work of the user based on a work start behavior of the user when the user starts work and a work end behavior of the user when the user starts work. the server device includes an information receiving unit that receives information on the input time from the first user device, information on the number of steps of the user and information on the sleeping time of the user from the second user device via the first user device, and receives information on the working time of the user from the third user device; and a working time measuring unit that measures a degree to which the user regularly takes in meals based on the information on the input time received from the first user device. a first machine learning unit that analyzes, by machine learning, a relationship between the regular meal index, the number of steps, the sleeping hours, and the working hours of all users, and a judgment result of whether the user is mentally and physically healthy or not, which is judged using predetermined reference data; a first estimation unit that estimates whether the user is mentally and physically healthy or not based on the relationship analyzed by the first machine learning unit, using the regular meal index, the number of steps, the sleeping hours, and the working hours of the user to be judged as an input, and outputs the estimation result by the first estimation unit;and a first estimation result transmission unit that transmits the estimation result by the first estimation unit to a first user device of the user to be judged, the first user device comprising: a first estimation result display unit that displays the estimation result by the first estimation unit received from the server device; a self-judgment result input unit that inputs a judgment result of the user of the first user device as to whether or not the user is physically and mentally healthy; and a self-judgment result transmission unit that transmits the user's own judgment result input by the user to the server device, and the server device comprises a data amount determination unit that determines whether or not a data amount of the user's own judgment result received from the first user device exceeds a predetermined reference data amount for some users including the user to be judged of all the users, and a second machine learning unit that, when it is determined by the server device that the reference data amount has been exceeded, analyzes, for the some of the users, a relationship between the information on the regular eating index, the number of steps, the sleeping hours, and the working hours, and the judgment result of the user himself / herself, by machine learning; a second estimation unit that, based on the relationship analyzed by the second machine learning unit, estimates whether the user to be judged is physically and mentally healthy or not by inputting the information on the regular eating index, the number of steps, the sleeping hours, and the working hours of the user to be judged, and outputs the estimation result; and a second estimation result transmission unit that transmits the estimation result by the second estimation unit to a first user device of the user to be judged, and the first user device is equipped with a second estimation result display unit that displays the estimation result by the second estimation unit received from the server device.

[0008] According to this configuration, information on the time when the user to be judged ate a meal (input time when information on the ingested meal was input) is acquired from the first user terminal carried by the user to be judged, and an index (regular meal index) indicating the degree to which the user regularly eats meals is calculated from the information on the time (input time). Also, information on the number of steps walked by the user and the number of hours of sleep is acquired from the second user terminal carried by the user. Furthermore, information on the user's working hours (the time from the start of work to the end of work) is acquired from the third user terminal operated by the user during work. Then, when the information on the regular meal index, the number of steps, the hours of sleep, and the working hours is input to the server device, the first machine learning unit uses the relationship analyzed for all users to estimate whether the user to be judged is physically and mentally healthy, and the estimation result is displayed on the first user terminal. As a result, the user can know the estimation result (whether the user's mind and body are healthy compared to all users) estimated based on the relationship analyzed for all users regarding whether the user's mind and body are healthy or not.

[0009] Also, according to this configuration, the user's own judgment result as to whether or not the user is physically and mentally healthy is input from the first user terminal. Then, the input of the user's own judgment result (feedback from the user) is performed many times, and when the amount of data of the user's own judgment result for some users including the user to be judged among all users exceeds a predetermined reference data amount, the second machine learning unit uses the relationship analyzed for the some users to estimate whether or not the user to be judged is physically and mentally healthy, and the estimation result is displayed on the first user terminal. As a result, the user can know the estimation result (whether or not the user is physically and mentally healthy, based on the relationship analyzed for some users including the user, based on the feedback from the user) as to whether or not the user is physically and mentally healthy.

[0010] Furthermore, in the mental and physical health support system of the present invention, the data amount determination unit determines whether or not the data amount of the user's own judgment result received from the first user device for the user to be judged exceeds a predetermined standard data amount, and when the data amount determination unit determines that the standard data amount is exceeded, the second machine learning unit analyzes, by machine learning, the relationship between the information of the regular eating index, the number of steps, the sleeping time and the working hours for the user to be judged and the judgment result of the user to be judged, and the second estimation unit may estimate whether or not the user to be judged is physically and mentally healthy based on the relationship analyzed by the second machine learning unit, and output the information of the regular eating index, the number of steps, the sleeping time and the working hours of the user to be judged as input.

[0011] According to this configuration, the input of the judgment result of the user to be judged (user's own feedback) is performed many times, and when the amount of data of the judgment result of the user to be judged exceeds a predetermined reference data amount, the second machine learning unit uses the relationship analyzed about the user to be judged to estimate whether the user to be judged is mentally and physically healthy or not, and the estimation result is displayed on the first user terminal. This allows the user to know the estimation result (whether the user's current mental and physical health is healthy or not, based on the relationship analyzed about the past users to be judged, compared with the user's past self, based on the user's own feedback) as to whether the user's mental and physical health is healthy or not.

[0012] In addition, in the mind and body health support system of the present invention, when an image of a meal consumed by the user is taken using the first user device, information obtained by image analysis of the image is input to the meal information input unit as information regarding the meal consumed, and the first information transmission unit may transmit information on the time the image was taken to the server device as information on the input time.

[0013] According to this configuration, when an image of a meal taken by a user is taken using the first user device, the periodic meal index can be calculated using information on the time when the image was taken as information on the input time. In this case, by taking an image of a meal taken by the user using the first user device, information on the meal taken by the user can be easily input.

