JP2023144212A - System, mobile terminal, server, information processing device, program, or method - Google Patents

Abstract

To provide a system, a mobile terminal, a server, an information processing device, a program, and a method that can more appropriately use acquired user information.SOLUTION: An information processing device includes: an acquisition unit that acquires information related to the health of a first user and information related to the behavior of the first user; a machine learning unit that has a function that has machine learned the relationship between the information related to the health of the user, the information related to the behavior of the user, and information related to recommendation, and that applies the information related to the health of the first user and the information related to the behavior of the first user to generate the information related to recommendation regarding the first user; and a communication unit that communicates information related to a message to a mobile terminal related to the first user using the information related to the recommendation regarding the first user.SELECTED DRAWING: Figure 1

Description

The technology disclosed in this application relates to a system, a mobile terminal, a server, an information processing device, a program, or a method.

There is a need for technology that more appropriately uses information obtained from people.

JP2015-69531A JP2004-62687A Japanese Patent Application Publication No. 2005-141781

However, in any of the above techniques, the use of information obtained from people is insufficient. Therefore, various embodiments according to the present invention communicate systems, mobile terminals, servers, information processing devices, programs, or methods in order to solve the above problems.

An example system is
an acquisition unit that acquires information related to the health of the first user and information related to the behavior of the first user;
Equipped with a function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to recommendations, and the information related to the health of the first user and the information related to the first user. a machine learning unit that applies information related to behavior to generate information related to recommendations regarding the first user;
a communication unit that communicates information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
A system equipped with

An example computer program is
system,
acquisition means for acquiring information regarding the health of the first user and information regarding the behavior of the first user;
A function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to the recommendation, means for generating information related to a recommendation regarding the first user by applying the method to the information related to the first user;
communication means for communicating information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
A program to operate as.

An example method is
the system,
an acquisition step of acquiring information related to the health of the first user and information related to the behavior of the first user;
A function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to the recommendation, a generation step of generating information regarding a recommendation regarding the first user by applying the information to the information regarding the first user;
a communication step of communicating information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
How to do it.

According to an embodiment of the present invention, information about people can be used more appropriately.

FIG. 1 is a block diagram showing a specific example of the functions of an information processing device according to an embodiment. FIG. 2 is a block diagram illustrating an example of the relationship between information processing devices according to an embodiment. FIG. 3 is an example of the flow of processing by the system according to one embodiment. FIG. 4 is an example of the flow of processing by the system according to one embodiment. FIG. 5 is a block diagram illustrating an example of the relationship between information processing devices according to an embodiment. FIG. 6 is an example of the flow of processing by the system according to one embodiment. FIG. 7 is an example of a screen of a system according to an embodiment. FIG. 8 is an example of a screen of a system according to an embodiment. FIG. 9 is an example of the flow of processing by the system according to one embodiment. FIG. 10 is a block diagram showing the configuration of an information processing device according to an embodiment.

Various embodiments of the present invention will be described below with appropriate reference to the accompanying drawings.

1. Functions of the system according to an example of the present invention An example system according to the present invention has a function of acquiring information regarding a person and generating information regarding a recommendation based on the information. An example system may include an acquisition unit, a machine learning unit, a communication unit, and/or a display unit, as shown in FIG. Another example of the system may include an acquisition unit, a communication unit, and a display unit. Further, another example of the system may include an acquisition unit, a machine learning unit, and a communication unit.

1.1. Acquisition Unit The acquisition unit has a function of acquiring information. For example, the acquisition unit acquires attribute information, health information, behavior information, insurance premium information, recommendation information, and/or sub-concept information for one user or a specific group. You may obtain information.

The mode of acquisition may be various. For example, the server and/or the cloud may be acquired from a mobile terminal or other information processing device via wired or wireless communication, or the program in the server and/or cloud may be acquired from the mobile terminal or other information processing device. The program may be acquired from a program in the server and/or cloud via wired or wireless communication, or the program in the server and/or cloud may be acquired from a storage device in the server and/or cloud, or the program in the server and/or cloud may be acquired from a storage device in the server and/or cloud. A program within the mobile terminal may acquire information from the server and/or a program within the cloud, a mobile terminal or a program within the mobile terminal may acquire information based on user input, or a mobile terminal or a program within the mobile terminal may acquire information from a mobile terminal or a program within the mobile terminal. The program may be acquired from a program within the mobile terminal or a storage device within the mobile terminal.

The acquisition unit may acquire information using communication or may acquire information using a storage medium.

1.2. Machine learning unit The machine learning unit may include machine learned functions. For example, the machine learning unit may have already learned the relationship between information related to the user's health and/or information related to the user's behavior, and information related to the recommendation. Further, the machine learning unit may have a function of applying the machine learned function to other information. In addition, the machine learning unit only needs to have already learned the relationship between at least the information related to the user's health and/or at least the information related to the user's behavior, and at least the information related to the recommendation. Machine learning may be applied to relationships that include elements other than these elements. For example, the machine learning unit has already learned the relationship between attribute information about the user, information about the user's health, and/or information about the user's behavior, and information about the recommendation. Good too.

The machine learning unit may include a function using well-known artificial intelligence technology, for example, a function using neural network technology. The neural network technology may be a deep learning technology. Additionally, various aspects of neural network technology may be applied. Further, the machine learning section may use a rule-based technique or a statistical processing technique.

Further, the machine learning section may have a machine learning function. For example, the machine learning unit may have a function of performing machine learning on the relationship between information related to the user's health and/or information related to the user's behavior, and information related to recommendations. In this case, there is an advantage that these relationships can be learned by machine learning with higher accuracy.

Further, the machine learning unit may perform machine learning on relationships between other pieces of information, and in this case, may have a function that has already machine learned the relationships between such information.

1.3. Communication Department The communication department has a function of communicating information. The communication unit may have a function of communicating with a mobile terminal. Further, the communication unit may have a function of communicating with the management terminal. Communication may include sending and/or receiving. Communication may be wired or wireless.

The communication department will collect attribute information, health information, behavior information, insurance premium information, recommendation information, and/or information on sub-concepts of these regarding one user or a specific group. may have the function of communicating. The communication unit may use well-known communication technology.

1.4. Display Unit The display unit has a function of displaying information.

The display unit may display attribute information, information related to health, information related to behavior, information related to insurance premiums, information related to recommendations, and/or information on subordinate concepts thereof.

In addition, in the application documents, attribute information, health-related information, behavior-related information, insurance premium information, recommendation-related information, and/or information related to these subordinate concepts may be used as appropriate during the communication and processing process. , the format may be changed, and information may be added, modified, or deleted.

2. Example
2.1. Example of the overall picture in the embodiment The system according to the first embodiment may include a mobile terminal used by a user and a server that processes information acquired from the mobile terminal. For example, FIG. 2 illustrates an example system. In this figure, mobile terminals 21a and 21b may be connected via a network 22 so as to be able to communicate information with a server 23a. In this figure, two mobile terminals are illustrated, but the number may be one or more, and the number is not limited. The mobile terminal may be used by a user who uses the system according to this example (sometimes referred to as a user terminal). In addition, a program that implements the technology according to the present application is downloaded and installed on a user terminal via the Internet, and the program is sometimes referred to as a user application in the documents of the present application. Note that in the present application, the functions realized by the user application may be executed on a web browser on the Internet. In this case, the functions implemented in the user application may be implemented in a program executable on a web browser accessed over the Internet instead of the user application.

Note that such a user application may be able to create a user account. In this case, information that identifies the user may be used as the user's account. Information that identifies the user includes the user's name, user's email, user's phone number, ID that identifies the user, information that identifies the insurance product subscribed to by the user, and/or May include the user's address. The ID that identifies the user may be associated with the insurance product that the user subscribes to.

