Action proposition device and action proposition method

Abstract

To make a proposition suitable for invoking a behavioral change on a user such as the elderly such as stepping out or going out by the car.SOLUTION: An action proposition device according to the present disclosure comprises an acquisition unit, a recording unit, a selection unit, and a proposition unit. The acquisition unit communicates with a first information terminal that a first user uses via a network. The acquisition unit acquires user information of the first user that the first information terminal has received. The user information of the first user includes living sphere information indicating the living sphere of the first user. The recording unit stores candidate destination information including one or more candidate destinations. The selection unit selects from the candidate destination information one or more destinations exceeding a geographical range indicated at least by the living sphere information on the basis of profiling information derived by analyzing the user information of the first user. The proposition unit outputs, to the first information terminal, proposition information for proposing a selected destination to the first user by means of the first information terminal.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to an action suggestion device and an action suggestion method. [Background technology]

[0002] Elderly people who lose contact with society after retirement and stay at home, leading to mental and physical illness, is becoming a social issue. In addition, children of elderly people are worried about their parents who stay at home, and are looking for ways to encourage behavioral changes such as getting their parents to go out and get into the habit of going out by car.

[0003] Conventionally, a method for encouraging users to change their outing behavior, etc., is known to analyze the user's preferences and behavior through profiling and suggest actions based on the analysis results. Suggestions based on this profiling are used to recommend viewing content for video distribution services and to recommend products on EC (Electronic Commerce) sites.

[0004] For example, Patent Document 1 discloses a method for generating an experience itinerary based on preferences and user attributes (gender), and transmitting the generated experience itinerary to a vehicle for execution. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Special Publication No. 2022-517052 Summary of the Invention [Problem to be solved by the invention]

[0006] However, even if destinations and itineraries were suggested based on profiling, there was a problem as to whether elderly people who tend to stay at home would accept the suggestions and change their behavior by going out or going out.

[0007] One of the problems that the present disclosure aims to solve is to provide suitable suggestions for users such as elderly people to change their behavior, such as going outside or going out by car. [Means for solving the problem]

[0008] The action suggestion device according to the present disclosure includes an acquisition unit, a recording unit, a selection unit, and a suggestion unit. The acquisition unit communicates with a first information terminal used by a first user via a network. The acquisition unit acquires user information of the first user accepted by the first information terminal. The user information of the first user includes living area information indicating a living area of ​​the first user. The recording unit stores destination candidate information including one or more destination candidates. The selection unit selects, based on profiling information obtained by analyzing the user information of the first user, one or more destinations that are beyond at least a geographical range indicated by the living area information from the destination candidate information. The suggestion unit outputs, to the first information terminal, suggestion information for suggesting the selected destination to the first user via the first information terminal. Effect of the Invention

[0009] According to the present disclosure, users such as elderly people can receive suitable suggestions for making behavioral changes, such as going out or going out by car. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an action suggestion system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a functional configuration of the action suggestion device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of a functional configuration of a main user terminal used by a user who receives a proposal, which is a user terminal according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the functional configuration of a user terminal according to the embodiment, which is a support user terminal used by another user who supports the user receiving a proposal. [Figure 5A]FIG. 5A is a sequence chart showing an example of a sequence of information processing executed in the action suggestion system according to the embodiment. [Figure 5B] FIG. 5B is a sequence chart showing an example of a sequence of information processing executed in the action suggestion system according to the embodiment. [Figure 6A] FIG. 6A is a diagram showing an example of a display screen of a user terminal according to the embodiment. [Figure 6B] FIG. 6B is a diagram illustrating an example of a display screen of the user terminal according to the embodiment. [Figure 6C] FIG. 6C is a diagram illustrating an example of a display screen of a user terminal according to an embodiment. [Figure 6D] FIG. 6D is a diagram showing an example of a display screen of a user terminal according to an embodiment. [Figure 7A] FIG. 7A is a diagram illustrating an example of a display screen of an IOT home appliance according to the embodiment. [Figure 7B] FIG. 7B is a diagram illustrating an example of a display screen of the IOT home appliance according to the embodiment. [Figure 8] FIG. 8 is a flowchart showing an example of the flow of information processing in the behavior modification determination process of FIG. 5B for determining whether or not the behavior modification resulting from the proposal has been successful. [Figure 9] FIG. 9 is a diagram illustrating an example of a configuration of point table information according to the embodiment. [Figure 10] FIG. 10 is a diagram for explaining the learning information model according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of a configuration of input data of the learning information model according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, with reference to the drawings, embodiments of an action suggestion system, an action suggestion device, a user terminal, an action suggestion method, a program, and a recording medium according to the present disclosure will be described.

[0012] In the description of the present disclosure, components having the same or substantially the same functions as those described above with respect to the previously-mentioned drawings may be given the same reference numerals, and the description may be omitted as appropriate. In addition, even when the same or substantially the same parts are shown, the dimensions and ratios of the components may be different depending on the drawing. In addition, for example, from the viewpoint of ensuring the visibility of the drawings, reference numerals may be given only to the main components in the description of each drawing, and reference numerals may not be given to components having the same or substantially the same functions as those described above with respect to the previously-mentioned drawings.

[0013] Below, an example will be described in which the technology according to the present disclosure is applied to encouraging elderly people who tend to stay at home to change their behavior and go out.

[0014] The technology disclosed herein can be applied to people other than the elderly, such as company workers who have nothing to do on weekends and stay at home, or people looking for a new hobby. A new hobby can be a mobility activity, such as collecting stamps from shrines and temples, collecting castle stamps, pilgrimages to sacred places in subcultures, or map-based games.

[0015] In addition, although the target of this disclosure is inactive elderly people who tend to stay at home, the technology according to this disclosure can also be applied to so-called active seniors.

[0016] Conventionally, a technology that proposes products and viewing content to users involves profiling a user's tastes, gender, etc., and then proposing products and viewing content that are preferred by similar users. This technology is used on electronic commerce (EC) sites and distribution services on the Internet. Collaborative filtering is a well-known algorithm for this purpose.

[0017] It is also possible to apply machine learning techniques to this proposed technology, form a learning information model that accumulates cases where proposals were successful as success data, and improve the accuracy of successful proposals.

[0018] However, the inventors have found through research and analysis that if the user is an elderly person who tends to stay at home and the suggestion is to go out, a problem occurs in that the elderly person will not accept the suggestion itself if the suggestion is merely a destination suggestion based on profiling. By not accepting, we mean that the suggestion itself is not heard or is not interested.

[0019] The proposal is generally made with smartphone or personal computer applications, but a certain level of IT literacy is required to use them, and there are few elderly people who are good at these. On the other hand, elderly people who are good at IT are less likely to stay at home and become socially isolated, which creates a contradiction in that they are not interested in the technology disclosed in this disclosure.

[0020] Furthermore, even if the suggestion is accepted and a behavioral change to going out occurs, there is the problem of what extent of movement should be judged as a successful outing. When considering going out as a habit, it is not appropriate to judge a daily trip to a nearby convenience store as an outing, and if a learning information model is constructed and adjusted using these as successful data, there is also the problem that the accuracy of the success of the suggestion will be affected.

[0021] In addition, when considering the habit of going out, the inventors of the present disclosure have also found the problem of needing motivation to continue, such as wanting to go out again. Solving this problem is ideal for elderly people who are good at IT, as it makes going out more enjoyable and is expected to make it a habit.

[0022] In order to solve the above-mentioned problems found by the inventors, embodiments of the technology according to the present disclosure will be described below.

[0023] 1 is a diagram showing an example of the configuration of an action suggestion system 7 according to an embodiment. The action suggestion system 7 includes a server 1, at least one user terminal, and at least one network device.

[0024] Fig. 1 illustrates an example of an action suggestion system 7 including, as at least one user terminal, a main user terminal 2 and a support user terminal 3. Fig. 1 also illustrates an example of an action suggestion system 7 including, as at least one network device, an IOT home appliance 4 and an in-vehicle terminal 5.