[0014] In addition, in the mind and body health support system of the present invention, when information about a meal consumed by the user is input or selected by the user using the first user device, the meal information input unit inputs the information obtained by the user input or selection as information about the meal consumed, and the first information transmission unit may transmit information about the time the user input or selection was made to the server device as information about the input time.

[0015] According to this configuration, when information on a meal taken by a user is input or selected by the user using the first user device, the periodic meal index can be calculated using information on the time when the user input or selection was made as information on the input time. In this case, by inputting or selecting information on a meal taken by a user using the first user device, information on the meal taken by the user can be easily input.

[0016] Furthermore, in the mind and body health support system of the present invention, the regular meal index calculation unit may calculate a breakfast index indicating the degree to which the user has properly taken breakfast, a lunch index indicating the degree to which the user has properly taken lunch, and a dinner index indicating the degree to which the user has properly taken dinner, based on the information of the input time received from the first user device, and calculate the regular meal index based on the breakfast index, the lunch index, and the dinner index.

[0017] According to this configuration, indices (breakfast index, lunch index, dinner index) indicating the degree to which the user appropriately ate breakfast, lunch, and dinner are calculated based on the information of the input time, and the regular meal index can be appropriately calculated based on these breakfast index, lunch index, and dinner index.

[0018] A method of the present invention is a method executed in a mind and body health support system including a first user device owned by a user who is a target of mind and body health support, a second user device worn by the user, a third user device operated by the user during work, and a server device communicably connected to the first user device and the third user device, the method including, as steps executed in the first user device, a meal information input step of inputting information about a meal ingested by the user when the user ingests a meal, and a first information transmission step of transmitting information about an input time when the information about the meal ingested by the user was input by the user to the server device, the method including, as steps executed in the second user device, a step count measurement step of measuring the number of steps of the user when the user walks, a sleep time measurement step of measuring the sleep time of the user when the user sleeps, and a second information transmission step of transmitting information about the number of steps of the user and information about the sleep time of the user to the server device via the first user device, the method including, as steps executed in the third user device, a meal information input step of inputting information about the meal ingested by the user when the user ingests a meal, and a first information transmission step of transmitting information about the number of steps of the user and information about the sleep time of the user to the server device via the first user device, and a third information transmission step of transmitting information on the user's working hours to the server device, the steps being executed in the server device, the method including: a working hours measurement step of measuring a working hours from the start of work to the end of work of the user based on a work start behavior when the user starts work and a work end behavior when the user starts work; and a third information transmission step of transmitting information on the user's working hours to the server device, the steps being executed in the server device, the information reception step of receiving information on the input time from the first user device, receiving information on the number of steps of the user and information on the sleeping hours of the user from the second user device via the first user device, and receiving information on the user's working hours from the third user device; a regular eating index calculation step of calculating a regular eating index indicating the degree to which the user regularly takes in meals based on the information on the input time received from the first user device; and a first machine learning step of analyzing, for all users, a relationship between the regular eating index, the information on the number of steps, the sleeping hours, and the working hours, and a determination result of whether the user is mentally and physically healthy, which is determined using predetermined reference data, by machine learning;the method further includes, as steps executed in the server device, a first estimation step of displaying the estimation result obtained by the first estimation step received from the server device, a self-assessment result input step of inputting a self-assessment result of the user of the first user device as to whether the user of the first user device is physically and mentally healthy or not, and a self-assessment result transmission step of transmitting the self-assessment result input by the user to the server device, the method further includes, as steps executed in the server device, a first estimation result display step of displaying the estimation result obtained by the first estimation step received from the server device, a self-assessment result input step of inputting a self-assessment result of the user of the first user device as to whether the user of the first user device is physically and mentally healthy or not, and a self-assessment result transmission step of transmitting the self-assessment result input by the user to the server device, the method further includes, as steps executed in the server device, The method includes a data amount determination step of determining whether or not the data amount of the user's own judgment result received from the user device exceeds a predetermined reference data amount; a second machine learning step of analyzing, by machine learning, the relationship between the information of the regular eating index, the number of steps, the sleeping time, and the working hours, and the user's own judgment result for the part of the users when it is determined by the data amount determination step that the reference data amount is exceeded; a second estimation step of estimating whether or not the user to be judged is mentally and physically healthy based on the relationship analyzed in the second machine learning step, using the information of the regular eating index, the number of steps, the sleeping time, and the working hours of the user to be judged as an input, and outputting the estimation result by the second estimation step to a first user device of the user to be judged, and the method further includes a second estimation result display step of displaying the estimation result by the second estimation step received from the server device as a step executed in the first user device.

[0019] In this method, as in the above system, information on the time when the user to be judged ate a meal (input time when information on the ingested meal was input) is obtained from a first user terminal carried by the user to be judged, and an index (regular meal index) indicating the degree to which the user regularly eats meals is calculated from the information on the time (input time). In addition, information on the number of steps walked by the user and the number of hours of sleep is obtained from a second user terminal carried by the user. Furthermore, information on the user's working hours (the time from the start of work to the end of work) is obtained from a third user terminal operated by the user during work. Then, when the information on the regular meal index, the number of steps, the hours of sleep, and the working hours is input to the server device, the first machine learning unit uses the relationship analyzed for all users to estimate whether the user to be judged is physically and mentally healthy, and the estimation result is displayed on the first user terminal. As a result, the user can know the estimation result (whether the user's mind and body are healthy compared to all users) estimated based on the relationship analyzed for all users regarding whether the user's mind and body are healthy or not.