Further, in this figure, the server 23a is connected to the administrator terminals 23b and 23c, but the configuration is not limited to this example. There may be no administrator terminal, or there may be two or more administrator terminals. The server 23a may be one or more servers, and the one or more servers may be one or more information processing devices. Further, the server 23a may be a cloud. In addition, in the case of a server and/or cloud, the information processing device itself on which the server and/or cloud is executed is an information processing device owned by the person who executes the processing executed in the server and/or cloud. Alternatively, the information processing device may be an information processing device that the executor does not own. In the latter case, an information processing device owned by a third party may be used. The information processing device will be described later.

Note that in the present document, the term "system" may refer to a single information processing device or a plurality of information processing devices such as a server, a cloud, a mobile terminal, and the like. For example, a system may refer to one or more servers and one or more mobile terminals. Further, for example, the system may refer only to one or more servers, or may refer only to one or more mobile terminals. Also, the server may additionally or alternatively be a cloud. The mobile terminal may be any of a variety of portable information processing devices, such as a smartphone, tablet, PDA, notebook computer, laptop, tablet PC, handheld, portable computer, and the like.

Next, the manner in which the system of this example is used will be explained.

2.2. Example 1
The embodiment of this example is an example of a system having a machine learning function. A machine learning unit included in an example server may perform machine learning on the relationship between user information, information related to the user's health, and/or information related to the user's behavior, and information related to recommendations.

In the present document, the attribute information about the user may include the user's gender, the user's age, and/or insurance participation information.

In the present document, the health-related information about the user may include information about the user's current health condition and/or past health information. Current health status information may include vital information, weight, blood sugar level, and/or stress level. Vital information may include pulse, heart rate, respiratory rate, blood pressure, and/or body temperature. Past health information may include information on medical examination results and/or information on announcements made by policyholders. In addition,

In the documents of this application, information regarding the user's behavior may include information regarding the user's exercise, diet, daily life, and/or information regarding how the app is used. . The information related to exercise may include information on the type of sport, information on calories consumed by the sport, information on the duration of the sport, information on the number of steps, and/or information on the video viewing time. The information regarding the meal may include information on the type of food, information on the calories of the food, and/or an image of the meal. The information related to meals may be information for each meal. Further, the calorie information in the information regarding the meal may be estimated based on the image of the meal. Information related to daily life may include information on wake-up time, information on bedtime, information on whether or not to smoke, and number (number of times) of smoking, and/or information on amount and frequency of alcohol consumption. The information related to the usage mode of the app may include information about the frequency of logging into the app, information about the timing of inputting information related to the behavior of the user to the app, and information related to the display in the app. The information related to the display in the application may include information related to a message displayed based on information related to a recommendation, which will be described later, and/or information regarding the timing at which the message is displayed. In addition, below, the user's behavior will mainly be described as exercise and eating, but information related to daily life and/or information related to how the app is used may also be used in addition to or in place of these. may be done. In this case, it becomes possible to collect more information about the user's life and information about the user via the application, and there is an advantage that the possibility of using the user's information appropriately increases.

In particular, when information related to a user's behavior includes information related to a message, information related to the timing at which the message is displayed, and information related to exercise, the timing at which the message is displayed and the information related to exercise are included. There is an advantage that machine learning can be performed by associating information related to the message and exercise, and it is possible to learn more information about the user by machine learning based on the actual exercise that the user performed based on the content and timing of the message. . If such information can be learned by machine learning, there is an advantage in that it may be possible to obtain messages that enable the user to exercise more and information about the display timing of the messages.

Further, the information related to the recommendation may include information related to the message and/or the field to which the message belongs.

The information related to the message may include information identifying the message, information related to the timing of the message, and/or information related to the message delivery algorithm.

The fields to which the message belongs may include at least malignant neoplasm prevention, dementia prevention, and/or lifestyle-related diseases.

Note that the information related to recommendations in machine learning may be set based on information provided by humans on a rule-based basis, or may be based on information actually collected from a specific group such as insurance policyholders. But that's fine. The former includes, for example, the user's article viewing history, gender, age, type of insurance contract, notified medical history, and benefit payment history, and information related to recommendations set in advance for these. Information related to recommendations may be used based on relationship rules. In this case, so to speak, preset rule-based information is subjected to machine learning. On the other hand, the latter basically provides information regarding various recommendations for a specific group (this information may be information obtained based on a rule base or information obtained using machine learned functions). As a result of using actual actions (such as exercise and/or eating), information related to recommendations for actions that are desirable in real life can be used as correct answer information for recommendations in machine learning. It is possible to use this information as such information.

Next, the flow of information processing in the system of this example will be explained using FIG. 3.

<Step 1>
An acquisition unit included in an example server may acquire user information, health information, and/or behavior information for a plurality of users. The user may be, for example, an insurance policyholder. In the case of an insurance policyholder, information regarding the results of a health checkup, which is a subordinate concept of health-related information, may be information obtained at the time of signing an insurance contract or the like. In this case, an information processing device may include a database that stores the results of a health checkup provided at the time of the insurance contract in association with information that identifies the policyholder. Furthermore, the system according to the present application may or may not include an information processing device provided with such a database. In the latter case, the system according to the present application can communicate information with such information processing device using well-known communication technology, and may obtain the results of the medical examination corresponding to the policyholder from such a database. .

<Step 2>
A machine learning unit included in an example server may perform machine learning on the relationship between information related to health and/or information related to user behavior, and information related to recommendations.

<Step 3>
When acquiring health-related information and/or user behavior information, a machine learning unit equipped with a machine-learned function included in an example server generates recommendation-related information in response. It's fine. Such machine learned functions may include health-related information and/or user behavior information that is different from the health-related information and/or user behavior information used during machine learning. Even when the information is applied, there is an advantage that information related to the corresponding recommendation can be generated.

2.3. Example 2
The system of this example is an example of generating information related to recommendations based on information obtained from an example of a mobile terminal. This will be explained below using FIG. 4.

<Step 1>
The server may acquire health-related information and/or information related to the user's behavior regarding one user from the user terminal.

The user's health-related information and behavior-related information may be acquired by the user terminal from a measuring device used by the user, by a function provided in the user terminal, or by the user terminal. The information may be acquired based on the user's input to the information.

The user terminal may acquire information related to the user's actions. The user terminal may accept input from the user and may store information regarding the user's actions. The input by the user may be information input by the user using a touch panel, buttons, or the like on a user terminal. Furthermore, in addition to or in place of this configuration, the user terminal may acquire information related to the user's actions. Information related to user behavior includes, for example, information on the number of steps a user takes when walking, information on the number of steps when a user goes up and down stairs, viewing time when a user views a specific video, and/or may include information related to movement when the user moves the user terminal. Further, the information related to the user's behavior may include information for identifying the user and/or information on the date and time of measurement or acquisition in association with this information. The information on the number of steps may be information based on a function of detecting the number of steps within the user terminal. Further, the information on the number of stages may be information based on a function of detecting the number of stages within the user terminal. The information on the number of steps and the information on the number of steps are considered to be information indicating that the user is taking actions that are specifically linked to better health. The viewing time may be the viewing time of a user application or a video associated with the above-mentioned message. Viewing time (duration) time is considered to be the time that the user actually watches the video, and viewing duration is the action of the user to become interested in the video and gain knowledge from the video, and it is the amount of time that the user actually watches the video. It is considered to be information that indicates that a person is engaging in behavior that is linked to health. If a video (especially a video related to exercise) associated with the user app or the above-mentioned message is being played, information related to movement may indicate actions in line with the exercise shown in the video. , is considered to be information that indicates that the user is taking actions that are specifically linked to health. Note that the information related to movement may be calculated based on longitude and latitude information obtained by GPS. Further, the information related to movement may be calculated by a gyro sensor in the user terminal using tilt information of the user terminal. In the above, by acquiring information indicating that the user is taking specific actions that are linked to health, the user's awareness becomes more active (compared to the case where he or she does not take any actions that lead to health). This means that information indicating that something has changed can be collected, and there is an advantage of being able to use such information.