[0025] In the action suggestion system 7, the server 1 and at least one user terminal are communicatively connected via a network 6. As the network 6, for example, a telecommunication line such as the Internet can be used.

[0026] The server 1 is a device that manages the entire action suggestion system 7. The server 1 is realized by at least one server device provided on a cloud, for example. When the server 1 is realized by two or more server devices, the two or more server devices can cooperate with each other via an API (Application Programming Interface). The server 1 is configured with an action suggestion device 10. The action suggestion device 10 is a device that suggests an action such as going out to a user. The action suggestion device 10 may be at least one of the server devices of the server 1 itself, or may be a virtual device realized by at least one of the server devices of the server 1 executing software. Typically, the server 1 has a hardware configuration using a normal computer, including a processor, a RAM (Random Access Memory), a ROM (Read Only Memory), a recording device, an input / output I / F (interface), a network I / F, and a power source. In addition, in the server 1, the processor loads a program stored in the ROM or the like into the RAM and executes it, that is, the application is executed, thereby realizing each function of the action suggestion device 10 (see FIG. 2).

[0027] The user terminals 2 and 3 are information terminals used by users of the service provided by the action suggestion device 10. In this embodiment, the user (main user) of the main user terminal 2 is a target person such as an elderly person whose behavioral change is to be encouraged. The user (sub-user) of the support user terminal 3 is at least one user who supports the behavioral change of the target person, such as the child or grandchild of the elderly person. Naturally, a plurality of support user terminals 3 may be prepared for each sub-user who supports the target person, such as the son, daughter, and grandchild of the elderly person (target person). The user terminals 2 and 3 are, for example, smartphones, and have a hardware configuration including a processor, RAM, ROM, a recording device, an input / output I / F, a network I / F, a wireless communication I / F, sensors such as GPS, and a power source. The user terminals 2 and 3 are realized by the processor loading a program stored in the ROM or the like into the RAM and executing it, that is, by executing the application.

[0028] Here, the main user terminal 2 is an example of a first information terminal. Also, a main user such as an elderly person is an example of a first user. Also, the support user terminal 3 is an example of a second information terminal. Also, sub-users such as the child and grandchild generations of the elderly are an example of a second user.

[0029] In addition, various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), or a dedicated arithmetic circuit realized by an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array) can be used as appropriate as the processors of the server 1 and the user terminals 2 and 3.

[0030] As the recording devices of the server 1 and the user terminals 2 and 3, various recording media and recording devices such as HDDs (Hard Disk Drives), SSDs (Solid State Drives), and Flash memories can be appropriately used.

[0031] In the action suggestion system 7, at least one of the user terminals 2 and 3 and at least one network device are connected to each other so as to be able to communicate with each other via wired or wireless communication. In the example of Fig. 1, each of the IOT home appliances 4 and the in-vehicle terminal 5 is connected to the main user terminal 2 by short-range wireless communication such as Wi-Fi (registered trademark) or Bluetooth (registered trademark), and communicates with the server 1 via the main user terminal 2.

[0032] Examples of the IOT home appliances 4 include power home appliances such as power distributors, lighting equipment, solar cells, and chargers. Examples of the IOT home appliances 4 include devices that present video, music, and game content to users, such as TVs, VTRs, AI speakers, on-demand video receiving devices, and game devices. Examples of the IOT home appliances 4 include cooking home appliances such as coffee makers and microwave ovens, cleaning home appliances such as washing machines, dishwashers, and vacuum cleaners, sanitary home appliances such as baths and toilets, and air conditioning devices such as ventilation fans, electric fans, coolers, and air purifiers. Examples of the IOT home appliances 4 include health home appliances such as blood pressure monitors, weight scales, and smart watches that acquire heart rate and movement data, and monitoring devices such as door phones, baby monitors, and security cameras.

[0033] Two or more IOT home appliances 4 may be connected to be able to communicate with each other. The IOT home appliance 4 is configured to be able to acquire at least its own IOT data (edge ​​terminal information). The IOT home appliance 4 is also configured to be able to transmit the acquired IOT data of its own appliance to one of the user terminals 2 and 3 connected thereto. The IOT home appliance 4 may transmit the IOT data of its own appliance to one of the user terminals 2 and 3 via another IOT home appliance 4.

[0034] Here, the IOT data (edge ​​terminal information) of the IOT home appliance 4 is, for example, product information, power ON / OFF information, and operation status information.

[0035] The product information may include information on the type of product, such as cooking appliances such as coffee makers and microwave ovens, beauty appliances such as hair dryers and steamers, air conditioning appliances such as air conditioners, refrigerators, lighting, and TVs, as well as information on the product type, such as entry-level models, high-volume models, high-grade models, and specialty models.

[0036] The operation status information may include information on the channel being viewed and program information if the IOT home appliance 4 is a TV. If the IOT home appliance 4 is an air conditioner, the operation status information may include information on the operation menu such as rapid cooling and high-power airflow. If the IOT home appliance 4 is a microwave oven, the operation status information may include information on whether only the heating time setting is being used or whether the cooking menu is being used.

[0037] The in-vehicle terminal 5 is an information processing terminal mounted on a vehicle, and is realized by a computer such as an ECU (Electronic Control Unit) or an OBU (On Board Unit) provided inside the vehicle. The in-vehicle terminal 5 may be an external computer installed near the dashboard of the vehicle, or may also function as a car navigation device.

[0038] The vehicle to which the in-vehicle terminal 5 is attached is typically an automobile, but may be any mobility (moving body) capable of transporting people, such as a motorcycle, bicycle, electric kickboard, electric wheelchair, or electric cart such as a senior car. The mobility may also be an autonomous vehicle that performs automatic driving. Furthermore, a drone capable of transporting people may also be used as the mobility.

[0039] In addition, a vehicle configured as a connected car has a communication means for communicating with the outside. In this case, the in-vehicle terminal 5 may communicate with the server 1 directly without going through the user terminals 2 and 3.

[0040] <About the Action Suggestion Device> 2 is a diagram showing an example of a functional configuration of the action suggestion device 10 according to the embodiment. The action suggestion device 10 realizes functions as a reception means 11, an output means 12, a control means 14, a communication means 13, and a recording means 15 by executing a program loaded in a memory such as a RAM by a processor.

[0041] The reception means 11 receives instructions from an operator via an input / output I / F such as a keyboard, a mouse, etc. The operator may be replaced by an AI. In this case, the reception means 11 may receive instructions from the AI ​​without going through the input / output I / F.

[0042] The output means 12 outputs video information and audio information to the outside via a display and a speaker.

[0043] The communication means 13 communicates with the user terminals 2 and 3 connected to the network 6 via a network interface. Here, the communication means 13 is an example of an acquisition unit and a proposal unit.

[0044] The control means 14 is an application executed in the action suggestion device 10, and includes a communication unit 141, an action suggestion unit 142, an action determination unit 143, a learning unit 144, an action record playback unit 145, and a satisfaction degree calculation unit 146.

[0045] The communication unit 141 implements a closed SNS between the main user terminal 2 and the support user terminal 3. Here, the relationship between the main user terminal 2 and the support user terminal 3 is between internal user terminals.

[0046] A closed SNS is a service that allows conversation (chat) and sharing of photo information limited to a user group. Here, a user group is a group such as a family indicated by the user group information 15h stored in the recording means 15. A closed SNS is used for the purpose of exchanging and collecting opinions on proposed destination candidates. Also, when a main user goes out to a proposed destination, it is used as an application for sharing action and memory information 15e of the trip.

[0047] The action suggestion unit 142 suggests a destination for causing a behavioral change to a main user such as an elderly person. Here, the action suggestion unit 142 is an example of an acquisition unit, a selection unit, and a suggestion unit.