[0020] Also, with this method, the user's own judgment result as to whether or not the user is physically and mentally healthy is input from the first user terminal. Then, the input of the user's own judgment result (feedback from the user) is performed many times, and when the amount of data of the user's own judgment result for some users including the user to be judged among all users exceeds a predetermined reference data amount, the second machine learning unit uses the relationship analyzed for the some users to estimate whether or not the user to be judged is physically and mentally healthy, and the estimation result is displayed on the first user terminal. As a result, the user can know the estimation result (whether or not the user is physically and mentally healthy, based on the relationship analyzed for some users including the user, based on the feedback from the user) as to whether or not the user is physically and mentally healthy. Effect of the Invention

[0021] According to the present invention, a user can know whether his / her own mental and physical health is in comparison with all other users, and based on feedback from the user, a user can know whether his / her own mental and physical health is in comparison with users with similar attributes. [Brief description of the drawings]

[0022] [Figure 1] 1 is a block diagram showing a configuration of a mind and body health support system according to an embodiment of the present invention. [Diagram 2] FIG. 13 is a diagram showing an example of a determination result (one month, six months, and one year after the system is used) in an embodiment of the present invention. [Diagram 3] 2 is a sequence diagram for explaining the operation (first machine learning) of the mind and body health support system in the embodiment of the present invention. FIG. [Figure 4] FIG. 4 is a sequence diagram illustrating the operation of the mind and body health support system in the embodiment of the present invention (one month after the system was started to be used). [Diagram 5] FIG. 2 is a sequence diagram illustrating the operation of the mind and body health support system in the embodiment of the present invention (six months and one year after the system is used). DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Hereinafter, a mental and physical health support system according to an embodiment of the present invention will be described with reference to the drawings. In this embodiment, a mental and physical health support system used in a system for supporting the mental and physical health of employees will be described as an example.

[0024] The configuration of a mental and physical health support system according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the mental and physical health support system according to the present embodiment. As shown in FIG. 1, the mental and physical health support system 1 includes a first user device 2 carried by a user (employee) who is a target of mental and physical health support, a second user device 3 worn by the user, a third user device 4 operated by the user during work hours, and a server device 5 communicably connected to the first user device 2 and the third user device 4 via a network N. For example, the first user device 2 is a smartphone or the like, the second user device 3 is a wearable device such as a smartwatch, and the third user device 4 is a personal computer or the like.

[0025] As shown in Fig. 1, the first user device 2 includes, as functional blocks, a dietary information input unit 20, a first information transmission unit 21, a first estimated result display unit 22, a self-assessment result input unit 23, a self-assessment result transmission unit 24, and a second estimated result display unit 25. The second user device 3 includes, as functional blocks, a step counter 30, a sleep time counter 31, and a second information transmission unit 32. The third user device 4 includes, as functional blocks, a working time counter 40, and a third information transmission unit 41. The server device 5 includes, as functional blocks, an information receiver 50, a periodic meal index calculator 51, a data amount determiner 52, a first machine learning unit 53, a first estimation unit 54, a first estimated result transmission unit 55, a second machine learning unit 56, a second estimation unit 57, and a second estimated result transmission unit 58.

[0026] First, each component of the first user device 2 will be described in detail. The meal information input unit 20 has a function for inputting information about a meal that the user has eaten when the user has eaten the meal. The information about the meal that has been eaten is, for example, the name of the food or menu item that has been eaten, such as "bread," "salad," "ramen," or "hamburger." If the first user device 2 has a user input function (a function for directly inputting the menu item name of the meal that has been eaten as text), information input by the user using the first user device 2 (for example, "bread," "salad") is input to the meal information input unit 20 as information about the meal that has been eaten.

[0027] In addition, if the first user device 2 has a user selection function (a function that displays candidates for the name of the meal eaten (e.g., "ramen," "curry rice," etc.) and allows the user to select one of the candidates), information selected by the user using the first user device 2 (e.g., "ramen") is input into the meal information input unit 20 as information regarding the meal eaten.

[0028] Furthermore, if the first user device 2 has a camera function (a function for taking an image of the meal eaten), information obtained by image analysis of an image (an image of the meal eaten) taken by the user using the first user device 2 (for example, the name of the menu item eaten obtained by image recognition, such as "hamburger steak") is input to the meal information input unit 20 as information regarding the meal eaten.

[0029] The first information transmission unit 21 has a function of transmitting information on the input time (timestamp) when information on the ingested meal is input to the server device 5 via the network N. When information input or selected by the user using the first user device 2 is input to the meal information input unit 20 as information on the ingested meal, information on the time when the user input or selection was made is transmitted to the server device 5 as input time information.

[0030] In addition, when information obtained by image analysis of an image (an image of the meal eaten) taken by the user using the first user device 2 (for example, the name of the meal eaten obtained by image recognition) is input to the meal information input unit 20 as information regarding the meal eaten, information on the time the image was taken is transmitted to the server device 5 as information on the input time.

[0031] The first estimation result display unit 22 has a function of displaying an estimation result (described later) by the first estimation unit 54 received from the server device 5. Moreover, the second estimation result display unit 25 displays an estimation result (described later) by the second estimation unit 57 received from the server device 5.

[0032] The self-assessment result input section 23 has a function of inputting the user's own judgment result as to whether the user of the first user device 2 is mentally and physically healthy or not. The user's own judgment result may be, for example, a score out of 100, or an evaluation such as "good," "average," or "bad." For example, if the first user device 2 has a user input function (a function for directly inputting the user's own judgment result as text), the user's own judgment result (score, evaluation, etc.) input by the user using the first user device 2 is input to the self-assessment result input section 23.

[0033] The self-assessment result transmitting section 24 has a function of transmitting the user's own assessment result (score, evaluation, etc.) input by the user as described above to the server device 5 via the network N.

[0034] Next, each component of the second user device 3 will be described in detail. The step count measurement unit 30 has a function of measuring the number of steps (the number of steps taken in a day) of the user when the user walks. The sleep time measurement unit 31 has a function of measuring the sleep time (the sleep time in a day) of the user when the user sleeps. The measurement of the number of steps and the sleep time can be performed using known technology.

