system

Abstract

We provide the system. [Solution] A processing means that analyzes the goals set by the user and generates an individualized action plan based on those goals, A means of automatically curating information sources related to the generated action plan and providing learning support, A means for receiving user progress in real time, analyzing said progress, and providing feedback to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] Many individuals face difficulties in formulating specific action plans in the process of self-realization and goal achievement. Also, it is difficult to select appropriate information sources and obtain meaningful feedback, and there are also challenges in maintaining motivation during the process. These problems are due to the lack of flexible responses of existing resources and support to individual needs.

Means for Solving the Problems

[0005] This invention provides a processing means that analyzes user-set goals and generates a personalized action plan, thereby establishing a concrete plan for achieving those goals. It also enables appropriate information access by automatically curating relevant information sources and providing learning support. Furthermore, it supports maintaining motivation throughout the process by analyzing the user's progress in real time and providing feedback. This enables flexible and effective support tailored to the individual needs of each user.

[0006] "Users" refer to individuals or corporations that use this system, set goals, and strive to achieve them.

[0007] A "goal" refers to a specific result or state that the user hopes to achieve.

[0008] "Analysis" refers to the process of interpreting, refining, or specifying the input goals.

[0009] An "individualized action plan" is a set of action guidelines tailored to the user's specific goals.

[0010] "Processing means" refers to technical methods used within a system to perform goal analysis and generate action plans.

[0011] An "information source" refers to anything that provides data, materials, or related content that is useful for learning or achieving goals.

[0012] "Curation" refers to the process of selecting relevant information sources and organizing and presenting them in a way that is easy for users to understand.

[0013] "Progress status" refers to the current state of activities that users are undertaking to achieve their goals and the results associated with those activities.

[0014] "Receiving in real time" means receiving progress information from users as it comes in and immediately.

[0015] "Feedback" is to evaluate the progress of users and provide responses including improvement points and encouragement.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is implemented as a system to provide the necessary support to ensure that users achieve their set goals without fail. This system consists of terminals, servers, and software programs, and utilizes advanced technologies such as natural language processing, machine learning, and data analysis.

[0038] First, users input their goals in text format using a device. These goals can be diverse, but must include specific achievements. The device analyzes and refines the input goals using natural language processing technology. During the analysis process, the device may ask additional questions to the user as needed to further concretize the goals.

[0039] The analyzed target data is sent from the terminal to the server. Upon receiving this target data, the server uses a pre-trained machine learning algorithm to generate an action plan optimized for the individual user. This action plan includes steps to be achieved, necessary materials, and information sources to refer to.

[0040] Furthermore, the server references a wealth of information sources on the internet and automatically selects (curates) learning content relevant to the user's goals and action plans. This selected content is provided to the user through their device, allowing them to deepen their self-study based on that content.

[0041] Furthermore, users are required to periodically report their progress using their devices. This progress data is sent to the server in real time, and the server quickly generates feedback based on this data, which is then provided to the user via their device. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0042] For example, if a user sets a goal such as "I want to acquire business English conversation skills," the system can recommend relevant online lessons, provide a list of necessary vocabulary words, and suggest the next steps based on their learning progress.

[0043] In this way, this system efficiently and effectively supports the goal achievement process by providing individually optimized support to users.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user enters the details of their objective into the terminal. The terminal sends the received objective to a natural language processing module for initial analysis.

[0047] Step 2:

[0048] The device presents the user with additional questions to obtain more specific information based on the analysis results. The user then answers these questions.

[0049] Step 3:

[0050] The device integrates the user's responses and sends the resulting target data to the server in JSON format.

[0051] Step 4:

[0052] The server analyzes the received target data and uses machine learning algorithms to generate an individually optimized action plan based on the user's characteristics.

[0053] Step 5:

[0054] The server automatically searches the internet for relevant information sources and curates learning content. The selected content is then sent to the device.

[0055] Step 6:

[0056] Users perform activities according to their action plan via a terminal and input their progress into the terminal. The input data is immediately sent to the server.

[0057] Step 7:

[0058] The server analyzes progress data in real time and generates evaluations and feedback. This feedback includes suggestions for improvement and next steps.

[0059] Step 8:

[0060] The device receives feedback from the server and presents it to the user. Based on that feedback, the user decides on their next action.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In today's world, there is a need for systems that effectively support individuals in achieving their goals. Conventional support systems often struggle to customize action plans to suit the specific circumstances of each user, and the information they provide is frequently inappropriate. This results in inefficient goal achievement for users.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for analyzing goals entered by the user via a terminal and refining them using natural language processing technology, means for generating an individualized action plan using a machine learning algorithm based on the refined goals, and means for selecting and providing educational content related to the action plan from information sources. This makes it possible to provide an optimal action plan according to the user's situation and to select relevant learning content.