Further, the user's stress level, for example, stress information may be acquired by various methods. For example, the determination may be made based on the user's blood flow. The user's blood flow may be venous. For example, blood flow may be based on the user's facial veins. The user's facial veins may be measured based on a captured image of the user's face. In this case, the user terminal itself or another information processing device in cooperation with the user terminal may image the user's face and acquire stress-related information based on the captured image. Information related to stress may include a numerical value indicating the degree of stress. Here, when a numerical value indicating the degree of stress is higher than a predetermined threshold value, it may indicate that stress is high. Information related to stress may include a value measured by a device that measures stress, a date and time when stress was measured or input, information that identifies the measuring device that measured stress, and/or information that identifies the user.

<Step 2>
The machine learning unit of the server applies the acquired health-related information and/or information related to the user's behavior and makes recommendations regarding the user. may generate information related to

<Step 3>
The server transmits information related to a message using the information related to the recommendation regarding the one user to the user terminal regarding the one user, and the user terminal displays the information related to the message. It may be used for display on a device. Note that the information related to the recommendation and the information related to the message may be the same or different.

For example, when the information related to the recommendation includes information that specifies a message, the specified message, the information that specifies the message, or the message specified based on the information may be transmitted to the user terminal. The information specifying the message may, for example, specify any predetermined message, and may be, for example, a message ID. Here, the message may be generated by specifying a predetermined message format and a variable within the message as such a placeholder. In such cases, the information identifying the message may include information identifying the format of such message and/or identifying variables within such message. Here, variables in the message may be the type of exercise (type of sport), duration of exercise, calories burned by exercise, and/or frequency of exercise if it is about exercise, and if it is about meals, The type of meal and/or the calorie intake of the meal may be used. An example server may transmit information identifying such a message to a user terminal, and perform processing for displaying the message on the user terminal. From the viewpoint of maintaining health, ideal exercise and ideal diet are preferable with respect to exercise and diet, and messages tend to be content that recommends such ideal exercise and ideal diet. However, it would be meaningless if, as a result of pursuing only such ideals, users do not accept them and end up giving up on lifestyle habits to become healthy. Therefore, from the perspective of users (rather than seeking only the ideal) to get closer to a lifestyle that makes them less likely to get sick (even if it is not necessarily ideal), A configuration based on the technical philosophy of providing messages as advice to help people adopt difficult lifestyle habits can be considered. In other words, it is possible to provide advice that is easy for users to accept and that is suitable for each user's way of thinking, emotions, and habits. In particular, the machine learning department uses machine learning functions to learn the relationship between information related to past actions of various people and information related to recommendations, which will lead to machine learning of people's behavior patterns. This has the advantage of being able to provide more appropriate messages in order to provide more appropriate advice to users.

Further, when the information related to the recommendation includes information related to the timing of the message, the server may perform processing based on the information related to the timing. For example, the server may send information related to a message to a user terminal based on information related to timing, or the server may display information related to a message on a user terminal based on information related to timing. You may perform processing to make it happen.

Additionally, if the information related to the recommendation includes information that identifies the message and information related to the timing in an associated manner, the server processes the message so that it is displayed on the user terminal based on the information related to the timing. It's fine. For example, as information in a manner in which message specifying information and timing information are associated, the display order for a day is 1 exercise message 2, 3 exercise message 3, and 1 meal message. Assume that the information includes information for displaying messages in order and at predetermined times. In this case, the server displays the user's message at the time corresponding to each message in the order of exercise message 1, exercise message 2, exercise message 3, and meal message 1 in accordance with the display order. It may also be sent to the terminal. Alternatively, the server may display time 1 corresponding to exercise message 1, time 2 corresponding to exercise message 2, time 3 corresponding to exercise message 3, and time 3 corresponding to exercise message 3 in accordance with the display order. Information in which the message and time are associated, ie, time 4 corresponding to message 1, may be transmitted to the user terminal. Further, such exercise and meal messages may be different for each user. More specifically, for the user terminal 1, the server sends exercise message 1, exercise message 2, exercise message 3, and meal message 1 in the following order at the time corresponding to each message. , to the user terminal, and to the user terminal 2, which is different from user terminal 1, the server sends the messages in the following order: meal message 1, exercise message 1, meal message 2, meal message 3. , may be transmitted to the user terminal at a time corresponding to each message. Note that in this case as well, information in which the message and time are associated may be transmitted to the user terminal 1 and/or the user terminal 2.

The user terminal that has acquired this information may display a message corresponding to each time on the display device at each time. Depending on the user's lifestyle and personality, it is thought that whether or not a user actually takes action (e.g., eating or exercising) is influenced by the content of the message, the order of display, the timing of display, etc. Therefore, by making recommendations based on message content, display order, and display timing that are more suitable for the user, the system is designed to bring the user's lifestyle closer to one that is less likely to cause illness.

The field to which the message belongs may include at least early detection and/or prevention of malignant neoplasms, dementia prevention, and lifestyle-related diseases. For example, in one example of a server, a message about exercise and/or diet to be provided to a user is predetermined, and a machine learning unit can detect and/or prevent early detection and/or prevention of malignant neoplasms, prevent dementia, or , lifestyle-related diseases, etc., the messages belonging to the specified field may be sequentially transmitted to the user and displayed on the user terminal. Note that instead of this configuration, a message corresponding to the field may be stored in the user terminal, and displayed on the user terminal based on information specifying the field to which the message sent from the server belongs. .

Further, the information related to the message may include information for displaying a video for promoting health (for example, a link to the video, a URL to the video, etc.).

Further, the information related to the message may include information related to services for improving health that can be used by the user. The services may be, for example, services related to lifestyle diseases, services related to cancer, and/or services related to dementia. Further, the service may include information related to exercise, information related to disease testing, and/or information related to disease prevention.

Information related to exercise may include information related to membership in an exercise facility, information related to a specific exercise service provided to an exercise facility (sports club, etc.), and/or information related to a specific exercise at an exercise facility based on information related to the user's exercise. may include information related to athletic services. In particular, by including information on services that are compatible with (or in some cases suitable for) users identified using information on the user's current exercise, the user will be more motivated to use the service. It has the advantage of being expensive. The information regarding the exercise service may include the content of the exercise service, the days of the week, frequency, cost, location, and/or comments about the exercise service by other users. Furthermore, the information related to exercise may include a link that allows membership and/or reservation of a service for exercise. In this case, it may be possible to move to a reservation page dedicated to the user by clicking on such a link on the user terminal. In this case, there is an advantage that the user can make a reservation more easily.

Furthermore, the information related to disease testing may include information about related diseases based on the health status of the user and the diseases the user is concerned about. The user's health status may be identified based on medical examination results, diseases related to the user's relatives, information related to the exercise and/or diet of both users, and the like. Furthermore, the diseases that the user is concerned about may include diseases that are identified using information on diseases related to the insurance that the user has subscribed to and/or the insurance that the user has considered enrolling in. Further, the information related to testing for a disease may include information on the disease itself, the location where the test is taken, the cost, test items, test details, and/or the availability of reservations for the test. Even if you have to make a reservation or feel burdened by taking a test, displaying information about the test has the advantage of making it easier to get tested. Furthermore, the information related to disease testing may include a link that allows reservations for testing. In this case, it may be possible to move to a reservation page dedicated to the user by clicking on such a link on the user terminal. In this case, there is an advantage that the user can make a reservation more easily.

