system

Abstract

The system according to this embodiment aims to provide an optimized life plan for an individual and to offer continuous follow-up and optimization suggestions. [Solution] The system according to the embodiment comprises an extraction unit, a construction unit, a generation unit, an optimization unit, a presentation unit, and a follow-up unit. The extraction unit extracts user information. The construction unit constructs a knowledge graph based on the information extracted by the extraction unit. The generation unit generates a life plan based on the knowledge graph constructed by the construction unit. The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. The presentation unit presents multiple scenarios improved by the optimization unit. The follow-up unit provides continuous follow-up and optimization suggestions based on the scenarios presented by the presentation unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system. [[ID=**7**]]

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In the prior art, there is a problem that it is difficult to provide a life design optimized for an individual, and there is a lack of continuous follow-up and optimization proposals.

[0005] The system according to the embodiment aims to provide a life design optimized for an individual and perform continuous follow-up and optimization proposals.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an extraction unit, a construction unit, a generation unit, an optimization unit, a presentation unit, and a follow-up unit. The extraction unit extracts user information. The construction unit constructs a knowledge graph based on the information extracted by the extraction unit. The generation unit generates a life plan based on the knowledge graph constructed by the construction unit. The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. The presentation unit presents multiple scenarios improved by the optimization unit. The follow-up unit provides continuous follow-up and optimization suggestions based on the scenarios presented by the presentation unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide an optimized life plan for an individual and offer continuous follow-up and optimization suggestions. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The life planning simulation system according to an embodiment of the present invention is a system that uses AI to provide a life planning simulation optimized for an individual. This life planning simulation system can explore life possibilities through dialogue between the user and the AI ​​and generate and compare multiple life scenarios. Furthermore, the life planning simulation system can provide continuous follow-up and optimization suggestions. For example, the life planning simulation system allows the user to initiate a dialogue with the AI ​​through a dialogue interface. The AI ​​extracts user information using natural language processing technology and constructs a knowledge graph. Based on this knowledge graph, the AI ​​generates an optimal life plan for the user. The generated life plan is continuously improved using reinforcement learning and Bayesian optimization. Next, the AI ​​generates multiple life scenarios and presents them to the user. The user can compare these scenarios and select the one that is best suited to them. Based on the selected scenario, the AI ​​provides continuous follow-up and optimization suggestions. Features of this service include personalized life planning, presentation of multiple scenarios, continuous support, secure data management, and an intuitive user interface. Generative AI technologies such as natural language processing, knowledge graphs, reinforcement learning, and Bayesian optimization are also utilized. The service flow involves the user interacting with the AI ​​through a dialogue interface, and user information being extracted through natural language processing. Next, a knowledge graph is constructed, and a life plan is generated. The generative model is improved using reinforcement learning and Bayesian optimization, and the optimal life plan is explored. Finally, multiple scenarios are presented to the user. This service has market potential due to the arrival of the 100-year life era, the development of AI and big data analysis technologies, and the increasing demand for personalized services. Possible revenue models include subscriptions (1,000 yen / month), premium plans (2,000 yen / month), corporate plans, partnerships, and data analysis. The vision of this service is to realize a society where everyone can live a life true to themselves, by providing personalized support through AI. It aims to balance the pursuit of individual happiness with the development of society as a whole, and to improve the quality of people's lives.This allows the life planning simulation system to provide users with a life plan optimized for them and offer ongoing support.

[0029] The life planning simulation system according to this embodiment comprises an extraction unit, a construction unit, a generation unit, an optimization unit, a presentation unit, and a follow-up unit. The extraction unit extracts user information. The extraction unit extracts user information using, for example, natural language processing technology. The extraction unit can extract information such as personal information, behavioral data, and interests from the user's dialogue content and input data. For example, the extraction unit analyzes text data entered by the user and extracts important keywords and phrases. The extraction unit can also analyze the user's dialogue history and extract past behavioral patterns and interests. Furthermore, the extraction unit can collect the user's social media activity and online behavioral data to understand the user's interests. The construction unit constructs a knowledge graph based on the information extracted by the extraction unit. The construction unit constructs a knowledge graph that visually represents user information by defining nodes and edges, for example. The construction unit can represent the user's personal information and behavioral data as nodes and their relationships as edges. For example, the construction unit represents information such as the user's occupation, hobbies, and life events as nodes, and their relationships as edges. The construction unit can also dynamically update the knowledge graph based on the user's past behavioral data and dialogue history. The generation unit generates a life plan based on the knowledge graph constructed by the construction unit. For example, the generation unit generates a career plan and a life event plan based on the user's goals and desires. The generation unit can generate and present multiple life scenarios based on the user's information. For example, the generation unit generates multiple scenarios that take into account the user's occupational choices and the timing of life events. The generation unit can also generate a personalized life plan based on the user's interests and values. The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. For example, the optimization unit improves the life plan based on user feedback using reinforcement learning algorithms. The optimization unit can search for the optimal life plan based on the user's choices and actions. For example, the optimization unit collects feedback on the scenario selected by the user and improves the life plan based on that feedback.The optimization unit can also use Bayesian optimization to adjust multiple parameters and explore the optimal life plan. The presentation unit presents the user with multiple scenarios improved by the optimization unit. The presentation unit can present multiple scenarios to the user using, for example, a visually appealing interface. The presentation unit can visually display the features and benefits of each scenario to make it easier for the user to compare them. For example, the presentation unit can display the career plan and timing of life events for each scenario using graphs and charts. The presentation unit can also provide an intuitive interface for the user when selecting a scenario. The follow-up unit provides continuous follow-up and optimization suggestions based on the scenarios presented by the presentation unit. For example, the follow-up unit provides regular follow-up based on the scenario selected by the user. The follow-up unit can collect the user's progress and feedback and make optimization suggestions based on that. For example, the follow-up unit monitors the user's progress toward their set goals and provides advice and support as needed. The follow-up unit can also re-evaluate the life plan and make optimization suggestions in response to the user's life events and changes in their environment. As a result, the life planning simulation system according to the embodiment can efficiently extract user information, construct a knowledge graph, generate a life plan, optimize it, present scenarios, and provide follow-up support.

[0030] The extraction unit extracts user information. For example, it uses natural language processing (NLP) techniques to extract user information. Specifically, the extraction unit analyzes text data entered by the user and extracts important keywords and phrases. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis, and by combining these, it can understand the user's intentions and emotions. For example, if a user enters "I want to work abroad in the future," the extraction unit extracts the keywords "future," "overseas," and "want to work," understanding the user's aspirations. The extraction unit can also analyze the user's conversation history to extract past behavioral patterns and interests. For example, if a user previously said they were "interested in programming," this information is recorded and used to inform future career plans. Furthermore, the extraction unit can collect user social media activity and online behavior data to understand the user's interests. For example, if a user frequently posts about "travel" or "cooking," this information is used to identify the user's hobbies and interests. This allows the extraction unit to collect comprehensive data from diverse user sources and accurately understand the user's needs and desires.

[0031] The construction unit builds a knowledge graph based on the information extracted by the extraction unit. For example, the construction unit defines nodes and edges to build a knowledge graph that visually represents user information. Specifically, nodes represent the user's personal information and behavioral data, and edges indicate their relationships. For example, information such as the user's occupation, hobbies, and life events are represented as nodes, and their relationships are represented as edges. If the user is an "engineer" and interested in "programming," this information is represented as nodes, and an edge is drawn between "engineer" and "programming." The construction unit can also dynamically update the knowledge graph based on the user's past behavioral data and conversation history. For example, if the user becomes interested in "data science," that information is added, and the existing nodes and edges are updated. Furthermore, the construction unit can integrate data from different sources to build a more detailed and accurate knowledge graph. For example, it can integrate the user's social media activity and online behavioral data to more accurately understand the user's interests and behavioral patterns. This allows the construction unit to visually and dynamically represent user information and provide the foundation necessary for subsequent processing.

[0032] The generation unit generates life plans based on the knowledge graph constructed by the construction unit. For example, the generation unit generates career plans and life event plans based on the user's goals and desires. Specifically, the generation unit can generate and present multiple life scenarios to the user based on the user's information. For example, if a user desires to "work abroad in the future," the generation unit will generate a scenario based on that desire, taking into account overseas career plans, necessary skills, and the timing of life events. The generation unit can also generate personalized life plans based on the user's interests and values. For example, if a user is interested in "programming" and "travel," it will propose a career plan and life events that satisfy both. Furthermore, the generation unit considers the user's past behavioral data and dialogue history to generate realistic and actionable scenarios. For example, if a user was previously interested in "data science," it will propose a data science-related career plan based on that information. In this way, the generation unit can generate and provide users with diverse life scenarios based on their desires and interests.

[0033] The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. For example, the optimization unit uses reinforcement learning algorithms to improve the life plan based on user feedback. Specifically, it collects feedback on the scenario selected by the user and improves the life plan based on that feedback. For example, if a user provides feedback that "this career plan is not realistic," the optimization unit generates a new scenario based on that information. The optimization unit can also use Bayesian optimization to adjust multiple parameters and explore the optimal life plan. For example, it adjusts the optimal career plan and the timing of life events based on the user's interests, values, and past behavioral data. Furthermore, the optimization unit can explore the optimal life plan based on the user's choices and actions. For example, if a user is interested in "data science," it proposes a career plan that makes the most of that interest. In this way, the optimization unit can continuously improve the life plan based on user feedback and behavioral data and provide the user with the optimal scenario.

[0034] The presentation unit presents the user with multiple scenarios improved by the optimization unit. For example, the presentation unit presents multiple scenarios using a visually appealing interface. Specifically, it displays career plans and the timing of life events for each scenario using graphs and charts, making it easy for users to compare scenarios. For example, scenario A might show "working overseas at age 30," while scenario B might show "starting a business at age 35," visually displaying the characteristics and benefits of each scenario. The presentation unit can also provide an intuitive interface for users to select scenarios. For example, it might use drag-and-drop functionality or sliders to allow users to easily customize scenarios. Furthermore, the presentation unit can reflect user feedback in real time and update the scenario content. For example, if a user provides feedback such as "I want this scenario to be more flexible," the presentation unit regenerates the scenario based on that information. In this way, the presentation unit can present scenarios visually and intuitively to the user, helping them make the best choice.

[0035] The follow-up unit provides continuous follow-up and optimization suggestions based on the scenarios presented by the presentation unit. For example, the follow-up unit performs regular follow-up based on the scenario selected by the user. Specifically, the follow-up unit collects the user's progress and feedback and makes optimization suggestions based on this information. For example, it monitors the user's progress toward their set goals and provides advice and support as needed. The follow-up unit can also re-evaluate the user's life plan and make optimization suggestions in response to the user's life events and changes in their environment. For example, if a user experiences a new life event such as "starting a family," the follow-up unit re-evaluates the life plan based on this information and proposes a new scenario. Furthermore, the follow-up unit can continuously improve the overall system performance based on user feedback. For example, if a user provides feedback that "this scenario is not realistic," the system's algorithm is adjusted based on that information to generate a more realistic scenario. In this way, the follow-up unit can provide the user with continuous support and optimization suggestions, helping them to achieve their goals.

[0036] The Data Management Department can perform secure data management. For example, the Data Management Department can protect user data using encryption technology. The Data Management Department can encrypt users' personal information and behavioral data to protect them from unauthorized access. For example, the Data Management Department can encrypt data using encryption algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman). The Data Management Department can also perform access control and manage users' access rights to data. For example, the Data Management Department can set different access rights for each user, restricting data viewing and editing. Furthermore, the Data Management Department can regularly back up data to prepare for data loss or corruption. For example, the Data Management Department can use cloud storage to back up data and restore data in the event of a disaster or system failure. In this way, the Data Management Department can securely manage user data and improve data security.