[0048] As an example, the action suggestion unit 142 as an acquisition unit communicates with the main user terminal 2 used by the main user via the network 6, using the communication means 13. Furthermore, the action suggestion unit 142 acquires user information of the main user accepted by the main user terminal 2, using the communication means 13. Here, the user information of the main user includes living area information 15b indicating the living area of ​​the main user.

[0049] As an example, the action suggestion unit 142 as an acquisition unit communicates with a support user terminal 3 used by a sub-user such as a child via the network 6 through the communication means 13. In addition, the action suggestion unit 142 acquires user information of the sub-user received by the support user terminal 3 through the communication means 13.

[0050] As an example, the action suggestion unit 142 as an acquisition unit further acquires, via the communication means 13, location information indicating the location of the main user terminal 2 in route guidance to the destination based on the suggested information.

[0051] As an example, the action suggestion unit 142 as a selection unit selects a destination to be suggested from the destination candidate information 15a based on profiling information obtained by analyzing the user information of the main user. For example, the action suggestion unit 142 selects one or more destinations that are beyond the geographical range indicated by at least the living area information of the main user.

[0052] As an example, the action suggestion unit 142 as a selection unit selects one or more destinations different from the destinations based on the profiling information of the main user as suggested destinations from the candidate destination information 15a, further based on profiling information obtained by analyzing the user information of the sub-user.

[0053] As an example, the behavior suggestion unit 142 as a selection unit inputs profiling information obtained by analyzing user information into the learning information model 15d, and obtains the destination to be selected, i.e., the suggested destination, output from the learning information model 15d in response to the input of the profiling information.

[0054] As an example, the action suggestion unit 142 as a suggestion unit outputs, via the communication means 13, suggestion information for suggesting the destination selected by the user to the user on at least one of the user terminals 2 and 3, to at least one of the user terminals 2 and 3.

[0055] As an example, the action suggestion unit 142 as a suggestion unit outputs, via the communication means 13, suggestion information for suggesting to the main user (see Figure 6C) a destination selected by the main user and a destination selected by the sub-user in a comparable manner to the main user.

[0056] The behavior determination unit 143 determines whether a behavior change has occurred due to the destination suggestion. Here, the behavior determination unit 143 is an example of a determination unit.

[0057] As an example, the behavior determination unit 143 determines whether the proposed information output to the main user terminal 2 is successful data that has caused a behavioral change in the main user. For example, the behavior determination unit 143 determines whether the proposed information is successful data based on the location information of the main user terminal 2 and the living area information of the main user.

[0058] As an example, when route guidance to a destination based on the proposed information is started in the main user terminal 2, the behavior determination unit 143 determines that the proposed information is successful data.

[0059] As an example, the behavior determination unit 143 does not treat long-distance trips by means other than vehicles, such as traveling by bullet train or airplane, as successful data. This configuration makes it possible to suppress a decrease in the accuracy of destination suggestions associated with trips from a different perspective to the promotion of behavioral change, such as trips about once a year.

[0060] The learning unit 144 performs machine learning on the learning information model 15d.

[0061] As an example, the learning unit 144 learns parameters of the learned information model 15d so as to output a destination according to the input profiling information, from among one or more destinations included in the destination candidate information 15a.

[0062] As an example, the learning unit 144 learns the parameters of the learned information model 15d by using a destination based on the proposal information determined to be successful data and the profiling information corresponding to the destination.

[0063] The action record reproducing unit 145 generates action recollection information 15e.

[0064] The satisfaction level calculation unit 146 calculates the satisfaction level. Here, the satisfaction level is information indicating the satisfaction level of the user inside and outside the vehicle when going to a destination based on the proposed information. The satisfaction level has an influence on the habituation and continuity of going out, and continuing to propose destinations with high satisfaction levels promotes the habituation of going out and becomes an element of long-term successful data, a so-called "addiction" element. Here, the satisfaction level calculation unit 146 is an example of a calculation unit.

[0065] As an example, the satisfaction level calculation unit 146 calculates the user's satisfaction level for the destination based on the proposed information determined to be successful data. The satisfaction level calculation unit 146 also stores information indicating the calculated satisfaction level as satisfaction level information 15f in the recording means 15. The satisfaction level calculation unit 146 also outputs the satisfaction level information 15f indicating the calculated satisfaction level to at least one of the user terminals 2 and 3 via the communication means 13.

[0066] As an example, the satisfaction level calculation unit 146 calculates the satisfaction level by detecting the sound of a cheerful conversation in a car moving to a destination, or by image analysis of a person's smile from video information in the car. For example, the satisfaction level calculation unit 146 scores the number of times a smile image in which a smile of a user (e.g., a main user) is recognized and the number of times laughter is detected among images obtained by a camera in the car or the user terminals 2 and 3 during an outing. The satisfaction level calculation unit 146 may calculate the satisfaction level by, for example, the amount of photo information taken outside the car or image analysis. For example, the satisfaction level calculation unit 146 scores the satisfaction level by giving a score of 10 points if a smile image is detected 10 times or more, and adding an additional 10 points if there is a smile image of a companion (e.g., a sub-user) among the detected smile images. Similarly, the satisfaction level calculation unit 146 also scores the satisfaction level by the number of times laughter is detected in the car and the presence or absence of a companion. The satisfaction level calculation unit 146 also adds points based on the number of photos and videos taken by the user terminals 2 and 3 inside and outside the vehicle.

[0067] The recording means 15 stores destination candidate information 15a, living area information 15b, point information table 15c, learning information model 15d, behavioral memory information 15e, satisfaction level information 15f, profile information 15g, user group information 15h, questionnaire information 15i, reservation route information 15j, and location information 15k. Here, the recording means 15 is an example of a recording unit.

[0068] The destination candidate information 15a is information including one or more destination candidates. Specifically, the destination candidate information 15a is information indicating one or more destinations that are the destinations of an outing. The destination candidate information 15a may include intermediate stops on the journey to the destination. The destination may be set to a typical tourist spot, or to a point where other main users or sub-users have high satisfaction. The main user may also set a nearby point outside the living area that he or she has not yet visited as the destination. The information indicating the destination is assumed to be information such as an address, latitude and longitude information, etc., that is sufficient to provide route guidance on a map at least in a car navigation function.

[0069] The living area information 15b is information indicating the living area of ​​the main user. As an example, the living area information 15b is defined by a predetermined rule, such as within a 2 km radius from the main user's residence confirmed by a questionnaire or the like. Of course, the living area information 15b may be defined based on the location information of the main user terminal 2.

[0070] The point information table 15c is a table showing an increase in the level of behavioral change regarding going out by adding points (see FIG. 9).

[0071] The learning information model 15d is a machine learning model in which parameters are trained to output a destination according to the input profiling information among one or more destinations included in the destination candidate information 15a. Details of the learning information model 15d will be described later (see FIG. 10 and FIG. 11).

[0072] The learning information model 15d may be stored outside the action suggestion device 10. In this case, the action suggestion unit 142 executes input and output to and from the learning information model 15d via the communication means 13.

[0073] The behavioral recollection information 15e is information generated by the behavioral record playback unit 145. As the behavioral recollection information 15e, video, photos, and audio information from inside and outside the car during a trip to a proposed destination are recorded. The behavioral recollection information 15e includes photos showing accompanying people, photos showing participants having fun, and videos of beautiful landscapes and tourist spots. The behavioral recollection information 15e may also include image, video, and audio data that has been subjected to a digest process in which these images, videos, and audio are picked up, or a process in which the images, videos, and audio are arranged in chronological order.

[0074] The image information, video information, and audio information are acquired via cameras and microphones attached to the user terminals 2 and 3 and the vehicle-mounted terminal 5 , and are input into the action suggestion device 10 by the communication means 13 .

[0075] The behavioral recollection information 15e may also include animation data of a route to a destination that is synthesized with bird's-eye view 3D map information. The behavioral recollection information 15e may also include in-car audio and background music.