[0035] The second information transmission unit 32 has a function of transmitting information on the user's number of steps and sleeping hours (number of steps and sleeping hours per day) measured as described above to the server device 5 via the first user device 2. The first user device 2 and the second user device 3 are capable of short-range communication with each other using, for example, Bluetooth (registered trademark), and the information on the user's number of steps and sleeping hours is transmitted from the second user device 3 to the first user device 2 by short-range communication, and is then sent from the first user device 2 to the server device 5 via the network N.

[0036] Next, each component of the third user device 4 will be described in detail. The working time measurement unit 40 has a function of measuring the working time (working time per day) of a user from the start of work to the end of work based on a work start behavior when the user starts work and a work end behavior when the user starts work. For example, the work start behavior includes an operation of starting (booting) the third user device 4 and an operation of logging into a work system using the third user device 4. In addition, the work end behavior includes an operation of shutting down the third user device 4 and an operation of logging out of a work system using the third user device 4.

[0037] The third information transmission unit 41 has a function of transmitting information on the user's working hours (working hours per day) measured as described above to the server device 5 via the network N.

[0038] Finally, each component of the server device 5 will be described in detail. The information receiving unit 50 has a function of receiving information on the input time from the first user device 2 via the network N. The information receiving unit 50 also has a function of receiving information on the user's step count and sleep time (number of steps and sleep time per day) from the second user device 3 via the network N and the first user device 2. The information receiving unit 50 also has a function of receiving information on the user's working hours (working hours per day) from the third user device 4 via the network N.

[0039] The periodic meal index calculation unit 51 has a function of calculating a periodic meal index indicating the degree to which the user regularly takes meals (one day's worth of meals: breakfast, lunch, and dinner) based on the information of the input time received from the first user device 2. In this embodiment, the periodic meal index calculation unit 51 calculates a breakfast index indicating the degree to which the user properly takes breakfast, a lunch index indicating the degree to which the user properly takes lunch, and a dinner index indicating the degree to which the user properly takes dinner based on the information of the input time received from the first user device 2, and calculates the periodic meal index based on the breakfast index, lunch index, and dinner index.

[0040] For example, if the input time received from the first user device 2 includes a time between 7:00 and 9:00, a breakfast index of "1 point" is assigned. If the input time received from the first user device 2 includes a time between 11:00 and 13:00, a lunch index of "1 point" is assigned. If the input time received from the first user device 2 includes a time between 18:00 and 22:00, a dinner number of "1 point" is assigned. The regular meal index calculation unit 51 then calculates the total score (maximum of 3 points) of the breakfast index, lunch index, and dinner index as the regular meal index.

[0041] The first machine learning unit 53 has a function of analyzing, by machine learning, the relationship between the information on the regular eating index, the number of steps, the sleeping hours, and the working hours of all users, and the judgment result of whether the user is mentally and physically healthy or not, which is judged using predetermined reference data (for example, public information published by the Ministry of Internal Affairs and Communications, the Ministry of Health, Labor and Welfare, etc.). Any method such as deep learning by a neural network is used for this machine learning. For example, in the case of a neural network, the information on the regular eating index, the number of steps, the sleeping hours, and the working hours is input to an input layer, and the judgment result of whether the user is mentally and physically healthy or not, which is judged using the reference data, is output from an output layer. Then, the weighting coefficient between the neurons of the neural network is optimized by supervised learning using analysis data in which the data input to the input layer and the data output from the output layer are linked.

[0042] The first estimation unit 54 has a function of estimating and outputting whether the user to be judged is physically and mentally healthy by inputting information on the regular meal index, number of steps, sleep time, and working hours of the user to be judged based on the relationship analyzed by the first machine learning unit 53. For example, in the case of the above-mentioned neural network, information on the regular meal index (e.g., 3 points), number of steps (e.g., 10,500 steps), sleep time (e.g., 6 hours), and working hours (e.g., 8 hours) of the user to be judged on the day to be judged of the user to be judged of, is input to the input layer, and a judgment result (e.g., 80 points) of whether the user is physically and mentally healthy or not, which is judged using predetermined reference data, is output from the output layer, thereby performing estimation.

[0043] The first estimation result transmission unit 55 has a function of transmitting the above-mentioned judgment result (judgment result in comparison with all users) to the first user device 2 of the user to be judged via the network N. The judgment result transmitted to the first user device 2 (estimated result by the first estimation unit 54) is displayed on the screen (first estimation result display unit 22) of the first user device 2. FIG. 2(a) is a diagram showing an example of the judgment result (one month after the system is used) displayed on the first user device 2. In the example of FIG. 2(a), the judgment result in comparison with all users (e.g., 80 points) is indicated by a circle.

[0044] The data amount determination unit 52 has a function of determining whether or not the data amount of the judgment result of the user himself / herself received from the first user device 2 for some users including the user to be judged (users with attributes similar to the user to be judged, for example, "male, in his 20s, general employee") among all users exceeds a predetermined standard data amount. In this embodiment, for example, after six months have passed since the start of use of the system, it is determined that the data amount of the judgment result of the user himself / herself received from the first user device 2 for some users (users with similar attributes) exceeds the predetermined standard data amount.

[0045] The second machine learning unit 56 has a function of analyzing, by machine learning, the relationship between the information on the regular meal index, the number of steps, the sleep time, and the working hours of some users (users with similar attributes) and the user's own judgment result, for some users (users with similar attributes). Any method such as deep learning using a neural network is used for this machine learning. For example, in the case of a neural network, the information on the regular meal index, the number of steps, the sleep time, and the working hours of some users (users with similar attributes) is input to an input layer, and the user's own judgment result is output from an output layer. Then, the weighting coefficient between the neurons of the neural network is optimized by supervised learning using analysis data in which the data input to the input layer and the data output from the output layer are linked.