[0037] The interface unit can provide an intuitive user interface. For example, the interface unit can conduct usability testing and design an interface that is easy for users to use. The interface unit can improve the interface design based on user feedback. For example, the interface unit can design button placements and navigation menus that are easy for users to operate. The interface unit can also provide a visually appealing interface based on design guidelines. For example, the interface unit can select colors and fonts and adjust the layout to provide an interface that users can operate intuitively. Furthermore, the interface unit can adopt responsive design to provide an interface that is compatible with different devices and screen sizes. For example, the interface unit can design an interface that can be comfortably operated on various devices such as smartphones, tablets, and personal computers. In this way, the interface unit can provide an interface that is easy for users to use and improve the user experience.

[0038] The extraction unit can extract user information using natural language processing. For example, the extraction unit can analyze the user's input text using morphological analysis and extract important keywords and phrases. The extraction unit can extract information such as personal information, behavioral data, and interests from the user's dialogue content and input data. For example, the extraction unit analyzes the text data entered by the user and extracts important keywords and phrases. The extraction unit can also analyze the grammatical structure of the user's input text using grammatical analysis and understand the relationships between information. Furthermore, the extraction unit can understand the meaning of the user's input text using semantic analysis and extract information. For example, the extraction unit can extract the user's goals and desires from the user's dialogue content and reflect them in their life plan. In this way, the extraction unit can improve the accuracy of user information extraction by using natural language processing.

[0039] The optimization unit can improve the generative model using reinforcement learning and Bayesian optimization. For example, the optimization unit can improve the life plan based on user feedback using reinforcement learning algorithms. The optimization unit can explore the optimal life plan based on user choices and actions. For example, the optimization unit collects feedback on the scenario selected by the user and improves the life plan based on that feedback. The optimization unit can also use Bayesian optimization to adjust multiple parameters and explore the optimal life plan. For example, the optimization unit can use a Gaussian process to explore the parameter space of the life plan and find the optimal parameters. Furthermore, the optimization unit can use an acquisition function to find the optimal life plan while balancing exploration and utilization. In this way, the optimization unit can improve the accuracy of the generative model by using reinforcement learning and Bayesian optimization.

[0040] The presentation unit can generate and present multiple life scenarios to the user. For example, it can present multiple scenarios to the user using a visually appealing interface. The presentation unit can visually display the features and benefits of each scenario to make it easier for the user to compare them. For example, it can display career plans and the timing of life events for each scenario using graphs and charts. Furthermore, the presentation unit can provide an intuitive interface for the user to select a scenario. In addition, the presentation unit can visually display the simulation results of each scenario, making it easier for the user to understand the impact of each scenario. For example, it can display changes in income and quality of life for each scenario using graphs and charts. By presenting multiple scenarios, the presentation unit enables the user to select the most suitable one.

[0041] The follow-up department can provide continuous follow-up and optimization suggestions based on the selected scenario. For example, the follow-up department can conduct regular follow-ups based on the scenario selected by the user. The follow-up department can collect user progress and feedback and make optimization suggestions based on this. For example, the follow-up department can monitor the user's progress toward the goals they have set and provide advice and support as needed. The follow-up department can also re-evaluate the life plan and make optimization suggestions in response to the user's life events and changes in their environment. Furthermore, based on user feedback, the follow-up department can identify areas for improvement in the life plan and continuously optimize it. In this way, the follow-up department can support the user's life plan by providing continuous follow-up and optimization suggestions.

[0042] The extraction unit can analyze the user's past conversation history and select the optimal information extraction method. For example, the extraction unit can extract information using a similar method based on the conversation style the user has preferred in the past. The extraction unit can save the user's conversation history and analyze it using natural language processing techniques. For example, the extraction unit can analyze the content of the user's past conversations and extract specific keywords or phrases. The extraction unit can also consider topics the user has avoided in the past and extract information in a way that avoids them. Furthermore, the extraction unit can prioritize the extraction of specific keywords from the user's past conversation history. For example, the extraction unit can extract relevant information based on keywords the user has frequently mentioned in the past. In this way, the extraction unit can select the optimal information extraction method by analyzing past conversation history.

[0043] The extraction unit can filter information based on the user's current life circumstances and areas of interest during the information extraction process. For example, if the user is seeking information related to their current job, the extraction unit will prioritize extracting information related to that field. The extraction unit can understand the user's life circumstances and areas of interest and filter information accordingly. For example, if the user has started a new hobby, the extraction unit will extract information related to that hobby. The extraction unit can also filter and extract relevant information based on the user's life circumstances (e.g., moving, changing jobs). Furthermore, the extraction unit can prioritize extracting highly relevant information based on the user's areas of interest. For example, the extraction unit will extract information related to topics the user is interested in. In this way, the extraction unit can extract more relevant information by filtering information based on the user's life circumstances and areas of interest.

[0044] The extraction unit can prioritize extracting highly relevant information by considering the user's geographical location during information extraction. For example, if the user is in a specific region, the extraction unit will prioritize extracting information related to that region. The extraction unit can collect the user's geographical location information and filter information based on it. For example, if the user is traveling, the extraction unit will extract information related to the travel destination. Also, if the user is planning to move, the extraction unit can prioritize extracting information about the new region. Furthermore, the extraction unit can prioritize extracting highly relevant information based on the user's geographical location. For example, the extraction unit will extract information related to events and news in the region where the user is currently located. In this way, the extraction unit can prioritize extracting highly relevant information by considering geographical location information.

[0045] The extraction unit can analyze a user's social media activity and extract relevant information during the information extraction process. For example, the extraction unit can extract information related to topics that the user frequently mentions on social media. The extraction unit can collect a user's social media activity and analyze it using natural language processing techniques. For example, the extraction unit can analyze the content of a user's social media posts and extract relevant information. The extraction unit can also extract relevant information based on information shared by the user's social media friends. Furthermore, the extraction unit can extract information that the user might be interested in from their social media activity. For example, the extraction unit can extract information related to topics that the user is interested in. In this way, the extraction unit can extract relevant information by analyzing social media activity.

[0046] The construction unit can select the optimal construction method when building a knowledge graph by referring to the user's past behavior data. For example, the construction unit can build a knowledge graph containing similar information based on information that the user has previously preferred. The construction unit can store the user's behavior data and analyze it using natural language processing techniques. For example, the construction unit can analyze the user's past behavior data and extract specific patterns. The construction unit can also extract specific patterns from the user's past behavior data and build a knowledge graph based on them. Furthermore, the construction unit can analyze the user's past behavior data and select the most efficient construction method. For example, the construction unit can define the optimal nodes and edges based on the user's past behavior data. This allows the construction unit to select the optimal knowledge graph construction method by referring to past behavior data.

[0047] The builder can customize the knowledge graph construction method based on the user's current life situation when building the knowledge graph. For example, if a user starts a new job, the builder will build a knowledge graph that includes information related to that job. The builder can understand the user's life situation and customize the knowledge graph based on that. For example, if a user is planning to move, the builder will build a knowledge graph that includes information about the new area. The builder can also build a knowledge graph that includes relevant information based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the builder can prioritize including highly relevant information in the knowledge graph based on the user's life situation. For example, the builder will prioritize adding nodes and edges related to the user's current life situation. This allows the builder to provide more relevant information by customizing the knowledge graph based on the current life situation.

[0048] The builder can select the optimal build method when constructing a knowledge graph, taking into account the user's geographical location. For example, if the user is in a specific region, the builder will construct a knowledge graph that includes information related to that region. The builder can collect the user's geographical location information and customize the knowledge graph based on it. For example, if the user is traveling, the builder will construct a knowledge graph that includes information related to the travel destination. Also, if the user is planning to move, the builder can construct a knowledge graph that includes information about the new region. Furthermore, the builder can prioritize including highly relevant information in the knowledge graph based on the user's geographical location. For example, the builder will include information related to events and news in the user's current location in the knowledge graph. In this way, the builder can provide highly relevant information by taking geographical location into consideration.

[0049] The construction unit can analyze a user's social media activity and propose construction methods when building a knowledge graph. For example, the construction unit can build a knowledge graph that includes information related to topics that the user frequently mentions on social media. The construction unit can collect a user's social media activity and analyze it using natural language processing techniques. For example, the construction unit can analyze the content of a user's social media posts and include relevant information in the knowledge graph. The construction unit can also include relevant information in the knowledge graph based on information shared by the user's social media friends. Furthermore, the construction unit can include information that the user might be interested in from their social media activity in the knowledge graph. For example, the construction unit can include information related to topics that the user is interested in in the knowledge graph. In this way, the construction unit can provide highly relevant information by analyzing social media activity.

[0050] The generation unit can select the optimal generation method by referring to the user's past behavioral data when generating a life plan. For example, the generation unit can generate a similar plan based on a life plan the user has preferred in the past. The generation unit can store the user's behavioral data and analyze it using natural language processing technology. For example, the generation unit can analyze the user's past behavioral data and extract specific patterns. The generation unit can also extract specific patterns from the user's past behavioral data and generate a life plan based on them. Furthermore, the generation unit can analyze the user's past behavioral data and select the most efficient generation method. For example, the generation unit can set optimal life plan parameters based on the user's past behavioral data. This allows the generation unit to select the optimal life plan generation method by referring to past behavioral data.

[0051] The generation unit can customize the generation method based on the user's current living situation when generating a life plan. For example, if the user starts a new job, the generation unit will generate a life plan related to that job. The generation unit can understand the user's living situation and customize the life plan based on it. For example, if the user is planning to move, the generation unit will generate a life plan based on the new area. The generation unit can also generate a life plan based on the user's current living situation (e.g., marriage, childbirth). Furthermore, the generation unit can prioritize including highly relevant information in the life plan based on the user's living situation. For example, the generation unit will prioritize adding elements related to the user's current living situation. In this way, the generation unit can provide more relevant information by customizing the life plan based on the current living situation.

[0052] The generation unit can select the optimal generation method when generating a life plan, taking into account the user's geographical location information. For example, if the user is in a specific region, the generation unit will generate a life plan related to that region. The generation unit can collect the user's geographical location information and customize the life plan based on it. For example, if the user is traveling, the generation unit will generate a life plan related to the travel destination. Also, if the user is planning to move, the generation unit can generate a life plan based on the new region. Furthermore, the generation unit can prioritize including highly relevant information in the life plan based on the user's geographical location information. For example, the generation unit will include information related to events and news in the user's current location in the life plan. In this way, the generation unit can provide highly relevant information by taking geographical location information into consideration.

[0053] The generation unit can analyze the user's social media activity and propose generation methods when generating a life plan. For example, the generation unit can generate a life plan related to topics that the user frequently mentions on social media. The generation unit can collect the user's social media activity and analyze it using natural language processing techniques. For example, the generation unit can analyze the content of the user's social media posts and include relevant information in the life plan. The generation unit can also include relevant information in the life plan based on information shared by the user's social media friends. Furthermore, the generation unit can include information that the user might be interested in from their social media activity in the life plan. For example, the generation unit can include information related to topics that the user is interested in in the life plan. In this way, the generation unit can provide highly relevant information by analyzing social media activity.

[0054] The optimization unit can select the optimal optimization method by referring to the user's past behavior data during optimization. For example, the optimization unit can perform optimization using a similar method based on the user's preferred optimization method in the past. The optimization unit can store the user's behavior data and analyze it using natural language processing technology. For example, the optimization unit can analyze the user's past behavior data and extract specific patterns. The optimization unit can also extract specific patterns from the user's past behavior data and perform optimization based on them. Furthermore, the optimization unit can analyze the user's past behavior data and select the most efficient optimization method. For example, the optimization unit can set optimal optimization parameters based on the user's past behavior data. This allows the optimization unit to select the optimal optimization method by referring to past behavior data.