[0076] The satisfaction level information 15f is information indicating the satisfaction level calculated by the satisfaction level calculation unit 146. The satisfaction level information 15f may include the image, video, or audio used in the calculation of the satisfaction level, or may include the detection result of a smile or laughter for the image, video, or audio.

[0077] The profile information 15g is information obtained by analyzing at least the user information of the user terminals 2 and 3. The profile information 15g may be generated by analysis by the action suggestion device 10, such as the action suggestion unit 142, or may be generated by analysis outside the action suggestion device 10. Here, the profile information 15g is an example of profiling information.

[0078] As an example, the profile information 15g is generated by analyzing user responses (user information) to a questionnaire or analyzing data acquired from the IOT home appliance 4. The profile information 15g is a vector value obtained by combining each of the analyzed factors. The profile information 15g may have vector values ​​divided into categories, and in the embodiment according to the present disclosure, the profile information 15g has vector values ​​for each of the categories of physical profile information and mental profile information (see FIG. 11).

[0079] The user group information 15h is information indicating the relationship between a user of one main user terminal 2 (main user) and users of one or more support user terminals 3 (sub-users). In one example of an embodiment of the present disclosure, the main user is an elderly person, and the sub-users are the elderly person's family members, such as their children and grandchildren. The information indicating this relationship is used in arbitration when the elderly person, who is the main user, selects a proposed destination. Typically, the final decision is left to the main user, who selects whether to prioritize his or her own preferred destination or the preferred destination of a sub-user, such as his or her children or grandchildren.

[0080] The questionnaire information 15i is information for presenting a questionnaire (see FIG. 6A) to a user on the user terminal 2, 3. The user's answers to the questions in the questionnaire (user information) are analyzed as profile information 15g and recorded in the recording means 15, as described above.

[0081] The "preference questions" in the questionnaire are typically used to confirm the user's preferences for traveling or going out, such as liking history, liking food, liking visiting shrines and temples, liking walking, liking driving a car, liking enjoying nature, liking taking photos, etc. "Preferences" can also be obtained by analyzing IOT data from IOT home appliances. Typically, "preferences" are estimated based on the genre of TV viewing information.

[0082] The "personality questions" in the questionnaire include "want to take time to have fun" and "want to have fun in a minimal amount of time." In psychology, there is a personality test called the Big Five, which classifies personality using a five-factor model of openness, conscientiousness, extraversion, agreeableness, and neuroticism. Of course, the questions in the questionnaire may be questions designed to derive these five factors.

[0083] The "lifestyle questions" in the survey include whether or not you like cleanliness, whether you like eco-friendly living, whether you are an early riser, etc. In addition to the survey user responses, lifestyle information is also generated by analyzing IoT data from IoT home appliances4. For example, if you use your washing machine or vacuum cleaner a lot, you like eco-friendly living, and if you own a lot of eco-friendly home appliances, it can be inferred from the time of your life, whether you are an early riser, and whether you are regular or irregular based on whether the lights are on or off.

[0084] The "living area question" in the questionnaire confirms the user's address. The living area is analyzed within a predetermined radius, such as a 2 km radius, from the confirmed address, and recorded as living area information 15b. The living area information may be statistically differentiated by age or gender. The location information acquired by the location information acquisition unit 255 of the main user terminal 2 may be analyzed, and the range of daily travel may be used as living area information. In this case, nursing homes, community centers, agricultural cooperatives, and workplaces that are visited daily beyond 2 km can also be determined as living areas. The living area information 15b may be information generated by the living area acquisition unit 257 of the main user terminal 2, rather than being acquired from the questionnaire results.

[0085] The reservation route information 15j is route information for guiding the user to the proposed destination.

[0086] The location information 15 k is location information of the main user acquired by the location information acquisition unit 255 of the main user terminal 2 .

[0087] <About user devices> 3 is a diagram showing an example of a functional configuration of a main user terminal 2 according to an embodiment, which is used by a main user who receives a proposal. The main user terminal 2 realizes functions as a communication means 21, an I / F means 22, an output means 23, a sensor means 24, and a control means 25 by executing a program loaded in a memory such as a RAM by a processor.

[0088] The communication means 21 communicates with the action suggestion device 10 via a network I / F. The communication means 21 also communicates with the IOT home appliance 4 and the in-vehicle terminal 5 via a wireless communication I / F.

[0089] The communication means 21 also communicates with a support user terminal 3. This communication may be wireless communication compatible with various standards such as 3G, 4G, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc., or may be performed via the Internet. Note that communication between the user terminals 2 and 3 is also performed via the action suggestion device 10. In this communication, typically, the communication unit 141 of the action suggestion device 10 functions as a closed SNS, and chats and photo exchanges are performed.

[0090] The I / F means 22 is a user interface such as a camera, a microphone, a touch panel, etc., and typically receives instructions from the main user via a touch panel or voice recognition.

[0091] The output means 23 is a display and a speaker, and outputs video information and audio information.

[0092] The sensor means 24 includes a GPS (Global Positioning System) sensor for acquiring position information, an angular velocity sensor, and a biosensor for measuring pulse rate.

[0093] The control means 25 is an application executed on the main user terminal 2, and includes a navigation unit 251, an IOT data acquisition unit 252, a reception unit 253, an inside / outside vehicle information acquisition unit 254, a location information acquisition unit 255, a service connection unit 256, and a living area acquisition unit 257.

[0094] The navigation unit 251 generates guidance information for guiding the main user to a specified destination (for example, a destination based on the proposed information) and outputs it to the outside via the output means 23 (see FIG. 6D). The guidance information is typically information for superimposing and displaying the vehicle position, the direction to the destination, the predicted arrival time, route information at intersections, guide information, etc., on the route on the map information.

[0095] The IOT data acquisition unit 252 acquires data from a communicable IOT home appliance 4 via the communication means 21. There are cases where data from the IOT home appliance 4 is acquired directly via an I / F such as Wi-Fi, and cases where data is acquired indirectly from an I / F such as Wi-Fi of a smart remote controller that transmits commands to the IOT home appliance 4. In addition, a device that analyzes the data acquired by the IOT home appliance 4 and performs an MCI (mild cognitive impairment) diagnosis is also an IOT home appliance 4 from which data is acquired.

[0096] The reception unit 253 receives instructions from the main user via the I / F means 22. Typically, the reception unit 253 receives user instructions via a touch panel or voice recognition.

[0097] As an example, the reception unit 253 outputs (presents) a screen 81 (see FIG. 6A) for receiving user information via the output means 23. Furthermore, the reception unit 253 receives user information of the main user including life area information indicating the life area of ​​the main user who uses the main user terminal 2 via the I / F means 22. Furthermore, the reception unit 253 transmits the received user information of the main user to the connected suggested service (action suggestion device 10) via the communication means 21.

[0098] As an example, the reception unit 253 acquires suggested information from the action suggestion device 10 through the communication means 21. This suggested information includes information indicating a destination selected from the destination candidate information 15a based on the profile information 15g obtained by analyzing the user information of the main user. Furthermore, the reception unit 253 outputs (presents) through the output means 23 a screen 82 (see FIG. 6B) for presenting a destination based on the suggested information to the main user. Furthermore, the reception unit 253 outputs (presents) through the output means 23 a screen 83 (see FIG. 6C) for accepting a designation (selection) of a destination to go to from among a plurality of destinations based on the proposed information. Furthermore, the reception unit 253 accepts a designation (selection) of a destination by the main user through the I / F means 22.

[0099] The vehicle interior / exterior information acquisition unit 254 acquires information about the interior and exterior of the vehicle via the camera and microphone of the I / F means 22. The vehicle interior / exterior information acquisition unit 254 acquires video, photos, audio, and the like from the interior and exterior of the vehicle. Note that the acquisition of information about the interior and exterior of the vehicle by the vehicle interior / exterior information acquisition unit 254 may be acquisition of AR content that acquires video data linked with location information from the outside via the network 6.