Further, the information related to disease prevention may include information related to training for disease prevention and/or information related to a specific community. In particular, by including information on disease prevention that is appropriate (in some cases, suitable) for the identified user using information on the user's current behavior, the user will be more likely to use the service. This has the advantage of increasing motivation. Such prevention information may include the content of the training, the date and time of training, frequency, cost, location, and/or comments about the training by other users. Furthermore, the information related to disease prevention may include a link that allows enrollment and/or reservation of preventive services. In this case, it may be possible to move to a reservation page dedicated to the user by clicking on such a link on the user terminal. In this case, there is an advantage that the user can make a reservation more easily. Information regarding a particular community may also include how to join a particular community, the date, time, frequency, and location of community meetings, and/or comments about other users' participation in the community. In particular, in order to prevent dementia, it is good to belong to a specific community and have a certain relationship with other people. This has the advantage of increasing the possibility that it will be possible to delay the

<Step 4>
The user terminal may acquire information corresponding to the information related to the message and transmit it to the server. Acquisition of information may be as described above. In particular, when the user terminal acquires information corresponding to the information related to the message and sends it to the server, the server has the advantage of being able to acquire and store the information in association with the information related to the message.

For example, if the information related to the message is a message that includes content that recommends a specific exercise and/or meal, the user terminal can display information on whether such specific exercise and/or meal was performed (in the present document, action result information). Such action result information may be information input by the user to the user terminal, information determined by the user terminal, or information obtained by the user terminal from another system. good. The information input by the user may be an input of information indicating whether a particular exercise and/or diet has been followed in response to recommendations. In this case, although it is a self-report, it is significant that the user can easily input information as to whether or not he or she has followed the recommended specific exercise and/or diet. Further, the user terminal may determine the presence or absence and/or degree of the recommended specific exercise by measuring the movement of the user terminal itself using a gyro function or the like within the user terminal. Further, the user terminal may determine the presence or absence and/or degree of a recommended specific meal based on a photo of the meal that the user eats. In this case, the user terminal is equipped with an imaging function, and based on the image of the meal eaten by the user captured by the imaging function, the user terminal identifies the content of the meal eaten and the presence or absence of a recommended specific meal. and/or the degree may be determined. This behavior result information may be used as behavior-related information in the server as input information for machine learning. That is, information related to a behavior that includes both information related to a message to a user and information related to a corresponding behavior in association with each other may be used as an input for machine learning. In this case, the correspondence between the user's actual behavior (exercise and/or diet) corresponding to the message (specific message about exercise and/or diet and/or the timing of that message) There is an advantage that machine learning can be used to learn what kind of message should be shown to the user and at what timing.

In this case, health-related information about one user and the user's actual behavior corresponding to the above-mentioned message (specific message about exercise and/or diet and/or timing of the message) Machine learning may be performed on the relationship between information on behavior including (exercise and/or diet). In addition, as another aspect, health-related information about one user and the user's information corresponding to the above-mentioned message (specific message about exercise and/or diet and/or timing of the message) Machine learning may be performed on the relationship between information related to actions including actual actions (exercise and/or meals) and information related to messages. Here, the information related to the message as a reply may include positive data or negative data.

In addition, if the information related to the message includes multiple recommended exercises and/or meals, the user terminal may include a game-like function when the user selects the exercise and/or meal to perform. . For example, the user terminal may select a particularly recommended exercise and/or meal from among a plurality of recommended exercises and/or meals using a predetermined random number function. In this case, the user terminal displays a plurality of recommended exercises and/or meals, displays an animation for selecting among the plurality of exercises and/or meals, and as a result of the animation, etc., the user terminal displays a plurality of recommended exercises and/or meals. One or more selected exercises and/or meals may be displayed. In this case, even if there are many recommended exercises and/or meals, the user can select the exercise and/or meal to perform while enjoying the animation, which has the advantage of allowing the user to enjoy health prevention activities. .

In addition, if the information related to the message includes multiple recommended exercises and/or meals, the user terminal will provide rewards other than health when the user selects the exercise and/or meal. It may also include a function to For example, the user terminal may display predetermined points in association with each of a plurality of recommended exercises and/or meals. When the user performs one or more exercises and/or meals selected from these plurality of recommended exercises and/or meals, the exercise and/or meals associated with each of the selected one or more exercises and/or meals are performed. The user may be able to earn predetermined points. In this case, by accumulating such points, the user may be able to obtain the right to receive a prize or obtain points that can be used to purchase products other than prizes. In this case, the user has the advantage of increasing the enjoyment of receiving prizes, products, etc. as rewards by doing the exercise and/or eating that should be done.

2.4. Example 3
The system of this example utilizes machine learning functions for other information. An example server may have machine learning capabilities for at least three different types of input/output relationships.

The first machine learning unit may have a function of performing machine learning on the relationship between at least information related to health and/or information related to behavior, and at least information related to malignant neoplasm.

The first machine learning unit generates information regarding malignant neoplasm regarding one user in response to application of health information and/or behavior information regarding one user. It's fine. The information regarding malignant neoplasm may include the possibility that malignant neoplasm will develop, and/or the age or period at which malignant neoplasm will develop. Alternatively, the information regarding malignant neoplasm may include the type of malignant neoplasm, the possibility that the malignant neoplasm will develop, and/or the age or period at which the malignant neoplasm will develop. In the latter case, there is the advantage that more detailed information can be obtained depending on the type of malignant neoplasm. Alternatively or additionally, the information regarding malignant neoplasms may include information regarding behavioral goals for one user to avoid developing malignant neoplasms or to reduce the likelihood of developing malignant neoplasms. Note that when the information related to malignant neoplasm includes information related to the goal of the action for one user, there is an advantage that the goal for the one user becomes clear. In particular, since each user is different in terms of constitution and lifestyle, it is thought that each user has goals that are suitable for them, and by clarifying these goals, it is possible to make recommendations that are more suitable for the user. . Although it may be necessary to verify whether such a goal is medically accurate, from a statistical perspective using machine learning technology (the technical philosophy of the technology that does not always pursue only the ideal) ) The use of information related to behavioral goals generated based on a certain degree of rationality in the form of machine learning has a unique technical significance and the advantage of presenting information that is the user's goal. Note that the information related to goals may include information related to exercise goals and/or information related to dietary goals. The information related to the exercise goal may include the amount of exercise, exercise time, and/or amount of calories consumed by exercise, etc. in a predetermined period. The information related to the dietary goal may include the amount of food, the type of meal, the type of nutrition of the meal, the calorie amount of the meal, etc. in a predetermined period.

In addition, when health-related information and/or behavior-related information about one group consisting of multiple users is applied, the first machine learning unit correspondingly learns whether the one group is malignant or not. Information regarding the neoplasm may be generated.

The information regarding malignant neoplasm may include the possibility that malignant neoplasm will develop, and/or the age or period at which malignant neoplasm will develop. Alternatively, the information regarding malignant neoplasm may include the type of malignant neoplasm, the possibility that the malignant neoplasm will develop, and/or the age or period at which the malignant neoplasm will develop. In the latter case, there is the advantage that more detailed information can be obtained depending on the type of malignant neoplasm.

The second machine learning unit may have a function of performing machine learning on the relationship between at least health-related information and/or behavior-related information and at least dementia-related information.

The second machine learning unit is configured to generate dementia-related information about the one user in response to the application of health-related information and/or behavioral information about the one user. good. The information related to dementia may include the possibility that dementia will develop and/or the age or time that dementia will develop. Alternatively, the information related to dementia may include the type of dementia, the possibility that dementia will develop, and/or the age or period at which dementia will develop. In the latter case, there is the advantage that more detailed information can be obtained depending on the type of dementia. Further, the information related to dementia may alternatively or additionally include information related to a behavioral goal for one user to avoid developing dementia or to be less likely to develop dementia. In addition, when the information related to dementia includes information related to the goal of such behavior for one user, there is an advantage that the goal for the one user becomes clear. In particular, since each user is different in terms of constitution and lifestyle, it is thought that each user has goals that are suitable for them, and by clarifying these goals, it is possible to make recommendations that are more suitable for the user. . Note that the information that can be included in the information regarding the goal is the same as described above, except that it is information for not developing dementia or for being less likely to develop dementia.