[0066] "Goals" refer to the specific results or accomplishments that users wish to achieve.

[0067] "Analysis" refers to the process of analyzing input content using natural language processing techniques to refine or break down information.

[0068] "Natural language processing technology" refers to the technology used to process and understand human language using computers, and includes text analysis and data extraction.

[0069] A "machine learning algorithm" refers to a mathematical method that allows computers to learn from data and make improved decisions based on that learning experience.

[0070] An "action plan" refers to a plan that includes specific steps and actions to support users in achieving their goals.

[0071] "Educational content" refers to information and materials aimed at acquiring the knowledge and skills necessary to achieve a goal.

[0072] "Information source" refers to a source on the internet or other media that provides relevant data or knowledge.

[0073] "Elaboration" refers to the process of analyzing information and supplementing content to make the entered goals clearer and more detailed.

[0074] "Selection" refers to the process of extracting highly relevant information from diverse sources and picking out only the necessary content.

[0075] "Feedback" refers to evaluations, suggestions for improvement, and advice provided regarding a user's behavior and progress.

[0076] This invention is configured as a system that efficiently supports users in achieving their goals. It mainly consists of a terminal, a server, and multiple software components.

[0077] First, the user enters their goal via the terminal. The goal is entered as a specific item they want to achieve, in the form of a text field, such as "Improve my English business conversation skills." The terminal analyzes this text using natural language processing technology to refine the goal. Python natural language processing libraries (such as NLTK or spaCy) are used for the analysis.

[0078] The analyzed target data is sent from the terminal to the server, which receives it. The server uses machine learning algorithms to generate a personalized action plan. This utilizes analytical tools such as Scikit-learn and TENSORFLOW®. The action plan includes specific learning steps and recommendations.

[0079] Furthermore, the server selects and provides relevant educational content from internet sources. By searching its extensive database, it can present users with courses and materials tailored to their goals. For example, it can suggest, "We recommend taking this course once a week."

[0080] Users periodically report their progress via their devices. An example of their progress might be, "This week I learned 10 business terms." The server receives this information in real time, analyzes the user's progress, and generates feedback. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0081] An example of a prompt message might be: "Please enter a specific goal you would like to achieve. Example: Improve my English business conversation skills."

[0082] This system can individually optimize and effectively support the user's goal achievement process.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user uses a device to input their goal. The entered goal is in text format; for example, it might be "Improve my English business conversation skills." This text data is then passed to the device as input.

[0086] Step 2:

[0087] The terminal analyzes the input text data using natural language processing techniques. Here, a Python natural language processing library (NLTK or spaCy) is used to extract target keywords and important attributes. This process involves splitting the text into tokens and tagging them by part of speech. As a result, refined target data is generated.

[0088] Step 3:

[0089] The terminal sends the analyzed target data to the server. This is done via a secure communication protocol (e.g., HTTPS using SSL). The transmitted data is expressed in JSON format, containing the specific details of the target.

[0090] Step 4:

[0091] The server uses machine learning algorithms based on the received target data to generate a personalized action plan. Here, it uses Scikit-learn or TensorFlow models and analyzes past training data and similar targets to recommend the most appropriate training steps and resources. The output of this process is a plan that includes specific action steps.

[0092] Step 5:

[0093] The server selects appropriate educational content from the internet based on the action plan and collects data from the information sources. It performs web scraping using Python's BeautifulSoup and extracts links to online courses and video lessons related to the goals. This process outputs automatically selected learning resources.

[0094] Step 6:

[0095] The server sends the selected educational content and action plan to the terminal. The terminal displays this on the screen to the user, encouraging them to use it. Specifically, it supports the user's learning by providing clickable links and downloadable materials at each step of the action plan.

[0096] Step 7:

[0097] Users periodically report their learning progress via their devices. This input includes specific progress information, such as the number and content of knowledge items acquired. The devices transmit this information to the server in real time.