[0100] The location information acquisition unit 255 acquires location information of the main user terminal 2 via the GPS sensor of the sensor means 24. In addition, the location information acquisition unit 255 transmits the acquired location information to the connected proposed service via the communication means 21.

[0101] The service connection unit 256 connects to a proposed service that proposes a destination action. For example, the service connection unit 256 connects the main user terminal 2 to a proposed service provided by the action proposal device 10. As an example, the service connection unit 256 manages contract information and billing information of a main user who uses the proposed service, account information linked thereto, and login information, and executes a connection process with the action proposal device 10 that is necessary for using the service.

[0102] The living area acquisition unit 257 may generate the living area information 15b of the main user by statistical processing based on the location information accompanying the movement of the main user terminal 2. In the statistical processing, for example, the living area information 15b is a circular area of ​​a geographical range having a radius equal to the average distance from home to points repeatedly reached on a weekly basis. Note that distant points reached by commuting, etc. may be excluded from the statistical processing as singular points, or may be combined with other circular areas as an elliptical area having a diameter between the distant point and home. Note that when the living area information 15b is acquired based only on the answers to the questionnaire, the living area acquisition unit 257 may not be provided in the user terminals 2 and 3.

[0103] The action suggestion device 10 (server 1) and the main user terminal 2 execute the suggested service through server and client processing. The execution of the suggested service through server and client processing is not limited to the above-mentioned configuration. For example, in the case of a cloud-native system configuration, the navigation unit 251, the IOT data acquisition unit 252, the reception unit 253, the vehicle interior / exterior information acquisition unit 254, and the location information acquisition unit 255, which are applications executed by the client-side control means 25, may be executed as applications of the server-side control means 14. In this case, the applications executed within the client-side control means 25 are the service connection unit 256 and a browser unit (not shown) that receives services from the server 1 and displays a web browser.

[0104] 4 is a diagram showing an example of a functional configuration of a support user terminal 3, which is a user terminal according to the embodiment and is used by another user (sub-user) who supports a main user who receives a proposal. The support user terminal 3 realizes functions as a communication means 31, an I / F means 32, an output means 33, a sensor means 34, and a control means 35 by executing a program loaded in a memory such as a RAM by a processor.

[0105] The support user terminal 3 and the main user terminal 2 are in principle the same, with only the users in the user group being different. Here, a user group is typically a group formed by family members or relatives. In this embodiment, the user of the main user terminal 2 is a user (main user) such as an elderly person. The user of the support user terminal 3 is a child or grandchild of the main user such as an elderly person, and is a sub-user who supports the main user.

[0106] The main user and the sub-users, that is, the user terminals 2 and 3, are identified by the action suggestion device 10, and the relationship between them is managed based on the user group information 15h.

[0107] Unless otherwise specified, the communication means 31, I / F means 32, output means 33, sensor means 34 and control means 35 of the support user terminal 3 correspond to the communication means 21, I / F means 22, output means 23, sensor means 24 and control means 25 of the main user terminal 2, respectively, and detailed explanations will be omitted.

[0108] The server 1 may be a plurality of server devices that communicate via a network. In this case, each server shares a role, and uses an API (Application Program Interface) to start each other's programs and exchange data. Examples of the roles that are shared include a role of profiling the user using data from the IOT home appliances 4 and survey information (see S13 and S17 in FIG. 5A), a role of suggesting a destination to go to and mediating the user's selection based on the profiling results (see S22 and S24 in FIG. 5A), a role of displaying and guiding a route for a moving vehicle, detecting location information, acquiring information inside and outside the vehicle, and generating and reproducing memory information (see S31, S32, S33, S34, and S36 in FIG. 5B), and a role of calculating satisfaction with going out, judging behavioral changes, and performing learning processing (see S41, S42, and S43 in FIG. 5B).

[0109] Next, the flow of the process executed by the action suggestion system 7 configured as above will be described.

[0110] Fig. 5A and Fig. 5B are sequence charts showing an example of a sequence of information processing executed in the action suggestion system 7 according to the embodiment. Fig. 6A to Fig. 6D are diagrams showing an example of a display screen displayed on the user terminals 2 and 3 in the information processing. Fig. 7A and Fig. 7B are diagrams showing an example of a display screen displayed on a TV, which is an IOT home appliance 4, in the memory information display processing of Fig. 5B.

[0111] 6A to 6D may be displayed on the IOT home appliance 4 or the in-vehicle terminal 5. Moreover, the display screens of FIGS.

[0112] The sequence charts in FIGS. 5A and 5B show the processes and the input and output of information of the user terminals 2 and 3, the IOT home appliance 4, the in-vehicle terminal 5, and the action suggestion device 10 that constitute the action suggestion system 7.

[0113] Fig. 5A shows the first half of a series of sequence charts, specifically, the data acquisition part and the before-going-out part, while Fig. 5B shows the second half of the sequence charts, specifically, the during-going-out part and the after-going-out part.

[0114] <Data Acquisition Part> First, the data acquisition part will be described.

[0115] The main user terminal 2 acquires the living area information of the main user through the living area acquisition unit 257 (S10). The main user terminal 2 also outputs the acquired living area information to the action suggestion device 10 (S11). Then, the action suggestion device 10 records the received living area information in the recording means 15 as living area information 15b.

[0116] The IOT home appliance 4 acquires edge terminal information of its own device, and outputs the acquired edge terminal information to the action suggestion device 10 via the main user terminal 2 (S12). Here, the edge terminal information is IOT data as described above, and is information indicating the power ON / OFF and operation status of its own device, and product information. Then, the action suggestion device 10 performs a process of storing the received edge terminal information as home appliance data (S13). This stored home appliance data is profiled together with questionnaire information in a profiling process (see S17) described later.

[0117] The action suggestion device 10 transmits the survey information 15i to the user terminals 2 and 3 (S14a, S14b). Then, the user terminals 2 and 3 present to the user a screen 81 for accepting survey input from the user based on the received survey information 15i.

[0118] FIG. 6A illustrates a screen 81 of the user terminal 2, 3 that accepts questionnaire input. The screen 81 includes items such as gender, age, preferences, personality, lifestyle, and living area as questionnaire input items. The user answers the questions presented in each item on the screen 81. The user terminal 2, 3 accepts the user's answers via the accepting unit 253 (S15a, S15b) and transmits the accepted questionnaire input results to the action suggestion device 10 (S16a, S16b). Then, the action suggestion device 10 performs profiling processing of the main user and the sub-user based on the received questionnaire input results and the accumulated IOT data (S17).

[0119] In this profiling process, profile information 15g (profiling information) is generated for each target user. The profiling information includes a physical profile and a mental profile (see FIG. 11). The physical profile is a vector value of information formed by analysis of health data specific to an individual organism, such as race, height, sex, weight, age, and blood pressure. The mental profile is mental information independent of the body, and is a vector value of information formed by analysis of personality data such as preferences, lifestyle, and the Big Five of psychology. These values ​​are vector values ​​composed of multiple values, such as preference A 40%, preference B 30%, preference C 15%, and preference D 15%.

[0120] <Before going out part> Next, the pre-go part will be explained.

[0121] The main user terminal 2 transmits a service start request to the action suggestion device 10 (S21). This service is a suggestion service that realizes destination suggestions for the user.

[0122] The action suggestion device 10, which has received the service start request, performs a process of suggesting an outing based on the profile information 15g of the user making the suggestion (S22), and transmits the suggested information of the destination to be the outing to the user terminal 2, 3 (S22a, S22b). Collaborative filtering is an example of an algorithm for performing the suggestion process. The past destination records of users similar to the user's profile information 15g are suggested as destination candidates. The data (see FIG. 11) accumulated as successful data in the learning information model 15d is used as the destination records. The profile information and destination record data may be acquired from outside and used.