[0055] The optimization unit can customize the optimization means based on the user's current life situation during optimization. For example, if the user starts a new job, the optimization unit will provide optimization means related to that job. The optimization unit can understand the user's life situation and customize the optimization means based on that. For example, if the user is planning to move, the optimization unit will provide optimization means based on the new area. The optimization unit can also provide relevant optimization means based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the optimization unit can prioritize including highly relevant information in the optimization means based on the user's life situation. For example, the optimization unit will prioritize adding elements related to the user's current life situation. This allows the optimization unit to provide more relevant information by customizing the optimization means based on the current life situation.

[0056] The optimization unit can select the optimal optimization method during optimization by considering the user's geographical location information. For example, if the user is in a specific region, the optimization unit can provide optimization methods related to that region. The optimization unit can collect the user's geographical location information and customize the optimization methods based on it. For example, if the user is traveling, the optimization unit can provide optimization methods related to the travel destination. Also, if the user is planning to move, the optimization unit can provide optimization methods based on the new region. Furthermore, the optimization unit can prioritize including highly relevant information in the optimization methods based on the user's geographical location information. For example, the optimization unit can include information related to events and news in the user's current location in the optimization methods. In this way, the optimization unit can provide highly relevant information by considering geographical location information.

[0057] The optimization unit can analyze the user's social media activity during optimization and propose optimization methods. For example, the optimization unit can provide optimization methods related to topics that the user frequently mentions on social media. The optimization unit can collect the user's social media activity and analyze it using natural language processing technology. For example, the optimization unit can analyze the content of the user's social media posts and include relevant information in the optimization methods. The optimization unit can also provide relevant optimization methods based on information shared by the user's social media friends. Furthermore, the optimization unit can include information that the user might be interested in from their social media activity in the optimization methods. For example, the optimization unit can include information related to topics that the user is interested in in the optimization methods. In this way, the optimization unit can provide highly relevant information by analyzing social media activity.

[0058] The presentation unit can select the optimal presentation method when presenting a scenario by referring to the user's past selection history. For example, the presentation unit can present a scenario using a similar method to those the user has previously preferred. The presentation unit can save the user's selection history and analyze it using natural language processing techniques. For example, the presentation unit can analyze the user's past selection history and extract specific patterns. The presentation unit can also extract specific patterns from the user's past selection history and present a scenario based on them. Furthermore, the presentation unit can analyze the user's past selection history and select the most efficient presentation method. For example, the presentation unit can set optimal scenario presentation parameters based on the user's past selection history. This allows the presentation unit to select the optimal scenario presentation method by referring to past selection history.

[0059] The presentation unit can customize the presentation method based on the user's current life situation when presenting scenarios. For example, if the user has started a new job, the presentation unit will present scenarios related to that job. The presentation unit can understand the user's life situation and customize the scenarios accordingly. For example, if the user is planning to move, the presentation unit will present scenarios based on the new area. The presentation unit can also present relevant scenarios based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the presentation unit can prioritize including highly relevant information in the scenarios based on the user's life situation. For example, the presentation unit will prioritize adding elements related to the user's current life situation. In this way, the presentation unit can provide more relevant information by customizing the scenarios based on the current life situation.

[0060] The presentation unit can select the optimal presentation method when presenting scenarios, taking into account the user's geographical location information. For example, if the user is in a specific region, the presentation unit will present scenarios related to that region. The presentation unit can collect the user's geographical location information and customize scenarios based on it. For example, if the user is traveling, the presentation unit will present scenarios related to their travel destination. Furthermore, if the user is planning to move, the presentation unit can present scenarios based on the new region. In addition, the presentation unit can prioritize including highly relevant information in scenarios based on the user's geographical location information. For example, the presentation unit can include information related to events and news in the user's current location in the scenario. This allows the presentation unit to provide highly relevant information by considering geographical location information.

[0061] The presentation unit can analyze the user's social media activity and propose presentation methods when presenting scenarios. For example, the presentation unit can present scenarios related to topics that the user frequently mentions on social media. The presentation unit can collect the user's social media activity and analyze it using natural language processing techniques. For example, the presentation unit can analyze the content of the user's social media posts and include relevant information in the scenario. The presentation unit can also present relevant scenarios based on information shared by the user's social media friends. Furthermore, the presentation unit can include information that the user might be interested in from their social media activity in the scenario. For example, the presentation unit can include information related to topics that the user is interested in in the scenario. In this way, the presentation unit can provide highly relevant information by analyzing social media activity.

[0062] The follow-up unit can select the optimal follow-up method by referring to the user's past behavioral data during follow-up. For example, the follow-up unit can perform follow-up using a similar method based on the follow-up method the user preferred in the past. The follow-up unit can store the user's behavioral data and analyze it using natural language processing technology. For example, the follow-up unit can analyze the user's past behavioral data and extract specific patterns. The follow-up unit can also extract specific patterns from the user's past behavioral data and perform follow-up based on them. Furthermore, the follow-up unit can analyze the user's past behavioral data and select the most efficient follow-up method. For example, the follow-up unit can set optimal follow-up parameters based on the user's past behavioral data. This allows the follow-up unit to select the optimal follow-up method by referring to past behavioral data.

[0063] The follow-up unit can customize follow-up methods based on the user's current life situation during follow-up. For example, if a user starts a new job, the follow-up unit will provide follow-up related to that job. The follow-up unit can understand the user's life situation and customize follow-up methods based on that. For example, if a user is planning to move, the follow-up unit will provide follow-up based on the new area. The follow-up unit can also provide relevant follow-up based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the follow-up unit can prioritize including highly relevant information in the follow-up methods based on the user's life situation. For example, the follow-up unit will prioritize adding elements related to the user's current life situation. In this way, the follow-up unit can provide more relevant information by customizing the follow-up methods based on the current life situation.

[0064] The follow-up unit can select the optimal follow-up method by considering the user's geographical location information during follow-up. For example, if the user is in a specific region, the follow-up unit will perform follow-up activities related to that region. The follow-up unit can collect the user's geographical location information and customize the follow-up methods based on it. For example, if the user is traveling, the follow-up unit will perform follow-up activities related to the travel destination. Also, if the user is planning to move, the follow-up unit can perform follow-up activities based on the new region. Furthermore, the follow-up unit can prioritize including highly relevant information in the follow-up activities based on the user's geographical location information. For example, the follow-up unit can include information related to events and news in the user's current location in the follow-up activities. In this way, the follow-up unit can provide highly relevant information by considering geographical location information.

[0065] The follow-up unit can analyze the user's social media activity during follow-up and propose follow-up methods. For example, the follow-up unit can perform follow-ups related to topics that the user frequently mentions on social media. The follow-up unit can collect the user's social media activity and analyze it using natural language processing technology. For example, the follow-up unit can analyze the content of the user's social media posts and include relevant information in the follow-up methods. The follow-up unit can also perform relevant follow-ups based on information shared by the user's social media friends. Furthermore, the follow-up unit can include information that the user might be interested in from their social media activity in the follow-up methods. For example, the follow-up unit can include information related to topics that the user is interested in in the follow-up methods. In this way, the follow-up unit can provide highly relevant information by analyzing social media activity.

[0066] The data management department can select the optimal data management method by referring to the user's past data usage history during data management. For example, the data management department can manage data using a similar method based on the data management method the user previously preferred. The data management department can store the user's data usage history and analyze it using natural language processing technology. For example, the data management department can analyze the user's past data usage history and extract specific patterns. The data management department can also extract specific patterns from the user's past data usage history and perform data management based on them. Furthermore, the data management department can analyze the user's past data usage history and select the most efficient data management method. For example, the data management department can set optimal data management parameters based on the user's past data usage history. This allows the data management department to select the optimal data management method by referring to past data usage history.

[0067] The data management department can select the optimal management method when managing data, taking into account the user's geographical location information. For example, if a user is in a specific region, the data management department will manage the data in accordance with the data protection laws of that region. The data management department can collect the user's geographical location information and customize the data management methods based on it. For example, if a user is traveling, the data management department will manage the data in accordance with the data protection laws of the destination. Also, if a user is planning to move, the data management department can manage the data in accordance with the data protection laws of the new region. Furthermore, the data management department can prioritize including highly relevant information in the data management methods based on the user's geographical location information. For example, the data management department can include information related to the data protection laws of the region where the user is currently located in the data management methods. In this way, the data management department can provide highly relevant information by taking geographical location information into consideration.

[0068] The interface unit can select the optimal display method by referring to the user's past operation history when displaying the interface. For example, the interface unit can provide a similar design based on the user's previously preferred interface design. The interface unit can save the user's operation history and analyze it using natural language processing technology. For example, the interface unit can analyze the user's past operation history and extract specific patterns. The interface unit can also extract specific patterns from the user's past operation history and display the interface based on them. Furthermore, the interface unit can analyze the user's past operation history and select the most efficient display method. For example, the interface unit can set optimal interface display parameters based on the user's past operation history. This allows the interface unit to select the optimal interface display method by referring to past operation history.

[0069] The interface unit can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, the interface unit provides a display method that matches the screen size. The interface unit can collect the user's device information and customize the interface display means based on it. For example, if the user is using a tablet, the interface unit provides a display method optimized for a large screen. The interface unit can also provide a concise and highly visible display method if the user is using a smartwatch. Furthermore, the interface unit can prioritize including highly relevant information in the interface display means based on the user's device information. For example, the interface unit includes information related to the characteristics of the device the user is currently using in the interface display means. In this way, the interface unit can provide highly relevant information by taking device information into consideration.

[0070] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0071] The life planning simulation system can also include a hobby management unit that customizes the life plan based on the user's hobbies and interests. For example, the hobby management unit collects data on events and activities the user has participated in in the past to understand their hobbies and interests. This allows it to provide a life plan tailored to the user's hobbies. For instance, if the user is interested in music, it can suggest music-related events and courses. It can also provide information and resources related to a user's desire to start a new hobby. Furthermore, the hobby management unit can provide opportunities for building relationships and networking through shared hobbies. This allows users to enjoy their hobbies while leading a fulfilling life.

[0072] The life planning simulation system can also include a financial management unit that acquires the user's financial data and adjusts the life plan based on their financial situation. The financial management unit, for example, acquires data from the user's bank accounts and credit cards and analyzes income and expenditure patterns. This allows it to provide a life plan tailored to the user's financial situation. For instance, if the user wants to increase their savings, it can offer advice on saving and suggest investments. It can also provide budget management and asset management plans based on the user's financial goals. Furthermore, the financial management unit can adjust the financial plan based on the user's life events (e.g., marriage, childbirth, moving). This allows the user to live a financially stable life.

[0073] The life planning simulation system can also include a social relationships management unit that acquires the user's social network data and adjusts the life plan based on those social relationships. For example, the social relationships management unit acquires data on friends and followers from the user's social media accounts and analyzes the user's social network. This allows it to provide a life plan based on the user's social relationships. For instance, if the user wants to build new relationships, it can provide networking opportunities with people who share common hobbies and interests. It can also leverage the user's social network to suggest career opportunities and business partnerships. Furthermore, the social relationships management unit can suggest activities and events to strengthen the user's social relationships. This allows the user to build rich social relationships and lead a fulfilling life.