[0046] The second estimation unit 57 has a function of estimating whether or not the user to be judged is physically and mentally healthy by inputting information on the regular meal index, number of steps, sleep time, and working hours of the user to be judged based on the relationship analyzed by the second machine learning unit 56, and outputting the result. For example, in the case of the above neural network, information on the regular meal index (e.g., 3 points), number of steps (e.g., 10,500 steps), sleep time (e.g., 6 hours), and working hours (e.g., 8 hours) of the user to be judged on the day to be judged of the user ... mentally and physically healthy (e.g., 78 points) is output from the output layer, so that estimation is performed.

[0047] The second estimation result transmission unit 58 has a function of transmitting the above-mentioned judgment result (judgment result in comparison with some users) to the first user device 2 of the user to be judged via the network N. The judgment result transmitted to the first user device 2 (estimated result by the second estimation unit 57) is displayed on the screen (second estimation result display unit 25) of the first user device 2. FIG. 2(b) is a diagram showing an example of the judgment result (six months after the system is used) displayed on the first user device 2. In the example of FIG. 2(b), the judgment result in comparison with some users (e.g., 78 points) is shown by a triangular mark. Note that in FIG. 2(b), the judgment result in comparison with all users (e.g., 80 points) is also superimposed and displayed by a circle, but this superimposition is not necessarily required.

[0048] Furthermore, the data amount determination unit 52 has a function of determining whether or not the data amount of the determination result of the user (the user himself) to be determined, received from the first user device 2, exceeds a predetermined reference data amount. In this embodiment, for example, after one year has passed since the start of use of the system, it is determined that the data amount of the determination result of the user (the user himself) to be determined, received from the first user device 2, exceeds the predetermined reference data amount.

[0049] The second machine learning unit 56 has a function of analyzing, by machine learning, the relationship between the information on the regular meal index, the number of steps, the sleep time, and the working hours of the user to be judged (the user himself / herself) and the judgment result of the user himself / herself, when the data amount judgment unit 52 judges that the reference data amount has been exceeded. For this machine learning, any method such as deep learning by a neural network is used. For example, in the case of a neural network, the information on the regular meal index, the number of steps, the sleep time, and the working hours of the user to be judged (the user himself / herself) is input to an input layer, and the judgment result of the user himself / herself is output from an output layer. Then, the weighting coefficient between the neurons of the neural network is optimized by supervised learning using analysis data in which the data input to the input layer and the data output from the output layer are linked.

[0050] The second estimation unit 57 has a function of estimating and outputting whether the user to be judged is physically and mentally healthy by inputting information on the regular meal index, number of steps, sleep time, and working hours of the user to be judged based on the relationship analyzed by the second machine learning unit 56. For example, in the case of the above neural network, information on the regular meal index (e.g., 3 points), number of steps (e.g., 10,500 steps), sleep time (e.g., 6 hours), and working hours (e.g., 8 hours) of the user to be judged on the day to be judged of the user to be judged of, is input to the input layer, and a judgment result (e.g., 75 points) of whether the user is physically and mentally healthy or not, which is judged using predetermined reference data, is output from the output layer, thereby performing estimation.

[0051] The second estimation result transmission unit 58 has a function of transmitting the above-mentioned judgment result (judgment result compared with the past user himself) to the first user device 2 of the judgment target user via the network N. The judgment result transmitted to the first user device 2 (estimated result by the second estimation unit 57) is displayed on the screen (second estimation result display unit 25) of the first user device 2. FIG. 2(c) is a diagram showing an example of the judgment result (one year after the system is used) displayed on the first user device 2. In the example of FIG. 2(c), the judgment result compared with the past user himself (e.g., 75 points) is shown by a square mark. Note that in FIG. 2(c), the judgment result compared with all users (e.g., 80 points) is also superimposed with a circle mark, and the judgment result compared with some users (e.g., 78 points) is also superimposed with a triangle mark, but these superimposed displays are not necessarily required.

[0052] The operation of the mind and body health support system 1 configured as above will be described with reference to the sequence diagrams of FIGS.

[0053] First, the operation when the first machine learning is performed in the mind and body health support system 1 of this embodiment will be described. Fig. 3 is a sequence diagram showing the operation when the first machine learning is performed in the mind and body health support system 1 of this embodiment. As shown in Fig. 3, when the first machine learning is performed in the mind and body health support system 1 of this embodiment, first, for all users, when the user eats a meal, information about the ingested meal is input into the first user device 2 (S1), and information about the input time when the information about the ingested meal was input by the user is transmitted to the server device 5 (S2).

[0054] Furthermore, for all users, the third user device 4 measures the working hours of the user in one day from the start to the end of the work day (S3), and the information on the working hours of the user is transmitted to the server device 5 (S4). Furthermore, for all users, the second user device 3 measures the number of steps taken by the user in one day (S5), measures the number of hours slept by the user in one day (S6), and transmits information on the number of steps and the number of hours slept by the user to the server device 5 via the first user device 2 (S7).

[0055] Then, the server device 5 calculates a regular eating index indicating the degree to which the user eats meals regularly based on the input time information received from the first user device 2 (S8), and analyzes, by machine learning, the relationship for all users between the regular eating index, the number of steps, sleep time, and working hours, and the judgment result of whether the user is physically and mentally healthy or not, which is judged using specified reference data (S9).