[0098] Step 8:

[0099] The server generates feedback based on the received progress data. Using a generation AI model, evaluations, improvement suggestions, and motivational advice are created based on the user's progress. This feedback is then delivered to the user via their device.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Even when users set goals, it is often difficult for them to effectively execute action plans to achieve them. Furthermore, without appropriate feedback and support, it is difficult to maintain motivation toward achieving goals. The present invention aims to solve these problems and provide a system that supports users in effectively achieving their goals.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes means for analyzing goals set by the user and generating an individualized action plan based on those goals; means for automatically selecting information sources related to the generated action plan and providing learning support; means for receiving the user's progress in real time, analyzing that progress, and providing feedback to the user; and means for presenting information that supports goal achievement using a visual aid device. As a result, the user can effectively take actions toward achieving their goals while receiving information visually, and can receive continuous support through feedback.

[0105] A "user" is someone who uses this system to achieve their own goals.

[0106] "Goals" refer to specific items or conditions that users wish to achieve.

[0107] "Analysis" refers to the process of analyzing and refining the goals set by the user using natural language processing technology and other methods.

[0108] An "action plan" is a plan that includes individualized, specific action steps and necessary information based on analyzed goals.

[0109] "Information sources" refer to information available on the internet or in databases that is relevant to action plans and supports users' learning.

[0110] "Progress status" refers to the degree of achievement and the progress of efforts toward the goals set by the user.

[0111] "Feedback" refers to responses that include evaluations, suggestions for improvement, and advice for maintaining motivation, based on progress.

[0112] A "visual assistance device" is a device that allows users to receive information visually, and usually refers to a wearable device.

[0113] This invention is an advanced system designed to support users in achieving their goals. It primarily consists of a server, terminals, and visual assistance devices, and utilizes natural language processing, machine learning, and data analysis technologies. Specific embodiments are described below.

[0114] First, the user inputs their desired goal via text or voice using a device. The server analyzes this goal using a natural language processing library (e.g., spaCy) to refine it. During this process, additional questions may be displayed on the device as needed to prompt the user for further input. The analyzed goal data is sent to the server, where a machine learning library (e.g., TensorFlow) generates an individualized action plan. This action plan is then sent to the device and presented to the user through a visual aid. The visual aid is envisioned to be a wearable device such as smart glasses.

[0115] The server also automatically selects relevant information and learning content from the internet and other data sources and sends it to the terminal. This information helps users more effectively execute their action plans. Users perform daily activities based on their action plans and report their progress to the server via their terminal. This progress data is analyzed in real time on the server, and feedback is generated. The feedback includes an assessment of achievement, suggestions for improvement, and advice to boost motivation, and is provided to the user through visual aids.

[0116] For example, when a store employee sets a sales target for a new product, using a visual aid allows them to interact with customers while checking real-time information on successful sales cases and popular products. This supports the optimal approach to achieving the target.

[0117] An example of a prompt to input into the generating AI model would be: "To design an application that helps store staff achieve their goals, consider the flow from goal setting to providing feedback."

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The user enters their goal using a terminal, either as text or voice. The entered data is sent directly to the server. The server uses a natural language processing library to analyze the text data and refine the goal. If voice data is used, speech recognition software is used to convert it to text. The analyzed data is then formatted to meet the user's specific goal requirements.

[0121] Step 2:

[0122] The server receives refined goal data and generates personalized action plans using machine learning models. It takes analyzed goal data as input and identifies feasible tasks and necessary resources based on it. In this process, data analysis algorithms select the optimal plan and send the results to the terminal.

[0123] Step 3:

[0124] The terminal receives the action plan generated from the server and presents it visually to the user through a visual aid. At this point, the information is displayed on the screen in an easy-to-understand format so that the user can understand the details of the plan. Based on this information, the user plans and carries out their daily activities.

[0125] Step 4:

[0126] Users report their progress to the server via their devices. This data is stored on the server in real time and processed by a data analysis engine. Based on the input progress data, the current level of achievement and any problems are analyzed, and the next steps to take are determined.

[0127] Step 5:

[0128] The server generates feedback based on the analysis of progress data and provides it to the user through the terminal and visual aids. This feedback includes areas for improvement, suggestions for next actions, and encouraging messages to boost motivation. The user then uses this feedback to adjust their actions and move towards achieving their goals.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] This invention is implemented in a more advanced form by incorporating an emotion engine as a system that provides support for achieving user-defined goals. This system consists of a terminal, a server, and an emotion engine as its main components, and utilizes natural language processing, machine learning, emotion recognition technology, and the like.

[0131] In the initial stages of the system, users input their goals as text via a terminal. The terminal analyzes the received goals using natural language processing technology. This analysis includes prompting additional questions, and the terminal asks the user questions as needed to help them refine their goals.