[0074] The life planning simulation system can also include a learning management unit that acquires user learning data and adjusts the life plan based on the user's learning progress. For example, the learning management unit acquires data from online courses and learning platforms the user is taking, and understands their learning progress. This allows the system to provide a life plan tailored to the user's learning situation. For instance, if a user wants to acquire a new skill, the system can suggest courses and resources related to that skill. It can also provide a learning plan and schedule based on the user's learning goals. Furthermore, the learning management unit can suggest career opportunities and further education based on the user's learning outcomes. This allows users to achieve optimal life planning while growing personally through learning.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The extraction unit extracts user information. The extraction unit extracts user information using, for example, natural language processing technology. The extraction unit can extract information such as personal information, behavioral data, and interests from the user's dialogue content and input data. For example, the extraction unit analyzes the text data entered by the user and extracts important keywords and phrases. The extraction unit can also analyze the user's dialogue history and extract past behavioral patterns and interests. Furthermore, the extraction unit can collect the user's social media activity and online behavior data to understand the user's interests. Step 2: The construction unit builds a knowledge graph based on the information extracted by the extraction unit. The construction unit, for example, defines nodes and edges to build a knowledge graph that visually represents the user's information. The construction unit can represent the user's personal information and behavioral data as nodes and their relationships as edges. For example, the construction unit can represent information such as the user's occupation, hobbies, and life events as nodes and their relationships as edges. The construction unit can also dynamically update the knowledge graph based on the user's past behavioral data and dialogue history. Step 3: The generation unit generates a life plan based on the knowledge graph built by the construction unit. For example, the generation unit generates a career plan and life event plans based on the user's goals and aspirations. Based on the user's information, the generation unit can generate and present multiple life scenarios to the user. For example, the generation unit generates multiple scenarios that take into account the user's career choices and the timing of life events. The generation unit can also generate a personalized life plan based on the user's interests and values. Step 4: The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. For example, the optimization unit improves the life plan based on user feedback using reinforcement learning algorithms. The optimization unit can explore the optimal life plan based on user choices and actions. For example, the optimization unit collects feedback on the scenario selected by the user and improves the life plan based on that feedback. The optimization unit can also explore the optimal life plan by adjusting multiple parameters using Bayesian optimization. Step 5: The presentation unit presents the user with multiple scenarios improved by the optimization unit. The presentation unit presents the multiple scenarios to the user, for example, using a visually appealing interface. The presentation unit can visually display the features and benefits of each scenario to make it easier for the user to compare them. For example, the presentation unit can display the career plan and timing of life events for each scenario using graphs and charts. The presentation unit can also provide an intuitive interface for the user to use when selecting a scenario. Step 6: The Follow-up Department provides ongoing follow-up and optimization suggestions based on the scenario presented by the Presentation Department. For example, the Follow-up Department conducts regular follow-up based on the scenario selected by the user. The Follow-up Department can collect the user's progress and feedback and make optimization suggestions based on this. For example, the Follow-up Department monitors the user's progress toward their set goals and provides advice and support as needed. The Follow-up Department can also re-evaluate the user's life plan and make optimization suggestions in response to changes in the user's life events and environment.

[0077] (Example of form 2) The life planning simulation system according to an embodiment of the present invention is a system that uses AI to provide a life planning simulation optimized for an individual. This life planning simulation system can explore life possibilities through dialogue between the user and the AI ​​and generate and compare multiple life scenarios. Furthermore, the life planning simulation system can provide continuous follow-up and optimization suggestions. For example, the life planning simulation system allows the user to initiate a dialogue with the AI ​​through a dialogue interface. The AI ​​extracts user information using natural language processing technology and constructs a knowledge graph. Based on this knowledge graph, the AI ​​generates an optimal life plan for the user. The generated life plan is continuously improved using reinforcement learning and Bayesian optimization. Next, the AI ​​generates multiple life scenarios and presents them to the user. The user can compare these scenarios and select the one that is best suited to them. Based on the selected scenario, the AI ​​provides continuous follow-up and optimization suggestions. Features of this service include personalized life planning, presentation of multiple scenarios, continuous support, secure data management, and an intuitive user interface. Generative AI technologies such as natural language processing, knowledge graphs, reinforcement learning, and Bayesian optimization are also utilized. The service flow involves the user interacting with the AI ​​through a dialogue interface, and user information being extracted through natural language processing. Next, a knowledge graph is constructed, and a life plan is generated. The generative model is improved using reinforcement learning and Bayesian optimization, and the optimal life plan is explored. Finally, multiple scenarios are presented to the user. This service has market potential due to the arrival of the 100-year life era, the development of AI and big data analysis technologies, and the increasing demand for personalized services. Possible revenue models include subscriptions (1,000 yen / month), premium plans (2,000 yen / month), corporate plans, partnerships, and data analysis. The vision of this service is to realize a society where everyone can live a life true to themselves, by providing personalized support through AI. It aims to balance the pursuit of individual happiness with the development of society as a whole, and to improve the quality of people's lives.This allows the life planning simulation system to provide users with a life plan optimized for them and offer ongoing support.

[0078] The life planning simulation system according to this embodiment comprises an extraction unit, a construction unit, a generation unit, an optimization unit, a presentation unit, and a follow-up unit. The extraction unit extracts user information. The extraction unit extracts user information using, for example, natural language processing technology. The extraction unit can extract information such as personal information, behavioral data, and interests from the user's dialogue content and input data. For example, the extraction unit analyzes text data entered by the user and extracts important keywords and phrases. The extraction unit can also analyze the user's dialogue history and extract past behavioral patterns and interests. Furthermore, the extraction unit can collect the user's social media activity and online behavioral data to understand the user's interests. The construction unit constructs a knowledge graph based on the information extracted by the extraction unit. The construction unit constructs a knowledge graph that visually represents user information by defining nodes and edges, for example. The construction unit can represent the user's personal information and behavioral data as nodes and their relationships as edges. For example, the construction unit represents information such as the user's occupation, hobbies, and life events as nodes, and their relationships as edges. The construction unit can also dynamically update the knowledge graph based on the user's past behavioral data and dialogue history. The generation unit generates a life plan based on the knowledge graph constructed by the construction unit. For example, the generation unit generates a career plan and a life event plan based on the user's goals and desires. The generation unit can generate and present multiple life scenarios based on the user's information. For example, the generation unit generates multiple scenarios that take into account the user's occupational choices and the timing of life events. The generation unit can also generate a personalized life plan based on the user's interests and values. The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. For example, the optimization unit improves the life plan based on user feedback using reinforcement learning algorithms. The optimization unit can search for the optimal life plan based on the user's choices and actions. For example, the optimization unit collects feedback on the scenario selected by the user and improves the life plan based on that feedback.The optimization unit can also use Bayesian optimization to adjust multiple parameters and explore the optimal life plan. The presentation unit presents the user with multiple scenarios improved by the optimization unit. The presentation unit can present multiple scenarios to the user using, for example, a visually appealing interface. The presentation unit can visually display the features and benefits of each scenario to make it easier for the user to compare them. For example, the presentation unit can display the career plan and timing of life events for each scenario using graphs and charts. The presentation unit can also provide an intuitive interface for the user when selecting a scenario. The follow-up unit provides continuous follow-up and optimization suggestions based on the scenarios presented by the presentation unit. For example, the follow-up unit provides regular follow-up based on the scenario selected by the user. The follow-up unit can collect the user's progress and feedback and make optimization suggestions based on that. For example, the follow-up unit monitors the user's progress toward their set goals and provides advice and support as needed. The follow-up unit can also re-evaluate the life plan and make optimization suggestions in response to the user's life events and changes in their environment. As a result, the life planning simulation system according to the embodiment can efficiently extract user information, construct a knowledge graph, generate a life plan, optimize it, present scenarios, and provide follow-up support.

[0079] The extraction unit extracts user information. For example, it uses natural language processing (NLP) techniques to extract user information. Specifically, the extraction unit analyzes text data entered by the user and extracts important keywords and phrases. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis, and by combining these, it can understand the user's intentions and emotions. For example, if a user enters "I want to work abroad in the future," the extraction unit extracts the keywords "future," "overseas," and "want to work," understanding the user's aspirations. The extraction unit can also analyze the user's conversation history to extract past behavioral patterns and interests. For example, if a user previously said they were "interested in programming," this information is recorded and used to inform future career plans. Furthermore, the extraction unit can collect user social media activity and online behavior data to understand the user's interests. For example, if a user frequently posts about "travel" or "cooking," this information is used to identify the user's hobbies and interests. This allows the extraction unit to collect comprehensive data from diverse user sources and accurately understand the user's needs and desires.

[0080] The construction unit builds a knowledge graph based on the information extracted by the extraction unit. For example, the construction unit defines nodes and edges to build a knowledge graph that visually represents user information. Specifically, nodes represent the user's personal information and behavioral data, and edges indicate their relationships. For example, information such as the user's occupation, hobbies, and life events are represented as nodes, and their relationships are represented as edges. If the user is an "engineer" and interested in "programming," this information is represented as nodes, and an edge is drawn between "engineer" and "programming." The construction unit can also dynamically update the knowledge graph based on the user's past behavioral data and conversation history. For example, if the user becomes interested in "data science," that information is added, and the existing nodes and edges are updated. Furthermore, the construction unit can integrate data from different sources to build a more detailed and accurate knowledge graph. For example, it can integrate the user's social media activity and online behavioral data to more accurately understand the user's interests and behavioral patterns. This allows the construction unit to visually and dynamically represent user information and provide the foundation necessary for subsequent processing.

[0081] The generation unit generates life plans based on the knowledge graph constructed by the construction unit. For example, the generation unit generates career plans and life event plans based on the user's goals and desires. Specifically, the generation unit can generate and present multiple life scenarios to the user based on the user's information. For example, if a user desires to "work abroad in the future," the generation unit will generate a scenario based on that desire, taking into account overseas career plans, necessary skills, and the timing of life events. The generation unit can also generate personalized life plans based on the user's interests and values. For example, if a user is interested in "programming" and "travel," it will propose a career plan and life events that satisfy both. Furthermore, the generation unit considers the user's past behavioral data and dialogue history to generate realistic and actionable scenarios. For example, if a user was previously interested in "data science," it will propose a data science-related career plan based on that information. In this way, the generation unit can generate and provide users with diverse life scenarios based on their desires and interests.

[0082] The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. For example, the optimization unit uses reinforcement learning algorithms to improve the life plan based on user feedback. Specifically, it collects feedback on the scenario selected by the user and improves the life plan based on that feedback. For example, if a user provides feedback that "this career plan is not realistic," the optimization unit generates a new scenario based on that information. The optimization unit can also use Bayesian optimization to adjust multiple parameters and explore the optimal life plan. For example, it adjusts the optimal career plan and the timing of life events based on the user's interests, values, and past behavioral data. Furthermore, the optimization unit can explore the optimal life plan based on the user's choices and actions. For example, if a user is interested in "data science," it proposes a career plan that makes the most of that interest. In this way, the optimization unit can continuously improve the life plan based on user feedback and behavioral data and provide the user with the optimal scenario.

[0083] The presentation unit presents the user with multiple scenarios improved by the optimization unit. For example, the presentation unit presents multiple scenarios using a visually appealing interface. Specifically, it displays career plans and the timing of life events for each scenario using graphs and charts, making it easy for users to compare scenarios. For example, scenario A might show "working overseas at age 30," while scenario B might show "starting a business at age 35," visually displaying the characteristics and benefits of each scenario. The presentation unit can also provide an intuitive interface for users to select scenarios. For example, it might use drag-and-drop functionality or sliders to allow users to easily customize scenarios. Furthermore, the presentation unit can reflect user feedback in real time and update the scenario content. For example, if a user provides feedback such as "I want this scenario to be more flexible," the presentation unit regenerates the scenario based on that information. In this way, the presentation unit can present scenarios visually and intuitively to the user, helping them make the best choice.

[0084] The follow-up unit provides continuous follow-up and optimization suggestions based on the scenarios presented by the presentation unit. For example, the follow-up unit performs regular follow-up based on the scenario selected by the user. Specifically, the follow-up unit collects the user's progress and feedback and makes optimization suggestions based on this information. For example, it monitors the user's progress toward their set goals and provides advice and support as needed. The follow-up unit can also re-evaluate the user's life plan and make optimization suggestions in response to the user's life events and changes in their environment. For example, if a user experiences a new life event such as "starting a family," the follow-up unit re-evaluates the life plan based on this information and proposes a new scenario. Furthermore, the follow-up unit can continuously improve the overall system performance based on user feedback. For example, if a user provides feedback that "this scenario is not realistic," the system's algorithm is adjusted based on that information to generate a more realistic scenario. In this way, the follow-up unit can provide the user with continuous support and optimization suggestions, helping them to achieve their goals.