In addition, when health-related information and/or behavior-related information about a group consisting of multiple users is applied, the second machine learning unit correspondingly learns the cognition of the group. may generate information related to the disease.

The information related to dementia may include the possibility that dementia will develop and/or the age or time that dementia will develop. Alternatively, the information related to dementia may include the type of dementia, the possibility that dementia will develop, and/or the age or period at which dementia will develop. In the latter case, there is the advantage that more detailed information can be obtained depending on the type of dementia.

The third machine learning unit may have a function of performing machine learning on the relationship between at least health-related information and/or behavior-related information and at least lifestyle-related disease information.

When health-related information and/or behavior-related information about one user is applied, the third machine learning unit generates lifestyle-related disease information about the one user in response. It's fine. Information related to lifestyle-related diseases may include the possibility that a lifestyle-related disease will develop, and/or the age or period at which a malignant neoplasm will develop. Alternatively, the information related to lifestyle-related diseases may include the type of lifestyle-related disease, the possibility that the lifestyle-related disease will develop, and/or the age or period at which the lifestyle-related disease will develop. In the latter case, there is the advantage that more detailed information can be obtained depending on the type of lifestyle-related disease. Furthermore, the information related to lifestyle-related diseases may alternatively or additionally include information related to behavioral goals for the one user to avoid or become less likely to develop lifestyle-related diseases. Note that when the information related to lifestyle-related diseases includes information related to the goals of such behavior for one user, there is an advantage that the goals for the one user become clear. In particular, since each user is different in terms of constitution and lifestyle, it is thought that each user has goals that are suitable for them, and by clarifying these goals, it is possible to make recommendations that are more suitable for the user. . Note that the information that can be included in the information regarding the goal is the same as described above, except that the information is information for not getting a lifestyle-related disease or for being less likely to get a lifestyle-related disease.

In addition, when health-related information and/or behavior-related information about one group consisting of multiple users is applied, the third machine learning section Information related to habitual diseases may be generated.

Information related to lifestyle-related diseases may include the possibility that a lifestyle-related disease will develop, and/or the age or period at which a lifestyle-related disease will develop. Alternatively, the information related to lifestyle-related diseases may include the type of lifestyle-related disease, the possibility that the lifestyle-related disease will develop, and/or the age or period at which the lifestyle-related disease will develop. In the latter case, there is the advantage that more detailed information can be obtained depending on the type of lifestyle-related disease.

A server of an example system may include some or all of the first to third machine learning units within the server. Alternatively, the first to third machine learning units are provided in one or more information processing devices outside the example system, and the server of the example system is provided outside the system. The information processing apparatus may be accessible to one or more information processing apparatuses having the first to third machine learning units.

FIG. 5 shows how the first machine learning section 20a, the second machine learning section 20b, and the third machine learning section 20c are used in the latter case. The machine learning unit may be connectable to the server directly or indirectly. Indirect connection may be, for example, connected via the Internet 22. Next, the processing flow of the system of this example will be explained using FIG.

<Step 1>
An example server acquires health-related information and/or behavior-related information about a specific group, transmits it to an information processing device including first to third machine learning units, and correspondingly acquires health-related information and/or behavioral information about a specific group. Information related to malignant neoplasms, information related to dementia, and information related to lifestyle-related diseases may be acquired from the third machine learning section, respectively. Note that the health-related information may be information obtained from the user in advance and stored in a database based on information obtained at the time of signing an insurance contract or the like. Moreover, the information related to behavior may be information related to past behavior of people belonging to a specific group. Additionally, the specific group may be policyholders and/or users of the user app. The policyholder or the user of the user application may be only the policyholder, only the user of the user application, or the policyholder or the user of the user application.

<Step 2>
An example server provides statistical information about malignant neoplasms, dementia, and lifestyle-related diseases in a specific group based on information related to malignant neoplasms, dementia, and lifestyle-related diseases. May be generated. Note that an example of information included in the statistical information will be described later.

<Step 3>
An example server may acquire health-related information and/or behavior-related information from a user terminal. Note that the health-related information may be information obtained from the user in advance and stored in a database based on information obtained at the time of signing an insurance contract or the like.

<Step 4>
An example server transmits health-related information and/or behavior-related information about the user to an information processing device that includes first to third machine learning units, and correspondingly sends health-related information and/or behavioral information about the user to Correspondingly, information related to malignant neoplasms, information related to dementia, and information related to lifestyle-related diseases may be acquired from the machine learning unit.

<Step 5>
An example server generates behavioral evaluation information based on information related to malignant neoplasms, information related to dementia, information related to lifestyle-related diseases, and information related to behavior obtained from user terminals. The evaluation information may be sent to the user terminal.

The evaluation information regarding behavior may be evaluation information regarding each of information regarding malignant neoplasm, information regarding dementia, and lifestyle-related diseases. For example, regarding a malignant neoplasm, evaluation information regarding the malignant neoplasm may be generated from information regarding the behavioral goal obtained from the machine learning function and information regarding the user's behavior. For example, for information related to behavioral goals obtained from the machine learning function (information related to exercise and/or information related to meals), information related to actual behavior (information related to exercise and/or Evaluation information regarding the extent to which the actual behavior was performed relative to the behavioral goal may be generated by comparison with the information regarding meals (meal-related information). For example, if the target calorie intake for meals is 2,500 calories, but 3,000 calories are ingested, the excess portion is greater than the target, so the corresponding evaluation may be given. Such evaluation may be performed from the viewpoint of each disease (malignant neoplasm, dementia, lifestyle-related disease). In this case, since each behavior (meal, exercise) has a different effect on each disease, there is an advantage in being able to provide information that is easier for users to understand by being evaluated from each perspective. In particular, users may have illnesses that they are particularly concerned about in relation to the illnesses of relatives or acquaintances, so rather than simply looking at the relationship between behavior (diet, exercise) and general illnesses, users are more concerned about specific illnesses. Specifically, by generating evaluations in relation to each specific disease (malignant neoplasm, dementia, lifestyle-related disease), there is an advantage in being able to become more aware of the necessity of the target action.

Moreover, the above-mentioned evaluation information may additionally or alternatively include evaluation information regarding vital information and/or stress information. An example server has target vital information and target stress information set in advance regarding vital information and stress information, and evaluation information of vital information obtained from a user with respect to the preset vital information, Evaluation information of stress information obtained from a user with respect to stress information set in advance may be generated. In the case of vital information, evaluation information of the user's vital information may be generated, for example, by digitizing information such as the user's blood pressure relative to normal blood pressure, the user's response to normal body temperature, and the like. Furthermore, in the case of stress information, evaluation information of the user's stress information may be generated by, for example, digitizing information on the user's stress value relative to the normal stress value.

<Step 6>
The user terminal may display information based on evaluation information regarding the behavior and/or information regarding the user's location acquired from the server on the display device of the user terminal.

When the user terminal displays evaluation information, the user has the advantage of being able to understand the evaluation of the current behavior toward the goal and being able to change his or her behavior.

Furthermore, when the user terminal displays information related to the user's location, the user has the advantage of being able to understand his or her position in a specific group.

