system

Abstract

We provide the system. [Solution] A means of inputting and collecting attribute data from users, such as preferences, interests, and background, A means for analyzing the aforementioned attribute data and generating activity candidates suitable for the user using a learning model, A means to further narrow down the aforementioned activity candidates based on personal information, A means of presenting users with a narrowed-down list of activity options and allowing them to select from them, Means for coordinating resources and other participants to realize the selected activity candidates, A means for visually displaying the activity candidates using the user's portable visual device, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] After an elderly person finishes their professional life, it is important to find appropriate activities based on their interests and hobbies in order to lead an active and fulfilling life. However, in many cases, it is not easy for the elderly themselves to find their potential interests or new activities that make use of their past experiences. Also, it is difficult for them to find the resources to start activities and the contacts with other participants on their own. Thus, there are factors that make it difficult for the elderly to lead an engaged life even after finishing their professional life.

Means for Solving the Problems

[0005] This invention provides a means for inputting and collecting data such as hobbies, interests, and work history from users. It also includes a means for analyzing this data and generating activity candidates suitable for the user using a generative model. Furthermore, it narrows down the obtained activity candidates based on persona information, presents them to the user, and allows them to select. To realize these selected activity candidates, it employs a means for matching the user with necessary resources and other participants. This enables elderly individuals to efficiently find and engage in activities best suited to them. The invention also includes a function for collecting feedback after activity completion and continuously improving the generative model.

[0006] "User data" refers to personal information that users input or provide, such as their hobbies, interests, and work history.

[0007] A "generative model" is an algorithm or machine learning model that analyzes input user data and generates appropriate activity candidates based on that analysis.

[0008] "Suggested activities" are potential activity options suggested based on the user's hobbies, interests, and past experiences.

[0009] "Persona information" refers to detailed user profiles and is data referenced when narrowing down potential activities.

[0010] "Resources" refer to the equipment, information, personnel, or other supporting materials and means necessary to carry out an activity.

[0011] "Matching" is the process of connecting users with the necessary resources and other participants to realize their chosen activity.

[0012] "Feedback" refers to opinions, evaluations, and experience-based information provided by users after they have carried out a suggested activity. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0035] First, the user uses their device to input information such as their personal hobbies, interests, work history, and desired activities. The device then encrypts this information and sends it to the server. This is to protect the security and privacy of user data.

[0036] The server preprocesses the received data and performs analysis using a generative model. This generative model utilizes machine learning techniques to generate the most suitable activity candidates based on the user's preferences and past experiences. The generated activity candidates are further refined using the user's persona information. This persona information enables more personalized suggestions.

[0037] Next, the server sends the narrowed-down list of activity options to the device, which then visually presents them to the user. The user can compare the presented options and select an activity that suits their interests and circumstances. By narrowing down the options, the user can create a more specific and feasible plan.

[0038] Furthermore, the server matches users with the necessary resources and other participants to realize their chosen activity. For example, if a user requests a cooking class, the server gathers information on local cooking classes and online classes and presents suitable opportunities. This feature helps users get started with activities in a way that suits them.

[0039] As a concrete example, consider the case of Mr. A, who wants to spend his leisure time after retirement meaningfully, using the system. Mr. A inputs his past work, hobbies, preferences, and interests into a terminal. The server analyzes this information and suggests activities such as landscaping or pottery to the user. Mr. A becomes interested in pottery and chooses to participate in a local pottery class. The system matches Mr. A with a class, providing a smooth experience. In this way, Mr. A can find a new hobby and make his second life more fulfilling.

[0040] As described above, the invention provides a system that helps older adults utilize their own experiences and interests, find meaningful activities, and support their implementation.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users enter their hobbies, interests, past work experience, and desired activities on their device.

[0044] Step 2:

[0045] The terminal encrypts the entered user data and sends it to the server. This ensures the security of the information.

[0046] Step 3:

[0047] The server preprocesses the received user data, removing noise and preparing it for analysis.

[0048] Step 4:

[0049] The server uses a generative model to analyze pre-processed data and generate activity candidates that are suitable for the user. This model is based on machine learning techniques and takes into account the user's interests and past experiences.

[0050] Step 5:

[0051] The server further refines the generated activity candidates based on the user's persona information and selects the optimal option.

[0052] Step 6:

[0053] The server sends a selection of activity options to the terminal, which then presents them to the user. The user can then review the options through a visual interface.

[0054] Step 7:

[0055] Users select specific activities from the presented options based on their interests and preferences.

[0056] Step 8:

[0057] The server matches the necessary resources and other participants to fulfill the selected activity. Specifically, it gathers and presents information on relevant stores and online courses.

[0058] Step 9:

[0059] Users perform activities and input the results and experiences as feedback through their devices.

[0060] Step 10:

[0061] The server analyzes the collected feedback and improves the generative model. At this stage, the accuracy of suggestions for future users is improved.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] For seniors to lead fulfilling second lives after retiring from their professional careers, support is needed to help them find activities that take into account their hobbies, interests, and past experiences. However, current systems struggle to adequately suggest activities suitable for individual users and provide feasible plans. It is necessary to solve this problem and provide users with more personalized activity suggestions and support for their implementation.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for inputting and collecting information such as hobbies, interests, and work history from users; means for encrypting the information using a standard security protocol; and means for analyzing the encrypted information and generating activity candidates using a machine learning algorithm. This makes it possible to propose appropriate activity candidates that reflect the individuality of the user, and to provide concrete planning and support for leading a fulfilling second life.

[0067] A "user" refers to an individual who uses this system to receive activity suggestions based on their hobbies and interests.

[0068] "Information" refers to data necessary to identify an individual user, such as their hobbies, interests, and work history.

[0069] "Standard security protocols" refer to methods for encrypting and protecting data during the transmission and reception of information, and include SSL / TLS, among others.

[0070] "Encryption" refers to the process of transforming information using a specific algorithm to protect data from unauthorized access.

[0071] A "machine learning algorithm" refers to a learning model that makes predictions and decisions based on past data and patterns.

[0072] "Activity suggestions" refer to proposals for activities that are suited to the user's hobbies and work experience, with the aim of enriching the user's life.

[0073] "Personalization information" refers to data that represents individual characteristics of a user, such as their past activity history and current interests.

[0074] "Resources" refer to the physical and human resources necessary to carry out the selected activities.

[0075] "Response" refers to the adjustments and arrangements necessary to carry out the activity selected by the user.

[0076] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0077] Users use their devices to input personal information such as hobbies, interests, work history, and desired activities. The device encrypts the entered information in real time using standard security protocols such as SSL / TLS and sends it to the server. This ensures secure data transfer while protecting user privacy.

[0078] The server decrypts the received encrypted data and prepares it through preprocessing, including noise reduction and anomaly handling. Then, it uses a generative AI model powered by machine learning algorithms to generate activity candidates based on user information. This analysis process proposes appropriate activities that reflect the user's preferences and past experiences.

[0079] For example, if a user enters the prompt, "Please suggest activities I can enjoy after retirement. My past interests include weaving and cooking with herbs," into the system, the server analyzes this and lists relevant activity candidates. These candidates are further refined based on individual information to provide suggestions tailored to the user.

[0080] The server sends a selection of activity candidates to the device, which then visually presents them to the user. The user can then select an activity that interests them from the presented options and use this to create a concrete action plan.

[0081] This system matches users with the resources and participants needed to realize their chosen activities, supporting them in smoothly starting new endeavors. For example, if a user chooses a local pottery class as their activity, the server uses this information to suggest appropriate classes and events, providing a platform to enrich the user's second life.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user uses a terminal to input their personal information, such as hobbies, interests, work history, and desired activities. Once input is complete, the terminal encrypts this data using standard security protocols (e.g., SSL / TLS) and sends it to the server. This input data is raw data used as the basis for subsequent analysis.

[0085] Step 2:

[0086] The server decrypts the encrypted user information received from the terminal. After decryption, it performs preprocessing to make the data easier to handle. This preprocessing includes data cleaning techniques such as noise reduction, outlier handling, and standardization. As a result, formatted user data is generated.

[0087] Step 3:

[0088] The server inputs pre-processed data into a generating AI model. This model generates activity candidates based on patterns and trends derived from multiple user data. In this step, machine learning algorithms are used to list highly suitable activities based on the user's interests and past experiences. The output is a list of corresponding activity candidates.

[0089] Step 4:

[0090] The server refines the generated list of suggested activities by referencing more detailed user individual information (such as personal preferences and past selection history). This process aims to provide results optimized for the user using a filtering algorithm. The output of this step is the final, compact list of suggested activities.

[0091] Step 5:

[0092] The server sends these narrowed-down activity candidates to the terminal. The terminal visually presents the received activity candidates to the user. Here, the user can compare the provided options and choose the activity that interests them. The output of this step is the specific activity that the user selects.

[0093] Step 6:

[0094] For activities selected by the user, the server identifies the resources and other participants necessary to carry them out. Based on this, the server collects specific information, such as location and time, to support the planning. This process involves necessary data integration and access to referenced databases, and the output is comprehensive information for carrying out the activity.

[0095] This series of processes allows users to start new activities based on reliable information and build a fulfilling second life that makes the most of their abilities.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] A problem exists in that older adults often find it difficult to find activities that allow them to lead fulfilling second lives based on their individual interests and past experiences after ending their working lives. Furthermore, even when they find activities, they often struggle to find the necessary information and participants to implement them. Therefore, there is a need for a system that proposes activities tailored to individual needs and provides support until participation is achieved.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for inputting and collecting attribute data such as preferences, interests, and history from the user; means for analyzing the attribute data and generating activity candidates suitable for the user using a learning model; and means for visually displaying the narrowed-down activity candidates using the user's portable visual device. This makes it possible for the user to easily discover appropriate activities based on their interests and to smoothly proceed through the process of participation.

[0101] "User" refers to an individual who uses this system, with the primary target audience being the elderly.

[0102] "Preferences" refers to information about a user's personal tastes and hobbies.

[0103] "Interests" refers to information that indicates what a user is interested in or what activities they are interested in.

[0104] "Career history" refers to information including the user's past work experience and educational background.

[0105] "Attribute data" refers to data that includes information such as preferences, interests, and background, entered by the user.

[0106] A "learning model" is a model that uses machine learning techniques to generate optimal activity candidates for the user.

[0107] "Activity suggestions" are specific activity options proposed based on the user's attribute data.

[0108] "Personal information" refers to information that can identify a user, including their hobbies, preferences, and work history.

[0109] "Resources" refer to the materials, locations, and funds necessary to realize the selected activity candidates.

[0110] "Fitting" refers to the process of matching a proposed activity with the necessary resources and other participants to realize that activity.

[0111] "Portable visual devices" refer to visual information terminals worn and used by users, such as smart glasses and head-mounted displays.

[0112] This invention provides a system that enables elderly people to lead fulfilling second lives. The system mainly consists of users, terminals, and a server.

[0113] The server receives attribute data such as preferences, interests, and history sent by the user and analyzes it. This analysis utilizes a learning model powered by machine learning techniques. This learning model has the ability to generate optimal activity suggestions for the user and further refines these suggestions using personal information.

[0114] To ensure data security, attribute data transmitted from the user's device is encrypted. This prevents unauthorized access to the data by third parties.

[0115] The narrowed-down activity candidates are visually displayed using the user's portable visual device, such as smart glasses. This allows the user to intuitively recognize the suggested activity candidates and make selections based on their interests. For the selected activity, the server provides appropriate resources and matches the user with other participants.

[0116] As a concrete example, consider the case of Ms. C, a 70-year-old, using this system. Ms. C uses smart glasses to input her hobbies and past work experience. Based on this information, the server suggests activities to Ms. C, such as a gardening club or a digital photography class. Ms. C becomes interested in the gardening club and selects the activity. The server then supports her smooth participation by showing her the nearest club she can join. Throughout this entire process, Ms. C has the opportunity to actively participate in new activities.

[0117] Example of a prompt:

[0118] "User Age: 70 Hobbies: Photography Work History: Educator Interests: Gardening Priority: High Suggestion"

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The device receives attribute data from the user, such as preferences, interests, and history, as input. The user inputs their own information using the smart glasses interface via taps or voice input. This data is encrypted and transmitted to the server in a secure state.