[0085] The Data Management Department can perform secure data management. For example, the Data Management Department can protect user data using encryption technology. The Data Management Department can encrypt users' personal information and behavioral data to protect them from unauthorized access. For example, the Data Management Department can encrypt data using encryption algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman). The Data Management Department can also perform access control and manage users' access rights to data. For example, the Data Management Department can set different access rights for each user, restricting data viewing and editing. Furthermore, the Data Management Department can regularly back up data to prepare for data loss or corruption. For example, the Data Management Department can use cloud storage to back up data and restore data in the event of a disaster or system failure. In this way, the Data Management Department can securely manage user data and improve data security.

[0086] The interface unit can provide an intuitive user interface. For example, the interface unit can conduct usability testing and design an interface that is easy for users to use. The interface unit can improve the interface design based on user feedback. For example, the interface unit can design button placements and navigation menus that are easy for users to operate. The interface unit can also provide a visually appealing interface based on design guidelines. For example, the interface unit can select colors and fonts and adjust the layout to provide an interface that users can operate intuitively. Furthermore, the interface unit can adopt responsive design to provide an interface that is compatible with different devices and screen sizes. For example, the interface unit can design an interface that can be comfortably operated on various devices such as smartphones, tablets, and personal computers. In this way, the interface unit can provide an interface that is easy for users to use and improve the user experience.

[0087] The extraction unit can extract user information using natural language processing. For example, the extraction unit can analyze the user's input text using morphological analysis and extract important keywords and phrases. The extraction unit can extract information such as personal information, behavioral data, and interests from the user's dialogue content and input data. For example, the extraction unit analyzes the text data entered by the user and extracts important keywords and phrases. The extraction unit can also analyze the grammatical structure of the user's input text using grammatical analysis and understand the relationships between information. Furthermore, the extraction unit can understand the meaning of the user's input text using semantic analysis and extract information. For example, the extraction unit can extract the user's goals and desires from the user's dialogue content and reflect them in their life plan. In this way, the extraction unit can improve the accuracy of user information extraction by using natural language processing.

[0088] The optimization unit can improve the generative model using reinforcement learning and Bayesian optimization. For example, the optimization unit can improve the life plan based on user feedback using reinforcement learning algorithms. The optimization unit can explore the optimal life plan based on user choices and actions. For example, the optimization unit collects feedback on the scenario selected by the user and improves the life plan based on that feedback. The optimization unit can also use Bayesian optimization to adjust multiple parameters and explore the optimal life plan. For example, the optimization unit can use a Gaussian process to explore the parameter space of the life plan and find the optimal parameters. Furthermore, the optimization unit can use an acquisition function to find the optimal life plan while balancing exploration and utilization. In this way, the optimization unit can improve the accuracy of the generative model by using reinforcement learning and Bayesian optimization.

[0089] The presentation unit can generate and present multiple life scenarios to the user. For example, it can present multiple scenarios to the user using a visually appealing interface. The presentation unit can visually display the features and benefits of each scenario to make it easier for the user to compare them. For example, it can display career plans and the timing of life events for each scenario using graphs and charts. Furthermore, the presentation unit can provide an intuitive interface for the user to select a scenario. In addition, the presentation unit can visually display the simulation results of each scenario, making it easier for the user to understand the impact of each scenario. For example, it can display changes in income and quality of life for each scenario using graphs and charts. By presenting multiple scenarios, the presentation unit enables the user to select the most suitable one.

[0090] The follow-up department can provide continuous follow-up and optimization suggestions based on the selected scenario. For example, the follow-up department can conduct regular follow-ups based on the scenario selected by the user. The follow-up department can collect user progress and feedback and make optimization suggestions based on this. For example, the follow-up department can monitor the user's progress toward the goals they have set and provide advice and support as needed. The follow-up department can also re-evaluate the life plan and make optimization suggestions in response to the user's life events and changes in their environment. Furthermore, based on user feedback, the follow-up department can identify areas for improvement in the life plan and continuously optimize it. In this way, the follow-up department can support the user's life plan by providing continuous follow-up and optimization suggestions.

[0091] The extraction unit can estimate the user's emotions and adjust the timing of information extraction based on the estimated emotions. For example, if the user is stressed, the extraction unit will delay information extraction until the user is relaxed. The extraction unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the extraction unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the extraction unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the extraction unit can estimate the user's emotions based on fluctuations in heart rate. This allows the extraction unit to adjust the timing of information extraction according to the user's emotions, enabling more appropriate information extraction. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The extraction unit can analyze the user's past conversation history and select the optimal information extraction method. For example, the extraction unit can extract information using a similar method based on the conversation style the user has preferred in the past. The extraction unit can save the user's conversation history and analyze it using natural language processing techniques. For example, the extraction unit can analyze the content of the user's past conversations and extract specific keywords or phrases. The extraction unit can also consider topics the user has avoided in the past and extract information in a way that avoids them. Furthermore, the extraction unit can prioritize the extraction of specific keywords from the user's past conversation history. For example, the extraction unit can extract relevant information based on keywords the user has frequently mentioned in the past. In this way, the extraction unit can select the optimal information extraction method by analyzing past conversation history.

[0093] The extraction unit can filter information based on the user's current life circumstances and areas of interest during the information extraction process. For example, if the user is seeking information related to their current job, the extraction unit will prioritize extracting information related to that field. The extraction unit can understand the user's life circumstances and areas of interest and filter information accordingly. For example, if the user has started a new hobby, the extraction unit will extract information related to that hobby. The extraction unit can also filter and extract relevant information based on the user's life circumstances (e.g., moving, changing jobs). Furthermore, the extraction unit can prioritize extracting highly relevant information based on the user's areas of interest. For example, the extraction unit will extract information related to topics the user is interested in. In this way, the extraction unit can extract more relevant information by filtering information based on the user's life circumstances and areas of interest.

[0094] The extraction unit can estimate the user's emotions and determine the priority of information to extract based on the estimated emotions. For example, if the user is feeling anxious, the extraction unit will prioritize extracting information that provides a sense of security. The extraction unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the extraction unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the extraction unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the extraction unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the extraction unit can provide more appropriate information by determining the priority of information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0095] The extraction unit can prioritize extracting highly relevant information by considering the user's geographical location during information extraction. For example, if the user is in a specific region, the extraction unit will prioritize extracting information related to that region. The extraction unit can collect the user's geographical location information and filter information based on it. For example, if the user is traveling, the extraction unit will extract information related to the travel destination. Also, if the user is planning to move, the extraction unit can prioritize extracting information about the new region. Furthermore, the extraction unit can prioritize extracting highly relevant information based on the user's geographical location. For example, the extraction unit will extract information related to events and news in the region where the user is currently located. In this way, the extraction unit can prioritize extracting highly relevant information by considering geographical location information.

[0096] The extraction unit can analyze a user's social media activity and extract relevant information during the information extraction process. For example, the extraction unit can extract information related to topics that the user frequently mentions on social media. The extraction unit can collect a user's social media activity and analyze it using natural language processing techniques. For example, the extraction unit can analyze the content of a user's social media posts and extract relevant information. The extraction unit can also extract relevant information based on information shared by the user's social media friends. Furthermore, the extraction unit can extract information that the user might be interested in from their social media activity. For example, the extraction unit can extract information related to topics that the user is interested in. In this way, the extraction unit can extract relevant information by analyzing social media activity.

[0097] The construction unit can estimate the user's emotions and adjust the method of constructing the knowledge graph based on the estimated user emotions. For example, if the user is relaxed, the construction unit will construct a knowledge graph containing detailed information. The construction unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the construction unit can analyze the user's facial expression data captured by a camera and estimate emotions. It can also analyze the user's voice data recorded by a microphone and estimate emotions. Furthermore, the construction unit can collect biometric data such as heart rate and skin electrical activity using sensors and estimate emotions. For example, the construction unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the construction unit can construct a more appropriate knowledge graph by adjusting the method of constructing the knowledge graph according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The construction unit can select the optimal construction method when building a knowledge graph by referring to the user's past behavior data. For example, the construction unit can build a knowledge graph containing similar information based on information that the user has previously preferred. The construction unit can store the user's behavior data and analyze it using natural language processing techniques. For example, the construction unit can analyze the user's past behavior data and extract specific patterns. The construction unit can also extract specific patterns from the user's past behavior data and build a knowledge graph based on them. Furthermore, the construction unit can analyze the user's past behavior data and select the most efficient construction method. For example, the construction unit can define the optimal nodes and edges based on the user's past behavior data. This allows the construction unit to select the optimal knowledge graph construction method by referring to past behavior data.

[0099] The builder can customize the knowledge graph construction method based on the user's current life situation when building the knowledge graph. For example, if a user starts a new job, the builder will build a knowledge graph that includes information related to that job. The builder can understand the user's life situation and customize the knowledge graph based on that. For example, if a user is planning to move, the builder will build a knowledge graph that includes information about the new area. The builder can also build a knowledge graph that includes relevant information based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the builder can prioritize including highly relevant information in the knowledge graph based on the user's life situation. For example, the builder will prioritize adding nodes and edges related to the user's current life situation. This allows the builder to provide more relevant information by customizing the knowledge graph based on the current life situation.

[0100] The system builder can estimate the user's emotions and prioritize the knowledge graph based on those emotions. For example, if the user is feeling anxious, the system builder will prioritize including information that provides a sense of security in the knowledge graph. The system builder can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the system builder can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the system builder can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the system builder can estimate the user's emotions based on fluctuations in heart rate. This allows the system builder to provide more appropriate information by prioritizing the knowledge graph according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The builder can select the optimal build method when constructing a knowledge graph, taking into account the user's geographical location. For example, if the user is in a specific region, the builder will construct a knowledge graph that includes information related to that region. The builder can collect the user's geographical location information and customize the knowledge graph based on it. For example, if the user is traveling, the builder will construct a knowledge graph that includes information related to the travel destination. Also, if the user is planning to move, the builder can construct a knowledge graph that includes information about the new region. Furthermore, the builder can prioritize including highly relevant information in the knowledge graph based on the user's geographical location. For example, the builder will include information related to events and news in the user's current location in the knowledge graph. In this way, the builder can provide highly relevant information by taking geographical location into consideration.

[0102] The construction unit can analyze a user's social media activity and propose construction methods when building a knowledge graph. For example, the construction unit can build a knowledge graph that includes information related to topics that the user frequently mentions on social media. The construction unit can collect a user's social media activity and analyze it using natural language processing techniques. For example, the construction unit can analyze the content of a user's social media posts and include relevant information in the knowledge graph. The construction unit can also include relevant information in the knowledge graph based on information shared by the user's social media friends. Furthermore, the construction unit can include information that the user might be interested in from their social media activity in the knowledge graph. For example, the construction unit can include information related to topics that the user is interested in in the knowledge graph. In this way, the construction unit can provide highly relevant information by analyzing social media activity.

[0103] The generation unit can estimate the user's emotions and adjust the life plan generation method based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate a detailed life plan. The generation unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the generation unit can analyze the user's facial expression data captured by a camera and estimate emotions. It can also analyze the user's voice data recorded by a microphone and estimate emotions. Furthermore, the generation unit can collect biometric data such as heart rate and skin electrical activity using sensors and estimate emotions. For example, the generation unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the generation unit can provide a more appropriate life plan by adjusting the life plan generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The generation unit can select the optimal generation method by referring to the user's past behavioral data when generating a life plan. For example, the generation unit can generate a similar plan based on a life plan the user has preferred in the past. The generation unit can store the user's behavioral data and analyze it using natural language processing technology. For example, the generation unit can analyze the user's past behavioral data and extract specific patterns. The generation unit can also extract specific patterns from the user's past behavioral data and generate a life plan based on them. Furthermore, the generation unit can analyze the user's past behavioral data and select the most efficient generation method. For example, the generation unit can set optimal life plan parameters based on the user's past behavioral data. This allows the generation unit to select the optimal life plan generation method by referring to past behavioral data.