[0123] The user terminals 2 and 3 perform a destination selection process based on the received destination proposal information by accepting user input through the acceptance unit 253 (S23a, S23b). For example, the user terminals 2 and 3 present the user with a screen 82 for selecting a destination based on the proposal information, i.e., a destination from proposed destination candidates.

[0124] 6B illustrates a screen 82 of the user terminal 2, 3 that presents a destination based on the suggested information to the user. The screen 82 includes at least one display 821-824 of a destination / itinner route candidate. The user terminal 2, 3 accepts the user's selection result (S23a, S23b) and transmits destination selection information indicating the accepted selection result to the action suggestion device 10 (S22a, S22b).

[0125] The action suggestion device 10 that has received the destination selection information performs an arbitration process to arbitrate the destination selection information received from the main user terminal 2 and the destination selection information received from the support user terminal 3 (S24).

[0126] For example, the action suggestion device 10 outputs, via the communication means 13, suggestion information for suggesting to the main user a destination selected by the main user and a destination selected by a sub-user in a comparable manner to the main user terminal 2. Then, the main user terminal 2 presents a screen 83 for reconciliation to the user based on the suggestion information.

[0127] Fig. 6C illustrates an example of a screen 83 of the user terminal 2 for mediation. The screen 83 is a UI that displays destination / itinner route candidate (B) 831 selected in profiling of the user (elderly person, etc.) of the main user terminal 2 and destination / itinner route candidate (C) 832 selected in profiling of the user (children, grandchildren, etc.) of the support user terminal 3 in a comparative manner, and allows the main user (elderly person, etc.) to select a destination. Fig. 6C illustrates a case where the main user selects destination / itinner route candidate (C) 832 selected in profiling of the user (children, grandchildren, etc.) of the support user terminal 3.

[0128] Thus, as an example of the arbitration process according to the embodiment, when there are destination candidates A and B selected by the main user and destination candidate C selected by the sub-user, the action suggestion device 10 allows the main user to select from among destination candidates A, B, and C. The main user may select from among destination candidates A (e.g., scenery and nature perspective) and destination candidates B (e.g., historical ruins perspective) proposed based on his / her profile, or may select destination candidate C (e.g., park and pool perspective) proposed by the sub-user based on the profile of the sub-user (children and grandchildren). By broadening the range of options for the main user (elderly person, etc.) to include other preferences (supporters and accompanying persons), it is expected that the destination suggestions will be more easily accepted by the main user.

[0129] In the arbitration process, the main user terminal 2 accepts the selection result of the main user in the arbitration and transmits the accepted selection result to the action suggestion device 10. Then, the action suggestion device 10 transmits the received selection result, i.e., the arbitration result, to the user terminals 2 and 3 as proposal result information (S25a, S25b). In this manner, the destination proposed by the proposal service is determined.

[0130] <Out and about part> Next, the part about going out will be explained.

[0131] The action suggestion device 10 transmits route information to the determined destination as destination information to the in-vehicle terminal 5 (S30). The in-vehicle terminal 5 performs route display and route guidance based on the received destination information (S31). Fig. 6D illustrates an example of a route display screen 84. The screen 84 includes a route display 841 that guides the main user to destination C beyond the living area.

[0132] The main user terminal 2 and the in-vehicle terminal 5 each detect the movement of the terminal (S32a, S32b) and transmit their respective location information to the action suggestion device 10 (S33a, S33b). Here, the action suggestion device 10 detects location information from both the main user terminal 2 and the in-vehicle terminal 5, but adopts one of them. In this case, the action suggestion device 10 prioritizes location information transmitted by the in-vehicle terminal 5, if any. The in-vehicle terminal 5 may also be used by an application of the main user terminal 2. In this case, the location information transmitted from the in-vehicle terminal 5 is the location information from the main user terminal 2.

[0133] The in-vehicle terminal 5 also acquires information inside and outside the vehicle by detecting information inside and outside the vehicle using a camera and a microphone (S34). The acquired video information, audio information, and photo information are transmitted to the action suggestion device 10 (S35), and the action suggestion device 10 generates action recollection information 15e, which is a digest video (S36). The action suggestion device 10 may generate the action recollection information 15e using video information, audio information, and photo information acquired by the camera and microphone of the user terminals 2 and 3 that are determined to be in the same range (for example, inside the vehicle) based on the detection result of the position information of the terminal, in addition to the in-vehicle terminal 5. When the action suggestion device 10 reaches the proposed destination, the action suggestion device 10 may generate the action recollection information 15e using video information, audio information, and photo information acquired by the camera and microphone of the user terminals 2 and 3 instead of the in-vehicle terminal 5.

[0134] <After-going part> Next, the after-going part will be explained.

[0135] The action suggestion device 10 plays the action recollection information 15e (S37). The playback may be started by a request from the user or by a push from the user terminals 2 and 3 or the action suggestion device 10. The played photo / video information is transmitted to the user terminals 2 and 3 (S38a, S38b). The photo / video information may also be transmitted to the IOT home appliance 4 via the main user terminal 2 (S38c). The user terminals 2 and 3 and the IOT home appliance 4 that have received the photo / video information each perform a display process of the action recollection information 15e (S39a, S39b, S39c). This display process may be a signage type output, or may be a process that accepts a request from the user and outputs photos and videos on demand.

[0136] 7A and 7B show examples of screens 85 and 86 that display the behavioral recollection information 15e.

[0137] For example, the display of the behavioral memory information 15e may be a display 851 showing the degree of achievement of the destination reached by the main user with respect to the living area information 15b on the map information, as shown in the screen 85 of Fig. 7A. In the example of Fig. 7A, the destination, that is, the destination of the outing, is filled in like a map game, and the progress of the achievement degree of the outing can be easily grasped. By showing the degree of achievement in this way, it can be a success reward not only for elderly people who tend to stay at home, but also for active elderly people, and it is expected that going out will become a habit.

[0138] For example, as shown in a screen 86 of FIG. 7B, the behavioral recollection information 15e may be displayed with UIs 862, 863 that reproduce the video and audio information outside and inside the car during the outing, together with an overview 861 such as destination area information (area B b1), satisfaction level, and information on accompanying persons. In addition, this screen 86 may display a UI 864 of a closed SNS with accompanying persons, so that the main user can enjoy a conversation looking back on the outing with the accompanying person (e.g., a sub-user). An example of the conversation is "Grandpa, it was fun, please take me again" if the accompanying person is a granddaughter. Of course, an album-type UI may also be displayed. In the outing calculation process (S41), feedback information on the display of the behavioral recollection information 15e, conversations on the closed SNS, or the number of times of such conversations may be taken into consideration.

[0139] In addition, when the behavioral memory information 15e is reproduced in a signage format, it is also preferable to display information that encourages the user to request to go out next time, from the viewpoint of forming a habit. An example of the display is "You had fun with your granddaughter on your last trip (to area B). Where are you going next?"

[0140] The user terminals 2 and 3 that have performed the display process of the action recollection information 15e transmit feedback information to the action suggestion device 10 (S40a, S40b). An example of the feedback information is the number of times or the time that the action recollection information 15e has been displayed.

[0141] The action suggestion device 10 performs an outing satisfaction degree calculation process (S41). The outing satisfaction degree calculation process may be performed before the memory information display process (S37) or in parallel with the memory information display process. When the outing satisfaction degree calculation process is performed before the memory information display process, information indicating the calculated satisfaction degree (satisfaction degree information 15f) may be included as part of the photo / video information to be transmitted (S38a, S38b, S38c).

[0142] Thereafter, the action suggestion device 10 performs a action change determination process (S42), and performs a learning process based on the result of the action change determination process (S43).