[0122] Step 2:

[0123] The server receives encrypted data sent from the terminal and decrypts it. During this process, it analyzes user attribute data as input. Using machine learning techniques, particularly generative AI models, it generates activity candidates suitable for the user through data analysis. The output is a list of the generated activity candidates.

[0124] Step 3:

[0125] The server refines the generated list of potential activities based on personal information. This involves data processing that considers the user's priorities and past preferences to extract highly relevant activities. The output is a refined list of potential activities.

[0126] Step 4:

[0127] The server sends the narrowed-down list of activity candidates to the user's portable visual device. The terminal receives this data as input and displays it for the user to visually confirm. This allows the user to intuitively recognize and compare the activity candidates. The output is a visual display on the terminal.

[0128] Step 5:

[0129] The user selects an activity of interest from the suggested options presented on the device. The user's selection is sent to the server as input, and the next process is initiated based on this information.

[0130] Step 6:

[0131] The server matches the necessary resources and other participants to fulfill the selected activity. This involves performing data calculations, matching information from the database, and searching for relevant activity participants and location information. The output is specific activity participation information tailored to the user.

[0132] Step 7:

[0133] The server sends the final participation information to the terminal, which then displays it to the user again. Based on the information presented, the user can then prepare for the specific activities.

[0134] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0135] This invention provides a system that helps older adults find and support activities that enhance their emotional satisfaction after they have retired from their working lives. The system comprises a user, a terminal, a server, and an emotion engine.

[0136] Users use the device to input data about their hobbies, interests, work history, and desired lifestyle. The device also has a camera and microphone, which the emotion engine uses to analyze the user's voice and facial expressions.

[0137] The emotion engine recognizes emotions from the user's speech and facial expressions. This emotion information is sent to the server and used as data to personalize the user's experience. The server preprocesses both user data and emotion information and analyzes them using a generative model. This analysis generates optimal activity candidates based on the user's current emotional state and past history.

[0138] The generated activity candidates are further refined using the user's persona information. The server sends the refined activity candidates to the device, which then presents them to the user. The user can then select an activity that they feel emotionally satisfied with. In this process, it is also possible to provide an interface that aligns with the user's emotions by leveraging the real-time feedback provided by the emotion engine.

[0139] The selected activity is matched by the server with the necessary resources and collaborators. As a concrete example, consider a scenario where person A wants to find a new hobby and uses the system. As A is inputting information, the emotion engine analyzes his smile and tone of voice. Based on this emotion data, the server suggests art workshops and local volunteer activities that A might enjoy. A chooses an art workshop, and it is expected that this activity will provide emotional satisfaction and a sense of fulfillment.

[0140] Thus, the invention aims to enhance the quality of life by understanding and responding to the user's emotions and suggesting more appropriate activities.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The user enters their hobbies, interests, work history, and new activities they would like to try into the device. The device's camera and microphone simultaneously transmit the user's facial expressions and voice to the emotion engine.

[0144] Step 2:

[0145] The emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is encrypted and sent to the server.

[0146] Step 3:

[0147] The server preprocesses the received user data and sentiment data, removing noise and preparing it for analysis.

[0148] Step 4:

[0149] The server uses a generative model to analyze user data in detail. This model generates activity candidates that take into account the user's emotional state and past trends.

[0150] Step 5:

[0151] The generated activity candidates are further refined based on persona information. During this process, emotional data is also considered, and activities that enhance emotional satisfaction are prioritized.

[0152] Step 6:

[0153] The server sends a selection of activity options to the device. The device presents these options using an interface tailored to the user's emotional state. The user can then select an activity based on their interests and emotional state.

[0154] Step 7:

[0155] Based on the user's selection, the server matches them with resources, participants, or related information to support their activity and provides the necessary information to the terminal.

[0156] Step 8:

[0157] The user performs the selected activity and enters the results and impressions of the experience into the device. This information is sent to the server as feedback.

[0158] Step 9:

[0159] The server analyzes the collected feedback data and continuously improves the generative model and sentiment engine. This process improves the accuracy of future suggestions and the quality of the user experience.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] There is a challenge in finding appropriate activities that enhance emotional satisfaction for older adults after they have retired from their working lives. In particular, there is a need for methods to improve life satisfaction by recommending activities that take into account the individual emotional state and attribute information of older adults.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes means for inputting and collecting attribute information from the user via a data terminal, means for analyzing the user's emotions in real time and acquiring emotion information, and means for generating activity candidates suitable for the user using a generative model. This makes it possible to provide personalized activity suggestions based on the user's emotions and attributes.

[0165] A "data terminal" is a device used by users to input information and collect emotional data.

[0166] "Attribute information" refers to personal information about a user, such as their hobbies, interests, and work history.

[0167] An "imaging device" is a device used to acquire images or videos.

[0168] A "voice input device" is a device used to acquire voice data.

[0169] "Emotional information" refers to data about emotions analyzed from the user's facial expressions and voice.

[0170] A "server" is a centralized management system that processes and analyzes data sent by users.

[0171] A "generative model" is an algorithm that analyzes user data and generates optimal activity candidates.

[0172] "Activity options" refer to a set of activity choices presented to the user.

[0173] "Personal characteristics data" refers to information based on a user's past behavior and preferences.

[0174] "Resources" refer to elements such as materials and time necessary to carry out an activity.

[0175] A "collaborator" refers to a third party who provides assistance in realizing an activity.

[0176] "Response data" refers to feedback information obtained from users after an activity has been carried out.

[0177] "Protection processing" refers to encryption or security technologies used to protect information from unauthorized access.

[0178] This system helps older adults find activities that provide emotional satisfaction after they have retired from their working lives. The system is primarily implemented with a configuration that includes users, terminals, a server, and an emotion engine.

[0179] First, the user enters attribute information based on their personal information using a terminal. This terminal provides a user interface for entering information, where the user enters information about their hobbies, interests, past work experience, and desired lifestyle. The terminal is also equipped with input devices such as a camera and microphone, which are used by the emotion engine.

[0180] The device uses these features to capture the user's facial expressions and voice, acquiring emotional information in real time. The emotion engine analyzes this information to obtain information about the user's emotional state. This information is then transmitted from the device to the server.

[0181] Next, the server analyzes the attribute and emotional information it receives. Using a generative AI model, the server analyzes this information and generates the most suitable activity candidates for the user based on their current emotional state and past information.

[0182] The generated activity suggestions are further refined based on personal characteristics data. The server sends this refined information to the device, which then presents it to the user. The user can then select from the presented activity suggestions that they feel emotionally satisfied with.

[0183] For selected activities, the server coordinates the necessary resources and collaborators, thereby supporting the implementation of the activity.

[0184] As a concrete example, the prompt might say, "Tell me how to analyze the user's current emotions and suggest activities that match their hobbies and interests."

[0185] The implementation of this system is expected to improve users' quality of life by enabling activity suggestions based on individual emotions and attribute information.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The user uses the device to input attribute information about their hobbies, interests, work history, and desired lifestyle. The device receives this information as text data through the user interface. Specifically, input fields are displayed on a form screen, and the user enters the information using the keyboard or touch input.

[0189] Step 2:

[0190] The device uses its built-in camera and microphone to record the user's facial expressions and voice, acquiring emotional data. An emotion engine processes this data, analyzing emotional information in real time. Input is real-time audio and video, while output is parameters indicating emotion. The camera and microphone operate automatically to avoid interfering with user interaction.

[0191] Step 3:

[0192] The device sends the collected attribute and sentiment information to the server. At this stage, the data is compiled in JSON format and securely transferred to the server over the internet. Specifically, a communication module embedded in the device packets the data and transmits it.

[0193] Step 4:

[0194] The server preprocesses the received data and inputs it into the generated AI model. Preprocessing involves data cleaning and normalization, preparing the data for analysis by the AI ​​model. The output is a list of potential activities, and the process involves parallel database access and model inference.

[0195] Step 5:

[0196] The server narrows down the generated activity candidates based on personal characteristics data. Past selection history and preference parameters are considered to extract the most suitable activity. The output is an optimized activity list, and this process is performed through algorithmic scoring.

[0197] Step 6:

[0198] The terminal presents the user with activity options sent from the server. The terminal displays a UI in card or list format that visually represents the activities. The user can then make the optimal selection. The output is the user's selection, and the specific action is updating the user interface display.

[0199] Step 7:

[0200] The server matches users with the necessary resources and collaborators based on their selections. Based on the selected data, activity preparations are initiated through external APIs and database integrations. These operations include resource reservations and notifications to relevant parties.

[0201] (Application Example 2)

[0202] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0203] Finding ways for older adults to enhance their emotional well-being after their working lives have ended is challenging. Furthermore, there is a lack of systems that suggest activities based on individual preferences and interests, and then optimize those activities based on emotional responses.

[0204] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0205] In this invention, the server includes means for acquiring information such as preferences, interests, and experiences from the user; means for recognizing emotions from the user's voice and facial expressions using emotion analysis technology and optimizing activity candidates using that information; and means for matching the selected activity candidates with resources and other collaborators to realize those activities. This makes it possible to propose individually optimized activities to the user and to select emotionally satisfying activities.

[0206] "Preferences" refer to a user's personal enjoyment of specific hobbies or activities.

[0207] "Interest" refers to a user's interest in or desire to engage with a particular field or topic.

[0208] "Experience" refers to information about a user's past activities, work history, and other related information.

[0209] "Emotional analysis technology" is a technology that determines a user's emotions and psychological state by analyzing their voice and facial expressions.

[0210] "Resources" refer to the material or human support necessary to realize an activity.

[0211] A "collaborator" is another participant or partner necessary to carry out the proposed activity together.

[0212] A "user interface" refers to the visual and operational elements that allow a user to interact with a system.

[0213] "Optimization" is the process of adjusting choices and activities to the most suitable form based on the individual user's preferences and emotions.

[0214] This invention is a system that helps elderly people find and select activities that provide emotional satisfaction. The main components of the system are a user terminal, a server, a generative AI model, and an interface that utilizes emotion analysis technology.

[0215] Users input information about their preferences, interests, and experiences through a device. This device is equipped with a camera and microphone, allowing it to collect voice and facial expression data during information input. This enables emotion analysis technology to determine the user's emotions and provide real-time feedback.

[0216] The server processes the received user information and emotional data, and uses a generative AI model to generate appropriate activity candidates. This model provides personalized activities based on the user's past activity history and preferences. The generated activity candidates are further refined based on attribute information and presented as options optimized for the user's emotional state.

[0217] When a user selects an activity from the presented options, the server matches them with the necessary resources and collaborators to accomplish that activity. Furthermore, the user interface dynamically changes based on the sentiment analysis results, providing an intuitive and emotionally satisfying user experience.

[0218] For example, if a user is smiling while searching for a new painting class, the system will detect this positive emotion and present a wider range of art workshop options. A possible prompt to input into the generative AI model would be: "Please enter user information below for the activity recommendation system and analyze the emotion data."

[0219] This allows users to actually experience personalized activity suggestions, and the activity choices can be emotionally fulfilling.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The user inputs information about their preferences, interests, and experiences using the device. The camera and microphone collect voice and facial expressions in real time, and this data is sent to the device. The input data is pre-processed to format it and prepare it for transmission to the server.

[0223] Step 2:

[0224] The server analyzes the received user information and voice / facial expression data. Using emotion analysis technology, it recognizes emotions from voice tone and facial expressions, identifying the user's current emotional state. The emotional information is then formatted into a dataset for input into an AI model.

[0225] Step 3:

[0226] The server uses a generative AI model to generate activity suggestions best suited to the user. Based on the input data, the model creates a recommendation list of activities that match the user's interests and past history. The generated recommendation list is further filtered using the user's attribute information to provide an optimized activity list as output.

[0227] Step 4:

[0228] The server sends filtered activity candidates to the terminal and presents them to the user. The terminal displays a dynamic user interface that takes the user's emotional information into account, adjusting the visual effects and operation methods appropriately according to the user's emotions. The user makes a selection from the activity candidates.

[0229] Step 5:

[0230] The server matches the user with the resources and collaborators necessary to realize the activity selected by the user. It identifies the partners and materials needed for the activity and provides the user with guidance and support information for preparation. The selection results are recorded throughout the system as the final output.

[0231] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0232] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0233] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0234] [Second Embodiment]

[0235] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0236] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0237] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0238] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0239] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0240] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0241] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0242] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0243] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0244] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0245] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0246] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0247] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0248] First, the user uses their device to input information such as their personal hobbies, interests, work history, and desired activities. The device then encrypts this information and sends it to the server. This is to protect the security and privacy of user data.