[0105] The generation unit can customize the generation method based on the user's current living situation when generating a life plan. For example, if the user starts a new job, the generation unit will generate a life plan related to that job. The generation unit can understand the user's living situation and customize the life plan based on it. For example, if the user is planning to move, the generation unit will generate a life plan based on the new area. The generation unit can also generate a life plan based on the user's current living situation (e.g., marriage, childbirth). Furthermore, the generation unit can prioritize including highly relevant information in the life plan based on the user's living situation. For example, the generation unit will prioritize adding elements related to the user's current living situation. In this way, the generation unit can provide more relevant information by customizing the life plan based on the current living situation.

[0106] The generation unit can estimate the user's emotions and determine the priority of life plans to generate based on the estimated emotions. For example, if the user is feeling anxious, the generation unit will prioritize generating life plans that provide a sense of security. The generation unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the generation unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the generation unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the generation unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the generation unit can provide more appropriate information by determining the priority of life plans according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The generation unit can select the optimal generation method when generating a life plan, taking into account the user's geographical location information. For example, if the user is in a specific region, the generation unit will generate a life plan related to that region. The generation unit can collect the user's geographical location information and customize the life plan based on it. For example, if the user is traveling, the generation unit will generate a life plan related to the travel destination. Also, if the user is planning to move, the generation unit can generate a life plan based on the new region. Furthermore, the generation unit can prioritize including highly relevant information in the life plan based on the user's geographical location information. For example, the generation unit will include information related to events and news in the user's current location in the life plan. In this way, the generation unit can provide highly relevant information by taking geographical location information into consideration.

[0108] The generation unit can analyze the user's social media activity and propose generation methods when generating a life plan. For example, the generation unit can generate a life plan related to topics that the user frequently mentions on social media. The generation unit can collect the user's social media activity and analyze it using natural language processing techniques. For example, the generation unit can analyze the content of the user's social media posts and include relevant information in the life plan. The generation unit can also include relevant information in the life plan based on information shared by the user's social media friends. Furthermore, the generation unit can include information that the user might be interested in from their social media activity in the life plan. For example, the generation unit can include information related to topics that the user is interested in in the life plan. In this way, the generation unit can provide highly relevant information by analyzing social media activity.

[0109] The optimization unit can estimate the user's emotions and adjust the optimization method based on the estimated emotions. For example, if the user is relaxed, the optimization unit will perform a detailed optimization process. The optimization unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the optimization unit can analyze the user's facial expression data captured by a camera and estimate emotions. It can also analyze the user's voice data recorded by a microphone and estimate emotions. Furthermore, the optimization unit can collect biometric data such as heart rate and skin electrical activity using sensors and estimate emotions. For example, the optimization unit can estimate the user's emotions based on fluctuations in heart rate. This allows the optimization unit to adjust the optimization method according to the user's emotions, enabling more appropriate optimization. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0110] The optimization unit can select the optimal optimization method by referring to the user's past behavior data during optimization. For example, the optimization unit can perform optimization using a similar method based on the user's preferred optimization method in the past. The optimization unit can store the user's behavior data and analyze it using natural language processing technology. For example, the optimization unit can analyze the user's past behavior data and extract specific patterns. The optimization unit can also extract specific patterns from the user's past behavior data and perform optimization based on them. Furthermore, the optimization unit can analyze the user's past behavior data and select the most efficient optimization method. For example, the optimization unit can set optimal optimization parameters based on the user's past behavior data. This allows the optimization unit to select the optimal optimization method by referring to past behavior data.

[0111] The optimization unit can customize the optimization means based on the user's current life situation during optimization. For example, if the user starts a new job, the optimization unit will provide optimization means related to that job. The optimization unit can understand the user's life situation and customize the optimization means based on that. For example, if the user is planning to move, the optimization unit will provide optimization means based on the new area. The optimization unit can also provide relevant optimization means based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the optimization unit can prioritize including highly relevant information in the optimization means based on the user's life situation. For example, the optimization unit will prioritize adding elements related to the user's current life situation. This allows the optimization unit to provide more relevant information by customizing the optimization means based on the current life situation.

[0112] The optimization unit can estimate the user's emotions and determine optimization priorities based on the estimated emotions. For example, if the user is feeling anxious, the optimization unit will prioritize optimizations that provide a sense of security. The optimization unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the optimization unit can analyze the user's facial expression data captured by a camera and estimate emotions. It can also analyze the user's voice data recorded by a microphone and estimate emotions. Furthermore, the optimization unit can collect biometric data such as heart rate and skin electrical activity using sensors and estimate emotions. For example, the optimization unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the optimization unit can provide more appropriate information by determining optimization priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0113] The optimization unit can select the optimal optimization method during optimization by considering the user's geographical location information. For example, if the user is in a specific region, the optimization unit can provide optimization methods related to that region. The optimization unit can collect the user's geographical location information and customize the optimization methods based on it. For example, if the user is traveling, the optimization unit can provide optimization methods related to the travel destination. Also, if the user is planning to move, the optimization unit can provide optimization methods based on the new region. Furthermore, the optimization unit can prioritize including highly relevant information in the optimization methods based on the user's geographical location information. For example, the optimization unit can include information related to events and news in the user's current location in the optimization methods. In this way, the optimization unit can provide highly relevant information by considering geographical location information.

[0114] The optimization unit can analyze the user's social media activity during optimization and propose optimization methods. For example, the optimization unit can provide optimization methods related to topics that the user frequently mentions on social media. The optimization unit can collect the user's social media activity and analyze it using natural language processing technology. For example, the optimization unit can analyze the content of the user's social media posts and include relevant information in the optimization methods. The optimization unit can also provide relevant optimization methods based on information shared by the user's social media friends. Furthermore, the optimization unit can include information that the user might be interested in from their social media activity in the optimization methods. For example, the optimization unit can include information related to topics that the user is interested in in the optimization methods. In this way, the optimization unit can provide highly relevant information by analyzing social media activity.

[0115] The presentation unit can estimate the user's emotions and adjust the scenario presentation method based on the estimated user emotions. For example, if the user is relaxed, the presentation unit will present a detailed scenario. The presentation unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the presentation unit can analyze the user's facial expression data captured by a camera and estimate emotions. It can also analyze the user's voice data recorded by a microphone and estimate emotions. Furthermore, the presentation unit can collect biometric data such as heart rate and skin electrical activity using sensors and estimate emotions. For example, the presentation unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the presentation unit can provide more appropriate information by adjusting the scenario presentation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0116] The presentation unit can select the optimal presentation method when presenting a scenario by referring to the user's past selection history. For example, the presentation unit can present a scenario using a similar method to those the user has previously preferred. The presentation unit can save the user's selection history and analyze it using natural language processing techniques. For example, the presentation unit can analyze the user's past selection history and extract specific patterns. The presentation unit can also extract specific patterns from the user's past selection history and present a scenario based on them. Furthermore, the presentation unit can analyze the user's past selection history and select the most efficient presentation method. For example, the presentation unit can set optimal scenario presentation parameters based on the user's past selection history. This allows the presentation unit to select the optimal scenario presentation method by referring to past selection history.

[0117] The presentation unit can customize the presentation method based on the user's current life situation when presenting scenarios. For example, if the user has started a new job, the presentation unit will present scenarios related to that job. The presentation unit can understand the user's life situation and customize the scenarios accordingly. For example, if the user is planning to move, the presentation unit will present scenarios based on the new area. The presentation unit can also present relevant scenarios based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the presentation unit can prioritize including highly relevant information in the scenarios based on the user's life situation. For example, the presentation unit will prioritize adding elements related to the user's current life situation. In this way, the presentation unit can provide more relevant information by customizing the scenarios based on the current life situation.

[0118] The presentation unit can estimate the user's emotions and determine the priority of scenarios to present based on the estimated emotions. For example, if the user is feeling anxious, the presentation unit will prioritize scenarios that provide a sense of security. The presentation unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the presentation unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the presentation unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the presentation unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the presentation unit can provide more appropriate information by determining the priority of scenarios according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0119] The presentation unit can select the optimal presentation method when presenting scenarios, taking into account the user's geographical location information. For example, if the user is in a specific region, the presentation unit will present scenarios related to that region. The presentation unit can collect the user's geographical location information and customize scenarios based on it. For example, if the user is traveling, the presentation unit will present scenarios related to their travel destination. Furthermore, if the user is planning to move, the presentation unit can present scenarios based on the new region. In addition, the presentation unit can prioritize including highly relevant information in scenarios based on the user's geographical location information. For example, the presentation unit can include information related to events and news in the user's current location in the scenario. This allows the presentation unit to provide highly relevant information by considering geographical location information.

[0120] The presentation unit can analyze the user's social media activity and propose presentation methods when presenting scenarios. For example, the presentation unit can present scenarios related to topics that the user frequently mentions on social media. The presentation unit can collect the user's social media activity and analyze it using natural language processing techniques. For example, the presentation unit can analyze the content of the user's social media posts and include relevant information in the scenario. The presentation unit can also present relevant scenarios based on information shared by the user's social media friends. Furthermore, the presentation unit can include information that the user might be interested in from their social media activity in the scenario. For example, the presentation unit can include information related to topics that the user is interested in in the scenario. In this way, the presentation unit can provide highly relevant information by analyzing social media activity.

[0121] The follow-up unit can estimate the user's emotions and adjust the follow-up method based on the estimated emotions. For example, if the user is relaxed, the follow-up unit will perform a more detailed follow-up. The follow-up unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the follow-up unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the follow-up unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the follow-up unit can estimate the user's emotions based on fluctuations in heart rate. This allows the follow-up unit to provide more appropriate information by adjusting the follow-up method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0122] The follow-up unit can select the optimal follow-up method by referring to the user's past behavioral data during follow-up. For example, the follow-up unit can perform follow-up using a similar method based on the follow-up method the user preferred in the past. The follow-up unit can store the user's behavioral data and analyze it using natural language processing technology. For example, the follow-up unit can analyze the user's past behavioral data and extract specific patterns. The follow-up unit can also extract specific patterns from the user's past behavioral data and perform follow-up based on them. Furthermore, the follow-up unit can analyze the user's past behavioral data and select the most efficient follow-up method. For example, the follow-up unit can set optimal follow-up parameters based on the user's past behavioral data. This allows the follow-up unit to select the optimal follow-up method by referring to past behavioral data.

[0123] The follow-up unit can customize follow-up methods based on the user's current life situation during follow-up. For example, if a user starts a new job, the follow-up unit will provide follow-up related to that job. The follow-up unit can understand the user's life situation and customize follow-up methods based on that. For example, if a user is planning to move, the follow-up unit will provide follow-up based on the new area. The follow-up unit can also provide relevant follow-up based on the user's current life situation (e.g., marriage, childbirth). Furthermore, the follow-up unit can prioritize including highly relevant information in the follow-up methods based on the user's life situation. For example, the follow-up unit will prioritize adding elements related to the user's current life situation. In this way, the follow-up unit can provide more relevant information by customizing the follow-up methods based on the current life situation.

[0124] The follow-up unit can estimate the user's emotions and determine the priority of follow-up based on the estimated emotions. For example, if the user is feeling anxious, the follow-up unit will prioritize follow-up that provides reassurance. The follow-up unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the follow-up unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the follow-up unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the follow-up unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the follow-up unit can provide more appropriate information by determining the priority of follow-up according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0125] The follow-up unit can select the optimal follow-up method by considering the user's geographical location information during follow-up. For example, if the user is in a specific region, the follow-up unit will perform follow-up activities related to that region. The follow-up unit can collect the user's geographical location information and customize the follow-up methods based on it. For example, if the user is traveling, the follow-up unit will perform follow-up activities related to the travel destination. Also, if the user is planning to move, the follow-up unit can perform follow-up activities based on the new region. Furthermore, the follow-up unit can prioritize including highly relevant information in the follow-up activities based on the user's geographical location information. For example, the follow-up unit can include information related to events and news in the user's current location in the follow-up activities. In this way, the follow-up unit can provide highly relevant information by considering geographical location information.