For example, FIG. 7 is an example of what is displayed on the display device on the user terminal. As an example, the user terminal may display evaluation information regarding the goals and current status of lifestyle diseases 01, vital data 02, stress 03, cognitive function 04, and/or cancer prediction 05, respectively. By displaying each of these items, there is an advantage that the overall balance can be understood. Furthermore, since the relationship between the goal and the current state is displayed for each item, there is an advantage that it can be easily understood. Additionally, comprehensive evaluation 06 may also be displayed. The comprehensive evaluation may be based on all of the multiple items. The comprehensive evaluation may be based on, for example, a value calculated by an arithmetic formula of weighted coefficients using each element of the above-mentioned lifestyle diseases 01 to cancer prediction 05 as variables. Further, the ΔΔ service 07 may be specified based on the evaluation of each item or the comprehensive evaluation described above. Further, the ΔΔ service 07 may be a service specified based on information related to the message. By displaying the service in this way, there is an advantage that the next action can be easily understood.

Moreover, in addition to or in place of the generation of the above-mentioned evaluation information, the exemplary server may generate information regarding the position of the user in a specific group and transmit it to the user terminal. The information related to the position may be a ranking in a specific group, a rank set in the specific group, statistical information of a corresponding user in the distribution of statistical information in the specific group, or the like. The specific group may be a group to which the user belongs, or may be a group to which the user does not belong. The particular group may be a group of policyholders. For example, the specific group may be a group of policyholders for an insurance contract provided by an organization operated by the system of this example. Further, the specific group may be a subgroup of the same age group to which the user belongs, or a subgroup of the same gender to which the user belongs, among the group of policyholders.

For example, on the user terminal in Figure 8, statistical information for a specific group regarding the overall evaluation is shown in graph 01 of the case expressed by a normal distribution, and the user's position within the graph is displayed. has been done. By displaying the user's position in a specific group in this way, there is an advantage that the user's position within the group can be understood. The position of the user in this specific group may be determined by ranking using evaluation information of each person in the specific group. In addition, by displaying the health behavior 02 carried out by the predetermined high-ranking people in the comprehensive evaluation, the user can understand what the high-ranking people in the comprehensive evaluation are doing and promote healthy behavior. There are benefits that could be promoted. Here, the health behavior 02 performed by a predetermined high-ranking person may be a behavior performed by a predetermined high-ranking person in a specific group. For example, if 80% of the top 10% of people walk 8,000 steps a day, the health behavior "Walk 8,000 steps a day" may be displayed. Furthermore, by being able to display the progress status 03 of fellow users, there is an advantage that the actions of fellow players can be more referenced. For example, it is assumed that 50% of the previous users are trying to walk 8,000 steps a day as described above. In that case, users who are not trying to "walk 8,000 steps a day" have the advantage of being motivated to be in the top 10% by trying to "walk 8,000 steps a day."

2.5. Example 4
The system of this example uses insurance premium rates.

<Step 1>
An example server acquires health-related information and/or behavior-related information about a specific group, transmits it to an information processing device including first to third machine learning units, and correspondingly acquires health-related information and/or behavioral information about a specific group. Information related to malignant neoplasms, information related to dementia, and information related to lifestyle-related diseases may be acquired from the third machine learning section, respectively.

<Step 2>
An example server provides statistical information about malignant neoplasms, dementia, and lifestyle-related diseases in a specific group based on information related to malignant neoplasms, dementia, and lifestyle-related diseases. May be generated. The statistical information in the present document may include information on whether or not malignant neoplasms, dementia, and lifestyle-related diseases develop in such specific groups, and the timing of their onset. The statistical information may include, for example, probability information that a particular group of people will develop malignant neoplasms, dementia, and lifestyle-related diseases. Further, the statistical information may include information on mathematically expected values of malignant neoplasms, dementia, and lifestyle-related diseases for each person in a specific group for insurance premium calculation. This may be based on the logic that if healthy people continue to engage in health activities, they will not be hospitalized or undergo surgery, their lifespan will be extended, and they will be less likely to die.

<Step 3>
An exemplary server may generate the insurance premium rate calculation formula using a method capable of deriving a predetermined insurance premium rate calculation formula and the above-mentioned statistical information. Here, a well-known technique may be used as a method for deriving the formula for calculating the insurance premium rate. In other words, the basic idea of the insurance premium rate calculation formula is that the amount paid to the policyholder is based on the expected value based on the incidence rate of the policyholder's disease and mortality rate, and the amount paid by the policyholder and other Since the calculation formula is based on a balance between miscellaneous expenses and , a well-known technique that can derive a calculation formula showing such a balance may be used.

<Step 4>
An example server may acquire health-related information and/or behavior-related information from a user terminal. Further, the example server hypothetically generates one or more pieces of future health information and/or behavior information, and uses these acquired health information and/or behavior information. , and the generated health-related information and/or behavior-related information are transmitted together to an information processing device equipped with a first to third machine learning unit, and correspondingly, the first to third machine learning units are Information related to malignant neoplasms, information related to dementia, and information related to lifestyle-related diseases may be obtained from the machine learning department of .

Here, hypothetically generating means, for example, hypothetically generating the future behavior of the user, and by using such generated information as input to the first to third machine learning units, such There is an advantage that the accuracy of information related to malignant neoplasms, information related to dementia, and information related to lifestyle-related diseases is improved when hypothetical actions are taken. Note that the hypothetically generated information may be generated based on information regarding the user's past health and/or information regarding the user's behavior. Additionally, machine learning functionality may be used in such hypothetical generation. A well-known technique for predicting future information from past information may be applied to such a machine-learned function.

<Step 5>
An example server may collect information about the user based on information related to malignant neoplasms, information related to dementia, and/or information related to lifestyle-related diseases, and the above-mentioned insurance premium rate calculation formula. insurance premiums may be calculated.

In addition, in the hypothetical generation described above, if information related to future health and/or information related to behavior is generated hypothetically, the example server correspondingly generates information based on the calculation formula described above. The insurance premium may be calculated accordingly.

In addition, in the hypothetical generation described above, if a plurality of pieces of future health information and/or behavior information are hypothetically generated, the example server correspondingly generates information based on the above calculation formula. Accordingly, an insurance premium corresponding to each future health-related information and/or behavior-related information may be calculated. In this case, for example, insurance premiums corresponding to multiple future actions of the user will be calculated.

<Step 6>
An example server transmits one or more pieces of future health information and/or behavior information and corresponding insurance premium information about the user to a user terminal, and the user terminal transmits the information about the user. The information may be displayed on the display.

In particular, when a user terminal displays information related to a certain action and the corresponding insurance premium, the user will be able to understand what kind of insurance premium will be charged if he or she engages in such action (exercise or diet). There are understandable benefits. Note that in this case, the user terminal may additionally display the current insurance premium and/or the future regular insurance premium. In particular, it is common for insurance premiums to increase with age, so if a lower premium is displayed than the increasing premium due to the user's actions, the user may not be able to take such action. This has the advantage of creating motivation to do so. In other words, in this case, the benefit is that the user understands that by exercising and eating for better health, the user will be less likely to get sick and will be able to maintain better health, and will also be able to pay lower insurance premiums. There is.

In addition, when a user terminal displays information related to multiple actions and the corresponding insurance premiums, the user can determine what kind of insurance premiums will be incurred if he or she engages in such actions (exercise or diet). There are understandable benefits. For example, if the user walks more than XX steps every day in the future, the insurance fee will be △△, and if the user eats less than XX calories each day in addition to the XX steps each day, the □□ insurance premium will be displayed. By doing so, the relationship between exercise and insurance premiums becomes clear. Note that in this case, the user terminal may additionally display the current insurance premium and/or the future regular insurance premium. In particular, it is common for insurance premiums to increase with age, but if a lower premium than the increasing premium is displayed in association with the user's behavior, the user may feel that This has the advantage of creating motivation for such actions. In other words, in this case, the benefit is that the user understands that by exercising and eating for better health, the user will be less likely to get sick and will be able to maintain better health, and will also be able to pay lower insurance premiums. There is.