[0249] The server preprocesses the received data and performs analysis using a generative model. This generative model utilizes machine learning techniques to generate the most suitable activity candidates based on the user's preferences and past experiences. The generated activity candidates are further refined using the user's persona information. This persona information enables more personalized suggestions.

[0250] Next, the server sends the narrowed-down list of activity options to the device, which then visually presents them to the user. The user can compare the presented options and select an activity that suits their interests and circumstances. By narrowing down the options, the user can create a more specific and feasible plan.

[0251] Furthermore, the server matches users with the necessary resources and other participants to realize their chosen activity. For example, if a user requests a cooking class, the server gathers information on local cooking classes and online classes and presents suitable opportunities. This feature helps users get started with activities in a way that suits them.

[0252] As a concrete example, consider the case of Mr. A, who wants to spend his leisure time after retirement meaningfully, using the system. Mr. A inputs his past work, hobbies, preferences, and interests into a terminal. The server analyzes this information and suggests activities such as landscaping or pottery to the user. Mr. A becomes interested in pottery and chooses to participate in a local pottery class. The system matches Mr. A with a class, providing a smooth experience. In this way, Mr. A can find a new hobby and make his second life more fulfilling.

[0253] As described above, the invention provides a system that helps older adults utilize their own experiences and interests, find meaningful activities, and support their implementation.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] Users enter their hobbies, interests, past work experience, and desired activities on their device.

[0257] Step 2:

[0258] The terminal encrypts the entered user data and sends it to the server. This ensures the security of the information.

[0259] Step 3:

[0260] The server preprocesses the received user data, removing noise and preparing it for analysis.

[0261] Step 4:

[0262] The server uses a generative model to analyze pre-processed data and generate activity candidates that are suitable for the user. This model is based on machine learning techniques and takes into account the user's interests and past experiences.

[0263] Step 5:

[0264] The server further refines the generated activity candidates based on the user's persona information and selects the optimal option.

[0265] Step 6:

[0266] The server sends a selection of activity options to the terminal, which then presents them to the user. The user can then review the options through a visual interface.

[0267] Step 7:

[0268] Users select specific activities from the presented options based on their interests and preferences.

[0269] Step 8:

[0270] The server matches the necessary resources and other participants to fulfill the selected activity. Specifically, it gathers and presents information on relevant stores and online courses.

[0271] Step 9:

[0272] Users perform activities and input the results and experiences as feedback through their devices.

[0273] Step 10:

[0274] The server analyzes the collected feedback and improves the generative model. At this stage, the accuracy of suggestions for future users is improved.

[0275] (Example 1)

[0276] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0277] For seniors to lead fulfilling second lives after retiring from their professional careers, support is needed to help them find activities that take into account their hobbies, interests, and past experiences. However, current systems struggle to adequately suggest activities suitable for individual users and provide feasible plans. It is necessary to solve this problem and provide users with more personalized activity suggestions and support for their implementation.

[0278] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0279] In this invention, the server includes means for inputting and collecting information such as hobbies, interests, work history, etc. from users, means for encrypting the information using a standard security protocol, and means for analyzing the encrypted information and generating activity candidates using a machine learning algorithm. As a result, it becomes possible to propose appropriate activity candidates that reflect the individuality of the user and provide specific planning and support for leading a fulfilling second life.

[0280] The "user" refers to an individual who utilizes this system to receive proposals for activities based on hobbies and interests.

[0281] The "information" refers to data necessary for identifying the user individual, such as the user's hobbies, interests, work history, etc.

[0282] The "standard security protocol" refers to a method for realizing the encryption and protection of data in the process of sending and receiving information, and includes SSL / TLS, etc. [[ID=X]]

[0283] [[ID=X]] "Encryption" refers to the process of converting information using a specific algorithm to protect the data from unauthorized access.

[0284] The "machine learning algorithm" refers to a learning model for making predictions and decisions based on past data and patterns.

[0285] The "activity candidate" refers to a proposal for an activity that suits the user's hobbies and work history, and has the purpose of enriching the user's life.

[0286] The "personal information" refers to data representing individual characteristics such as the user's past activity history and current interests.

[0287] The "resource" refers to the physical and human resources necessary for implementing the selected activity.

[0288] "Correspondence" refers to the adjustments and preparations necessary for proceeding with the activity selected by the user.

[0289] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0290] Users use their devices to input personal information such as hobbies, interests, work history, and desired activities. The device encrypts the entered information in real time using standard security protocols such as SSL / TLS and sends it to the server. This ensures secure data transfer while protecting user privacy.

[0291] The server decrypts the received encrypted data and prepares it through preprocessing, including noise reduction and anomaly handling. Then, it uses a generative AI model powered by machine learning algorithms to generate activity candidates based on user information. This analysis process proposes appropriate activities that reflect the user's preferences and past experiences.

[0292] For example, if a user enters the prompt, "Please suggest activities I can enjoy after retirement. My past interests include weaving and cooking with herbs," into the system, the server analyzes this and lists relevant activity candidates. These candidates are further refined based on individual information to provide suggestions tailored to the user.

[0293] The server sends a selection of activity candidates to the device, which then visually presents them to the user. The user can then select an activity that interests them from the presented options and use this to create a concrete action plan.

[0294] This system matches users with the resources and participants needed to realize their chosen activities, supporting them in smoothly starting new endeavors. For example, if a user chooses a local pottery class as their activity, the server uses this information to suggest appropriate classes and events, providing a platform to enrich the user's second life.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The user uses a terminal to input their personal information, such as hobbies, interests, work history, and desired activities. Once input is complete, the terminal encrypts this data using standard security protocols (e.g., SSL / TLS) and sends it to the server. This input data is raw data used as the basis for subsequent analysis.

[0298] Step 2:

[0299] The server decrypts the encrypted user information received from the terminal. After decryption, it performs preprocessing to make the data easier to handle. This preprocessing includes data cleaning techniques such as noise reduction, outlier handling, and standardization. As a result, formatted user data is generated.

[0300] Step 3:

[0301] The server inputs pre-processed data into a generating AI model. This model generates activity candidates based on patterns and trends derived from multiple user data. In this step, machine learning algorithms are used to list highly suitable activities based on the user's interests and past experiences. The output is a list of corresponding activity candidates.

[0302] Step 4:

[0303] The server refines the generated list of suggested activities by referencing more detailed user individual information (such as personal preferences and past selection history). This process aims to provide results optimized for the user using a filtering algorithm. The output of this step is the final, compact list of suggested activities.

[0304] Step 5:

[0305] The server sends this filtered activity candidate to the terminal. The terminal visually presents the received activity candidate to the user. Here, the user can compare the provided options and select an activity that matches their interests. The output of this step is the specific activity selected by the user.

[0306] Step 6:

[0307] For the activity selected by the user, the server identifies the resources and other participants required for its realization. Based on this, the server collects specific information such as the venue and time, for example, and supports the planning. In this process, the necessary data integration and database access to the reference are performed, and the output is comprehensive information for activity execution.

[0308] Through this series of processes, the user can start a new activity based on reliable information and build a fulfilling second life that maximizes their capabilities.

[0309] (Application Example 1)

[0310] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0311] There is a problem that it is difficult for the elderly to find activities to lead a fulfilling second life based on their individual interests and past experiences after ending their professional lives. Also, even if they find an activity, it is often difficult to find the information and participants necessary for its realization. Therefore, there is a need for a system that proposes individually suitable activities and supports participation until the end.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0313] In this invention, the server includes means for inputting and collecting attribute data such as preferences, interests, and history from the user; means for analyzing the attribute data and generating activity candidates suitable for the user using a learning model; and means for visually displaying the narrowed-down activity candidates using the user's portable visual device. This makes it possible for the user to easily discover appropriate activities based on their interests and smoothly proceed through the process of participation.

[0314] "User" refers to an individual who uses this system, with the primary target audience being the elderly.

[0315] "Preferences" refers to information about a user's personal tastes and hobbies.

[0316] "Interests" refers to information that indicates what a user is interested in or what activities they are interested in.

[0317] "Career history" refers to information including the user's past work experience and educational background.

[0318] "Attribute data" refers to data that includes information such as preferences, interests, and background, entered by the user.

[0319] A "learning model" is a model that uses machine learning techniques to generate optimal activity candidates for the user.

[0320] "Activity suggestions" are specific activity options proposed based on the user's attribute data.

[0321] "Personal information" refers to information that can identify a user, including their hobbies, preferences, and work history.

[0322] "Resources" refer to the materials, locations, and funds necessary to realize the selected activity candidates.

[0323] "Fitting" refers to the process of matching a proposed activity with the necessary resources and other participants to realize that activity.

[0324] "Portable visual devices" refer to visual information terminals worn and used by users, such as smart glasses and head-mounted displays.

[0325] This invention provides a system to enable elderly people to lead fulfilling second lives. The system mainly consists of users, terminals, and a server.

[0326] The server receives attribute data such as preferences, interests, and history sent by the user and analyzes it. This analysis utilizes a learning model powered by machine learning techniques. This learning model has the ability to generate activity suggestions best suited to the user and further refines these suggestions using personal information.

[0327] To ensure data security, attribute data transmitted from the user's device is encrypted. This prevents unauthorized access to the data by third parties.

[0328] The narrowed-down activity candidates are visually displayed using the user's portable visual device, such as smart glasses. This allows the user to intuitively recognize the suggested activity candidates and make selections based on their interests. For the selected activity, the server provides appropriate resources and matches the user with other participants.

[0329] As a concrete example, consider the case of Ms. C, a 70-year-old, using this system. Ms. C uses smart glasses to input her hobbies and past work experience. Based on this information, the server suggests activities to Ms. C, such as a gardening club or a digital photography class. Ms. C becomes interested in the gardening club and selects the activity. The server then supports her smooth participation by showing her the nearest club she can join. Throughout this entire process, Ms. C has the opportunity to actively participate in new activities.

[0330] Example of a prompt:

[0331] "User Age: 70 Hobbies: Photography Work History: Educator Interests: Gardening Priority: High Suggestion"

[0332] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0333] Step 1:

[0334] The device receives attribute data from the user, such as preferences, interests, and history, as input. The user inputs their own information using the smart glasses interface via taps or voice input. This data is encrypted and transmitted to the server in a secure state.

[0335] Step 2:

[0336] The server receives encrypted data sent from the terminal and decrypts it. During this process, it analyzes user attribute data as input. Using machine learning techniques, particularly generative AI models, it generates activity candidates suitable for the user through data analysis. The output is a list of the generated activity candidates.

[0337] Step 3:

[0338] The server refines the generated list of potential activities based on personal information. This involves data processing that considers the user's priorities and past preferences to extract highly relevant activities. The output is a refined list of potential activities.

[0339] Step 4:

[0340] The server sends the narrowed-down list of activity candidates to the user's portable visual device. The terminal receives this data as input and displays it for the user to visually confirm. This allows the user to intuitively recognize and compare the activity candidates. The output is a visual display on the terminal.

[0341] Step 5:

[0342] The user selects an activity of interest from the suggested options presented on the device. The user's selection is sent to the server as input, and this information is used to initiate the next process.

[0343] Step 6:

[0344] The server matches the necessary resources and other participants to fulfill the selected activity. This involves performing data calculations, matching information from the database, and searching for relevant activity participants and location information. The output is specific activity participation information tailored to the user.

[0345] Step 7:

[0346] The server sends the final participation information to the terminal, which then displays it to the user again. Based on the information presented, the user can then prepare for the specific activities.

[0347] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0348] This invention provides a system that helps older adults find and support activities that enhance their emotional satisfaction after they have retired from their working lives. The system comprises a user, a terminal, a server, and an emotion engine.

[0349] Users use the device to input data about their hobbies, interests, work history, and desired lifestyle. The device also has a camera and microphone, which the emotion engine uses to analyze the user's voice and facial expressions.

[0350] The emotion engine recognizes emotions from the user's speech and facial expressions. This emotion information is sent to the server and used as data to personalize the user's experience. The server preprocesses both user data and emotion information and analyzes them using a generative model. This analysis generates optimal activity candidates based on the user's current emotional state and past history.