[0056] Next, the operation of the mind and body health support system 1 one month after the system has been used (when the amount of data of the user's own judgment results received from the first user device 2 does not exceed a predetermined reference data amount for some users) will be described. FIG. 4 is a sequence diagram showing the operation of the mind and body health support system 1 one month after the system has been used. As shown in FIG. 4, in the mind and body health support system 1 one month after the system has been used, when the user eats a meal, information about the meal eaten is input into the first user device 2 of the user to be judged (user A) (S10), and information about the input time when the information about the meal eaten was input by the user is transmitted to the server device 5 (S11).

[0057] Furthermore, the third user device 4 of the user to be judged (user A) measures the working hours of the user in one day from the start to the end of work (S12), and transmits the information on the working hours of the user to the server device 5 (S13). Furthermore, the second user device 3 of the user to be judged (user A) measures the number of steps taken by the user in one day (S14), measures the number of hours of sleep by the user in one day (S15), and transmits information on the number of steps and the hours of sleep by the user to the server device 5 via the first user device 2 (S16).

[0058] Then, the server device 5 calculates a regular eating index indicating the degree to which the user eats meals regularly based on the information of the input time received from the first user device 2 (S17), and based on the relationship analyzed by the first machine learning unit 53, the regular eating index (e.g., 3 points), number of steps (e.g., 10,500 steps), sleep time (e.g., 6 hours), and working hours (e.g., 8 hours) of the user to be judged on the day to be judged are input, and a judgment result (e.g., 80 points) of whether the user to be judged is physically and mentally healthy or not is estimated (S18).

[0059] The judgment result (judgment result compared with all users) is transmitted from the server device 5 to the first user device 2 of the user to be judged (S19), and is displayed on the screen (first estimation result display unit 22) of the first user device 2 as shown in FIG. 2(a) (S20). When the user to be judged inputs his / her own judgment result (e.g., a score of 75) as to whether the user of the first user device 2 is physically and mentally healthy or not (S21), the inputted judgment result of the user is transmitted from the first user device 2 to the server device 5 (S22). In this case, for some users, the data amount of the judgment result of the user received from the first user device 2 does not exceed the predetermined reference data amount, so the second machine learning is not performed.

[0060] Finally, the operation of the mind and body health support system 1 six months or one year after the use of the system (when the amount of data of the judgment result of the user himself / herself received from the first user device 2 for some users or the user himself / herself exceeds a predetermined reference data amount) will be described. FIG. 5 is a sequence diagram showing the operation of the mind and body health support system 1 six months or one year after the use of the system. As shown in FIG. 5, in the mind and body health support system 1 six months or one year after the use of the system, when the user to be judged (user A) eats a meal, information about the meal is input into the first user device 2 of the user (user A) (S30), and information on the input time when the information about the meal was input by the user is transmitted to the server device 5 (S31).

[0061] Furthermore, the third user device 4 of the user to be judged (user A) measures the working hours of the user for one day from the start to the end of work (S32), and transmits information on the working hours of the user to the server device 5 (S33). Furthermore, the second user device 3 of the user to be judged (user A) measures the number of steps taken by the user for one day (S34), measures the number of hours of sleep by the user for one day (S35), and transmits information on the number of steps and the hours of sleep by the user to the server device 5 via the first user device 2 (S36).

[0062] Then, the server device 5 calculates a regular eating index indicating the degree to which the user eats meals regularly based on the information of the input time received from the first user device 2 (S37), and based on the relationship analyzed by the first machine learning unit 53, the regular eating index (e.g., 3 points), number of steps (e.g., 10,500 steps), sleep time (e.g., 6 hours), and working hours (e.g., 8 hours) of the user to be judged on the day to be judged are input, and a judgment result (e.g., 80 points) of whether the user to be judged is physically and mentally healthy or not is estimated (S38).

[0063] In addition, based on the relationship analyzed by the second machine learning unit 56, the result of the judgment as to whether the user to be judged is physically and mentally healthy (e.g., 78 points or 75 points) is estimated (S39) using as input the information of the user to be judged's regular eating index (e.g., 3 points), number of steps (e.g., 10,500 steps), sleep time (e.g., 6 hours), and working hours (e.g., 8 hours) on the day to be judged of the user to be judged.

[0064] These judgment results (judgment results compared with some users or the user himself / herself) are transmitted from the server device 5 to the first user device 2 of the user to be judged (S40), and are displayed on the screen (second estimation result display unit 25) of the first user device 2 as shown in Fig. 2(b) or 2(c) (S41). When the user to be judged inputs his / her own judgment result (e.g., a score of 75) as to whether the user of the first user device 2 is physically and mentally healthy or not (S42), the input judgment result of the user himself / herself is transmitted from the first user device 2 to the server device 5 (S43).

[0065] In this case, for some users or the users themselves, the amount of data of the user's own judgment results received from the first user device 2 exceeds a predetermined standard data amount, so a second machine learning is performed to analyze the relationship between the information on the regular eating index, number of steps, sleeping time, and working hours and the user's own judgment results by machine learning (S43).

[0066] According to the mental and physical health support system 1 of the present embodiment, information on the time when the user to be judged ate a meal (input time when information on the ingested meal was input) is acquired from the first user terminal carried by the user to be judged, and an index (regular meal index) indicating the degree to which the user regularly eats meals is calculated from the information on the time (input time). Also, information on the number of steps walked by the user and the number of hours of sleep is acquired from the second user terminal carried by the user. Furthermore, information on the user's working hours (the time from the start of work to the end of work) is acquired from the third user terminal operated by the user during work. Then, when the information on the regular meal index, the number of steps, the hours of sleep, and the working hours is input to the server device 5, whether the user to be judged is mentally and physically healthy is estimated using the relationship analyzed for all users by the first machine learning unit 53, and the estimation result is displayed on the first user terminal. As a result, the user can know the estimation result (whether the user's mind and body are healthy compared to all users) estimated based on the relationship analyzed for all users regarding whether the user's mind and body are healthy or not.

