JP2020086567A - Action recommendation device and action recommendation system - Google Patents

Abstract

To provide an action recommendation device and an action recommendation system for recommending an action to be taken to a user.SOLUTION: In an action recommendation system, a manager server 200 comprises: communication means 210 for transmitting question data composed of a plurality of items to an arbitrary user, and for receiving answers of respective items to the question data transmitted by the question data transmission means; calculation means 230 for generating an input value acquired by changing several item content of the answers received by the answer reception means; the calculation means 230 for inputting the input value generated by the input value generation means to an AI device 300 having an artificial neural network learnt by a plurality of sets composed of mission data and the answers from the user who has executed the mission data, and for acquiring an output value corresponding thereto. The communication means transmits the mission data based on the output value acquired by the calculation means to the arbitrary user.SELECTED DRAWING: Figure 1

Description

The present invention relates to an action recommending device and an action recommending system, and in particular, an action recommending device and action recommending device that recommends an action to be taken to a user by using an artificial neural network in which statistical data regarding questioning to the user is learned. Regarding the system.

In Patent Document 1, the n-th mission data including a plurality of missions by the applicant is transmitted to a plurality of user terminals, and the n-th mission data transmitted from each user who has performed the n-th mission data. And a means for receiving the mission achievement ratio of the user related to the n-th mission data, and an improvement is found in the n-th inquiry data considering the user mission achievement ratio related to the n-th mission data. User who has transmitted the (n+1)th mission data, which has increased the load of at least one of the plurality of missions, to the user terminal and has performed the (n+1)th mission data when there is a question to be asked. In consideration of the means for receiving the user's mission achievement rate related to the (n+1)th inquiry data and the n+1th mission data transmitted from the above, and the user's mission achievement rate related to the (n+1)th mission data, A hypothesis verification device is disclosed, which comprises means for determining that the one mission contributes to the improvement of the inquiry item when the inquiry item further improves in the inquiry data. According to Patent Document 1, it becomes possible to know with high accuracy what kind of user each of the missions is preferable to, and as a result, the user has an incentive to perform a mission that is beneficial to himself/herself. The effect that will be worked is obtained.

Japanese Patent No. 6152313

The invention disclosed in Patent Document 1 can provide a user with a desired mission, but if the effect of mission execution is transmitted to the user in an easily understandable manner, , It will be possible to give an incentive to carry out the next mission.

That is, in order to improve the mission achievement rate of the user, it is meaningful to show the effect of the mission execution to the user, and in particular, if the effect of the mission execution is shown so that the transition of the behavior familiar to the user can be understood, It is presumed that the user may easily feel the effect.

Therefore, an object of the present invention is to improve the mission achievement rate of a user by effectively showing the result of mission execution to the user.

The behavior recommendation device of the present invention is
Transmission means for transmitting mission data including a plurality of missions to a user terminal,
Acquisition means for acquiring an output result to the user terminal by the user who has performed each mission data transmitted by the transmission means,
Reporting means for reporting the mission execution result by the user based on the output result obtained by the obtaining means,
Equipped with.

According to the present invention, the user can grasp the transition of behaviors that are familiar to him/herself, and can effectively obtain the result of mission execution to obtain an incentive to improve the mission achievement rate. ..

The acquisition means is typically capable of acquiring output results such as the number of keystrokes of the keyboard attached to the user terminal, the amount of movement of the mouse, the number of smiles of the user imaged by the camera, the program activation frequency, and the file usage frequency. As described above, the usage time or usage of an input device such as a keyboard or mouse attached to the user terminal, the number of programs executed by the user terminal, the number of files used by the user terminal, and the number of steps the user terminal has It can be any one of the number of steps measured by the counting function, the moving distance measured by the GPS function of the user terminal, and the communication time with the user terminal with another user terminal. Other information that can be acquired by the acquisition means will also be described later.

Furthermore, the receiving means for receiving the inquiry data transmitted from the user who performed each mission data is provided, and the inquiry data is data including a plurality of items,
An input value generating means for generating an input value in which some item contents of the inquiry data received by the receiving means are changed,
The input value generated by the input value generating means is input to an artificial intelligence device having an artificial neural network learned by a plurality of sets of the mission data and answers from the user who has performed the mission data. And output value acquisition means for acquiring the output value corresponding to this,
Mission data transmitting means for transmitting mission data based on the output value acquired by the output value acquiring means to any user terminal,
Can also be provided.

In this case, the data based on the answer returned from the user is used as the input value, and by using the learned artificial neural network, the output value that cannot be realized by linear regression is calculated, and the mission data is calculated based on the output value. Since it is created, an advanced mission can be given to each user based on the task for each user.

The mission data can be created based on the degree of difficulty of performing the mission data used when learning the artificial neural network and an answer when the mission data is performed.

The artificial neural network can be an artificial neural network including a recurrent neural network that can be processed over time.

The inquiry data includes the user's usual eating habits, for example, the frequency of eating out and the frequency of eating lunches sold at convenience stores. Further, the interview data includes some activity levels including the presence/absence of usual headache, the presence/absence of usual abdominal pain, the ease of catching a cold, and the presence/absence of a habit of moving the body.

In addition, the action recommendation system of the present invention is
With the above action recommendation device,
An artificial intelligence device including the artificial neural network,
Equipped with.

It is a typical block diagram of the action recommendation system of embodiment of this invention. It is a figure which shows the example of inquiry data etc. of each user registered into DB400 of inquiry data etc. of FIG. It is a figure which shows the example of the result from the user who added the mission data. 7 is a flowchart showing an operation regarding an action recommendation among the operations of the administrator server 200 shown in FIG. 1. 7 is a flowchart showing an operation regarding an action recommendation among the operations of the administrator server 200 shown in FIG. 1. It is a figure which shows the example of the comparison table alert|reported to the user produced by the production|generation means 260 of FIG. FIG. 7 is a diagram showing an example of a transition destination screen when the recommended food menu display area 630 of FIG. 6 is selected by clicking or the like. It is a figure which shows the example of a pop-up screen at the time of selecting "the egg full omelet" of FIG.7(a). It is a figure which shows the example of a transition destination screen when it selects by clicking etc. of the health state display area 660 of FIG. FIG. 7 is a diagram showing an example of a transition destination screen when the numerical display area 650 of FIG. 6 is selected by clicking or the like. It is a figure which shows the example of a screen which changes when it selects by clicking "method" of the upper right of FIG. It is a figure which shows the detailed article supervised by the registered dietitian. It is a figure which shows the example of a screen which changes when it selects by clicking "My list" in the upper right of FIG. It is a figure which shows the example of a screen which changes when the location of "details" in the my list display area 710 of FIG.

100 user terminal 200 administrator server 210 communication means 220 learning means 230 calculating means 240 registration means 250 digitizing means 260 creating means 300 artificial intelligence (AI) device 400 inquiry data database (interview data DB)
500 administrator terminal

Embodiment of the invention

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, the action recommending device improves the mission achievement rate of the user by effectively showing the result of mission execution to the user, and the action recommending system in which an artificial intelligence device is added to this action recommending device, It will be described how to give an advanced mission to each user based on the task for each user.