[0351] The generated activity candidates are further refined using the user's persona information. The server sends the refined activity candidates to the device, which then presents them to the user. The user can then select an activity that they feel emotionally satisfied with. In this process, it is also possible to provide an interface that aligns with the user's emotions by leveraging the real-time feedback provided by the emotion engine.

[0352] The selected activity is matched by the server with the necessary resources and collaborators. As a concrete example, consider a scenario where person A wants to find a new hobby and uses the system. As A is inputting information, the emotion engine analyzes his smile and tone of voice. Based on this emotion data, the server suggests art workshops and local volunteer activities that A might enjoy. A chooses an art workshop, and it is expected that this activity will provide emotional satisfaction and a sense of fulfillment.

[0353] Thus, the invention aims to enhance the quality of life by understanding and responding to the user's emotions and suggesting more appropriate activities.

[0354] The following describes the processing flow.

[0355] Step 1:

[0356] The user enters their hobbies, interests, work history, and new activities they would like to try into the device. The device's camera and microphone simultaneously transmit the user's facial expressions and voice to the emotion engine.

[0357] Step 2:

[0358] The emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is encrypted and sent to the server.

[0359] Step 3:

[0360] The server preprocesses the received user data and sentiment data, removing noise and preparing it for analysis.

[0361] Step 4:

[0362] The server uses a generative model to analyze user data in detail. This model generates activity suggestions that take into account the user's emotional state and past trends.

[0363] Step 5:

[0364] The generated activity candidates are further refined based on persona information. During this process, emotional data is also considered, and activities that enhance emotional satisfaction are prioritized.

[0365] Step 6:

[0366] The server sends a selection of activity options to the device. The device presents these options using an interface tailored to the user's emotional state. The user can then select an activity based on their interests and emotional state.

[0367] Step 7:

[0368] Based on the user's selection, the server matches them with resources, participants, or related information to support their activity and provides the necessary information to the terminal.

[0369] Step 8:

[0370] The user performs the selected activity and enters the results and impressions of the experience into the device. This information is sent to the server as feedback.

[0371] Step 9:

[0372] The server analyzes the collected feedback data and continuously improves the generative model and sentiment engine. This process improves the accuracy of future suggestions and the quality of the user experience.

[0373] (Example 2)

[0374] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0375] A challenge exists in finding appropriate activities that enhance emotional satisfaction for older adults after they have retired from their working lives. In particular, there is a need for methods to improve life satisfaction by recommending activities that take into account the individual emotional state and attribute information of older adults.

[0376] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0377] In this invention, the server includes means for inputting and collecting attribute information from the user via a data terminal, means for analyzing the user's emotions in real time and acquiring emotion information, and means for generating activity candidates suitable for the user using a generative model. This makes it possible to provide personalized activity suggestions based on the user's emotions and attributes.

[0378] A "data terminal" is a device used by users to input information and collect emotional data.

[0379] "Attribute information" refers to personal information about a user, such as their hobbies, interests, and work history.

[0380] An "imaging device" is a device used to acquire images or videos.

[0381] A "voice input device" is a device used to acquire voice data.

[0382] "Emotional information" refers to data about emotions analyzed from the user's facial expressions and voice.

[0383] A "server" is a centralized management system that processes and analyzes data sent by users.

[0384] A "generative model" is an algorithm that analyzes user data and generates optimal activity candidates.

[0385] "Activity options" refer to a set of activity choices presented to the user.

[0386] "Personal characteristics data" refers to information based on a user's past behavior and preferences.

[0387] "Resources" refer to elements such as materials and time necessary to carry out an activity.

[0388] A "collaborator" refers to a third party who provides assistance in realizing an activity.

[0389] "Response data" refers to feedback information obtained from users after an activity has been carried out.

[0390] "Protection processing" refers to encryption or security technologies used to protect information from unauthorized access.

[0391] This system helps older adults find activities that provide emotional satisfaction after they have retired from their working lives. The system is primarily implemented with a configuration that includes users, terminals, a server, and an emotion engine.

[0392] First, the user enters attribute information based on their personal information using a terminal. This terminal provides a user interface for entering information, where the user enters information about their hobbies, interests, past work experience, and desired lifestyle. The terminal is also equipped with input devices such as a camera and microphone, which are used by the emotion engine.

[0393] The device uses these features to capture the user's facial expressions and voice, acquiring emotional information in real time. The emotion engine analyzes this information to obtain information about the user's emotional state. This information is then transmitted from the device to the server.

[0394] Next, the server analyzes the attribute and emotional information it receives. Using a generative AI model, the server analyzes this information and generates the most suitable activity candidates for the user based on their current emotional state and past information.

[0395] The generated activity suggestions are further refined based on personal characteristics data. The server sends this refined information to the device, which then presents it to the user. The user can then select from the presented activity suggestions that they feel emotionally satisfied with.

[0396] For selected activities, the server coordinates the necessary resources and collaborators, thereby supporting the implementation of the activity.

[0397] As a concrete example, the prompt might say, "Tell me how to analyze the user's current emotions and suggest activities that match their hobbies and interests."

[0398] The implementation of this system is expected to improve users' quality of life by enabling activity suggestions based on individual emotions and attribute information.

[0399] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0400] Step 1:

[0401] The user uses the device to input attribute information about their hobbies, interests, work history, and desired lifestyle. The device receives this information as text data through the user interface. Specifically, input fields are displayed on a form screen, and the user enters the information using the keyboard or touch input.

[0402] Step 2:

[0403] The device uses its built-in camera and microphone to record the user's facial expressions and voice, acquiring emotional data. An emotion engine processes this data, analyzing emotional information in real time. Input is real-time audio and video, while output is parameters indicating emotion. The camera and microphone operate automatically to avoid interfering with user interaction.

[0404] Step 3:

[0405] The device sends the collected attribute and sentiment information to the server. At this stage, the data is compiled in JSON format and securely transferred to the server over the internet. Specifically, a communication module embedded in the device packets the data and transmits it.

[0406] Step 4:

[0407] The server preprocesses the received data and inputs it into the generated AI model. Preprocessing involves data cleaning and normalization, preparing the data for analysis by the AI ​​model. The output is a list of potential activities, and the process involves parallel database access and model inference.

[0408] Step 5:

[0409] The server narrows down the generated activity candidates based on personal characteristics data. Past selection history and preference parameters are considered to extract the most suitable activity. The output is an optimized activity list, and this process is performed through algorithmic scoring.

[0410] Step 6:

[0411] The terminal presents the user with activity options sent from the server. The terminal displays a UI in card or list format that visually represents the activities. The user can then make the optimal selection. The output is the user's selection, and the specific action is updating the user interface display.

[0412] Step 7:

[0413] The server matches users with the necessary resources and collaborators based on their selections. Based on these selections, activity preparations are initiated through external APIs and database integrations. These operations include resource reservations and notifications to relevant parties.

[0414] (Application Example 2)

[0415] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0416] Finding ways for older adults to enhance their emotional well-being after ending their working lives is challenging. Furthermore, there is a lack of systems that suggest activities based on individual preferences and interests, and then optimize those activities based on emotional responses.

[0417] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0418] In this invention, the server includes means for acquiring information such as preferences, interests, and experiences from the user; means for recognizing emotions from the user's voice and facial expressions using emotion analysis technology and optimizing activity candidates using that information; and means for matching the selected activity candidates with resources and other collaborators to realize those activities. This makes it possible to propose individually optimized activities to the user and to select emotionally satisfying activities.

[0419] "Preferences" refer to a user's personal enjoyment of specific hobbies or activities.

[0420] "Interest" refers to a user's interest in or desire to engage with a particular field or topic.

[0421] "Experience" refers to information about a user's past activities, work history, and other related information.

[0422] "Emotional analysis technology" is a technology that determines a user's emotions and psychological state by analyzing their voice and facial expressions.

[0423] "Resources" refer to the material or human support necessary to realize an activity.

[0424] A "collaborator" is another participant or partner necessary to carry out the proposed activity together.

[0425] A "user interface" refers to the visual and operational elements that allow a user to interact with a system.

[0426] "Optimization" is the process of adjusting choices and activities to the most suitable form based on the individual user's preferences and emotions.

[0427] This invention is a system that helps elderly people find and select activities that provide them with emotional satisfaction. The main components of the system are a user terminal, a server, a generative AI model, and an interface that utilizes emotion analysis technology.

[0428] Users input information about their preferences, interests, and experiences through a device. This device is equipped with a camera and microphone, allowing it to collect voice and facial expression data during information input. This enables emotion analysis technology to determine the user's emotions and provide real-time feedback.

[0429] The server processes the received user information and emotional data, and uses a generative AI model to generate appropriate activity candidates. This model provides personalized activities based on the user's past activity history and preferences. The generated activity candidates are further refined based on attribute information and presented as options optimized for the user's emotional state.

[0430] When a user selects an activity from the presented options, the server matches them with the necessary resources and collaborators to accomplish that activity. Furthermore, the user interface dynamically changes based on the sentiment analysis results, providing an intuitive and emotionally satisfying user experience.

[0431] For example, if a user is smiling while searching for a new painting class, the system will detect this positive emotion and present a wider range of art workshop options. A possible prompt to input into the generative AI model would be: "Please enter user information below for the activity recommendation system and analyze the emotion data."

[0432] This allows users to actually experience personalized activity suggestions, and the activity choices can be emotionally fulfilling.

[0433] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0434] Step 1:

[0435] The user inputs information about their preferences, interests, and experiences using the device. The camera and microphone collect voice and facial expressions in real time, and this data is sent to the device. The input data is pre-processed to format it and prepare it for transmission to the server.

[0436] Step 2:

[0437] The server analyzes the received user information and voice / facial expression data. Using emotion analysis technology, it recognizes emotions from voice tone and facial expressions, identifying the user's current emotional state. The emotional information is then formatted into a dataset for input into an AI model.

[0438] Step 3:

[0439] The server uses a generative AI model to generate activity suggestions best suited to the user. Based on the input data, the model creates a recommendation list of activities that match the user's interests and past history. The generated recommendation list is further filtered using the user's attribute information to provide an optimized activity list as output.

[0440] Step 4:

[0441] The server sends filtered activity candidates to the terminal and presents them to the user. The terminal displays a dynamic user interface that takes the user's emotional information into account, adjusting the visual effects and operation methods appropriately according to the user's emotions. The user makes a selection from the activity candidates.

[0442] Step 5:

[0443] The server matches the user with the resources and collaborators necessary to realize the activity selected by the user. It identifies the partners and materials needed for the activity and provides the user with guidance and support information for preparation. The selection results are recorded throughout the system as the final output.

[0444] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0445] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0446] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0447] [Third Embodiment]

[0448] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0449] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0450] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0451] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0452] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0453] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0454] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0455] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0456] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0457] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0458] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0459] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0460] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0461] First, the user uses their device to input information such as their personal hobbies, interests, work history, and desired activities. The device then encrypts this information and sends it to the server. This is to protect the security and privacy of user data.

[0462] The server preprocesses the received data and performs analysis using a generative model. This generative model utilizes machine learning techniques to generate the most suitable activity candidates based on the user's preferences and past experiences. The generated activity candidates are further refined using the user's persona information. This persona information enables more personalized suggestions.

[0463] Next, the server sends the narrowed-down list of activity options to the device, which then visually presents them to the user. The user can compare the presented options and select an activity that suits their interests and circumstances. By narrowing down the options, the user can create a more specific and feasible plan.

[0464] Furthermore, the server matches users with the necessary resources and other participants to realize their chosen activity. For example, if a user requests a cooking class, the server gathers information on local cooking classes and online classes and presents suitable opportunities. This feature helps users get started with activities in a way that suits them.

[0465] As a concrete example, consider the case of Mr. A, who wants to spend his leisure time after retirement meaningfully, using the system. Mr. A inputs his past work, hobbies, preferences, and interests into a terminal. The server analyzes this information and suggests activities such as landscaping or pottery to the user. Mr. A becomes interested in pottery and chooses to participate in a local pottery class. The system matches Mr. A with a class, providing a smooth experience. In this way, Mr. A can find a new hobby and make his second life more fulfilling.

[0466] As described above, the invention provides a system that helps older adults utilize their own experiences and interests, find meaningful activities, and support their implementation.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] Users enter their hobbies, interests, past work experience, and desired activities on their device.

[0470] Step 2:

[0471] The terminal encrypts the entered user data and sends it to the server. This ensures the security of the information.