[0067] According to this embodiment, the user's own judgment result as to whether or not the user is physically and mentally healthy is input from the first user terminal. Then, the input of the user's own judgment result (feedback from the user) is performed many times, and when the amount of data of the user's own judgment result for some users including the user to be judged among all users exceeds a predetermined reference data amount, the second machine learning unit 56 estimates whether or not the user to be judged is physically and mentally healthy using the relationship analyzed for the some users, and the estimation result is displayed on the first user terminal. As a result, the user can know the estimation result (whether or not the user is physically and mentally healthy, based on the relationship analyzed for some users including the user, based on the feedback from the user) as to whether or not the user is physically and mentally healthy.

[0068] In addition, in this embodiment, the input of the judgment result of the user to be judged (user's own feedback) is performed many times, and when the amount of data of the judgment result of the user to be judged exceeds a predetermined reference data amount, the second machine learning unit 56 uses the relationship analyzed about the user to be judged to estimate whether the user to be judged is mentally and physically healthy or not, and the estimation result is displayed on the first user terminal. This allows the user to know the estimation result (whether the user's current mental and physical health is healthy or not, based on the relationship analyzed about the past users to be judged, compared with the user's past self, based on the user's own feedback) as to whether the user's mental and physical health is healthy or not.

[0069] In addition, in this embodiment, when an image of a meal taken by the user is taken using the first user device 2, the periodic meal index can be calculated using information on the time when the image was taken as information on the input time. In this case, by taking an image of the meal taken using the first user device 2, information on the meal taken by the user can be easily input.

[0070] In addition, in this embodiment, when information on a meal taken by the user is input or selected by the user using the first user device 2, the periodic meal index can be calculated using information on the time when the user input or selection was made as information on the input time. In this case, by inputting or selecting information on a meal taken by the user using the first user device 2, information on the meal taken by the user can be easily input.

[0071] In addition, in this embodiment, based on the information of the input time, indexes (breakfast index, lunch index, dinner index) indicating the degree to which the user appropriately ate breakfast, lunch, and dinner are calculated, and based on these breakfast index, lunch index, and dinner index, the regular meal index can be appropriately calculated.

[0072] Although the embodiments of the present invention have been described above by way of example, the scope of the present invention is not limited to these, and changes and modifications can be made according to the purpose within the scope of the claims. [Industrial Applicability]

[0073] As described above, the mental and physical health support system 1 of the present invention has the effect of enabling a user to know whether or not his or her own mental and physical health is healthy in comparison with all other users, and also to know whether or not his or her own mental and physical health is healthy in comparison with users with similar attributes based on feedback from the user, and is therefore useful as a system for supporting the mental and physical health of employees. [Explanation of symbols]

[0074] 1. Mental and physical health support system 2. First User Device 3. Second User Device 4. Third User Device 5. Server equipment 20 Meal information input section 21 First information transmission unit 22 First estimation result display section 23 Self-assessment result input section 24 Self-assessment result transmission unit 25 Second estimation result display section 30 Step counter 31 Sleep Time Measurement Unit 32 Second information transmission unit 40 Working Hours Measurement Department 41 Third Information Transmission Unit 50 Information Receiving Unit 51 Periodic Meal Index Calculation Section 52 Data amount determination unit 53 Machine Learning Department 1 54 1st estimation part 55 First estimation result transmission unit 56 Machine Learning Department 2 57 Second estimation part 58 Second estimation result transmission unit

Claims

1. A mental and physical health support system comprising: a first user device owned by a user who is a target of mental and physical health support; a second user device worn by the user; a third user device operated by the user during work hours; and a server device communicably connected to the first user device and the third user device, The first user device is a meal information input unit for inputting information about a meal consumed by the user when the user consumes a meal; a first information transmission unit that transmits to the server device information on an input time when the information on the meal taken by the user is input; Equipped with The second user device is a step counting unit that counts the number of steps of the user when the user walks; A sleep time measurement unit that measures a sleep time of the user when the user sleeps; a second information transmission unit configured to transmit information on the number of steps of the user and information on the sleeping hours of the user to the server device via the first user device; Equipped with The third user device is a working time measurement unit that measures the working time of the user from a work start to a work end based on a work start action when the user starts working and a work end action when the user starts working; a third information transmission unit configured to transmit information on the working hours of the user to the server device; Equipped with The server device includes: an information receiving unit that receives information of the input time from the first user device, receives information of the number of steps of the user and information of the sleeping hours of the user from the second user device via the first user device, and receives information of the working hours of the user from the third user device; a regular meal index calculation unit that calculates a regular meal index indicating a degree to which the user regularly eats meals based on the information of the input time received from the first user device; a first machine learning unit that analyzes, by machine learning, a relationship between the regular meal index, the number of steps, the sleeping hours, and the working hours of all users, and a judgment result of whether the user is mentally and physically healthy or not, which is judged using predetermined reference data; a first estimation unit that estimates whether the user to be determined is physically and mentally healthy based on the relationship analyzed by the first machine learning unit, using information on the regular meal index, the number of steps, the sleeping hours, and the working hours of the user to be determined as input, and outputs the result; a first estimation result transmission unit that transmits an estimation result by the first estimation unit to a first user device of the user to be determined; Equipped with The first user device is a first estimation result display unit that displays the estimation result by the first estimation unit received from the server device; a self-diagnosis result input unit for inputting a self-diagnosis result of a user of the first user device as to whether the user is mentally and physically healthy; a self-diagnosis result transmission unit that transmits the user's own diagnosis result input by the user to the server device; Equipped with The server device includes: a data amount determination unit that determines whether or not a data amount of the determination result of the user itself received from the first user device exceeds a predetermined reference data amount for some users including the user to be determined among all the users; a second machine learning unit that, when it is determined by the data amount determination unit that the reference data amount has been exceeded, analyzes, by machine learning, a relationship between the regular meal index, the number of steps, the sleeping hours, and the working hours of the partial user, and the determination result of the user himself / herself; a second estimation unit that estimates whether the user to be determined is mentally and physically healthy based on the relationship analyzed by the second machine learning unit, using information on the regular meal index, the number of steps, the sleeping hours, and the working hours of the user to be determined as input, and outputs the result; a second estimation result transmission unit that transmits an estimation result by the second estimation unit to a first user device of the user to be determined; Equipped with The first user device is A mind and body health support system comprising a second estimation result display unit that displays the estimation result by the second estimation unit received from the server device.