(Description of configuration)
FIG. 1 is a schematic configuration diagram of an action recommendation system according to an embodiment of the present invention. In FIG. 1, a user terminal 100, an administrator server (action recommendation device) 200, an artificial intelligence (Artificial Intelligence) device (hereinafter, referred to as “AI device”) 300, and a database of inquiry data and the like, which will be described below. (Hereinafter, referred to as “DB for inquiry data etc.”) 400 and an administrator terminal 500 are shown.

The user terminal 100 is a terminal operated by the user, and mainly receives inquiry data transmitted from the administrator server 200 or mission data including a plurality of missions, and answers the inquiry data of the user or performs the mission. Later answers are appropriately transmitted to the administrator server 200.

The user terminal 100 can be realized by a mobile phone, a smartphone, a personal computer, a video game, an IT device, an AV device, or the like that can perform wireless communication or wired communication with the administrator server 200.

The administrator server 200 is a server (action recommendation device) managed by the administrator of the action recommendation system of this embodiment. The administrator server 200 includes a communication unit 210, a learning unit 220, a calculating unit 230, a registering unit 240, a digitizing unit 250, and a creating unit 260, which will be described below. The function of each of these means may be realized by the cooperation of the CPU and the memory, for example.

The communication unit 210 transmits various data such as inquiry data and mission data registered in the inquiry data DB 400 to the user terminal 100. Further, the communication unit 210 receives various data such as an answer to the inquiry data transmitted from the user terminal 100. The communication unit 210 also serves as an acquisition unit that acquires the output result for the user terminal 100 and as a notification unit that notifies the user of the mission execution result based on the output result acquired by the acquisition unit, via the user terminal 100.

The interview data consists of multiple items such as sex, age, weight, and other personal data that the subject or patient answers at the time of a medical examination or initial examination performed at a hospital, etc., and the amount of alcohol and smoking. .. In addition, if possible, in addition to these, blood pressure, blood sugar level, and further, good or bad of awakening, presence/absence of headache/abdominal pain, presence/absence of chronic illness, ease of catching cold, presence/absence of physical activity, etc. You may ask various information including. Further, the user's usual eating habits, for example, the frequency of eating out and the frequency of eating lunches sold at convenience stores are included, but the present invention is not necessarily limited to interviews regarding health conditions.

In addition, the timing of transmitting the inquiry data is indispensable for the user to use the behavior recommendation system for the first time, and then, for example, once a month, once a year, or from the user's request. It is possible that some or all of the cases such as when there is. In particular, if the notification is made on the same day of every month or on the same day of every year, it is possible to give regular advice on health according to the result of the inquiry, which is suitable for the user.

Moreover, the acquisition unit that the communication unit 210 is capable of acquiring various information. This information includes, for example, the usage time or usage amount of the input device of the user terminal 100 or the input device connected thereto. The input device mentioned here includes an input key or a microphone for voice input when the user terminal 100 is a mobile phone, and a touch panel display or a microphone for voice input when the user terminal 100 is a smartphone. In the case of a computer, a mouse, a keyboard, and the like can be given. In the case of a video game, a game controller can be given. In the case of IT equipment, its input operation buttons can be given. In the case of AV equipment, its input button can be given. Or a remote controller can be mentioned.

Further, as the information that can be acquired by the acquisition unit that the communication unit 210 takes, when the user terminal 100 is a smartphone or a personal computer, the usage time or the number of programs executed by the smartphone or the personal computer, or the number of files used. It can also be used time or number, or the number of games executed in the case of a video game. If the user terminal 100 is a smartphone, the number of steps measured by the pedometer function, the user terminal 100 is a mobile phone or a smartphone. In this case, the data communication time for a call made with another user terminal, and the data communication time for sending and receiving mail including the case of a personal computer can be used.

The learning unit 220 uses, as learning data, a set of mission data (including inquiry data) and answers of users who have performed the mission (including answers corresponding to the inquiry data) stored in the inquiry data DB 400. The artificial neural network of the AI device 300 is used to perform learning by using the artificial neural network. For example, it is conceivable to input learning data through a programming API.

Here, even if a researcher or the like seeks a monitor in order to collect interview data and responses to it, and mission data and effects such as the achievement rate to this, it is normally necessary to monitor tens of thousands of monitors. Collecting numbers is very difficult.

However, in the case of the action recommending system of the present exemplary embodiment, if the user can operate the user terminal 100, the mission data and the effect such as the achievement rate can be collected. From a rate perspective, the total number of users will be very large.

In particular, as will be described later, the desired application software can be installed in the user terminal 100, and the application server can be used to transmit the achievement rate for mission data by the administrator server 200 without the user explicitly transmitting the achievement rate. It is suitable to do so.

The calculation unit 230 uses the AI device 300 having the artificial neural network learned by the learning unit 220 as an input value with some of the answers to the inquiry data transmitted to the user terminal 100 changed, and responds to this. The output value to be calculated is calculated.

The registration means 240 registers various data of the answers to the inquiry data/mission data, which are transmitted from the user terminal 100 and received by the communication means 210, in the inquiry data DB 400. Then, using the registered data, learning of the artificial neural network of the AI device 300 can be continuously executed.

The digitizing means 250 digitizes various data transmitted to the user terminal 100 or the administrator terminal 500, such as digitizing the achievement rate of mission data by the user transmitted from the user terminal 100.

The creating means 260 creates a notification medium such as the screen examples shown in FIGS. 6 to 11 including the achievement rate of the mission data digitized by the digitizing means 250. The screen created by the creating unit 260 is transmitted to the user terminal 100 through the communication unit 210 either by request from the user terminal 100 or spontaneously.

The AI device 300 is for identifying mission data to be transmitted to the user terminal 100 by utilizing a mathematical model such as an artificial neural network. As the artificial neural network, it is preferable to use a recurrent neural network, which has strength in temporal processing, but is not limited to this.

In particular, if an artificial neural network, which has strength in temporal processing, is used, it is possible to reduce the number of questions in the medical inquiry data and use it as highly recommended information by setting a unique task for each user.

The inquiry data etc. DB 400 stores a set of mission data including inquiry data to be transmitted to the user terminal 100 and an answer of the user who performed the mission including an answer corresponding to the inquiry data transmitted from the user terminal 100. Will be registered in advance.

The administrator terminal 500 is a terminal operated by the administrator of the action recommendation system of this embodiment. Although the administrator terminal 500 is not limited to this, for example, a desktop personal computer or the like can be used. The administrator operates the administrator terminal 500 to register the mission data to be transmitted to the user terminal 100 before the learning of the artificial neural network of the AI device 300. Specifically, for example, if there is a fact that it is good to eat an apple as a migraine countermeasure, the event of having a migraine and the mission of eating an apple are linked and registered.

Note that, for example, FIG. 1 shows an example in which the AI device 300 and the inquiry data etc. DB 400 are provided outside the administrator server 200. However, any one or at least one of them may be provided in the administrator server 200. It may be provided inside.