[0143] Here, the behavior change determination process (S42 in FIG. 5B) will be described in more detail with reference to the drawings. FIG. 8 is a flowchart showing an example of the flow of information processing of destination suggestion by the behavior suggestion device 10. This information processing is executed by, for example, the behavior determination unit 143 to determine whether or not the behavior change due to the suggestion has been successful.

[0144] First, the behavior determination unit 143 sets a reserved route (S101). This process is performed by setting reserved route information 15j read from the recording means 15. The behavior determination unit 143 also sets a daily activity area (S102). This process is performed by setting living area information 15b read from the recording means 15.

[0145] Thereafter, the behavior determination unit 143 determines whether guidance for the reserved route is to be started (S103). For example, the behavior determination unit 143 determines whether guidance for the reserved route is to be started based on whether or not the route display / route guidance (S31) processing in FIG. 5B has been performed. The route display / route guidance (S31) processing by the in-vehicle terminal 5 is performed independently of the departure / movement of the vehicle. The route display / route guidance (S31) processing is typically performed before departure to the proposed destination, but may be started while the vehicle is already traveling along another route.

[0146] If it is not determined that the guidance of the reserved route is to start (S103: No), the behavior determination unit 143 executes the process of S103 again after a predetermined time. If it is determined that the guidance of the reserved route is to start (S103: Yes), the behavior determination unit 143 determines whether the daily activity area has been exceeded (S104). This determination is made by comparing the position information 15k recorded in the behavior suggestion device 10 with the living area information 15b. If the current position of the main user terminal 2 and / or the in-vehicle terminal 5 indicated by the position information 15k exceeds the range indicated by the living area information 15b, the behavior determination unit 143 determines that the daily activity area has been exceeded. If it is not determined that the daily activity area has been exceeded (S104: No), the behavior determination unit 143 executes the process of S104 again after a predetermined time.

[0147] When guidance for the reserved route starts and it is determined that the user has left the daily activity area (S104: Yes), the behavior determination unit 143 determines whether the user has stayed at a stopover point (S105). This determination is made based on whether the location information indicating the current location of the main user terminal 2 and / or the in-vehicle terminal 5 indicates that the user has stayed at a base inside or outside the route for a predetermined period of time (e.g., 20 minutes) or more. The behavior determination unit 143 may also determine whether the user has stayed at a stopover point based on the acquired in-vehicle and out-of-vehicle information (S34). As an example, if a photograph has been taken, it is determined that the user has stayed at a stopover point, and if a user has taken a rest at a convenience store, it is determined that the user has not stayed at a stopover point.

[0148] If it is determined that the user stayed at the waypoint (S105: Yes), the behavior determination unit 143 adds detour points (S106). If it is not determined that the user stayed at the waypoint (S105: No), or after adding points, the behavior determination unit 143 determines whether the guidance has ended and the destination has been reached (S107). This determination is made based on whether the current position of the main user terminal 2 and / or the in-vehicle terminal 5 indicated by the position information 15k has reached the arrival point (destination) indicated by the reserved route information 15j. The determination also determines that the guidance has ended if the route guidance of the in-vehicle terminal 5 has ended or been canceled.

[0149] If the guidance ends without reaching the destination (S107: No), the behavior determination unit 143 adds travel distance points (S108). If the guidance ends with the destination reached (S107: Yes), the behavior determination unit 143 adds arrival points (S109). Thereafter, the behavior determination unit 143 tallies up success points, and determines whether the proposed information is successful data based on the points tallied (S110). If the tallied success points have a value, the behavioral change of going out is determined to be successful, and the user profile associated with this destination becomes successful data.

[0150] For example, if the main user changes their outing behavior in relation to the proposed destination, starts navigation on the navigation device for the proposed destination in their personal car, etc., and goes beyond their living area, 10 points are set as the initial value. After that, points are added for staying at intermediate points, traveling distance to the destination, etc. If the points are not 0, it is treated as successful data.

[0151] Here, the point addition according to the embodiment will be described. Fig. 9 is a diagram showing an example of the configuration of the point information table 15c according to the embodiment.

[0152] The behavior determination unit 143 refers to the point information table 15c stored in the recording means 15 and adds points according to the achievement level of the outing.

[0153] For example, as shown in FIG. 9, the behavior determination unit 143 adds 10 points when the navigation function starts guidance beyond the daily living area. At this point, it becomes successful data that the behavior change of going out is achieved. Subsequent point addition is point addition as the degree of achievement considered in the learning information model 15d described later. Whether the behavior change of going out has occurred for the proposed destination is added according to the number of stopovers, so-called detours (detour point addition) as shown in FIG. 9. Also, considering the meaning of going out, the purpose is not necessarily to reach the initially set destination, and detours are also included in the going out. For this reason, point addition is also performed according to the distance to the destination (travel distance point addition). For example, as shown in FIG. 9, the behavior determination unit 143 adds travel distance points based on the degree of movement and the distance to the destination (1 / 3, 1 / 2, 2 / 3, etc.).

[0154] In addition, for an elderly person, who is an example of a target of this implementation, a sense of accomplishment is greater if a child accompanies them than if they reach the destination alone, so points may be added when the parent and child go out together. Here, the parent and child are referred to as sub-users who support the elderly person, who is the main user, on his / her outings, and may of course be not only the child of the elderly person, but also a granddaughter or other related person.

[0155] Here, the learning information model 15d according to the embodiment will be described in more detail with reference to the drawings. Fig. 10 is a diagram for explaining the learning information model 15d according to the embodiment. Fig. 11 is a diagram showing an example of the configuration of a data set 89 of input data 881 of the learning information model 15d according to the embodiment.

[0156] The learning information model 15d is a machine learning model. The data accumulation, that is, learning, of the learning information model 15d is performed by the learning unit 144 of the control means 14.

[0157] Here, the learning of the learning information model 15d will be explained.

[0158] The "learning information model" is a function in the broad sense that classifies input values ​​(user profiling information) and outputs output values ​​(destinations) corresponding to the classification. The output values ​​(destinations) become candidates for suggestions to the user. This is also called destination estimation by the learning information model 15d.

[0159] "Learning the learning information model" means adjusting the parameters of the function that is the learning information model. By adjusting the parameters, the output (destination) for the input (profiling information) changes.

[0160] Classification function algorithms include SVM (support vector machine), regression model, decision tree, random forest, neural network, etc. Parameters differ depending on the algorithm, and in the case of a neural network, parameters include the number of neurons, threshold, number of layers, etc.

[0161] Here, the term "parameter" is used in a broad sense, and may refer to any value that controls the behavior of various algorithms, and is not limited to a mathematical meaning such as an argument of a function.

[0162] In the learning information model 15d, a data set 89 of input data 881 including destination data 882 and data of a corresponding profile 883 (profile information 15g) is inputted in the learning information model 15d. That is, the parameters of the learning information model 15d are determined based on the input destination and the profile corresponding to the destination. In other words, the parameters of the learning information model 15d are determined by "supervised learning" using the data set 89 as learning data.

[0163] Dataset 89 is a dataset in which data on physical profile, mental profile, success points, and satisfaction level are linked to the proposed destination. This dataset becomes learning data for machine learning. Specifically, a dataset with a value for success points is treated as successful data and teacher data in machine learning. Also, data with higher success points becomes higher ranking successful data. Success data may be ranked in combination with satisfaction level.

[0164] For example, the destinations in the first and second lines in Fig. 11 are both "Destination A", but the first line has a success point of 0, which indicates failure data, and the second line has a success point of 10, which indicates success data. By accumulating success data and failure data, the learning information model 15d can learn what kind of destination suggestions are most likely to be successful for the user's profile information 15g, and can improve the accuracy of suggestions.

[0165] For example, if the "tastes" element of a profile includes a love of history, and the "personality" factor is high in the active "openness" element, then destinations in historical districts with castles and other attractions will be preferred.