2. The data amount determination unit determines, for the user to be determined, whether or not a data amount of the determination result of the user itself received from the first user device exceeds a predetermined reference data amount; when it is determined by the data amount determination unit that the reference data amount has been exceeded, the second machine learning unit analyzes, by machine learning, a relationship between the regular meal index, the number of steps, the sleeping hours, and the working hours of the user to be determined, and a result of the determination of the user himself / herself; The mental and physical health support system of claim 1, wherein the second estimation unit estimates whether the user to be judged is physically and mentally healthy based on the relationship analyzed by the second machine learning unit, using as input information the regular eating index, number of steps, sleep time, and working hours of the user to be judged.

3. When an image of a meal ingested by the user is captured using the first user device, information obtained by performing image analysis on the image is input to the meal information input unit as information regarding the ingested meal, The mind and body health support system according to claim 1 , wherein the first information transmission unit transmits information on a time when the image was captured to the server device as the input time information.

4. When information about a meal taken by the user is input or selected by the user using the first user device, the information obtained by the user input or selection is input to the meal information input unit as information about the taken meal, The mind and body health support system according to claim 1 , wherein the first information transmission unit transmits information on a time when the user input or selection was made to the server device as the input time information.

5. 2. The mind and body health support system according to claim 1, wherein the regular meal index calculation unit calculates a breakfast index indicating a degree to which the user has properly eaten breakfast, a lunch index indicating a degree to which the user has properly eaten lunch, and a dinner index indicating a degree to which the user has properly eaten dinner, based on the information of the input time received from the first user device, and calculates the regular meal index based on the breakfast index, the lunch index, and the dinner index.

6. A method executed in a mental and physical health support system including a first user device owned by a user who is a target of mental and physical health support, a second user device worn by the user, a third user device operated by the user during work, and a server device communicatively connected to the first user device and the third user device, The method includes steps executed in the first user device, a meal information input step of inputting information about a meal consumed by the user when the user consumes a meal; a first information transmission step of transmitting to the server device information on an input time when the information on the meal taken by the user is input; Including, The method includes steps executed in the second user device, a step counting step of counting the number of steps of the user when the user walks; a sleep time measuring step of measuring a sleep time of the user when the user sleeps; a second information transmission step of transmitting information on the number of steps of the user and information on the sleeping hours of the user to the server device via the first user device; Including, The method includes steps executed in the third user device, a working time measuring step of measuring a working time from a start of work to an end of work of the user based on a work start action when the user starts working and a work end action when the user starts working; a third information transmission step of transmitting information on the user's working hours to the server device; Including, The method includes steps executed in the server device, an information receiving step of receiving information of the input time from the first user device, receiving information of the number of steps of the user and information of the sleeping hours of the user from the second user device via the first user device, and receiving information of the working hours of the user from the third user device; a regular meal index calculation step of calculating a regular meal index indicating a degree to which the user regularly takes in meals based on the information of the input time received from the first user device; a first machine learning step of analyzing, by machine learning, a relationship between the regular meal index, the number of steps, the sleeping hours, and the working hours of all users, and a judgment result of whether the user is mentally and physically healthy or not, which is judged using predetermined reference data; a first estimation step of estimating whether the user to be determined is physically and mentally healthy or not based on the relationship analyzed in the first machine learning step, using information on the regular meal index, the number of steps, the sleeping hours, and the working hours of the user to be determined as input, and outputting the result; a first estimation result transmission step of transmitting an estimation result by the first estimation step to a first user device of the user to be determined; Including, The method further comprises the step performed in the first user device: a first estimation result display step of displaying an estimation result obtained by the first estimation step and received from the server device; a self-diagnosis result input step of inputting a self-diagnosis result of the user of the first user device as to whether the user is mentally and physically healthy; a self-diagnosis result transmission step of transmitting the user's own diagnosis result input by the user to the server device; Including, The method further includes a step executed in the server device, a data amount determination step of determining whether or not the data amount of the determination result of the user himself / herself received from the first user device exceeds a predetermined reference data amount for some users including the user to be determined among all the users; a second machine learning step of analyzing, when it is determined that the reference data amount is exceeded by the data amount determination step, a relationship between the regular meal index, the number of steps, the sleeping hours, and the working hours of the partial user and the determination result of the user by machine learning; a second estimation step of estimating whether the user to be determined is physically and mentally healthy or not based on the relationship analyzed in the second machine learning step, using information on the regular meal index, the number of steps, the sleeping hours, and the working hours of the user to be determined as input, and outputting the result; a second estimation result transmission step of transmitting an estimation result by the second estimation step to a first user device of the user to be determined; Including, The method further comprises the step performed in the first user device: The method further comprises a second estimation result display step of displaying an estimation result obtained by the second estimation step and received from the server device.

Images