[0472] Step 3:

[0473] The server preprocesses the received user data, removing noise and preparing it for analysis.

[0474] Step 4:

[0475] The server uses a generative model to analyze pre-processed data and generate activity candidates that are suitable for the user. This model is based on machine learning techniques and takes into account the user's interests and past experiences.

[0476] Step 5:

[0477] The server further refines the generated activity candidates based on the user's persona information and selects the optimal option.

[0478] Step 6:

[0479] The server sends a selection of activity options to the terminal, which then presents them to the user. The user can then review the options through a visual interface.

[0480] Step 7:

[0481] Users select specific activities from the presented options based on their interests and preferences.

[0482] Step 8:

[0483] The server matches the necessary resources and other participants to fulfill the selected activity. Specifically, it gathers and presents information on relevant stores and online courses.

[0484] Step 9:

[0485] Users perform activities and input the results and experiences as feedback through their devices.

[0486] Step 10:

[0487] The server analyzes the collected feedback and improves the generative model. At this stage, the accuracy of suggestions for future users is improved.

[0488] (Example 1)

[0489] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0490] For seniors to lead fulfilling second lives after retiring from their professional careers, support is needed to help them find activities that take into account their hobbies, interests, and past experiences. However, current systems struggle to adequately suggest activities suitable for individual users and provide feasible plans. It is necessary to solve this problem and provide users with more personalized activity suggestions and support for their implementation.

[0491] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0492] In this invention, the server includes means for inputting and collecting information such as hobbies, interests, and work history from users; means for encrypting the information using a standard security protocol; and means for analyzing the encrypted information and generating activity candidates using a machine learning algorithm. This makes it possible to propose appropriate activity candidates that reflect the individuality of the user, and to provide concrete planning and support for leading a fulfilling second life.

[0493] A "user" refers to an individual who uses this system to receive activity suggestions based on their hobbies and interests.

[0494] "Information" refers to data necessary to identify an individual user, such as their hobbies, interests, and work history.

[0495] "Standard security protocols" refer to methods for encrypting and protecting data during the transmission and reception of information, and include SSL / TLS, among others.

[0496] "Encryption" refers to the process of transforming information using a specific algorithm to protect data from unauthorized access.

[0497] A "machine learning algorithm" refers to a learning model that makes predictions and decisions based on past data and patterns.

[0498] "Activity suggestions" refer to proposals for activities that are suited to the user's hobbies and work experience, with the aim of enriching the user's life.

[0499] "Personalization information" refers to data that represents individual characteristics of a user, such as their past activity history and current interests.

[0500] "Resources" refer to the physical and human resources necessary to carry out the selected activities.

[0501] "Response" refers to the adjustments and arrangements necessary to carry out the activity selected by the user.

[0502] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0503] Users use their devices to input personal information such as hobbies, interests, work history, and desired activities. The device encrypts the entered information in real time using standard security protocols such as SSL / TLS and sends it to the server. This ensures secure data transfer while protecting user privacy.

[0504] The server decrypts the received encrypted data and prepares it through preprocessing, including noise reduction and anomaly handling. Then, it uses a generative AI model powered by machine learning algorithms to generate activity candidates based on user information. This analysis process proposes appropriate activities that reflect the user's preferences and past experiences.

[0505] For example, if a user enters the prompt, "Please suggest activities I can enjoy after retirement. My past interests include weaving and cooking with herbs," into the system, the server analyzes this and lists relevant activity candidates. These candidates are further refined based on individual information to provide suggestions tailored to the user.

[0506] The server sends a selection of activity candidates to the device, which then visually presents them to the user. The user can then select an activity that interests them from the presented options and use this to create a concrete action plan.

[0507] This system matches users with the resources and participants needed to realize their chosen activities, supporting them in smoothly starting new endeavors. For example, if a user chooses a local pottery class as their activity, the server uses this information to suggest appropriate classes and events, providing a platform to enrich the user's second life.

[0508] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0509] Step 1:

[0510] The user uses a terminal to input their personal information, such as hobbies, interests, work history, and desired activities. Once input is complete, the terminal encrypts this data using standard security protocols (e.g., SSL / TLS) and sends it to the server. This input data is raw data used as the basis for subsequent analysis.

[0511] Step 2:

[0512] The server decrypts the encrypted user information received from the terminal. After decryption, it performs preprocessing to make the data easier to handle. This preprocessing includes data cleaning techniques such as noise reduction, outlier handling, and standardization. As a result, formatted user data is generated.

[0513] Step 3:

[0514] The server inputs pre-processed data into a generating AI model. This model generates activity candidates based on patterns and trends derived from multiple user data. In this step, machine learning algorithms are used to list highly suitable activities based on the user's interests and past experiences. The output is a list of corresponding activity candidates.

[0515] Step 4:

[0516] The server refines the generated list of suggested activities by referencing more detailed user individual information (such as personal preferences and past selection history). This process aims to provide results optimized for the user using a filtering algorithm. The output of this step is the final, compact list of suggested activities.

[0517] Step 5:

[0518] The server sends these narrowed-down activity candidates to the terminal. The terminal visually presents the received activity candidates to the user. Here, the user can compare the provided options and choose the activity that interests them. The output of this step is the specific activity that the user selects.

[0519] Step 6:

[0520] For activities selected by the user, the server identifies the resources and other participants necessary to carry them out. Based on this, the server collects specific information, such as location and time, to support the planning. This process involves necessary data integration and access to referenced databases, and the output is comprehensive information for carrying out the activity.

[0521] This series of processes allows users to start new activities based on reliable information and build a fulfilling second life that makes the most of their abilities.

[0522] (Application Example 1)

[0523] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0524] A problem exists in that older adults often find it difficult to find activities that allow them to lead fulfilling second lives based on their individual interests and past experiences after ending their working lives. Furthermore, even when they find activities, they often struggle to find the necessary information and participants to implement them. Therefore, there is a need for a system that proposes activities tailored to individual needs and provides support until participation is achieved.

[0525] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0526] In this invention, the server includes means for inputting and collecting attribute data such as preferences, interests, and history from the user; means for analyzing the attribute data and generating activity candidates suitable for the user using a learning model; and means for visually displaying the narrowed-down activity candidates using the user's portable visual device. This makes it possible for the user to easily discover appropriate activities based on their interests and smoothly proceed through the process of participation.

[0527] "User" refers to an individual who uses this system, with the primary target audience being the elderly.

[0528] "Preferences" refers to information about a user's personal tastes and hobbies.

[0529] "Interests" refers to information that indicates what a user is interested in or what activities they are interested in.

[0530] "Career history" refers to information including the user's past work experience and educational background.

[0531] "Attribute data" refers to data that includes information such as preferences, interests, and background, entered by the user.

[0532] A "learning model" is a model that uses machine learning techniques to generate optimal activity candidates for the user.

[0533] "Activity suggestions" are specific activity options proposed based on the user's attribute data.

[0534] "Personal information" refers to information that can identify a user, including their hobbies, preferences, and work history.

[0535] "Resources" refer to the materials, locations, and funds necessary to realize the selected activity candidates.

[0536] "Fitting" refers to the process of matching a proposed activity with the necessary resources and other participants to realize that activity.

[0537] "Portable visual devices" refer to visual information terminals worn and used by users, such as smart glasses and head-mounted displays.

[0538] This invention provides a system to enable elderly people to lead fulfilling second lives. The system mainly consists of users, terminals, and a server.

[0539] The server receives attribute data such as preferences, interests, and history sent by the user and analyzes it. This analysis utilizes a learning model powered by machine learning techniques. This learning model has the ability to generate activity suggestions best suited to the user and further refines these suggestions using personal information.

[0540] To ensure data security, attribute data transmitted from the user's device is encrypted. This prevents unauthorized access to the data by third parties.

[0541] The narrowed-down activity candidates are visually displayed using the user's portable visual device, such as smart glasses. This allows the user to intuitively recognize the suggested activity candidates and make selections based on their interests. For the selected activity, the server provides appropriate resources and matches the user with other participants.

[0542] As a concrete example, consider the case of Ms. C, a 70-year-old, using this system. Ms. C uses smart glasses to input her hobbies and past work experience. Based on this information, the server suggests activities to Ms. C, such as a gardening club or a digital photography class. Ms. C becomes interested in the gardening club and selects the activity. The server then supports her smooth participation by showing her the nearest club she can join. Throughout this entire process, Ms. C has the opportunity to actively participate in new activities.

[0543] Example of a prompt:

[0544] "User Age: 70 Hobbies: Photography Work History: Educator Interests: Gardening Priority: High Suggestion"

[0545] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0546] Step 1:

[0547] The device receives attribute data from the user, such as preferences, interests, and history, as input. The user inputs their own information using the smart glasses interface via taps or voice input. This data is encrypted and transmitted to the server in a secure state.

[0548] Step 2:

[0549] The server receives encrypted data sent from the terminal and decrypts it. During this process, it analyzes user attribute data as input. Using machine learning techniques, particularly generative AI models, it generates activity candidates suitable for the user through data analysis. The output is a list of the generated activity candidates.

[0550] Step 3:

[0551] The server refines the generated list of potential activities based on personal information. This involves data processing that considers the user's priorities and past preferences to extract highly relevant activities. The output is a refined list of potential activities.

[0552] Step 4:

[0553] The server sends the narrowed-down list of activity candidates to the user's portable visual device. The terminal receives this data as input and displays it for the user to visually confirm. This allows the user to intuitively recognize and compare the activity candidates. The output is a visual display on the terminal.

[0554] Step 5:

[0555] The user selects an activity of interest from the suggested options presented on the device. The user's selection is sent to the server as input, and this information is used to initiate the next process.

[0556] Step 6:

[0557] The server matches the necessary resources and other participants to fulfill the selected activity. This involves performing data calculations, matching information from the database, and searching for relevant activity participants and location information. The output is specific activity participation information tailored to the user.

[0558] Step 7:

[0559] The server sends the final participation information to the terminal, which then displays it to the user again. Based on the information presented, the user can then prepare for the specific activities.

[0560] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0561] This invention provides a system that helps older adults find and support activities that enhance their emotional satisfaction after they have retired from their working lives. The system comprises a user, a terminal, a server, and an emotion engine.

[0562] Users use the device to input data about their hobbies, interests, work history, and desired lifestyle. The device also has a camera and microphone, which the emotion engine uses to analyze the user's voice and facial expressions.

[0563] The emotion engine recognizes emotions from the user's speech and facial expressions. This emotion information is sent to the server and used as data to personalize the user's experience. The server preprocesses both user data and emotion information and analyzes them using a generative model. This analysis generates optimal activity candidates based on the user's current emotional state and past history.

[0564] The generated activity candidates are further refined using the user's persona information. The server sends the refined activity candidates to the device, which then presents them to the user. The user can then select an activity that they feel emotionally satisfied with. In this process, it is also possible to provide an interface that aligns with the user's emotions by leveraging the real-time feedback provided by the emotion engine.

[0565] The selected activity is matched by the server with the necessary resources and collaborators. As a concrete example, consider a scenario where person A wants to find a new hobby and uses the system. As A is inputting information, the emotion engine analyzes his smile and tone of voice. Based on this emotion data, the server suggests art workshops and local volunteer activities that A might enjoy. A chooses an art workshop, and it is expected that this activity will provide emotional satisfaction and a sense of fulfillment.

[0566] Thus, the invention aims to enhance the quality of life by understanding and responding to the user's emotions and suggesting more appropriate activities.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The user enters their hobbies, interests, work history, and new activities they would like to try into the device. The device's camera and microphone simultaneously transmit the user's facial expressions and voice to the emotion engine.

[0570] Step 2:

[0571] The emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is encrypted and sent to the server.

[0572] Step 3:

[0573] The server preprocesses the received user data and sentiment data, removing noise and preparing it for analysis.

[0574] Step 4:

[0575] The server uses a generative model to analyze user data in detail. This model generates activity suggestions that take into account the user's emotional state and past trends.

[0576] Step 5:

[0577] The generated activity candidates are further refined based on persona information. During this process, emotional data is also considered, and activities that enhance emotional satisfaction are prioritized.

[0578] Step 6:

[0579] The server sends a selection of activity options to the device. The device presents these options using an interface tailored to the user's emotional state. The user can then select an activity based on their interests and emotional state.

[0580] Step 7:

[0581] Based on the user's selection, the server matches them with resources, participants, or related information to support their activity and provides the necessary information to the terminal.