(Explanation of action)
Next, the action of the action recommendation system of the present embodiment will be outlined using a specific example. It should be noted that a more detailed description of the operation of the action recommendation system according to the present exemplary embodiment will be given together with the operation description given later.

First, for example, it is assumed that the inquiry data including the following 5 items is initially transmitted to the user terminal 100 and the answer result is obtained.
A: Do you eat salad at least once a week?
Yes; Eat No; Do not eat B: Do you use stairs rather than elevators and escalators?
Yes; Use No; Not use C: Is the amount of alcohol you drink in a week less than 4 go?
Yes; less than 4 go No; 4 go or more D: Isn't your tiredness gone through these days?
Yes; No No; Yes E: Is it good to wake up?
Yes; good No; bad

In the present embodiment, all the inquiry data can be answered with Yes/No, so that the burden on the user at the time of answering is reduced and the burden of data processing on the administrator server 200 is also reduced.

It is assumed that the inquiry data composed of this [ABCDE] is transmitted to the user α, and if the answer result from the user α is 1 in the case of Yes and 0 in the case of No, it is [11001]. Then, since the amount of liquor that the user α drinks is large in one week, it can be considered that this may be the cause of not getting tired.

Similarly, when the same inquiry data is transmitted to another user β, if the response result from another user β is [00101], the user β has a low vitamin intake and/or lack of exercise. It is possible that this is the reason why fatigue does not disappear.

However, the causal relationship between the answer results of the user α and the user β may be reversed. For example, the user β may not be able to secure a sufficient time for breakfast due to the fact that he/she does not wake up well, and thus his/her vitamin intake may be low.

However, taking the case of user β as an example, encouraging user β to increase the intake of vitamins and to eliminate lack of exercise may lead to improvement in the fact that fatigue is not lost. It can be said that it is useful because it has sex, and it is worth trying it.

Therefore, in the present embodiment, a set of the inquiry data transmitted to the user α and the answer result [11001] of the user α for the purpose of recommending what kind of action should be performed to a certain user, Similarly, for the purpose of causing the artificial neural network of the AI device 300 to learn the set of the inquiry data transmitted to the user β and the answer result [00101] of the user β, the inquiry data etc. DB 400 is registered in the inquiry data DB 400 by the registration means 240. I will register.

Further, as will be described later, based on these inquiry data, the mission data to be recommended to the user α and the user β are respectively transmitted, and the answers from the user α and the user β who have executed the mission data are also registered by the registration means 240. The inquiry data etc. are registered in the DB 400. To give a typical example of these mission data and answers, for the user α, the mission data of reducing the amount of liquor to be drunk in a week is given, and the answer that the user is less tired will be acquired.

If the number of users who use the behavior recommendation system of the present embodiment becomes very large, and therefore, if a large amount of inquiry data etc. is accumulated in the inquiry data etc. DB 400, it will be stored in the artificial neural network of the AI device 300. Let them learn.

Here, regarding the example of the user β, if the artificial neural network of the AI device 300 is not sufficiently learned, the data based on the inquiry data relating to the user β and the answer thereof are input to the AI device 300. However, it is not possible to grasp whether or not low vitamin intake and/or lack of exercise is likely to be the cause of not getting tired. If the neural network is in a sufficiently learned state, if the data based on the inquiry data related to the user β and the answer thereto is input to the AI device 300, it may be that vitamin intake is low and/or exercise is insufficient. It is possible to understand whether or not there is a high possibility that it is the cause of tiredness.

Specifically, by the calculation means 230,
・Only the variable of item A regarding vitamin intake is "1" instead of "0" [101],
・Only the variable of item B relating to lack of exercise is “1”, not “0” [011],
-The variables of both item A and item B are "1" instead of "0" [111],
The variables of both item A and item B are "1" instead of "0" [001],
Are input values to the AI device 300, and output values corresponding to these are acquired.

For example, in the interview data DB 400,
-When [ABC] is [101] and [D] is [1], the number of registered responses is 500,
-When [ABC] is [011] and [D] is [1], the number of registered answers is 500,
-When [ABC] is [111] and [D] is [1], the number of registered responses is 1000,
-When [ABC] is [001] and [D] is [1], the number of registered responses is 100,
Then, if [ABC] corresponding to [1000], which has the highest accumulated number, behaves as [111], it can be said that fatigue will be eliminated with a high probability statistically.

In other words, generally speaking, when an answer to the inquiry data is obtained from a specific user, the calculating means 230 appropriately changes each item (variable) such as [ABC] in the above example. If the input values for the learned AI device 300 are set, the output values corresponding to these can be acquired, and the mission based on the output values is given to the user.

In this way, it is possible to derive the results that the intake of vitamins is low, the lack of exercise, and the statistically high possibility of being the cause of not getting tired. Therefore, if you are told that you are less likely to get tired, use a mission such as eating salad at least once a week and use stairs rather than elevators and escalators for user γ. It can be said that the user γ eliminates the reason why the user is not statistically exhausted by adding a mission such as a help.

It should be noted that, by using the learned AI device 300, depending on the answer to the inquiry data, a mission of ingesting vitamins from vegetables is given to one user, and an intake of vitamins from fruits is given to another user. The result may be to add a mission to do so.

After assigning a mission to each user, the administrator server 200 acquires the answers from the users who have performed the mission, and also accumulates a set of the mission and its answer in the inquiry data DB 400.

By the way, such a series of processes may increase the number of items of the inquiry data in an attempt to provide a more useful mission that is finely and finely divided. Then, it is not enough to derive what the preferable mission is from the four combinations of about 2×2 as in the above example, and the amount of calculation becomes enormous.

Therefore, in the present embodiment, the learning means 220 also causes the artificial neural network of the AI device 300 to learn the set of missions including inquiry data and the answers thereof, which are accumulated in the inquiry data DB 400. Even with the amount of calculation, it is possible to derive what the desired mission is for each user.

If the above is put together and generalized, as an outline of the action of the action recommendation system of the present embodiment, first,
(1) Sending detailed and subdivided inquiry data to a plurality of (many) users,
(2) Give a mission that is considered preferable to each user,
(3) The artificial neural network of the AI device 300 is trained using a set of a mission including inquiry data and an answer when the mission is performed.

Next, after learning the artificial neural network of the AI device 300,
(4) A part (variable) of the answer transmitted from the specific user is input as an input value to the AI device 300 having the learned artificial neural network, and the corresponding output value is calculated. Then
(5) Select a mission based on the calculated output value, and give a more useful advanced mission to the specific user.
It turns out that.

Furthermore, if a specific user performs a high-level mission assigned to him/herself, and then the condition of the specific user improves/improves, that fact is stored in the DB 400 such as interview data, so the calculated output value The accuracy of will also be improved.

In addition, in the series of explanations so far, examples related to health such as being able to get rid of tiredness and sleeping well are given, but this behavior recommendation system is not only intended to improve health condition Please note that it can be used in a wide variety of fields by appropriately selecting the item contents of the inquiry data.