[0166] On the other hand, even if the user's "preferences" on the user device (main) are history lovers, if their "personality" is low in openness, it does not necessarily follow that they will prefer destinations in historical areas. If the family composition in the profile includes grandchildren, it can be inferred that they will prefer destinations with amusement parks and swimming pools, which are popular with grandchildren.

[0167] In the action suggestion system 7 according to the embodiment, the action suggestion device 10 not only analyzes the profile of the main user (elderly person, etc.), but also analyzes the profile of the sub-user who is the supporter of the main user (elderly person, etc.) (the child, grandchild, etc. of the elderly person), and can suggest a destination, making it easier for the main user (elderly person, etc.) to accept the suggestion. This is because even if the elderly person himself is not keen on going out, if he is with his child or grandchild, he may change his behavior in going out, and the probability of accepting the suggestion increases.

[0168] The destinations of the dataset 89 are destinations and itineraries proposed by the action suggestion device 10. The data of the profile 883 of the dataset 89 is obtained by analyzing the profile of the target user by analyzing questionnaires and IOT data. The profile 883 includes a physical profile such as gender, height, and family structure, and a mental profile such as preferences, personality, and lifestyle. The physical profile and the mental profile each have a vector value indicating the parameter condition of the profile. Here, the vector value indicates the value of each element of personality such as gender, preferences, Big 5, etc., as a matrix value or the like. The success points of the dataset 89 are an accumulation of the aggregated results of points given for going out to the proposed destination (for example, data after statistical processing). Moreover, the satisfaction level of the dataset 89 is an accumulation of satisfaction levels calculated for going out to the proposed destination (for example, data after statistical processing).

[0169] A behavior change success determination and a satisfaction degree calculation are performed for each data 881 in the data set 89. A behavior change determination process (S42 in FIG. 5B, FIG. 8) is performed for each data 881 in the data set 89, and the calculated success points are fed back to the learning information model 15d as a determination result together with the calculated satisfaction degree.

[0170] The machine learning is performed by generating a learning information model 15d that learns a dataset with a high success point as success data (teacher data), and machine learning is performed on the vector values ​​of the profiling data of the dataset 89 using a technique such as SVM.

[0171] As a result of machine learning, we are able to suggest destinations with many success points to users whose parameter conditions indicated by the vector values ​​of their profiles are similar, which is expected to improve the success rate of behavioral change through the suggested destinations.

[0172] In this way, in the action suggestion system 7 according to the present embodiment, the success points do not have a value and do not become success data unless the movement is beyond the living area, so that machine learning of the learning information model 15d can be performed with appropriate success data. This can improve the accuracy of outing suggestions.

[0173] The learning information model 15d is, for example, an SVM, but other models such as a regression model, a decision tree, a random forest, a neural network, or a machine learning model may also be used.

[0174] In this way, the behavior suggestion system 7 of the present disclosure can appropriately evaluate (judge) behavioral changes. Furthermore, an appropriate evaluation of behavioral changes enables appropriate suggestions from the perspective of promoting behavioral changes, such as suggestions that are easily accepted or suggestions that contribute to habituation.

[0175] In each of the above-mentioned embodiments, "determining whether it is A" may mean determining that it is A, determining that it is not A, or determining whether it is A or not.

[0176] Each program executed by each device of the action suggestion system 7 according to each of the above-described embodiments is provided by being recorded in a computer-readable storage medium such as a CD-ROM, FD, CD-R, DVD, etc., in a file in an installable or executable format.

[0177] Moreover, each program executed by each device of the action suggestion system 7 according to each embodiment described above may be configured to be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Moreover, each program executed by each device of the action suggestion system 7 according to each embodiment described above may be configured to be provided or distributed via a network such as the Internet.

[0178] Furthermore, each program executed by each device of the action suggestion system 7 according to each embodiment described above may be provided by being pre-installed in a ROM or the like.

[0179] Furthermore, the programs executed by each device of the action suggestion system 7 according to each of the above-mentioned embodiments have a modular configuration including each of the functional units described above, and in terms of actual hardware, a processor such as a CPU reads out and executes the program from a memory such as a ROM or HDD, thereby loading each of the functional units into the RAM of the memory, and generating each of the functional units in the RAM of the memory.

[0180] According to at least one of the embodiments described above, it is possible to provide a suitable suggestion for a user such as an elderly person to change his / her behavior, such as going outside or going out by car.

[0181] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0182] 1 Server 2 User terminal (main) 3 User terminal (support) 4 IOT home appliances 5. Vehicle-mounted terminal 6 Network 7. Action Suggestion System 10 Action suggestion device

Claims

1. an acquisition unit that communicates with a first information terminal used by a first user via a network and acquires user information of the first user received by the first information terminal, the user information including living area information indicating a living area of ​​the first user; A recording unit for storing destination candidate information including one or more destination candidates; A selection unit that selects, based on profiling information obtained by analyzing user information of the first user, one or more destinations that exceed at least the geographical range indicated by the living area information from the destination candidate information; a suggestion unit that outputs, to the first information terminal, suggestion information for suggesting the selected destination to the first user via the first information terminal; Action suggestion device.

2. The acquisition unit communicates with a second information terminal used by a second user via the network and acquires user information of the second user accepted by the second information terminal; The selection unit selects, from the destination candidate information, one or more destinations different from the destination based on the profiling information of the first user as the proposed destination, further based on profiling information obtained by analyzing the user information of the second user. The action suggestion device according to claim 1 .

3. The suggestion unit outputs, to the first information terminal, the suggestion information for suggesting to the first user a destination selected by the first user and a destination selected by the second user in a comparable manner. The action suggestion device according to claim 2 .

4. A determination unit that determines whether the proposed information output to the first information terminal is successful data that has caused a behavioral change of the first user, The acquisition unit further acquires location information indicating a location of the first information terminal in route guidance to the destination based on the proposal information, The determination unit determines whether the proposed information is the successful data based on the location information and the living area information. The action suggestion device according to claim 1 .

5. The determination unit determines that the proposed information is the successful data when the route guidance to the destination based on the proposed information is started on the first information terminal. The action suggestion device according to claim 4 .

6. The selection unit inputs profiling information obtained by analyzing the user information into a learning information model in which parameters are learned so as to output a destination corresponding to the input profiling information among one or more destinations included in the destination candidate information, and acquires the destination output from the learning information model in response to the input of the profiling information as a destination to be selected. The action suggestion device according to claim 4 .

7. A learning unit that learns parameters of the learning information model by using a destination based on the proposal information determined to be the successful data and the profiling information corresponding to the destination, The action suggestion device according to claim 6 .

8. A calculation unit that calculates a satisfaction level of the first user for a destination based on the proposed information determined to be the successful data, and outputs the calculated satisfaction level to the first information terminal. The action suggestion device according to claim 4 .

9. An action suggestion method executed by an action suggestion device that communicates with a first information terminal used by a first user via a network, comprising: acquiring user information of the first user, the user information including living area information indicating a living area of ​​the first user, the user information being accepted by the first information terminal; storing candidate destination information including one or more candidate destinations; Selecting one or more destinations beyond the geographical range indicated by the living area information from the destination candidate information based on profiling information obtained by analyzing user information of the first user; outputting, to the first information terminal, proposal information for proposing the selected destination to the first user by the first information terminal; Action proposal method.

10. An action suggestion method executed by a first information terminal that communicates with an action suggestion device that provides an action destination suggestion service via a network, comprising: Connecting to the suggestion service that provides suggestions for destinations of action; Receiving user information of a first user including life area information indicating a life area of ​​a first user who uses the first information terminal; Transmitting the received user information of the first user to the connected suggested service; acquiring, from the action suggestion device, proposal information for suggesting to the first user one or more destinations selected from destination candidate information including one or more destination candidates based on profiling information obtained by analyzing user information of the first user, the one or more destinations being outside at least the geographical range indicated by the living area information; Presenting a destination based on the suggested information to the first user. Action proposal method.

Images