[0582] Step 8:

[0583] The user performs the selected activity and enters the results and impressions of the experience into the device. This information is sent to the server as feedback.

[0584] Step 9:

[0585] The server analyzes the collected feedback data and continuously improves the generative model and sentiment engine. This process improves the accuracy of future suggestions and the quality of the user experience.

[0586] (Example 2)

[0587] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0588] A challenge exists in finding appropriate activities that enhance emotional satisfaction for older adults after they have retired from their working lives. In particular, there is a need for methods to improve life satisfaction by recommending activities that take into account the individual emotional state and attribute information of older adults.

[0589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0590] In this invention, the server includes means for inputting and collecting attribute information from the user via a data terminal, means for analyzing the user's emotions in real time and acquiring emotion information, and means for generating activity candidates suitable for the user using a generative model. This makes it possible to provide personalized activity suggestions based on the user's emotions and attributes.

[0591] A "data terminal" is a device used by users to input information and collect emotional data.

[0592] "Attribute information" refers to personal information about a user, such as their hobbies, interests, and work history.

[0593] An "imaging device" is a device used to acquire images or videos.

[0594] A "voice input device" is a device used to acquire voice data.

[0595] "Emotional information" refers to data about emotions analyzed from the user's facial expressions and voice.

[0596] A "server" is a centralized management system that processes and analyzes data sent by users.

[0597] A "generative model" is an algorithm that analyzes user data and generates optimal activity candidates.

[0598] "Activity options" refer to a set of activity choices presented to the user.

[0599] "Personal characteristics data" refers to information based on a user's past behavior and preferences.

[0600] "Resources" refer to elements such as materials and time necessary to carry out an activity.

[0601] A "collaborator" refers to a third party who provides assistance in realizing an activity.

[0602] "Response data" refers to feedback information obtained from users after an activity has been carried out.

[0603] "Protection processing" refers to encryption or security technologies used to protect information from unauthorized access.

[0604] This system helps older adults find activities that provide emotional satisfaction after they have retired from their working lives. The system is primarily implemented with a configuration that includes users, terminals, a server, and an emotion engine.

[0605] First, the user enters attribute information based on their personal information using a terminal. This terminal provides a user interface for entering information, where the user enters information about their hobbies, interests, past work experience, and desired lifestyle. The terminal is also equipped with input devices such as a camera and microphone, which are used by the emotion engine.

[0606] The device uses these features to capture the user's facial expressions and voice, acquiring emotional information in real time. The emotion engine analyzes this information to obtain information about the user's emotional state. This information is then transmitted from the device to the server.

[0607] Next, the server analyzes the attribute and emotional information it receives. Using a generative AI model, the server analyzes this information and generates the most suitable activity candidates for the user based on their current emotional state and past information.

[0608] The generated activity suggestions are further refined based on personal characteristics data. The server sends this refined information to the device, which then presents it to the user. The user can then select from the presented activity suggestions that they feel emotionally satisfied with.

[0609] For selected activities, the server coordinates the necessary resources and collaborators, thereby supporting the implementation of the activity.

[0610] As a concrete example, the prompt might say, "Tell me how to analyze the user's current emotions and suggest activities that match their hobbies and interests."

[0611] The implementation of this system is expected to improve users' quality of life by enabling activity suggestions based on individual emotions and attribute information.

[0612] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0613] Step 1:

[0614] The user uses the device to input attribute information about their hobbies, interests, work history, and desired lifestyle. The device receives this information as text data through the user interface. Specifically, input fields are displayed on a form screen, and the user enters the information using the keyboard or touch input.

[0615] Step 2:

[0616] The device uses its built-in camera and microphone to record the user's facial expressions and voice, acquiring emotional data. An emotion engine processes this data, analyzing emotional information in real time. Input is real-time audio and video, while output is parameters indicating emotion. The camera and microphone operate automatically to avoid interfering with user interaction.

[0617] Step 3:

[0618] The device sends the collected attribute and sentiment information to the server. At this stage, the data is compiled in JSON format and securely transferred to the server over the internet. Specifically, a communication module embedded in the device packets the data and transmits it.

[0619] Step 4:

[0620] The server preprocesses the received data and inputs it into the generated AI model. Preprocessing involves data cleaning and normalization, preparing the data for analysis by the AI ​​model. The output is a list of potential activities, and the process involves parallel database access and model inference.

[0621] Step 5:

[0622] The server narrows down the generated activity candidates based on personal characteristics data. Past selection history and preference parameters are considered to extract the most suitable activity. The output is an optimized activity list, and this process is performed through algorithmic scoring.

[0623] Step 6:

[0624] The terminal presents the user with activity options sent from the server. The terminal displays a UI in card or list format that visually represents the activities. The user can then make the optimal selection. The output is the user's selection, and the specific action is updating the user interface display.

[0625] Step 7:

[0626] The server matches users with the necessary resources and collaborators based on their selections. Based on these selections, activity preparations are initiated through external APIs and database integrations. These operations include resource reservations and notifications to relevant parties.

[0627] (Application Example 2)

[0628] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0629] Finding ways for older adults to enhance their emotional well-being after ending their working lives is challenging. Furthermore, there is a lack of systems that suggest activities based on individual preferences and interests, and then optimize those activities based on emotional responses.

[0630] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0631] In this invention, the server includes means for acquiring information such as preferences, interests, and experiences from the user; means for recognizing emotions from the user's voice and facial expressions using emotion analysis technology and optimizing activity candidates using that information; and means for matching the selected activity candidates with resources and other collaborators to realize those activities. This makes it possible to propose individually optimized activities to the user and to select emotionally satisfying activities.

[0632] "Preferences" refer to a user's personal enjoyment of specific hobbies or activities.

[0633] "Interest" refers to a user's interest in or desire to engage with a particular field or topic.

[0634] "Experience" refers to information about a user's past activities, work history, and other related information.

[0635] "Emotional analysis technology" is a technology that determines a user's emotions and psychological state by analyzing their voice and facial expressions.

[0636] "Resources" refer to the material or human support necessary to realize an activity.

[0637] A "collaborator" is another participant or partner necessary to carry out the proposed activity together.

[0638] A "user interface" refers to the visual and operational elements that allow a user to interact with a system.

[0639] "Optimization" is the process of adjusting choices and activities to the most suitable form based on the individual user's preferences and emotions.

[0640] This invention is a system that helps elderly people find and select activities that provide them with emotional satisfaction. The main components of the system are a user terminal, a server, a generative AI model, and an interface that utilizes emotion analysis technology.

[0641] Users input information about their preferences, interests, and experiences through a device. This device is equipped with a camera and microphone, allowing it to collect voice and facial expression data during information input. This enables emotion analysis technology to determine the user's emotions and provide real-time feedback.

[0642] The server processes the received user information and emotional data, and uses a generative AI model to generate appropriate activity candidates. This model provides personalized activities based on the user's past activity history and preferences. The generated activity candidates are further refined based on attribute information and presented as options optimized for the user's emotional state.

[0643] When a user selects an activity from the presented options, the server matches them with the necessary resources and collaborators to accomplish that activity. Furthermore, the user interface dynamically changes based on the sentiment analysis results, providing an intuitive and emotionally satisfying user experience.

[0644] For example, if a user is smiling while searching for a new painting class, the system will detect this positive emotion and present a wider range of art workshop options. A possible prompt to input into the generative AI model would be: "Please enter user information below for the activity recommendation system and analyze the emotion data."

[0645] This allows users to actually experience personalized activity suggestions, and the activity choices can be emotionally fulfilling.

[0646] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0647] Step 1:

[0648] The user inputs information about their preferences, interests, and experiences using the device. The camera and microphone collect voice and facial expressions in real time, and this data is sent to the device. The input data is pre-processed to format it and prepare it for transmission to the server.

[0649] Step 2:

[0650] The server analyzes the received user information and voice / facial expression data. Using emotion analysis technology, it recognizes emotions from voice tone and facial expressions, identifying the user's current emotional state. The emotional information is then formatted into a dataset for input into an AI model.

[0651] Step 3:

[0652] The server uses a generative AI model to generate activity suggestions best suited to the user. Based on the input data, the model creates a recommendation list of activities that match the user's interests and past history. The generated recommendation list is further filtered using the user's attribute information to provide an optimized activity list as output.

[0653] Step 4:

[0654] The server sends filtered activity candidates to the terminal and presents them to the user. The terminal displays a dynamic user interface that takes the user's emotional information into account, adjusting the visual effects and operation methods appropriately according to the user's emotions. The user makes a selection from the activity candidates.

[0655] Step 5:

[0656] The server matches the user with the resources and collaborators necessary to realize the activity selected by the user. It identifies the partners and materials needed for the activity and provides the user with guidance and support information for preparation. The selection results are recorded throughout the system as the final output.

[0657] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0658] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0659] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0660] [Fourth Embodiment]

[0661] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0662] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0663] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0664] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0665] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0666] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0667] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0668] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0669] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0670] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0671] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0672] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0673] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0675] First, the user uses their device to input information such as their personal hobbies, interests, work history, and desired activities. The device then encrypts this information and sends it to the server. This is to protect the security and privacy of user data.

[0676] The server preprocesses the received data and performs analysis using a generative model. This generative model utilizes machine learning techniques to generate the most suitable activity candidates based on the user's preferences and past experiences. The generated activity candidates are further refined using the user's persona information. This persona information enables more personalized suggestions.

[0677] Next, the server sends the narrowed-down list of activity options to the device, which then visually presents them to the user. The user can compare the presented options and select an activity that suits their interests and circumstances. By narrowing down the options, the user can create a more specific and feasible plan.

[0678] Furthermore, the server matches users with the necessary resources and other participants to realize their chosen activity. For example, if a user requests a cooking class, the server gathers information on local cooking classes and online classes and presents suitable opportunities. This feature helps users get started with activities in a way that suits them.

[0679] As a concrete example, consider the case of Mr. A, who wants to spend his leisure time after retirement meaningfully, using the system. Mr. A inputs his past work, hobbies, preferences, and interests into a terminal. The server analyzes this information and suggests activities such as landscaping or pottery to the user. Mr. A becomes interested in pottery and chooses to participate in a local pottery class. The system matches Mr. A with a class, providing a smooth experience. In this way, Mr. A can find a new hobby and make his second life more fulfilling.

[0680] As described above, the invention provides a system that helps older adults utilize their own experiences and interests, find meaningful activities, and support their implementation.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] Users enter their hobbies, interests, past work experience, and desired activities on their device.

[0684] Step 2:

[0685] The terminal encrypts the entered user data and sends it to the server. This ensures the security of the information.

[0686] Step 3:

[0687] The server preprocesses the received user data, removing noise and preparing it for analysis.

[0688] Step 4:

[0689] The server uses a generative model to analyze pre-processed data and generate activity candidates that are suitable for the user. This model is based on machine learning techniques and takes into account the user's interests and past experiences.

[0690] Step 5:

[0691] The server further refines the generated activity candidates based on the user's persona information and selects the optimal option.

[0692] Step 6:

[0693] The server sends a selection of activity options to the terminal, which then presents them to the user. The user can then review the options through a visual interface.

[0694] Step 7:

[0695] Users select specific activities from the presented options based on their interests and preferences.

[0696] Step 8:

[0697] The server matches the necessary resources and other participants to fulfill the selected activity. Specifically, it gathers and presents information on relevant stores and online courses.

[0698] Step 9:

[0699] Users perform activities and input the results and experiences as feedback through their devices.

[0700] Step 10:

[0701] The server analyzes the collected feedback and improves the generative model. At this stage, the accuracy of suggestions for future users is improved.

[0702] (Example 1)

[0703] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] For seniors to lead fulfilling second lives after retiring from their professional careers, support is needed to help them find activities that take into account their hobbies, interests, and past experiences. However, current systems struggle to adequately suggest activities suitable for individual users and provide feasible plans. It is necessary to solve this problem and provide users with more personalized activity suggestions and support for their implementation.

[0705] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0706] In this invention, the server includes means for inputting and collecting information such as hobbies, interests, and work history from users; means for encrypting the information using a standard security protocol; and means for analyzing the encrypted information and generating activity candidates using a machine learning algorithm. This makes it possible to propose appropriate activity candidates that reflect the individuality of the user, and to provide concrete planning and support for leading a fulfilling second life.