For example, but not limited to, examples of applications may include providing an advanced instructional menu for a particular athlete. Specifically, if the objective variable relating to the AI device 300 is replaced with a mileage, a sprint time, or the like, a guidance menu is given as mission data, and if the performance obtained when practicing it is given as an answer, what kind of Understand whether to select a guidance menu. Similarly, supplements to be taken by athletes can be specified by appropriately changing the objective variables.

Also, as a completely different example, if the objective variable is replaced with the sales of each employee, etc., it is determined which job should be assigned to which employee in order to increase the sales of the entire company. Can also be used for Generally speaking, as long as the number of explanatory variables is relatively large and the number of objective variables is relatively small, the action recommendation system can be preferably used.

(Description of application software)
Next, application software installed in the user terminal 100 will be described. Note that this application software does not necessarily have to be installed in the user terminal 100, and the user may appropriately select whether or not to install.

However, in conclusion, if this application software is installed in the user terminal 100, there is an advantage that the operation load on the user is reduced, and the action recommendation system can also exclude arbitrary answers. There are advantages.

Here, for example, when the user terminal 100 is a smartphone, since the smartphone usually has an image capturing unit, an image of the face image of the user who is using the user terminal 100 or the meal content of the user is captured. be able to. Further, when the user terminal 100 is a smartphone, it is a usage time, a call time, the number of steps of the user carrying the user terminal 100, and a movement route (movement distance) using the GPS function. You can also do it.

This application software transmits the captured image data of the face image or the image authentication result thereof or the log data of the usage time of the user terminal 100 to the administrator server 200 as appropriate using the communication means of the smartphone. To do. As a result, the acquisition unit of the communication unit 210 of the administrator server 200 can acquire these pieces of information and the information described below.

If the image pickup data of the face image transmitted from the user terminal 100 is not subjected to the image recognition processing, the administrator server 200 performs image processing on the captured image data and then determines whether or not the number of smiles is increased through matching processing or the like. It is determined whether the number of smiles per hour exceeds a predetermined threshold value, whether a salad is eaten, and the like.

Further, the administrator server 200 determines whether or not the number of daily steps has increased. As a result of these determinations, when it is confirmed that the number of steps of the user has increased, it is possible to determine that there is a high possibility that the difficulty in getting tired out tends to improve in the case of the previous example. ..

Further, when the user terminal 100 is a personal computer, if the personal computer is of a type including an image pickup means, it is used, and if a web camera connected to the personal computer is used, it is used by the user. Similar to the case where the terminal 100 is a smartphone, the face image of the user, the posture, the smiling time, the time during which the user may be talking, etc. may be transmitted to the administrator server 200.

Furthermore, regarding the usage time of the user terminal 100, if this application software is equipped with a task manager monitoring function or the like, the usage frequency of the user's keyboard or mouse or the number of programs or files used can be grasped. Therefore, this application software may appropriately transmit information indicating the usage time of the user terminal 100, such as the imaged data of the face image, to the administrator server 200.

The frequency of use of input devices such as a keyboard and a mouse can be obtained, more specifically, from the number of keystrokes on the keyboard, the moving distance of the mouse, and the like. The number of keystrokes on the keyboard can be obtained by using software or hardware called a key logger that monitors the key input to the computer, and regarding the moving distance of the mouse, the resolution of the display attached to the user terminal 10 ( dpi) and the moving distance of the mouse pointer.

An object placed near the keyboard may be in contact with a specific key for some reason while the user is away from the desk, or the user may fall asleep while inputting information to the keyboard. Then, a specific key may be continuously pressed. In the behavior recommendation system of the present embodiment, it is not preferable to use the number of raw keystrokes in such a case, so the key repeat portion is subjected to a processing process such as excluding it, and the processed May be the output result. That is, for example, when ten inputs of "k", such as "kkkkkkkkkk", are detected by the keylogger, the number of keystrokes can be treated once.

The use time or the number of programs can be grasped from the start time of the program through a task manager (operation system in a broad sense) or the like, and can be obtained from the start time. Note that even if multiple programs are running, it is rare for the user to make input for processing all of them, so use only the program displayed on the foreground of the display, for example. Counting time is also a method.

Regarding the usage time or the number of files, it is reasonable to judge the usage time from the time stamp of the file that has been used recently (most recently used file). Of course, not only the most recently used file but also the usage time for all changed files may be obtained from an educational perspective, but the load on the user terminal 10 is increased by searching the files for that purpose. It is advisable to determine how many files are to be used and the usage time is determined according to the specifications of the physical memory in the user terminal 10.

When the user terminal 10 is a camera-equipped notebook personal computer, the smiling time can be obtained from the face image of the user reflected in the moving image captured by the camera. Instead of capturing the image, the still image may be captured every 5 seconds and acquired based on the number of times.

In addition to the laptop computer with a built-in camera, you may take the same measures while using a smartphone, and even in the case of a desktop computer, you can do the same, provided that a webcam is connected. Good.

It should be noted that when this type of laptop computer is not connected to the power supply, the battery consumption amount is switched to the power saving mode, or the imaging frequency is reduced when the remaining battery power is below a predetermined threshold value. That is also a law.

By the way, it is considered that one user often uses a plurality of user terminals 10 on a daily basis. For example, a desktop computer is used in the office, a smartphone is used during traveling time, and a laptop computer is used at home. In order to deal with this, the acquisition unit may acquire the output results from the user with respect to the plurality of user terminals 10 and aggregate them. With this configuration, the notification unit can notify the mission execution result by the user based on the output result after the aggregation.

To summarize the above, the input to the acquisition means is a keyboard and a mouse attached to one or more user terminals 10 and each output from the operating system of the user terminal 10. Then, the process in the acquisition means is to obtain a value converted into annual income described later as appropriate according to the type of the input. Then, the output of the acquisition means becomes the obtained value.

When the output value of the acquisition means is examined, as a general theory, for example, work is done even on holidays such as Saturdays and Sundays, holidays such as year-end and New Year holidays, and even early morning or late night. It can be said that the user is highly conscious of the work and may have a high annual income because the user is statistically working on returning the holidays. Therefore, in consideration of such a situation, the acquisition means may perform a process of weighting in consideration of date and time information and obtaining a value converted into annual income.

Also, regarding the number of keyboard strokes, I explained that it is one method to use a modified number instead of using the raw number of keystrokes, but when focusing on the point of processing, using a mouse With regard to frequency as well, it means that processing is performed according to the resolution of the display, and with regard to programs, for example, the usage time is counted only for the program displayed in the foreground of the display. It can be understood as being processed because the time is not counted.

That is, in the action recommendation system of the present embodiment, the output result notified by the notification means can be the total result based on the processed information.

As described above, by transmitting the information and the like acquired by using the application software from the user terminal 100 to the administrator server 200 almost in real time or every few minutes to several hours, fatigue is caused early by performing the mission. It becomes possible to judge whether or not there is a tendency for improvement in health condition such as difficulty in getting out.

If an attempt is made to obtain an answer from the user who has performed the mission data without using the application software, the user may need to operate the user terminal 100, and thus the method using the application software is not recommended. It is preferable from the viewpoint of reducing the burden on the user.