[0132] Detailed user goal information is sent from the terminal to the server. Based on this goal data, the server generates an optimal action plan tailored to the user's individual characteristics and circumstances. The generated action plan includes the steps and reference information necessary to achieve the goals.

[0133] A key feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. The recognized emotional data is sent to a server, which then generates mental care content for the user based on this data. This content includes encouragement and relaxation techniques tailored to the emotional state.

[0134] Furthermore, the server uses all the data, including emotional state and progress information, to optimize action suggestions to help maintain user motivation. The learning environment and action plan are also adjusted in response to changes in emotions.

[0135] For example, if a user sets the goal of "improving their English skills to work abroad," the system will recommend lessons on necessary vocabulary and grammar. When the user's emotional state indicates tension or anxiety, the server will provide content to help them relax and support them in maintaining their motivation.

[0136] Through this system, users can receive support tailored to their individual needs, and the process toward achieving their goals can be advanced effectively and sustainably.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user enters their desired goals into the device. The device analyzes this input data using natural language processing technology to identify the basic objective.

[0140] Step 2:

[0141] The device evaluates the analyzed data and, if it determines that the goal needs to be made more specific, displays additional questions to the user. By answering these questions, the user sets the goal more concretely.

[0142] Step 3:

[0143] The device formats the specified goal data and sends it to the server. The server receives this data and generates a personalized action plan that takes the user's characteristics into account.

[0144] Step 4:

[0145] The server automatically curates learning content by selecting relevant information sources from the internet that align with the user's goals. This content is then sent to the device and presented to the user.

[0146] Step 5:

[0147] Users progress through learning activities based on recommended content and action plans. Progress is periodically entered into the device, and this data is sent to the server.

[0148] Step 6:

[0149] The server uses an emotion engine to analyze the user's facial expressions and voice data to understand their emotional state. This emotional data is then used to generate mental care content tailored to each individual's situation.

[0150] Step 7:

[0151] The server integrates and analyzes the acquired emotional and progress data to generate feedback and suggestions for the next action for the user. This feedback also includes advice on maintaining motivation based on the user's emotional state.

[0152] Step 8:

[0153] The device presents the user with feedback and advice received from the server. Based on this, the user further modifies their action plan and continues their activities toward their goals.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] In today's world, where it is essential to provide individually optimized action plans based on user-defined goals, it is difficult to grasp users' progress and emotional states in real time and provide appropriate feedback and mental care accordingly. Furthermore, there is a lack of efficient means to provide learning support from diverse information sources.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for analyzing user-set goals and generating an individualized action plan, means for automatically selecting information sources related to the generated action plan and providing learning support, and means for analyzing the user's emotional state and generating and providing content for mental care based on emotional information. This enables support tailored to each user's characteristics and circumstances, and facilitates the smooth progress of the process toward achieving goals.

[0159] "Analyzing goals" means using natural language processing technology to extract and understand the content of the goals set by the user.

[0160] An "individualized action plan" is a plan that includes optimized action plans and steps based on each user's individual goals.

[0161] "Automatically selecting information sources" means automatically choosing various databases and materials relevant to the purpose using machine learning technology.

[0162] "Providing learning support" means providing learning materials and resources to improve users' knowledge and skills.

[0163] "Receiving progress in real time" means instantly incorporating user activity and learning progress into the system.

[0164] Providing feedback means offering evaluations and suggestions for improvement regarding the user's progress and actions, and providing information to encourage their next steps.

[0165] "Analyzing emotional state" means inferring a user's psychological state from their facial expressions and voice, and then determining their emotions.

[0166] "Content for mental care" refers to advice and relaxation methods provided to support the mental health of users.

[0167] "Generative AI technology" is a technology that uses artificial intelligence to generate new information and data.

[0168] A "remote device" is an internet-connected electronic device that can be accessed by servers and users.

[0169] This invention is a system that provides advanced support for achieving user-defined goals. The system primarily consists of a terminal, a server, and an emotion engine. The system utilizes natural language processing, machine learning, and emotion recognition technologies.

[0170] The user enters their goal through the device. This goal is analyzed by natural language processing software installed on the device (e.g., Python's NLTK library), which then derives specific content and additional questions to help the user achieve the goal. For example, if the user sets a goal such as "I want to gain confidence in giving presentations in English," a detailed action plan will be presented based on that goal.

[0171] The analyzed target data is sent from the terminal to the server. The server generates an action plan using a generative AI model (e.g., TensorFlow). This plan includes curating relevant information and tasks to be performed. The analysis results are delivered to a remote device via data communication, making them accessible to the user.