An example of a mobile device is
an acquisition unit that acquires information related to one or more actions regarding one user and information related to insurance premiums associated with the information related to the one or more actions;
a display unit that displays information related to the one or more actions and information related to the corresponding insurance premium in association with each other;
may be provided.
In addition, the information related to the insurance premiums may include attribute information, health information, behavior information, insurance premium information, and/or recommendation information regarding the one user. It may be generated by being used in the calculation formula for calculating fees.
Further, the calculation formula for calculating the predetermined insurance premium may be based on information generated by using some or all of the first to third machine learning units described above for a specific group.

Note that the machine learning unit in the present application may be realized by a machine learned model. Here, the trained model is assumed to be used as a program module that is part of artificial intelligence software. The trained model of the present invention is used in a computer equipped with a CPU and memory. Specifically, a CPU of the computer may process machine learning and/or application of machine learned functions according to instructions from a trained model stored in memory.

2.6. For various embodiments , the system according to the first aspect comprises:
an acquisition unit that acquires information related to the health of the first user and information related to the behavior of the first user;
Equipped with a function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to recommendations, and the information related to the health of the first user and the information related to the first user. a machine learning unit that applies information related to behavior to generate information related to recommendations regarding the first user;
a communication unit that communicates information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
"It is equipped with the following."

The system according to the second aspect includes, in the first aspect, "
The information related to the recommendation includes information related to the order of messages,
” is a thing.

In the system according to the third aspect, in the first aspect or the second aspect, "
The information related to the recommendation includes information specifying any one of a plurality of predetermined fields,
The plurality of predetermined fields include at least early detection/prevention of malignant neoplasms, prevention of dementia, and/or lifestyle-related diseases,
The communication unit communicates information related to a message regarding the identified field.
” is a thing.

A system according to a fourth aspect includes, in any one of the first to third aspects, "
The information related to the recommendation includes information related to services available to the user.
” is a thing.

A system according to a fifth aspect includes, in any one of the first to fourth aspects, "
The information related to the service includes a link on the Internet corresponding to the service, or information related to a video related to the service.
” is a thing.

A system according to a sixth aspect includes, in any one of the first to fifth aspects, "
The system includes a statistical processing unit,
The acquisition unit acquires health-related information and behavior-related information regarding the first group,
The machine learning unit, based on the health-related information and behavioral information related to the first group, generates information related to malignant neoplasm related to the first group, information related to dementia related to the first group, and obtaining information related to lifestyle-related diseases related to the first group,
The statistical processing unit generates statistical information related to the first group based on information related to malignant neoplasm, information related to dementia, and information related to lifestyle-related diseases related to the first group,
Information regarding malignant neoplasms related to the first group is as follows:
By applying the health-related information and behavior-related information related to the first group to a function that has machine learned the relationship between the health-related information and behavior-related information and the information related to malignant neoplasms, generated,
Information regarding dementia related to the first group is as follows:
The health-related information and behavior-related information related to the first group are generated by applying a machine learning function to the relationship between the health-related information and behavior-related information and the dementia-related information. is,
Information regarding lifestyle-related diseases related to the first group is as follows:
By applying the health-related information and behavior-related information related to the first group to a function that has machine learned the relationship between the health-related information and behavior-related information and the lifestyle-related disease information, It is something that is generated.

A system according to a seventh aspect includes, in any one of the first to sixth aspects, "
The statistical processing unit generates evaluation information of the first user in the first group based on statistical information regarding the first group,
The communication unit communicates evaluation information of the first user to a mobile terminal related to the first user.
” is a thing.

A system according to an eighth aspect includes, in any one of the first to seventh aspects, "
The statistical information includes information regarding the age of onset of malignant neoplasms, dementia, or lifestyle-related diseases of people included in the first group.
”.

A system according to a ninth aspect includes, in any one of the first to eighth aspects, "
communicating information related to the insurance premium for the first user calculated using the insurance premium calculation formula generated using the information related to the age of onset to the mobile terminal related to the first user; ,
”.

A system according to a tenth aspect, in any one of the first to ninth aspects, includes:
The information related to the recommendation includes information related to behavior or meals,
The information related to the insurance premium for the first user includes information related to a plurality of insurance premiums,
The communication unit communicates information related to the insurance premium associated with the information related to the behavior or meal to the mobile terminal related to the first user.
”.

A system according to an eleventh aspect is a system according to any one of the first to tenth aspects described above.
The information related to the user's behavior includes information identifying a message addressed to the user and/or information related to the timing of the message.
”.

The computer program according to the twelfth aspect is “
system,
acquisition means for acquiring information regarding the health of the first user and information regarding the behavior of the first user;
A function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to the recommendation, means for generating information related to a recommendation regarding the first user by applying the method to the information related to the first user;
communication means for communicating information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
It is intended to be used as an operating system.

The method according to the thirteenth aspect comprises:
the system,
an acquisition step of acquiring information related to the health of the first user and information related to the behavior of the first user;
A function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to the recommendation, a generation step of generating information regarding a recommendation regarding the first user by applying the information to the information regarding the first user;
a communication step of communicating information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
"to carry out."

The mobile terminal according to the fourteenth aspect is “
an acquisition unit that acquires information related to the health of the first user and information related to the behavior of the first user;
a transmitting unit that transmits information related to the health of the first user and information related to the behavior of the first user to a server;
an acquisition unit that acquires information related to a message based on information related to the health of the first user and information related to the behavior of the first user from the server;
a display unit that displays a message based on information related to the message;
"It is equipped with the following."

The program according to the fifteenth aspect is “
mobile device,
acquisition means for acquiring information regarding the health of the first user and information regarding the behavior of the first user;
Transmission means for transmitting information related to the health of the first user and information related to the behavior of the first user to the server;
acquisition means for acquiring, from the server, information related to a message based on information related to the health of the first user and information related to the behavior of the first user;
Display means for displaying a message based on information related to the message;
"to carry out."

The method according to the sixteenth aspect comprises: “
The mobile device is
an acquisition step of acquiring information related to the health of the first user and information related to the behavior of the first user;
a transmitting step of transmitting information related to the health of the first user and information related to the behavior of the first user to a server;
an acquisition step of acquiring information related to a message based on information related to the health of the first user and information related to the behavior of the first user from the server;
a display step of displaying a message based on information related to the message;
"to carry out."

A system according to a seventeenth aspect is the system according to any one of the first to sixteenth aspects, in which "the system includes a memory capable of storing information related to the recommendation."

A program according to an eighteenth aspect is a program according to any one of the first to seventeenth aspects, in which "the system includes a memory capable of storing information related to the recommendation."

A method according to a nineteenth aspect is the method according to any one of the first to seventeenth aspects, in which "the system includes a memory capable of storing information related to the recommendation."

3. Information Processing Device The mobile terminal, server, or cloud used in the systems according to Examples 1 to 4 (and the embodiment 2.6) described above may be composed of one or more information processing devices. The information processing device 10 may include a bus 11, a calculation device 12, a storage device 13, an input device 14, a display device 15, and a communication IF 16, as shown in FIG. Further, the information processing device 10 may be directly or indirectly connected to a mobile terminal via the network 19. Further, the information processing device 10 may be connected to a database (not shown). Furthermore, the database may be included within the information processing device 10.

The bus 11 may have a function of transmitting information between the arithmetic device 12, the storage device 13, the input device 14, the display device 15, and the communication IF 16.

An example of the arithmetic device 12 is a processor. This may be a CPU or an MPU. It may also include a graphics processing unit, digital signal processor, and the like. In short, the arithmetic device 12 may be any device that can execute instructions of a program.

The storage device 13 is a device that records information. This may be either external memory or internal memory, and may be either main storage or auxiliary storage. Further, a magnetic disk (hard disk), optical disk, magnetic tape, semiconductor memory, etc. may be used. Further, it may have a storage device via a network or a storage device on a cloud via a network.