Further, as an effect obtained by using the application software, it is possible to objectively judge the state based on image recognition or the like in the administrator server 200, so that it is more objective than to make the user answer the inquiry data. It becomes possible to judge whether or not the health condition has a tendency to improve. Furthermore, it is practically impossible for the user to recognize the number of smiles per unit time and send it to the administrator server 200 without using application software. The user may send the evaluation.

However, even if the application software is not installed in the user terminal 100, if the inquiry data is appropriately transmitted to the user terminal 100 and the answer from the user is acquired, the administrator server 200 can avoid fatigue. It is possible to judge whether or not there is an improvement tendency.

Regardless of whether the application software is installed or not, the answer result to the inquiry data accumulated in the administrator server 200 is sequentially updated, and if the learning of the artificial neural network of the AI device 300 is continuously advanced, the user It is possible to obtain an additional effect that the mission data to be given to the user becomes more preferable.

Furthermore, for example, it is possible to find a causal relationship between a mission that is not currently known and its effect. For example, assuming that it was not known how to increase the number of user smiles per unit time, many users performed some mission, and as a result, the user smiles per unit time. If the number of times of the increase is increased, the mission may be a factor that increases the number of smiles statistically.

If so, as a secondary effect of the use of the behavior recommendation system of the present embodiment, it is possible to investigate this causal relationship in the future, and further, as a result, it may contribute to preventive medicine. In addition, the range of choices for future missions given to other users will be expanded.

That is, in this example, for example, when an attempt is made to increase the number of smiles, there are some missions that have been assigned so far, but there are some circumstances in which they are difficult to perform. On the other hand, there are cases in which it is easy to carry out missions for which it has been found that the number of smiles can be increased by using the action recommendation system.

In this way, it is possible to select missions in the order in which they are considered to be highly effective for the user, and among those with a high probability of achieving a certain effect, those with a high mission achievement rate in the past are selected. If you can do it, you will have more choices for future missions.

(Explanation of data registered in DB 400 such as inquiry data)
2 and 3 are diagrams showing examples of inquiry data of each user registered in the inquiry data DB 400 of FIG. 1.

As shown in FIG. 2 as an example, the items of the interview data are “sex”, “age”, “weight”, “blood sugar level”, “blood pressure”, “good sleep”, “wakefulness”, and “goodness”. The items "drinking amount" and "smoking amount" are shown. It should be noted that these items are merely examples, and presence/absence of chronic diseases such as headache may be provided.

In the answer field of the inquiry data, the user can easily input/select the inquiry data, so that, for example, five options can be prepared. 2 and 3 show an example in which the corresponding numerical values are registered. Specifically, for example, "1" is associated with male and "2" is associated with female for gender, and for weight, "1" is too thin, "2" tends to be thin, and "3" is "3". Usually, options such as “4” tend to be overweight and “5” are overweight are available.

It should be noted that the values that are generally considered to be better are set to be higher (in the above example, "normal" is 5 points, "overweight" is 0 points, "thinness" is 3 points, etc. ), for example, it is also effective to digitize the inquiry data with a maximum of 100 points, which leads to the numerical goal of the user.

The arrow shown in FIG. 3 is created based on the change in the data example shown in FIG. Here, it is shown that the goodness and badness of "awakening" are improved for users who have a high "achievement rate" of the mission.

It should be noted that here, for convenience of explanation of the data registered in the DB 400 such as the inquiry data, the data example shown in FIG. 2 is shown as if it was overwritten to become the data example shown in FIG. Since it is desired to increase the learning data before the completion of learning of the artificial neural network, it may be preferable not to overwrite.

(Explanation about learning data)
As described above, in the action recommendation system of the present embodiment, if the learning of the artificial neural network of the AI device 300 is not completed, the inquiry data and the like DB 400 is asked to accumulate the learning data of the artificial neural network. Accumulate a set of mission data including data and their answers.

For that purpose, the first mission to be given to the user α is
(1) Eat salad at least once a week,
(2) Use stairs rather than elevators and escalators,
(3) Limit the number of cigarettes to five per day,
There are three of them.

Then, it is assumed that the user α properly executes each of the first missions and then answers about the health condition. In this case, the set of the contents of each mission for the first time and the answer to the mission is stored in the DB 400 for the inquiry data.

Next, for example, the second mission with the following contents can be given to the user α. Note that, here, an example is shown in which the second mission is a modification of a part of the first mission, but it may be completely different from the first mission.
(1) Eat salad at least "2" times a week,
(2) Use stairs rather than elevators and escalators,
(3) Limit the number of cigarettes to five per day,

In fact, it is assumed that the second mission of the above contents is given to the user α, then the user α also achieves the second mission, and then answers about the health condition. In this case, the set of the contents of each mission for the second time and the answer to the mission is accumulated in the DB 400 such as inquiry data.

Next, for example, the third mission with the following contents can be given to the user α. Note that, here, an example in which the third mission is a modification of the first and second missions is shown, but it may be completely different from the first and second missions.
(1) Eat salad at least twice a week,
(2) Use stairs rather than elevators and escalators,
(3) Limit the number of cigarettes to "3" a day,

In fact, it is assumed that the third mission of the above content is given to the user α, then the user α also achieves the third mission, and then answers about the health condition. In this case, the set of the contents of each mission for the third time and the answer to the mission is accumulated in the DB 400 for the inquiry data.

In this way, the contents of the mission are changed as appropriate, and when the health condition is answered after that, the set of the contents of each mission and the answer to the mission is accumulated in the inquiry data DB 400. .. This is performed not only for the user α but also for other users.

Then, eventually, in the inquiry data DB 400, a set of mission data including many inquiry data and its answers is accumulated for hundreds or thousands of users. By using these as learning data, the artificial neural network of the AI device 300 is made to learn.

Then, for example, when the inquiry data is transmitted to another user terminal 100 and the answer corresponding to the inquiry data is returned from the user terminal 100, the calculation unit 230 sends the learned AI device 300 to the learned AI device 300. Therefore, a preferred mission for calculating a corresponding output value by using some of the answers to the inquiry data that have been changed as an input value and obtaining some specific effect for the user terminal 100 based on this output value. It is possible to select the data and send it by the communication means 210.

In other words, what kind of mission is performed and what kind of effect is obtained can be statistically grasped on the side of this action recommendation system as a highly accurate result that is not easily influenced by individual differences, and based on this, There is an effect that the mission data can be given to the user.

Further, as a side effect, for example, it becomes possible to assign a more effective mission to the user, and therefore, the user has a high probability of performing the assigned mission with a high probability of being effective. As a result, the incentive to carry out the mission will work, and as a result, the action recommendation system can be operated in a good cycle such that the accuracy of the response from the user fed back to the administrator server 200 is improved. ..

Then, the learning means 220 uses the set of mission data including the inquiry data accumulated in the inquiry data DB 400 and the answers thereof as the learning data of the AI device 300 regularly or irregularly, for example, every week. Train an artificial neural network.