[0126] The follow-up unit can analyze the user's social media activity during follow-up and propose follow-up methods. For example, the follow-up unit can perform follow-ups related to topics that the user frequently mentions on social media. The follow-up unit can collect the user's social media activity and analyze it using natural language processing technology. For example, the follow-up unit can analyze the content of the user's social media posts and include relevant information in the follow-up methods. The follow-up unit can also perform relevant follow-ups based on information shared by the user's social media friends. Furthermore, the follow-up unit can include information that the user might be interested in from their social media activity in the follow-up methods. For example, the follow-up unit can include information related to topics that the user is interested in in the follow-up methods. In this way, the follow-up unit can provide highly relevant information by analyzing social media activity.

[0127] The data management unit can estimate the user's emotions and adjust its data management methods based on those emotions. For example, if a user is feeling anxious, the data management unit can emphasize information about data security to provide reassurance. The data management unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the data management unit can analyze facial expression data captured by a camera to estimate emotions. It can also analyze voice data recorded by a microphone to estimate emotions. Furthermore, the data management unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the data management unit can estimate a user's emotions based on fluctuations in heart rate. This allows the data management unit to provide more appropriate information by adjusting its data management methods according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0128] The data management department can select the optimal data management method by referring to the user's past data usage history during data management. For example, the data management department can manage data using a similar method based on the data management method the user previously preferred. The data management department can store the user's data usage history and analyze it using natural language processing technology. For example, the data management department can analyze the user's past data usage history and extract specific patterns. The data management department can also extract specific patterns from the user's past data usage history and perform data management based on them. Furthermore, the data management department can analyze the user's past data usage history and select the most efficient data management method. For example, the data management department can set optimal data management parameters based on the user's past data usage history. This allows the data management department to select the optimal data management method by referring to past data usage history.

[0129] The data management department can estimate a user's emotions and determine data management priorities based on those estimated emotions. For example, if a user is feeling anxious, the data management department will prioritize security in data management. The data management department can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the data management department can analyze facial expression data captured by a camera to estimate emotions. It can also analyze voice data recorded by a microphone to estimate emotions. Furthermore, the data management department can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the data management department can estimate a user's emotions based on fluctuations in heart rate. This allows the data management department to provide more appropriate information by determining data management priorities according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0130] The data management department can select the optimal management method when managing data, taking into account the user's geographical location information. For example, if a user is in a specific region, the data management department will manage the data in accordance with the data protection laws of that region. The data management department can collect the user's geographical location information and customize the data management methods based on it. For example, if a user is traveling, the data management department will manage the data in accordance with the data protection laws of the destination. Also, if a user is planning to move, the data management department can manage the data in accordance with the data protection laws of the new region. Furthermore, the data management department can prioritize including highly relevant information in the data management methods based on the user's geographical location information. For example, the data management department can include information related to the data protection laws of the region where the user is currently located in the data management methods. In this way, the data management department can provide highly relevant information by taking geographical location information into consideration.

[0131] The interface unit can estimate the user's emotions and adjust the interface display method based on the estimated emotions. For example, if the user is tense, the interface unit can provide an interface with calming colors to reduce visual stress. The interface unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the interface unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the interface unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. For example, the interface unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the interface unit can provide more appropriate information by adjusting the interface display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0132] The interface unit can select the optimal display method by referring to the user's past operation history when displaying the interface. For example, the interface unit can provide a similar design based on the user's previously preferred interface design. The interface unit can save the user's operation history and analyze it using natural language processing technology. For example, the interface unit can analyze the user's past operation history and extract specific patterns. The interface unit can also extract specific patterns from the user's past operation history and display the interface based on them. Furthermore, the interface unit can analyze the user's past operation history and select the most efficient display method. For example, the interface unit can set optimal interface display parameters based on the user's past operation history. This allows the interface unit to select the optimal interface display method by referring to past operation history.

[0133] The interface unit can estimate the user's emotions and adjust the interface's operation procedures based on the estimated emotions. For example, if the user is nervous, the interface unit can provide simple and intuitive operation procedures. The interface unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the interface unit can analyze the user's facial expression data captured by a camera and estimate emotions. It can also analyze the user's voice data recorded by a microphone and estimate emotions. Furthermore, the interface unit can collect biometric data such as heart rate and skin electrical activity using sensors and estimate emotions. For example, the interface unit can estimate the user's emotions based on fluctuations in heart rate. As a result, the interface unit can provide more appropriate information by adjusting the interface's operation procedures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0134] The interface unit can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, the interface unit provides a display method that matches the screen size. The interface unit can collect the user's device information and customize the interface display means based on it. For example, if the user is using a tablet, the interface unit provides a display method optimized for a large screen. The interface unit can also provide a concise and highly visible display method if the user is using a smartwatch. Furthermore, the interface unit can prioritize including highly relevant information in the interface display means based on the user's device information. For example, the interface unit includes information related to the characteristics of the device the user is currently using in the interface display means. In this way, the interface unit can provide highly relevant information by taking device information into consideration.

[0135] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0136] The life planning simulation system can also include a health management unit that acquires the user's health data and adjusts the life plan based on their health status. The health management unit can, for example, acquire heart rate, steps, and sleep data from the user's fitness tracker or smartwatch. This allows the system to monitor the user's health status in real time and provide a life plan tailored to their health condition. For instance, if the user is experiencing stress, the system can suggest relaxing activities. It can also suggest lifestyle improvements to maintain health based on the user's health data. Furthermore, the health management unit can propose fitness and meal plans based on the user's health goals. This enables the user to achieve an optimal life plan while maintaining their health.

[0137] The life planning simulation system can also include a hobby management unit that customizes the life plan based on the user's hobbies and interests. For example, the hobby management unit collects data on events and activities the user has participated in in the past to understand their hobbies and interests. This allows it to provide a life plan tailored to the user's hobbies. For instance, if the user is interested in music, it can suggest music-related events and courses. It can also provide information and resources related to a user's desire to start a new hobby. Furthermore, the hobby management unit can provide opportunities for building relationships and networking through shared hobbies. This allows users to enjoy their hobbies while leading a fulfilling life.

[0138] The life planning simulation system can also include a financial management unit that acquires the user's financial data and adjusts the life plan based on their financial situation. The financial management unit, for example, acquires data from the user's bank accounts and credit cards and analyzes income and expenditure patterns. This allows it to provide a life plan tailored to the user's financial situation. For instance, if the user wants to increase their savings, it can offer advice on saving and suggest investments. It can also provide budget management and asset management plans based on the user's financial goals. Furthermore, the financial management unit can adjust the financial plan based on the user's life events (e.g., marriage, childbirth, moving). This allows the user to live a financially stable life.

[0139] The life planning simulation system can also include a social relationships management unit that acquires the user's social network data and adjusts the life plan based on those social relationships. For example, the social relationships management unit acquires data on friends and followers from the user's social media accounts and analyzes the user's social network. This allows it to provide a life plan based on the user's social relationships. For instance, if the user wants to build new relationships, it can provide networking opportunities with people who share common hobbies and interests. It can also leverage the user's social network to suggest career opportunities and business partnerships. Furthermore, the social relationships management unit can suggest activities and events to strengthen the user's social relationships. This allows the user to build rich social relationships and lead a fulfilling life.

[0140] The life planning simulation system can also include a learning management unit that acquires user learning data and adjusts the life plan based on the user's learning progress. For example, the learning management unit acquires data from online courses and learning platforms the user is taking, and understands their learning progress. This allows the system to provide a life plan tailored to the user's learning situation. For instance, if a user wants to acquire a new skill, the system can suggest courses and resources related to that skill. It can also provide a learning plan and schedule based on the user's learning goals. Furthermore, the learning management unit can suggest career opportunities and further education based on the user's learning outcomes. This allows users to achieve optimal life planning while growing personally through learning.

[0141] The life planning simulation system may also include an emotional feedback unit that estimates the user's emotions and adjusts the life planning feedback based on those estimated emotions. For example, if the user is feeling stressed, the emotional feedback unit might provide relaxing activities or advice. The emotional feedback unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For instance, it might analyze facial expression data captured by a camera to estimate emotions. It could also analyze voice data recorded by a microphone to estimate emotions. Furthermore, the emotional feedback unit could collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. This allows the emotional feedback unit to provide more appropriate advice and support by adjusting feedback according to the user's emotions.

[0142] The life planning simulation system may further include an emotional scenario unit that estimates the user's emotions and adjusts the life planning scenario based on the estimated emotions. For example, if the user is feeling anxious, the emotional scenario unit will prioritize presenting scenarios that provide a sense of security. The emotional scenario unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the emotional scenario unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the emotional scenario unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. As a result, the emotional scenario unit can provide a more appropriate life plan by adjusting the scenario according to the user's emotions.

[0143] The life planning simulation system may further include an emotional goal unit that estimates the user's emotions and adjusts the life planning goals based on those estimated emotions. For example, if the user is feeling motivated, the emotional goal unit will set challenging goals. The emotional goal unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the emotional goal unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the emotional goal unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. As a result, the emotional goal unit can provide a more appropriate life plan by adjusting goals according to the user's emotions.

[0144] The life planning simulation system may further include an emotion progress unit that estimates the user's emotions and adjusts the progress of the life planning based on those estimated emotions. For example, if the user is tired, the emotion progress unit may suggest slowing down the progress. The emotion progress unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For example, the emotion progress unit can analyze the user's facial expression data captured by a camera to estimate emotions. It can also analyze the user's voice data recorded by a microphone to estimate emotions. Furthermore, the emotion progress unit can collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. As a result, the emotion progress unit can provide more appropriate support by adjusting the progress according to the user's emotions.

[0145] The life planning simulation system may also include an emotional feedback unit that estimates the user's emotions and adjusts the life planning feedback based on those estimated emotions. For example, if the user is feeling stressed, the emotional feedback unit might provide relaxing activities or advice. The emotional feedback unit can estimate emotions using biometric data such as the user's facial expressions, voice, and heart rate. For instance, it might analyze facial expression data captured by a camera to estimate emotions. It could also analyze voice data recorded by a microphone to estimate emotions. Furthermore, the emotional feedback unit could collect biometric data such as heart rate and skin electrical activity using sensors to estimate emotions. This allows the emotional feedback unit to provide more appropriate advice and support by adjusting feedback according to the user's emotions.

[0146] The following briefly describes the processing flow for example form 2.