[0707] A "user" refers to an individual who uses this system to receive activity suggestions based on their hobbies and interests.

[0708] "Information" refers to data necessary to identify an individual user, such as their hobbies, interests, and work history.

[0709] "Standard security protocols" refer to methods for encrypting and protecting data during the transmission and reception of information, and include SSL / TLS, among others.

[0710] "Encryption" refers to the process of transforming information using a specific algorithm to protect data from unauthorized access.

[0711] A "machine learning algorithm" refers to a learning model that makes predictions and decisions based on past data and patterns.

[0712] "Activity suggestions" refer to proposals for activities that are suited to the user's hobbies and work experience, with the aim of enriching the user's life.

[0713] "Personalization information" refers to data that represents individual characteristics of a user, such as their past activity history and current interests.

[0714] "Resources" refer to the physical and human resources necessary to carry out the selected activities.

[0715] "Response" refers to the adjustments and arrangements necessary to carry out the activity selected by the user.

[0716] This invention provides a navigation system to help elderly people lead fulfilling second lives after ending their working lives. The system consists of a user, a terminal, and a server.

[0717] Users use their devices to input personal information such as hobbies, interests, work history, and desired activities. The device encrypts the entered information in real time using standard security protocols such as SSL / TLS and sends it to the server. This ensures secure data transfer while protecting user privacy.

[0718] The server decrypts the received encrypted data and prepares it through preprocessing, including noise reduction and anomaly handling. Then, it uses a generative AI model powered by machine learning algorithms to generate activity candidates based on user information. This analysis process proposes appropriate activities that reflect the user's preferences and past experiences.

[0719] For example, if a user enters the prompt, "Please suggest activities I can enjoy after retirement. My past interests include weaving and cooking with herbs," into the system, the server analyzes this and lists relevant activity candidates. These candidates are further refined based on individual information to provide suggestions tailored to the user.

[0720] The server sends a selection of activity candidates to the device, which then visually presents them to the user. The user can then select an activity that interests them from the presented options and use this to create a concrete action plan.

[0721] This system matches users with the resources and participants needed to realize their chosen activities, supporting them in smoothly starting new endeavors. For example, if a user chooses a local pottery class as their activity, the server uses this information to suggest appropriate classes and events, providing a platform to enrich the user's second life.

[0722] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0723] Step 1:

[0724] The user uses a terminal to input their personal information, such as hobbies, interests, work history, and desired activities. Once input is complete, the terminal encrypts this data using standard security protocols (e.g., SSL / TLS) and sends it to the server. This input data is raw data used as the basis for subsequent analysis.

[0725] Step 2:

[0726] The server decrypts the encrypted user information received from the terminal. After decryption, it performs preprocessing to make the data easier to handle. This preprocessing includes data cleaning techniques such as noise reduction, outlier handling, and standardization. As a result, formatted user data is generated.

[0727] Step 3:

[0728] The server inputs pre-processed data into a generating AI model. This model generates activity candidates based on patterns and trends derived from multiple user data. In this step, machine learning algorithms are used to list highly suitable activities based on the user's interests and past experiences. The output is a list of corresponding activity candidates.

[0729] Step 4:

[0730] The server refines the generated list of suggested activities by referencing more detailed user individual information (such as personal preferences and past selection history). This process aims to provide results optimized for the user using a filtering algorithm. The output of this step is the final, compact list of suggested activities.

[0731] Step 5:

[0732] The server sends these narrowed-down activity candidates to the terminal. The terminal visually presents the received activity candidates to the user. Here, the user can compare the provided options and choose the activity that interests them. The output of this step is the specific activity that the user selects.

[0733] Step 6:

[0734] For activities selected by the user, the server identifies the resources and other participants necessary to carry them out. Based on this, the server collects specific information, such as location and time, to support the planning. This process involves necessary data integration and access to referenced databases, and the output is comprehensive information for carrying out the activity.

[0735] This series of processes allows users to start new activities based on reliable information and build a fulfilling second life that makes the most of their abilities.

[0736] (Application Example 1)

[0737] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] A problem exists in that older adults often find it difficult to find activities that allow them to lead fulfilling second lives based on their individual interests and past experiences after ending their working lives. Furthermore, even when they find activities, they often struggle to find the necessary information and participants to implement them. Therefore, there is a need for a system that proposes activities tailored to individual needs and provides support until participation is achieved.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0740] In this invention, the server includes means for inputting and collecting attribute data such as preferences, interests, and history from the user; means for analyzing the attribute data and generating activity candidates suitable for the user using a learning model; and means for visually displaying the narrowed-down activity candidates using the user's portable visual device. This makes it possible for the user to easily discover appropriate activities based on their interests and smoothly proceed through the process of participation.

[0741] "User" refers to an individual who uses this system, with the primary target audience being the elderly.

[0742] "Preferences" refers to information about a user's personal tastes and hobbies.

[0743] "Interests" refers to information that indicates what a user is interested in or what activities they are interested in.

[0744] "Career history" refers to information including the user's past work experience and educational background.

[0745] "Attribute data" refers to data that includes information such as preferences, interests, and background, entered by the user.

[0746] A "learning model" is a model that uses machine learning techniques to generate optimal activity candidates for the user.

[0747] "Activity suggestions" are specific activity options proposed based on the user's attribute data.

[0748] "Personal information" refers to information that can identify a user, including their hobbies, preferences, and work history.

[0749] "Resources" refer to the materials, locations, and funds necessary to realize the selected activity candidates.

[0750] "Fitting" refers to the process of matching a proposed activity with the necessary resources and other participants to realize that activity.

[0751] "Portable visual devices" refer to visual information terminals worn and used by users, such as smart glasses and head-mounted displays.

[0752] This invention provides a system to enable elderly people to lead fulfilling second lives. The system mainly consists of users, terminals, and a server.

[0753] The server receives attribute data such as preferences, interests, and history sent by the user and analyzes it. This analysis utilizes a learning model powered by machine learning techniques. This learning model has the ability to generate activity suggestions best suited to the user and further refines these suggestions using personal information.

[0754] To ensure data security, attribute data transmitted from the user's device is encrypted. This prevents unauthorized access to the data by third parties.

[0755] The narrowed-down activity candidates are visually displayed using the user's portable visual device, such as smart glasses. This allows the user to intuitively recognize the suggested activity candidates and make selections based on their interests. For the selected activity, the server provides appropriate resources and matches the user with other participants.

[0756] As a concrete example, consider the case of Ms. C, a 70-year-old, using this system. Ms. C uses smart glasses to input her hobbies and past work experience. Based on this information, the server suggests activities to Ms. C, such as a gardening club or a digital photography class. Ms. C becomes interested in the gardening club and selects the activity. The server then supports her smooth participation by showing her the nearest club she can join. Throughout this entire process, Ms. C has the opportunity to actively participate in new activities.

[0757] Example of a prompt:

[0758] "User Age: 70 Hobbies: Photography Work History: Educator Interests: Gardening Priority: High Suggestion"

[0759] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0760] Step 1:

[0761] The device receives attribute data from the user, such as preferences, interests, and history, as input. The user inputs their own information using the smart glasses interface via taps or voice input. This data is encrypted and transmitted to the server in a secure state.

[0762] Step 2:

[0763] The server receives encrypted data sent from the terminal and decrypts it. During this process, it analyzes user attribute data as input. Using machine learning techniques, particularly generative AI models, it generates activity candidates suitable for the user through data analysis. The output is a list of the generated activity candidates.

[0764] Step 3:

[0765] The server refines the generated list of potential activities based on personal information. This involves data processing that considers the user's priorities and past preferences to extract highly relevant activities. The output is a refined list of potential activities.

[0766] Step 4:

[0767] The server sends the narrowed-down list of activity candidates to the user's portable visual device. The terminal receives this data as input and displays it for the user to visually confirm. This allows the user to intuitively recognize and compare the activity candidates. The output is a visual display on the terminal.

[0768] Step 5:

[0769] The user selects an activity of interest from the suggested options presented on the device. The user's selection is sent to the server as input, and this information is used to initiate the next process.

[0770] Step 6:

[0771] The server matches the necessary resources and other participants to fulfill the selected activity. This involves performing data calculations, matching information from the database, and searching for relevant activity participants and location information. The output is specific activity participation information tailored to the user.

[0772] Step 7:

[0773] The server sends the final participation information to the terminal, which then displays it to the user again. Based on the information presented, the user can then prepare for the specific activities.

[0774] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0775] This invention provides a system that helps older adults find and support activities that enhance their emotional satisfaction after they have retired from their working lives. The system comprises a user, a terminal, a server, and an emotion engine.

[0776] Users use the device to input data about their hobbies, interests, work history, and desired lifestyle. The device also has a camera and microphone, which the emotion engine uses to analyze the user's voice and facial expressions.

[0777] The emotion engine recognizes emotions from the user's speech and facial expressions. This emotion information is sent to the server and used as data to personalize the user's experience. The server preprocesses both user data and emotion information and analyzes them using a generative model. This analysis generates optimal activity candidates based on the user's current emotional state and past history.

[0778] The generated activity candidates are further refined using the user's persona information. The server sends the refined activity candidates to the device, which then presents them to the user. The user can then select an activity that they feel emotionally satisfied with. In this process, it is also possible to provide an interface that aligns with the user's emotions by leveraging the real-time feedback provided by the emotion engine.

[0779] The selected activity is matched by the server with the necessary resources and collaborators. As a concrete example, consider a scenario where person A wants to find a new hobby and uses the system. As A is inputting information, the emotion engine analyzes his smile and tone of voice. Based on this emotion data, the server suggests art workshops and local volunteer activities that A might enjoy. A chooses an art workshop, and it is expected that this activity will provide emotional satisfaction and a sense of fulfillment.

[0780] Thus, the invention aims to enhance the quality of life by understanding and responding to the user's emotions and suggesting more appropriate activities.

[0781] The following describes the processing flow.

[0782] Step 1:

[0783] The user enters their hobbies, interests, work history, and new activities they would like to try into the device. The device's camera and microphone simultaneously transmit the user's facial expressions and voice to the emotion engine.

[0784] Step 2:

[0785] The emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is encrypted and sent to the server.

[0786] Step 3:

[0787] The server preprocesses the received user data and sentiment data, removing noise and preparing it for analysis.

[0788] Step 4:

[0789] The server uses a generative model to analyze user data in detail. This model generates activity suggestions that take into account the user's emotional state and past trends.

[0790] Step 5:

[0791] The generated activity candidates are further refined based on persona information. During this process, emotional data is also considered, and activities that enhance emotional satisfaction are prioritized.

[0792] Step 6:

[0793] The server sends a selection of activity options to the device. The device presents these options using an interface tailored to the user's emotional state. The user can then select an activity based on their interests and emotional state.

[0794] Step 7:

[0795] Based on the user's selection, the server matches them with resources, participants, or related information to support their activity and provides the necessary information to the terminal.

[0796] Step 8:

[0797] The user performs the selected activity and enters the results and impressions of the experience into the device. This information is sent to the server as feedback.

[0798] Step 9:

[0799] The server analyzes the collected feedback data and continuously improves the generative model and sentiment engine. This process improves the accuracy of future suggestions and the quality of the user experience.

[0800] (Example 2)

[0801] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0802] A challenge exists in finding appropriate activities that enhance emotional satisfaction for older adults after they have retired from their working lives. In particular, there is a need for methods to improve life satisfaction by recommending activities that take into account the individual emotional state and attribute information of older adults.

[0803] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0804] In this invention, the server includes means for inputting and collecting attribute information from the user via a data terminal, means for analyzing the user's emotions in real time and acquiring emotion information, and means for generating activity candidates suitable for the user using a generative model. This makes it possible to provide personalized activity suggestions based on the user's emotions and attributes.

[0805] A "data terminal" is a device used by users to input information and collect emotional data.

[0806] "Attribute information" refers to personal information about a user, such as their hobbies, interests, and work history.

[0807] An "imaging device" is a device used to acquire images or videos.

[0808] A "voice input device" is a device used to acquire voice data.

[0809] "Emotional information" refers to data about emotions analyzed from the user's facial expressions and voice.

[0810] A "server" is a centralized management system that processes and analyzes data sent by users.

[0811] A "generative model" is an algorithm that analyzes user data and generates optimal activity candidates.

[0812] "Activity options" refer to a set of activity choices presented to the user.