The number of missions does not have to be three, but may be about five. However, if the number is too large, the mission achievement rate may decrease, so it is preferable to set the number to about 3 to 5.

(Explanation of operation)
FIG. 4 and FIG. 5 are flowcharts showing the operation regarding the action recommendation among the operations of the administrator server 200 shown in FIG. FIG. 4 shows a procedure before the completion of the initial setting in the operation regarding the action recommendation. The processes shown in FIGS. 4 and 5 are performed for each user.

<Processing before completion of initial settings>
First, the user operates the user terminal 100 to download the application software for the action recommendation system as described above, and installs it on the user terminal 100. After that, if the user activates the application software, inputs communication information such as name, sex, age, and mail address and taps the send button, the administrator server 200 is requested to send inquiry data. Is done.

In the administrator server 200, when the communication means 210 receives the inquiry data transmission request from the user terminal 100 (step S11), the user communication information and the like transmitted by the registration means 240 together with the transmission request is sent to the inquiry data DB 400. The inquiry data prepared in advance is transmitted to the user terminal 100 which is the transmission request source (step S12).

Then, in the user terminal 100, the inquiry data is received, and if the user inputs/selects his/her inquiry data in the user terminal 100 and taps the send button, the user terminal 100 sends a message to the administrator server 200. The inquiry data of the user is transmitted. Of course, the inquiry data may be transmitted to the user terminal 100 by the push type instead of the pull type.

In the administrator server 200, when the inquiry data is received by the communication unit 210 (step S13), the inquiry data is registered by the registration unit 240 in association with the communication information of the user already registered in the inquiry data DB 400. (Step S14).

By the above processing, the processing for initial setting such as member registration in the action recommendation system of the present embodiment is completed. The initial setting shown in FIG. 4 may be performed once for each user.

<Procedure after initial settings>
FIG. 5 shows a procedure after the initialization up to step S14 of FIG. 4 is completed. First, the administrator server 200 selects mission data from the mission data registered in the DB 400 for the inquiry data, etc., based on the answer to the received inquiry data (step S21).

Here, when the learning process for the artificial neural network of the AI device 400 has not been sufficiently performed, such as when the operation recommending system of the present embodiment is just started, the answer to the received inquiry data is obtained. Based on the above, the administrator transmits the mission data registered by using the administrator terminal 500. In the example described above, if the user has a migraine, the mission data of eating an apple corresponding to the event of having a migraine is to be transmitted.

On the other hand, when the learning process for the artificial neural network of the AI device 400 is sufficiently performed, the calculation unit 230 outputs the result of the mission data transmitted from the user who has performed the mission data to the learned AI device 300. A corresponding output value is calculated using the input values with some changes.

This point is important, so I will explain it again using another example. For example,
-Statistical data A that migraines are alleviated by eating apples more than once a week,
-Statistical data B that migraine is alleviated even if mild exercise is performed 2-3 times a week.
-Statistical data C that migraine hardly appears when eating apples more than once a week and performing mild exercise several times a week.
Was present.

Moreover,
Regarding statistical data A, it is a fact that migraine is alleviated in 30% of people,
Regarding statistical data B, it is a fact that migraine is alleviated in 40% of people,
As for the statistical data C, it is a fact that 95% of people have migraine relief.
And

Then, from the user α who has completed the initial setting,
・I don't eat apples much (variable 0),
・I feel a lack of exercise (variable 0),
・Migraine,
There is an answer.

Here, if a person selects a mission, typically, for the user α, based on the statistical data C, eat apples at least once a week and perform mild exercise several times a week. It is expected to choose the mission. However, in this embodiment,
(1) Variable 0 indicating that apples are not often eaten is changed to variable 1 and input to the AI device 300 having a learned artificial neural network,
(2) Variable 0, which indicates a lack of exercise, is changed to variable 1 and input to the AI device 300 having the learned artificial neural network,
(3) These both variables 0 are changed to variable 1 and input to the AI device 300 having the learned artificial neural network,
This is executed by the calculation means 230.

Then, since the AI device 300 is not a human being, even if the effect itself of the statistical data A to C cannot be recognized, according to the calculation means 230,
In the case of (1), an output value corresponding to that it is effective for 30% of people is obtained,
In the case of (2), an output value corresponding to 40% of people having an effect is obtained,
In the case of (3), an output value corresponding to 95% of people being effective will be obtained.

That is, the statistical data A to C are analysis results obtained by regression analysis, and the output values are analysis results obtained by deep learning of the learned AI device 300. Theoretically, these are equivalent.

Therefore, based on these output values, the administrator server 200 can understand that (2) is preferable to (1) and (3) is preferable to (2), and as a result, typically for the user α. Then, the mission of eating apples corresponding to (3) at least once a week and performing mild exercise several times a week is selected.

The mission data is transmitted to the user terminal 100 by the communication unit 210 (step S22).

After that, it is assumed that the user has performed the mission given from the administrator server 200. Typically, when the above-mentioned application software is not installed in the user terminal 100, the user operates the user terminal 100 to give a corresponding answer when newly receiving inquiry data. It can be input/selected and transmitted to the administrator server 200.

On the other hand, typically, when the above-described application software is installed in the user terminal 100 and the application software is activated, the user terminal 100 appropriately moves using the step count or the GPS function. The distance and the like can be acquired and transmitted to the administrator server 200.

Upon receiving the answer from the user, the administrator server 200 registers a set of the answer and the mission data related to the answer in the inquiry data DB 400 (step S23). Then, it is determined whether or not the accumulated number of sets of mission data and their answers in the inquiry data DB 400 is equal to or greater than a predetermined threshold value (step S24). The threshold for mission selection is set by the administrator. The next mission data is transmitted to the user terminal 100 by the communication unit 210.

As a result of the determination, if the set of mission data and its answer in the inquiry data DB 400 is not equal to or more than the predetermined threshold value, the process proceeds to step S21 and the next mission data is selected. The n-th mission data and the (n+1)-th confidential data may have the same content.

On the other hand, as a result of the determination in step S24, if the accumulated number of sets of mission data and the answers in the inquiry data DB 400 is equal to or more than a predetermined threshold, the learning means 220 stores the missions accumulated in the inquiry data DB 400. A learning process for the AI device 300 is performed using the set of data and the answer (step S25).

Through the above processing, a desired mission can be given to the user by using the AI device 300 having the learned artificial neural network, and further, by the set of the answer fed back from the user and the mission, It is also possible to continuously learn the artificial neural network.

Subsequently, the creating unit 260 creates various kinds of processing for displaying on the displays of the user terminal 100 and the administrator terminal 500 so that the user and the administrator can browse the information described later, and creates display data.

6 to 11 are diagrams showing examples of screens created by the creating means 260 shown in FIG. FIG. 6 shows an example of the TOP screen that is displayed after the user Taro logs in through the Web page in order to receive the service provided by the action recommendation system. As the information necessary for login, the login ID and the password may be given to the user at the time of the above-described initial setting.