[0147] Step 1: The extraction unit extracts user information. The extraction unit extracts user information using, for example, natural language processing technology. The extraction unit can extract information such as personal information, behavioral data, and interests from the user's dialogue content and input data. For example, the extraction unit analyzes the text data entered by the user and extracts important keywords and phrases. The extraction unit can also analyze the user's dialogue history and extract past behavioral patterns and interests. Furthermore, the extraction unit can collect the user's social media activity and online behavior data to understand the user's interests. Step 2: The construction unit builds a knowledge graph based on the information extracted by the extraction unit. The construction unit, for example, defines nodes and edges to build a knowledge graph that visually represents the user's information. The construction unit can represent the user's personal information and behavioral data as nodes and their relationships as edges. For example, the construction unit can represent information such as the user's occupation, hobbies, and life events as nodes and their relationships as edges. The construction unit can also dynamically update the knowledge graph based on the user's past behavioral data and dialogue history. Step 3: The generation unit generates a life plan based on the knowledge graph built by the construction unit. For example, the generation unit generates a career plan and life event plans based on the user's goals and aspirations. Based on the user's information, the generation unit can generate and present multiple life scenarios to the user. For example, the generation unit generates multiple scenarios that take into account the user's career choices and the timing of life events. The generation unit can also generate a personalized life plan based on the user's interests and values. Step 4: The optimization unit continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization. For example, the optimization unit improves the life plan based on user feedback using reinforcement learning algorithms. The optimization unit can explore the optimal life plan based on user choices and actions. For example, the optimization unit collects feedback on the scenario selected by the user and improves the life plan based on that feedback. The optimization unit can also explore the optimal life plan by adjusting multiple parameters using Bayesian optimization. Step 5: The presentation unit presents the user with multiple scenarios improved by the optimization unit. The presentation unit presents the multiple scenarios to the user, for example, using a visually appealing interface. The presentation unit can visually display the features and benefits of each scenario to make it easier for the user to compare them. For example, the presentation unit can display the career plan and timing of life events for each scenario using graphs and charts. The presentation unit can also provide an intuitive interface for the user to use when selecting a scenario. Step 6: The Follow-up Department provides ongoing follow-up and optimization suggestions based on the scenario presented by the Presentation Department. For example, the Follow-up Department conducts regular follow-up based on the scenario selected by the user. The Follow-up Department can collect the user's progress and feedback and make optimization suggestions based on this. For example, the Follow-up Department monitors the user's progress toward their set goals and provides advice and support as needed. The Follow-up Department can also re-evaluate the user's life plan and make optimization suggestions in response to changes in the user's life events and environment.

[0148] 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.

[0149] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0150] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the extraction unit, construction unit, generation unit, optimization unit, presentation unit, follow-up unit, data management unit, and interface unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the smart device 14 and analyzes the user's dialogue content and input data. The construction unit is implemented by the specific processing unit 290 of the data processing unit 12 and constructs a knowledge graph. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a life plan. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the life plan using reinforcement learning and Bayesian optimization. The presentation unit is implemented by the control unit 46A of the smart device 14 and presents multiple scenarios to the user. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides continuous follow-up and optimization suggestions. The data management unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the data using encryption technology. The interface is implemented by the control unit 46A of the smart device 14, providing an intuitive user interface. The correspondence between each part and the device or control unit is not limited to the example described above, and various modifications are possible.

[0152] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0153] 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.

[0154] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0155] 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.

[0156] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0157] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0158] 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.

[0159] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0160] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0161] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0162] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0163] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0164] 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.

[0165] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0166] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0167] Each of the multiple elements described above, including the extraction unit, construction unit, generation unit, optimization unit, presentation unit, follow-up unit, data management unit, and interface unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the user's dialogue content and input data. The construction unit is implemented by the specific processing unit 290 of the data processing unit 12 and constructs a knowledge graph. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a life plan. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the life plan using reinforcement learning and Bayesian optimization. The presentation unit is implemented by the control unit 46A of the smart glasses 214 and presents multiple scenarios to the user. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides continuous follow-up and optimization suggestions. The data management unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the data using encryption technology. The interface is implemented by the control unit 46A of the smart glasses 214, providing an intuitive user interface. The correspondence between each part and the device or control unit is not limited to the example described above, and various modifications are possible.

[0168] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0169] 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.

[0170] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0171] 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.

[0172] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0173] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0174] 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.

[0175] 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.

[0176] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0177] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0178] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0179] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0180] 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.

[0181] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0182] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0183] Each of the multiple elements described above, including the extraction unit, construction unit, generation unit, optimization unit, presentation unit, follow-up unit, data management unit, and interface unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the user's dialogue content and input data. The construction unit is implemented by the specific processing unit 290 of the data processing unit 12 and constructs a knowledge graph. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a life plan. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the life plan using reinforcement learning and Bayesian optimization. The presentation unit is implemented by the control unit 46A of the headset terminal 314 and presents multiple scenarios to the user. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides continuous follow-up and optimization suggestions. The data management unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the data using encryption technology. The interface is implemented by the control unit 46A of the headset terminal 314, providing an intuitive user interface. The correspondence between each part and the device or control unit is not limited to the example described above, and various modifications are possible.

[0184] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0185] 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.

[0186] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0187] 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.

[0188] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0189] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0190] 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.

[0191] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0192] 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.

[0193] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0194] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0195] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0196] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0197] 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.

[0198] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0199] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0200] Each of the multiple elements described above, including the extraction unit, construction unit, generation unit, optimization unit, presentation unit, follow-up unit, data management unit, and interface unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the robot 414 and analyzes the user's dialogue content and input data. The construction unit is implemented by the specific processing unit 290 of the data processing unit 12 and constructs a knowledge graph. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a life plan. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the life plan using reinforcement learning and Bayesian optimization. The presentation unit is implemented by the control unit 46A of the robot 414 and presents multiple scenarios to the user. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides continuous follow-up and optimization suggestions. The data management unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the data using encryption technology. The interface is implemented by the control unit 46A of the robot 414, providing an intuitive user interface. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0201] 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.

[0202] Figure 9 shows the 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.

[0203] 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.

[0204] 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.

[0205] 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, and motorcycles, 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 based, for example, 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.

[0206] 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."

[0207] 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.

[0208] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0217] 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 other things 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.

[0218] 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 to be incorporated by reference.

[0219] (Note 1) An extraction unit that extracts user information, A construction unit constructs a knowledge graph based on the information extracted by the extraction unit, A generation unit that generates a life plan based on the knowledge graph constructed by the aforementioned construction unit, An optimization unit that continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization, A presentation unit that presents multiple scenarios improved by the optimization unit, The system includes a follow-up unit that provides continuous follow-up and optimization suggestions based on the scenario presented by the aforementioned presentation unit. A system characterized by the following features. (Note 2) It has a data management department that ensures secure data management. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features an interface section that provides an intuitive user interface. The system described in Appendix 1, characterized by the features described herein. (Note 4) The extraction unit is Extract user information using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 5) The optimization unit, Improving generative models using reinforcement learning and Bayesian optimization. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned display unit is, Generate multiple life scenarios and present them to the user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned follow-up unit is, We provide continuous follow-up and optimization suggestions based on the selected scenario. The system described in Appendix 1, characterized by the features described herein. (Note 8) The extraction unit is It estimates the user's emotions and adjusts the timing of information extraction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The extraction unit is Analyze the user's past conversation history and select the optimal method for extracting information. The system described in Appendix 1, characterized by the features described herein. (Note 10) The extraction unit is During information extraction, filtering is performed based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The extraction unit is It estimates the user's emotions and determines the priority of information to extract based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The extraction unit is When extracting information, the system prioritizes extracting highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The extraction unit is During information extraction, the system analyzes the user's social media activity and extracts relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned construction unit is We estimate the user's emotions and adjust how the knowledge graph is built based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned construction unit is When constructing a knowledge graph, the optimal construction method is selected by referring to the user's past behavioral data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned construction unit is When building a knowledge graph, customize the construction method based on the user's current life situation. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned construction unit is It estimates the user's emotions and determines the priority of the knowledge graph based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned construction unit is When constructing a knowledge graph, the optimal construction method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned construction unit is When constructing a knowledge graph, we analyze users' social media activity and propose construction methods. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the user's emotions and adjusts the life plan generation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating a life plan, the system selects the optimal generation method by referring to the user's past behavioral data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is When generating a life plan, the generation method is customized based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is It estimates the user's emotions and determines the priorities of the life plan generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating a life plan, the optimal generation method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is When generating a life plan, we analyze the user's social media activity and propose generation methods. The system described in Appendix 1, characterized by the features described herein. (Note 26) The optimization unit, It estimates the user's emotions and adjusts the optimization method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The optimization unit, During optimization, the system selects the optimal optimization method by referring to the user's past behavioral data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The optimization unit, During optimization, the optimization method is customized based on the user's current lifestyle. The system described in Appendix 1, characterized by the features described herein. (Note 29) The optimization unit, It estimates user emotions and determines optimization priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The optimization unit, During optimization, the optimal optimization method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The optimization unit, During optimization, we analyze users' social media activity and propose optimization methods. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned display unit is, It estimates the user's emotions and adjusts how the scenario is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned display unit is, When presenting a scenario, the system selects the optimal presentation method by referring to the user's past selection history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned display unit is, When presenting a scenario, the presentation method is customized based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned display unit is, It estimates the user's emotions and determines the priority of the scenarios to present based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned display unit is, When presenting scenarios, the optimal presentation method is selected considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned display unit is, When presenting scenarios, we analyze users' social media activity and propose presentation methods. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned follow-up unit is, It estimates the user's emotions and adjusts the follow-up method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned follow-up unit is, During follow-up, the optimal follow-up method is selected by referring to the user's past behavioral data. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned follow-up unit is, When following up, customize the follow-up means based on the user's current living situation The system according to appended note 1, characterized in that (Appended note 41) The follow-up unit Estimate the user's emotion and determine the priority of follow-up based on the estimated user's emotion The system according to appended note 1, characterized in that (Appended note 42) The follow-up unit When following up, select the optimal follow-up method in consideration of the user's geographical location information The system according to appended note 1, characterized in that (Appended note 43) The follow-up unit When following up, analyze the user's social media activities and propose follow-up means The system according to appended note 1, characterized in that (Appended note 44) The data management unit Estimate the user's emotion and adjust the data management method based on the estimated user's emotion The system according to appended note 1, characterized in that (Appended note 45) The data management unit When managing data, select the optimal management method by referring to the user's past data usage history The system according to appended note 1, characterized in that (Appended note 46) The data management unit Estimate the user's emotion and determine the priority of data management based on the estimated user's emotion The system according to appended note 1, characterized in that (Appended note 47) The data management unit When managing data, select the optimal management method in consideration of the user's geographical location information The system according to appended note 1, characterized in that (Supplementary Note 48) The interface unit estimates the user's emotion and adjusts the display method of the interface based on the estimated user emotion The system according to Supplementary Note 1, characterized in that (Supplementary Note 49) The interface unit selects an optimal display method by referring to the user's past operation history when displaying the interface The system according to Supplementary Note 1, characterized in that (Supplementary Note 50) The interface unit estimates the user's emotion and adjusts the operation procedure of the interface based on the estimated user emotion The system according to Supplementary Note 1, characterized in that (Supplementary Note 51) The interface unit selects an optimal display method by considering the user's device information when displaying the interface The system according to Supplementary Note 1, characterized in that

Explanation of Signs

[0220] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims

1. An extraction unit that extracts user information, A construction unit constructs a knowledge graph based on the information extracted by the extraction unit, A generation unit that generates a life plan based on the knowledge graph constructed by the aforementioned construction unit, An optimization unit that continuously improves the life plan generated by the generation unit using reinforcement learning and Bayesian optimization, A presentation unit that presents multiple scenarios improved by the optimization unit, The system includes a follow-up unit that provides continuous follow-up and optimization suggestions based on the scenario presented by the aforementioned presentation unit. A system characterized by the following features.

2. It has a data management department that ensures secure data management. The system according to feature 1.

3. It features an interface section that provides an intuitive user interface. The system according to feature 1.

4. The extraction unit is Extract user information using natural language processing. The system according to feature 1.

5. The optimization unit, Improving generative models using reinforcement learning and Bayesian optimization. The system according to feature 1.

6. The aforementioned display unit is, Generate multiple life scenarios and present them to the user. The system according to feature 1.

7. The aforementioned follow-up unit is, We provide continuous follow-up and optimization suggestions based on the selected scenario. The system according to feature 1.

8. The extraction unit is It estimates the user's emotions and adjusts the timing of information extraction based on the estimated user emotions. The system according to feature 1.

9. The extraction unit is Analyze the user's past conversation history and select the optimal method for extracting information. The system according to feature 1.

10. The extraction unit is During information extraction, filtering is performed based on the user's current lifestyle and areas of interest. The system according to feature 1.

Images