[0813] "Personal characteristics data" refers to information based on a user's past behavior and preferences.

[0814] "Resources" refer to elements such as materials and time necessary to carry out an activity.

[0815] A "collaborator" refers to a third party who provides assistance in realizing an activity.

[0816] "Response data" refers to feedback information obtained from users after an activity has been carried out.

[0817] "Protection processing" refers to encryption or security technologies used to protect information from unauthorized access.

[0818] This system helps older adults find activities that provide emotional satisfaction after they have retired from their working lives. The system is primarily implemented with a configuration that includes users, terminals, a server, and an emotion engine.

[0819] First, the user enters attribute information based on their personal information using a terminal. This terminal provides a user interface for entering information, where the user enters information about their hobbies, interests, past work experience, and desired lifestyle. The terminal is also equipped with input devices such as a camera and microphone, which are used by the emotion engine.

[0820] The device uses these features to capture the user's facial expressions and voice, acquiring emotional information in real time. The emotion engine analyzes this information to obtain information about the user's emotional state. This information is then transmitted from the device to the server.

[0821] Next, the server analyzes the attribute and emotional information it receives. Using a generative AI model, the server analyzes this information and generates the most suitable activity candidates for the user based on their current emotional state and past information.

[0822] The generated activity suggestions are further refined based on personal characteristics data. The server sends this refined information to the device, which then presents it to the user. The user can then select from the presented activity suggestions that they feel emotionally satisfied with.

[0823] For selected activities, the server coordinates the necessary resources and collaborators, thereby supporting the implementation of the activity.

[0824] As a concrete example, the prompt might say, "Tell me how to analyze the user's current emotions and suggest activities that match their hobbies and interests."

[0825] The implementation of this system is expected to improve users' quality of life by enabling activity suggestions based on individual emotions and attribute information.

[0826] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0827] Step 1:

[0828] The user uses the device to input attribute information about their hobbies, interests, work history, and desired lifestyle. The device receives this information as text data through the user interface. Specifically, input fields are displayed on a form screen, and the user enters the information using the keyboard or touch input.

[0829] Step 2:

[0830] The device uses its built-in camera and microphone to record the user's facial expressions and voice, acquiring emotional data. An emotion engine processes this data, analyzing emotional information in real time. Input is real-time audio and video, while output is parameters indicating emotion. The camera and microphone operate automatically to avoid interfering with user interaction.

[0831] Step 3:

[0832] The device sends the collected attribute and sentiment information to the server. At this stage, the data is compiled in JSON format and securely transferred to the server over the internet. Specifically, a communication module embedded in the device packets the data and transmits it.

[0833] Step 4:

[0834] The server preprocesses the received data and inputs it into the generated AI model. Preprocessing involves data cleaning and normalization, preparing the data for analysis by the AI ​​model. The output is a list of potential activities, and the process involves parallel database access and model inference.

[0835] Step 5:

[0836] The server narrows down the generated activity candidates based on personal characteristics data. Past selection history and preference parameters are considered to extract the most suitable activity. The output is an optimized activity list, and this process is performed through algorithmic scoring.

[0837] Step 6:

[0838] The terminal presents the user with activity options sent from the server. The terminal displays a UI in card or list format that visually represents the activities. The user can then make the optimal selection. The output is the user's selection, and the specific action is updating the user interface display.

[0839] Step 7:

[0840] The server matches users with the necessary resources and collaborators based on their selections. Based on these selections, activity preparations are initiated through external APIs and database integrations. These operations include resource reservations and notifications to relevant parties.

[0841] (Application Example 2)

[0842] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0843] Finding ways for older adults to enhance their emotional well-being after ending their working lives is challenging. Furthermore, there is a lack of systems that suggest activities based on individual preferences and interests, and then optimize those activities based on emotional responses.

[0844] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0845] In this invention, the server includes means for acquiring information such as preferences, interests, and experiences from the user; means for recognizing emotions from the user's voice and facial expressions using emotion analysis technology and optimizing activity candidates using that information; and means for matching the selected activity candidates with resources and other collaborators to realize those activities. This makes it possible to propose individually optimized activities to the user and to select emotionally satisfying activities.

[0846] "Preferences" refer to a user's personal enjoyment of specific hobbies or activities.

[0847] "Interest" refers to a user's interest in or desire to engage with a particular field or topic.

[0848] "Experience" refers to information about a user's past activities, work history, and other related information.

[0849] "Emotional analysis technology" is a technology that determines a user's emotions and psychological state by analyzing their voice and facial expressions.

[0850] "Resources" refer to the material or human support necessary to realize an activity.

[0851] A "collaborator" is another participant or partner necessary to carry out the proposed activity together.

[0852] A "user interface" refers to the visual and operational elements that allow a user to interact with a system.

[0853] "Optimization" is the process of adjusting choices and activities to the most suitable form based on the individual user's preferences and emotions.

[0854] This invention is a system that helps elderly people find and select activities that provide them with emotional satisfaction. The main components of the system are a user terminal, a server, a generative AI model, and an interface that utilizes emotion analysis technology.

[0855] Users input information about their preferences, interests, and experiences through a device. This device is equipped with a camera and microphone, allowing it to collect voice and facial expression data during information input. This enables emotion analysis technology to determine the user's emotions and provide real-time feedback.

[0856] The server processes the received user information and emotional data, and uses a generative AI model to generate appropriate activity candidates. This model provides personalized activities based on the user's past activity history and preferences. The generated activity candidates are further refined based on attribute information and presented as options optimized for the user's emotional state.

[0857] When a user selects an activity from the presented options, the server matches them with the necessary resources and collaborators to accomplish that activity. Furthermore, the user interface dynamically changes based on the sentiment analysis results, providing an intuitive and emotionally satisfying user experience.

[0858] For example, if a user is smiling while searching for a new painting class, the system will detect this positive emotion and present a wider range of art workshop options. A possible prompt to input into the generative AI model would be: "Please enter user information below for the activity recommendation system and analyze the emotion data."

[0859] This allows users to actually experience personalized activity suggestions, and the activity choices can be emotionally fulfilling.

[0860] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0861] Step 1:

[0862] The user inputs information about their preferences, interests, and experiences using the device. The camera and microphone collect voice and facial expressions in real time, and this data is sent to the device. The input data is pre-processed to format it and prepare it for transmission to the server.

[0863] Step 2:

[0864] The server analyzes the received user information and voice / facial expression data. Using emotion analysis technology, it recognizes emotions from voice tone and facial expressions, identifying the user's current emotional state. The emotional information is then formatted into a dataset for input into an AI model.

[0865] Step 3:

[0866] The server uses a generative AI model to generate activity suggestions best suited to the user. Based on the input data, the model creates a recommendation list of activities that match the user's interests and past history. The generated recommendation list is further filtered using the user's attribute information to provide an optimized activity list as output.

[0867] Step 4:

[0868] The server sends filtered activity candidates to the terminal and presents them to the user. The terminal displays a dynamic user interface that takes the user's emotional information into account, adjusting the visual effects and operation methods appropriately according to the user's emotions. The user makes a selection from the activity candidates.

[0869] Step 5:

[0870] The server matches the user with the resources and collaborators necessary to realize the activity selected by the user. It identifies the partners and materials needed for the activity and provides the user with guidance and support information for preparation. The selection results are recorded throughout the system as the final output.

[0871] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0872] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0873] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0874] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0875] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0876] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0877] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0878] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0879] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0880] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0881] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0882] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0883] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0884] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0885] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0886] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0887] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0888] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0889] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0890] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0891] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0892] The following is further disclosed regarding the embodiments described above.

[0893] (Claim 1)

[0894] A means of inputting and collecting data from users such as hobbies, interests, and work history,

[0895] A means for analyzing the aforementioned data and generating suitable activity candidates for the user using a generative model,

[0896] A means to further narrow down the aforementioned activity candidates based on persona information,

[0897] A means of presenting users with a narrowed-down list of activity options and allowing them to select from them,

[0898] A means of matching selected activity candidates with resources and other participants,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, further comprising means for collecting feedback after the implementation of an activity and for improving the generative model.

[0902] (Claim 3)

[0903] The system according to claim 1, comprising means for encrypting user data and securely transmitting it to a server.

[0904] "Example 1"

[0905] (Claim 1)

[0906] A means of inputting and collecting information from users such as hobbies, interests, and work history,

[0907] A means for encrypting the aforementioned information using a standard security protocol,

[0908] A means for analyzing encrypted information and generating activity candidates using machine learning algorithms,

[0909] A means for further narrowing down the aforementioned activity candidates based on individual information,

[0910] A means of visually presenting and making selectable activity options,

[0911] The resources and means of engaging with participants to realize the selected activity candidates,

[0912] A system that includes this.

[0913] (Claim 2)

[0914] The system according to claim 1, further comprising means for collecting feedback after the implementation of an activity and for improving the machine learning algorithm.

[0915] (Claim 3)

[0916] The system according to claim 1, comprising means for encrypting user information and securely transmitting it to a computing device.

[0917] "Application Example 1"

[0918] (Claim 1)

[0919] A means of inputting and collecting attribute data from users, such as preferences, interests, and background,

[0920] A means for analyzing the aforementioned attribute data and generating activity candidates suitable for the user using a learning model,

[0921] A means to further narrow down the aforementioned activity candidates based on personal information,

[0922] A means of presenting users with a narrowed-down list of activity options and allowing them to select from them,

[0923] Means for coordinating resources and other participants to realize the selected activity candidates,

[0924] A means for visually displaying the activity candidates using the user's portable visual device,

[0925] A system that includes this.

[0926] (Claim 2)

[0927] The system according to claim 1, further comprising means for collecting feedback after implementation and improving the learning model.

[0928] (Claim 3)

[0929] The system according to claim 1, comprising means for encrypting user attribute data and securely transmitting it to a storage device.

[0930] "Example 2 of combining an emotion engine"

[0931] (Claim 1)

[0932] A means of inputting and collecting attribute information from users via a data terminal,

[0933] A means for analyzing the user's emotions in real time using an imaging device and an audio input device mounted on the aforementioned terminal, and acquiring emotional information,

[0934] A means for sending the attribute information and emotion information to a server and performing preprocessing,

[0935] A means for generating activity candidates suitable for the user based on the information using the aforementioned generation model,

[0936] A means to further narrow down the aforementioned activity candidates based on personal characteristics data,

[0937] A means of presenting a narrowed-down list of activity options to the end user and allowing them to select from them,

[0938] Means for aligning resources and collaborators to realize the selected activity candidates,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, further comprising means for collecting response data after the activity has been carried out and for improving the generation model.

[0942] (Claim 3)

[0943] The system according to claim 1, comprising means for protecting and processing user information and securely transmitting it to an information server.

[0944] "Application example 2 when combining with an emotional engine"

[0945] (Claim 1)

[0946] Means of obtaining information from users such as preferences, interests, and experiences,

[0947] A means for analyzing the aforementioned information and generating suitable activity candidates for the user using a generative model,

[0948] A means for further narrowing down the aforementioned activity candidates based on attribute information,

[0949] A means of presenting users with a narrowed-down list of activity options and allowing them to select from them,

[0950] A means of matching the selected activity candidates with resources and other collaborators,

[0951] A means of recognizing emotions from a user's voice and facial expressions using emotion analysis technology, and using that information to optimize activity candidates,

[0952] Means for adapting the user interface in real time based on the aforementioned emotional information,

[0953] A system that includes this.

[0954] (Claim 2)

[0955] The system according to claim 1, further comprising means for collecting evaluations after the implementation of an activity and for improving the generative model.

[0956] (Claim 3)

[0957] The system according to claim 1, comprising means for encrypting user information and securely transmitting it to a server. [Explanation of Symbols]

[0958] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of inputting and collecting attribute data from users, such as preferences, interests, and background, A means for analyzing the aforementioned attribute data and generating activity candidates suitable for the user using a learning model, A means to further narrow down the aforementioned activity candidates based on personal information, A means of presenting users with a narrowed-down list of activity options and allowing them to select from them, Means for coordinating resources and other participants to realize the selected activity candidates, A means for visually displaying the activity candidates using the user's portable visual device, A system that includes this.

2. The system according to claim 1, further comprising means for collecting feedback after implementation and improving the learning model.

3. The system according to claim 1, comprising means for encrypting user attribute data and securely transmitting it to a storage device.

Images