Here, as an example, a comment display area 610 in which comments for Taro are displayed, an article display area 620 in which special articles for all users are displayed, and a meal menu (mission data) recommended for Taro are displayed. A recommended food menu display area 630, a topics display area 640 showing various topics, a numerical display area 650 showing the achievement rate of Taro's mission data, etc., and Taro's health condition is pseudo-converted into annual income. A health condition display area 660 showing values and ranks is shown.

The contents displayed in the comment display area 610, the recommended food menu display area 630, the numerical value display area 650, and the health condition display area 660 are mainly created by the digitizing means 250. The contents displayed in the article display area 620 and the topics display area 640 are mainly input through the administrator terminal 500.

FIG. 7A shows an example of a transition destination screen when the recommended food menu display area 630 of FIG. 6 is selected by clicking or the like. Here, the type of meal, such as "Western food type" and "Japanese food type", is indicated, and "Western food type" is selected by Taro. Therefore, for Western food type such as "Omelet with a lot of eggs" and "Feeling Bolognese". The menu is displayed. Numerical values indicating how the pseudo annual income shown in the numerical value display area 650 and the health condition display area 660 are changed are also displayed in each menu.

These menus themselves may be unique to Taro, or may be common to all users. However, since the menu to be presented is the mission data for Taro, it is not necessarily shown to users other than Taro. In detail, these menus will be presented to Taro and users with similar characteristics to Taro.

The numbers attached to the menu are the basis for the above-mentioned pseudo annual income. This numerical value is calculated by the administrator server 200 by referring to the AI device 300 or the inquiry data DB 400 based on the achievement rate of the mission, that is, the degree of difficulty, and the effect of the mission execution, or by the administrator. It can be calculated through 500.

In general, the higher the difficulty level and the higher the effect, the higher the numerical value. When using such rules, even the most effective mission does not necessarily have the highest value in the presented menu if the achievement rate is low.

FIG. 7B shows an example of a pop-up screen in the case where the “omele with plenty of eggs” in FIG. 7A is selected. The content of this pop-up screen example is the same as the content of FIG. However, the contents may be different.

FIG. 8 shows an example of a transition destination screen when the health condition display area 660 of FIG. 6 is selected by clicking or the like. Here, "¥74,000,000" is shown in the upper left of the screen as a number corresponding to the pseudo annual income corresponding to the current health condition of Taro. In the middle left of the screen and the lower left of the screen, as a basis of the pseudo annual income, whether it is obtained by dietary improvement or lifestyle improvement is added.

On the right side of the screen, the basis for the pseudo annual income based on the usage of the keyboard and mouse (Items for Key and Mouse), the number of files opened, and the number of programs used (File and Program, respectively). In addition to the work time (for example, the time when the user sits in front of the personal computer for some work or the user sits in front of the personal computer and the file of a business program such as word processing software or spreadsheet software). Time), the number of smiles, the number of steps, and the grounds based on the travel distance (Items of Time, Smile, Walk, and GPS, respectively) are also shown. However, the display content shown in FIG. 8 is an example, and information other than these may be shown as a basis, or information different from these may be displayed.

Here, it can be further seen that the number of steps decreased while the amount of keyboard usage increased. If the user is a desk work and the work is busy and sufficient exercise time cannot be secured, such a transition of the performance may occur. At this time, it is also a method to add a function from the behavior recommendation system to the user terminal 100 to ask the user terminal 100 such as "Is the number of steps decreased, were you busy?

Taking the case of steps as an example, by measuring the number of steps on a daily basis, the average number of steps, the maximum number of steps, and the minimum number of steps per unit period, such as daily, weekly, or monthly, are acquired, and the average number of steps is used as a reference. As a result, it is possible to quantify by determining whether the activity level is high or low, and tabulating the high days as “¥1,000” and the low days as “¥-1,000”.

In addition, if the number of steps taken on the user's holiday, such as Saturday and Sunday, is also acquired, it is generally considered that the number of steps taken on a holiday is often smaller than the number of steps taken on a weekday. It may be a method to manage the number of steps and the number of steps on weekdays separately.

Further, when the number of days exceeds the maximum number of steps or the average number of steps increases by 20% or more, it can be estimated that there is a sudden action described below. In this case, for example, “¥+2,000” can be set. On the other hand, if the number of steps is less than the minimum number of steps or if the average number of steps is reduced by, for example, 20% or more, it can be estimated that there was a hospital visit described later. In this case, for example, "¥-2,000" can be set.

It should be noted that although the user is forced to manually input the load on the user, a user who separately carries a physical pedometer without using the pedometer function of the smartphone can use the pedometer through the user terminal 100. It is not excluded to manually input the number of steps measured in and send it to the action recommendation system.

When the user terminal 100 is a video game, IT equipment, AV equipment, or the like, the number of times and frequency of use of these may be used to measure the effect on mission execution, and these may be replaced with the information shown in FIG. Specifically, the IT device by the user, such as turning on the power supply of the IT device or the like (further, the time until the power is turned off thereafter), or performing a predetermined login via the network (and the time until the logout thereafter). It is possible to show a numerical value corresponding to the pseudo annual income based on the number of times of actions for etc.

FIG. 9 shows an example of the transition destination screen when the numerical value display area 650 of FIG. 6 is selected by clicking. It should be noted that even when the portion "view in chart" of FIG. 8 is selected by clicking or the like, a transition is made to the screen example shown in FIG.

Here, it is an example of a screen shown on the right side of the screen of FIG. Here, the usage transition and the like are shown in a line graph or a stacked bar graph according to the characteristics of the grounds, but the type of the graph is not limited to these, and the user can customize the display form as appropriate and select it. You can Furthermore, instead of using a graph, the answers to the missions are expressed by dots such as black and white, and the missions that have a high relationship with the answers and the missions that have a low relationship are color-coded. It is also one way to show in.

FIG. 10A shows an example of a screen that transits when the “method” at the upper right of FIG. 6 is selected by clicking. FIG. 10B shows an example of a screen that transitions when "Details" in the article of FIG. 10A is selected by clicking.

In the screen example of FIG. 10(a), Taro is presented with a mission of "eating three eggs a day", and the numbers corresponding to the above-mentioned pseudo annual income when the mission is achieved. Shows how much is improved. In addition, the expected effect of eating eggs and the reason thereof, recommended articles for Taro, recipe information related to eggs, shop information, and the like are displayed.

FIG. 10B shows a detailed article supervised by a registered dietitian. This example also shows what the protein contained in the egg means to the body, the fact that omelets and steamed buns are good as a menu, and a simple cooking method.

FIG. 11A shows an example of a screen that transits when "My list" in the upper right of FIG. 6 is selected by clicking or the like. FIG. 11A shows a mylist display area 710 for transmitting the information when a mission is completed, and a result display area for displaying a response result based on the execution frequency of each mission transmitted through the mylist display area 710. 720, a breakdown display area 730 showing the breakdown of the entire habitualized mission, and a mission display area 740 showing a list regarding the missions given to Taro.

In the mission display area 740, in addition to the mission of “eating three eggs a day” described with reference to FIG. 10, a plurality of missions presented to Taro so far have date information indicating the respective missions. , The information indicating the mission execution frequency by an asterisk, and the date information that makes the mission execution customary are also displayed.