Note that registers, L1 caches, L2 caches, etc. that store information near the arithmetic unit may be included in the arithmetic unit 12 in the schematic diagram of this figure, but in the design of computer architecture, information The storage device 13 may include these as devices for recording. In short, it is sufficient that the arithmetic device 12, the storage device 13, and the bus 11 are configured so that they can cooperate to execute information processing.

The storage device 13 can include programs that execute services related to the present invention. Further, data necessary for executing services related to the present invention can be recorded as appropriate.

In addition, although the above description describes the case where the arithmetic device 12 is executed based on the program provided in the storage device 13, one of the formats in which the above-mentioned bus 11, the arithmetic device 12, and the storage device 13 are combined is described. As such, the information processing according to the present system may be realized by a programmable logic device whose hardware circuit itself can be changed or by a dedicated circuit in which the information processing to be executed is determined.

The input device 14 is for inputting information, but may have other functions. Examples of the input device 14 include a keyboard, a mouse, a touch panel, and a pointing device such as a pen-type pointing device.

The display device 15 has a display, for example, but may have other functions. Further, the display device 15 may be a liquid crystal display, a plasma display, an organic EL display, or the like. In short, any device that can display information may be used. Further, the input device 14 may be partially provided like a touch panel.

The network 19, together with the communication IF 16, transmits information. That is, it has a function of transmitting information from the information processing device 10 to other information terminals 18 via the network. The communication IF 16 may be of any connection type, such as USB, IEEE1394, Ethernet (registered trademark), PCI, or SCSI. The network 19 may be wired or wireless, and may use optical fiber, coaxial cable, Ethernet cable, or the like.

In this figure, the information processing device 10 is described as one, but the information processing device 10 may be composed of a plurality of information processing devices. The plurality of information processing devices may be connected internally or externally. Further, when the information processing device 10 is composed of a plurality of information processing devices, the owners may be different. Further, the person who operates the information processing device 10 as a system according to the present invention may be different from the owner of the information processing device 10. Moreover, the above-mentioned server may be a physical entity or may be a virtual entity. For example, the information processing device 10 may be virtually realized using cloud computing.

It goes without saying that the invention examples described in the embodiments of the present application documents are not limited to those described in the present application documents, but can be applied to various examples within the scope of the technical idea.

Furthermore, the processes and procedures described in this document may be realized not only by those explicitly described in the embodiments but also by software, hardware, or a combination thereof. In particular, the technology described as processing performed by a server may be processed by an information processing device that is a cloud or a combination of a server and a cloud. Furthermore, the processes and procedures described in the documents of this application may be implemented as computer programs and may be executed by various computers. For example, the technology described as processing performed by a server may be realized by a function of a computer program installed in the server. Additionally, these programs may be stored on non-transitory or temporary storage media.

Claims (19)

an acquisition unit that acquires information related to the health of the first user and information related to the behavior of the first user;
Equipped with a function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to recommendations, and the information related to the health of the first user and the information related to the first user. a machine learning unit that applies information related to behavior to generate information related to recommendations regarding the first user;
a communication unit that communicates information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
A system equipped with The information related to the recommendation includes information related to the order of messages,
The system of claim 1. The information related to the recommendation includes information specifying any one of a plurality of predetermined fields,
The predetermined plurality of fields include at least early detection/prevention of malignant neoplasms, dementia prevention, and/or lifestyle-related diseases,
The communication unit communicates information related to a message regarding the identified field.
The system according to claim 1 or 2. The information related to the recommendation includes information related to services available to the user.
A system according to any one of claims 1 to 3. The information related to the service includes a link on the Internet corresponding to the service, or information related to a video related to the service.
The system according to claim 4. The system includes a statistical processing unit,
The acquisition unit acquires health-related information and behavior-related information regarding the first group,
The machine learning unit, based on the health-related information and behavioral information related to the first group, generates information related to malignant neoplasm related to the first group, information related to dementia related to the first group, and obtaining information related to lifestyle-related diseases related to the first group,
The statistical processing unit generates statistical information related to the first group based on information related to malignant neoplasm, information related to dementia, and information related to lifestyle-related diseases related to the first group,
Information regarding malignant neoplasms related to the first group is as follows:
By applying the health-related information and behavior-related information related to the first group to a function that has machine learned the relationship between the health-related information and behavior-related information and the information related to malignant neoplasms, generated,
Information regarding dementia related to the first group is as follows:
The health-related information and behavior-related information related to the first group are generated by applying a machine learning function to the relationship between the health-related information and behavior-related information and the dementia-related information. is,
Information regarding lifestyle-related diseases related to the first group is as follows:
By applying the health-related information and behavior-related information related to the first group to a function that has machine learned the relationship between the health-related information and behavior-related information and the lifestyle-related disease information, generated,
A system according to any one of claims 1 to 5. The statistical processing unit generates evaluation information of the first user in the first group based on statistical information regarding the first group,
The communication unit communicates evaluation information of the first user to a mobile terminal related to the first user.
The system according to claim 6. The statistical information includes information regarding the age of onset of malignant neoplasms, dementia, or lifestyle-related diseases of people included in the first group.
The system according to claim 6 or 7. communicating information related to the insurance premium for the first user calculated using the insurance premium calculation formula generated using the information related to the age of onset to the mobile terminal related to the first user; ,
The system according to claim 8. The information related to the recommendation includes information related to behavior or meals,
The information related to the insurance premium for the first user includes information related to a plurality of insurance premiums,
The communication unit communicates information related to the insurance premium associated with the information related to the behavior or meal to the mobile terminal related to the first user.
The system according to claim 9. The information related to the user's behavior includes information identifying a message addressed to the user and/or information related to the timing of the message.
A system according to any one of claims 1 to 10. system,
acquisition means for acquiring information regarding the health of the first user and information regarding the behavior of the first user;
A function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to the recommendation, means for generating information related to a recommendation regarding the first user by applying the method to the information related to the first user;
communication means for communicating information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
A program to operate as. the system,
an acquisition step of acquiring information related to the health of the first user and information related to the behavior of the first user;
A function that has machine learned the relationship between information related to the user's health, information related to the user's behavior, and information related to the recommendation, a generation step of generating information regarding a recommendation regarding the first user by applying the information to the information regarding the first user;
a communication step of communicating information related to a message to a mobile terminal related to the first user using information related to a recommendation regarding the first user;
How to do it. an acquisition unit that acquires information related to the health of the first user and information related to the behavior of the first user;
a transmitting unit that transmits information related to the health of the first user and information related to the behavior of the first user to a server;
an acquisition unit that acquires information related to a message based on information related to the health of the first user and information related to the behavior of the first user from the server;
a display unit that displays a message based on information related to the message;
A mobile terminal equipped with mobile device,
acquisition means for acquiring information regarding the health of the first user and information regarding the behavior of the first user;
Transmission means for transmitting information related to the health of the first user and information related to the behavior of the first user to the server;
acquisition means for acquiring, from the server, information related to a message based on information related to the health of the first user and information related to the behavior of the first user;
Display means for displaying a message based on information related to the message;
A program to run. The mobile device is
an acquisition step of acquiring information related to the health of the first user and information related to the behavior of the first user;
a transmitting step of transmitting information related to the health of the first user and information related to the behavior of the first user to a server;
an acquisition step of acquiring information related to a message based on information related to the health of the first user and information related to the behavior of the first user from the server;
a display step of displaying a message based on information related to the message;
How to do it. The system according to any one of claims 1 to 11, wherein the system includes a memory capable of storing information related to the recommendation. The program according to claim 12, wherein the system includes a memory capable of storing information related to the recommendation. 14. The method of claim 13, wherein the system includes a memory capable of storing information related to the recommendation.