FIG. 11B shows an example of a screen that transits when the “details” section in the mylist display area 710 of FIG. 11A is selected by clicking. Here, it is a guideline for determining the number of stars that indicate the frequency of mission execution, its input method, and how the pseudo annual income changes depending on the determined number of stars. The explanation is given.

If the screen examples shown in FIGS. 6 to 11 can be given to the user, the following effects can be expected.
Since a unique mission suitable for each user can be provided for each user, an excellent effect for each user can be expected by performing the mission given to each user.
-It is possible to provide a mission to a large number of users and obtain the execution result of each mission as feedback to improve the accuracy of effect measurement, and to assign a suitable unique mission according to the characteristics of the user.
-By showing the user the transition of behaviors (keyboard usage frequency, etc.) that are familiar to the user after performing the mission, let the user easily understand the effect of the mission, and continue performing the mission to the user. Incentive can be given.
-By devising a user interface (presentation of pseudo annual income, etc.), the user can be kept motivated to carry out the mission.

As described above, in the present embodiment, the behavior recommendation system has been mainly described by taking the improvement of the health condition for the user as an example, but the effects of performing the mission are various, and in addition to the number of times the user smiles as described above, Since sleeping time, meal amount, moving to a hospital, sudden action, etc. can be used for the effect measurement by the mission execution, for example, the user may be allowed to select an item to be displayed on the right side of FIG. ..

Incidentally, as a reminder, moving to the hospital can be said to be a preferable action because if the user is ill, it is a positive action to try to cure it. Also, in order to properly judge the health condition of the user on the side of this behavior recommendation system, it is good to know the history of disease occurrence, the history of hospital visits, the presence or absence of chronic diseases, etc. Is also a law.

By doing so, for example, when the user wants to browse the disease history at an arbitrary timing, it is possible to deal with it. Whether to move to the hospital can be predicted based on the GPS function and map application software provided on the smartphone or the like.

Further, as the sudden action, for example, an action such as going on a trip or watching a sport or watching a movie, which is not usually performed, can be cited. It can be said that such an action has a high degree of activity, because it is thought that the user's mind and body will be positively affected. For such actions, the numerical value corresponding to the pseudo annual income should be increased, so if the administrator decides this numerical value, it should be increased. Whether or not there is a sudden action may be determined by input from the user or using a smartphone or the like as in the case of going to the hospital.

In addition, it is preferable to determine whether or not there is a sudden action using application software installed on a smartphone, because it is possible to acquire where and what is being done without bothering the user. Of course, for example, if both playing tennis and watching tennis are selected as the items to be displayed on the right side of FIG. 8, it is determined by the user using the application software installed on the smartphone that the tennis court If it is, you cannot immediately know whether you are playing tennis or watching tennis.

Therefore, in the present embodiment, when it is specified that the user is on the tennis court by the GPS function and the map application software, the above-mentioned specification is performed in consideration of the step count information obtained from the pedometer. There is. Specifically, when playing tennis, the possibility of putting a smartphone etc. in the pocket cannot be said to be zero, but it is considered that this possibility is not very high, so for example, dozens of minutes If the total number of steps is not counted, it is determined that the player is playing tennis, and if not, it is determined that he is watching tennis. Further, if it is difficult to discriminate one of these, the user may be selectively inquired.

Similarly, when the user moves only within a predetermined range for a certain time or longer, for example, when the user browses an exhibition such as a painting at a museum, the user can use the GPS function and the map application software. It is also possible to determine the current level of the activity and determine the level of activity.

Further, in recent years, in order to effectively use the roof of a building, for example, some department stores have a futsal field provided on the roof. Normally, it would be difficult to determine whether the user is visiting the department store for shopping purposes or futsal purposes. However, in the present embodiment, the current location of the user is determined by the GPS function and the map application software. The above determination is performed by not only specifying the above, but also detecting the presence or absence of a slight movement of the smartphone or the like in a short time such as 1 to 2 minutes.

Specifically, for example, when the movement of the smartphone or the like is not confirmed by the GPS function of the smartphone or the like for 10 minutes, it is highly possible that the user has futsal with the smartphone or the like in the bag. Since it can be assumed, in this case, it is determined that he is futsal.

On the other hand, for example, when the movement of the smartphone or the like is confirmed by the GPS function of the smartphone or the like every one to two minutes, the user puts the smartphone or the like in the bag and some tenant shops, etc. Since it can be assumed that there is a high possibility that the user is looking for the item while moving the item, it is determined that he or she is shopping in this case.

Of course, although it is optional, it may not be possible to immediately determine which case it applies to. Therefore, in such a case, the user may be inquired as in the case of the example of tennis. The method of inquiring does not matter, and if the determination cannot be made, the inquiry may be made immediately or after a certain period of time.

Furthermore, inquiries to users are likely to be playing futsal regularly, especially for users who regularly behave in the same pattern. ○ Do you inquire about content such as "Are you futsal on the rooftop of a department store?"

If there is a response from the user that "I am playing futsal for 1 hour every Saturday from 15:00 on the rooftop of the XX department store", the user will be notified of the GPS function and map after that. When confirmed by the application software, it is possible to grasp the presence/absence and type of the mission data of the user without performing extra determination processing in this time period.

Claims (6)

Transmission means for transmitting mission data including a plurality of missions to a user terminal,
Acquisition means for acquiring an output result to the user terminal by the user who has performed each mission data transmitted by the transmission means,
Reporting means for reporting the mission execution result by the user based on the output result obtained by the obtaining means,
Action recommendation device equipped with. The acquisition means is
The usage time or usage of the input device attached to the user terminal,
The number of programs executed on the user terminal,
The number of files used on the user terminal,
The number of steps measured by the pedometer function of the user terminal,
Travel distance measured by the GPS function of the user terminal,
Communication time made by the user terminal with another user terminal,
The action recommendation device according to claim 1, which is at least one of the following. Furthermore, it comprises a receiving means for receiving inquiry data transmitted from the user who has performed each of the mission data, the inquiry data is data including a plurality of items,
An input value generating means for generating an input value in which some item contents of the inquiry data received by the receiving means are changed,
The input value generated by the input value generating means is input to an artificial intelligence device having an artificial neural network learned by a plurality of sets of the mission data and answers from users who have performed the mission data. And output value acquisition means for acquiring the output value corresponding to this,
Mission data transmitting means for transmitting mission data based on the output value acquired by the output value acquiring means to any user terminal,
The action recommendation device according to claim 1, further comprising: The action recommendation device according to claim 3, wherein the artificial neural network is an artificial neural network including a recurrent neural network and capable of temporal processing. The behavior recommendation device according to claim 1, wherein the inquiry data transmitted from the user who has performed each of the mission data includes a user's normal lifestyle and health condition. An action recommendation device according to claim 1,
An AI device including an artificial neural network in which the input value generated by the input value generating means is learned by a plurality of sets of the mission data and an answer from a user who has performed the mission data;
An action recommendation system that includes