[0172] Furthermore, the emotion engine analyzes the user's facial expressions and voice via the device to evaluate their emotional state. Using libraries such as OpenCV, it analyzes facial expressions in real time and generates and provides mental care content based on this analysis. This content includes suggestions for relaxation-oriented music.

[0173] As a result, this system can provide precise and flexible support tailored to the individual needs of each user, and optimize the process to achieve goals.

[0174] A concrete example of a prompt might be: "The user has the goal of 'improving their English skills to work abroad.' Use a generative AI model to propose an action plan that aligns with this goal, and further adjust mental support based on the results of an analysis of their emotional state."

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The user uses a terminal to input their set goal in text format. The entered text is sent to the goal analysis module. Here, the input is the user's goal text, and the output is text ready for analysis.

[0178] Step 2:

[0179] The terminal uses a natural language processing engine to analyze the input target text. It uses the Python NLTK library to extract keywords and sentence structure from the text. This clarifies the content of the goal and, if necessary, generates additional questions such as, "What steps are needed to achieve this goal?". The input is the target text from Step 1, and the output is a keyword list and additional questions.

[0180] Step 3:

[0181] Once the user answers additional questions, the device re-analyzes the responses and prepares to send the final target information to the server. This process updates the text data based on the new information and packages it in JSON format. The input is the user's answers, and the output is the updated target information.

[0182] Step 4:

[0183] The terminal sends target information formatted in JSON format to the server. A secure communication protocol is used to safely transmit the data. The input here is the formatted target information, and the output is the server's confirmation of receipt.

[0184] Step 5:

[0185] The server analyzes the received target information and generates an optimal action plan using a generative AI model. It uses the TensorFlow library to create action suggestions based on user patterns and past success stories. The input is JSON data, and the output is an action plan.

[0186] Step 6:

[0187] The generated action plan is stored on the server, and relevant information sources are automatically selected. Relevant information is searched from various databases, curated, and prepared for user presentation. The input is the action plan, and the output is a list of recommended information.

[0188] Step 7:

[0189] The server sends the action plan and information list to the terminal. This allows the user to access the detailed action plan via the terminal. The input is the action plan and information list, and the output is what is presented to the user.

[0190] Step 8:

[0191] The user inputs progress information into the system via a terminal. The terminal sends this data to the server in real time. At this stage, the input is progress information, and the output is the receipt of new data on the server.

[0192] Step 9:

[0193] The server analyzes the received progress data, and the progress management module generates feedback for the user. Based on the progress data, it analyzes which steps are on schedule and provides specific improvement suggestions. The input is progress information, and the output is a feedback message.

[0194] Step 10:

[0195] The emotion engine analyzes the user's facial expressions and voice to evaluate their emotional state. The device collects user emotion data using libraries such as OpenCV, and this data is analyzed on the server. The input is the user's voice and video data, and the output is the emotion evaluation result.

[0196] Step 11:

[0197] The server generates mental care content tailored to the user based on the emotion assessment results. It selects relaxation music from a music streaming service and sends it to the device as digital content. The input is the emotion assessment results, and the output is the mental care content.

[0198] (Application Example 2)

[0199] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0200] In modern times, the process of achieving user-defined goals often suffers from a lack of support tailored to individual needs, resulting in lower success rates. Furthermore, traditional support systems fail to consider users' emotional states and are ineffective in maintaining their motivation. Additionally, the lack of personalized, emotionally responsive interactions in shopping experiences makes it difficult to provide a highly satisfying experience.

[0201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0202] In this invention, the server includes means for analyzing user-set goals and generating an action plan, means for collecting information sources and providing learning support, means for analyzing progress and providing feedback, means for performing emotion analysis and providing information, means for recommending products, and means for generating dialogue for emotional interaction through conversations in a virtual store. This makes it possible to provide users with personalized support according to their emotional state and to effectively and sustainably advance the goal achievement process.

[0203] "Means of analyzing goals" refers to techniques for understanding the goals set by users and analyzing their purpose and the steps required in detail.

[0204] "Means for generating action plans" refers to technologies that, based on analyzed goals, devise specific steps and strategies for users to efficiently achieve those goals.

[0205] "Means of collecting information sources and providing learning support" refers to methods that automatically gather necessary data and reference information from the internet and other sources to support users' learning and goal achievement.

[0206] "Means of analyzing progress and providing feedback" refers to technologies that monitor the user's progress toward their goals and propose appropriate evaluations and improvement plans based on that progress.

[0207] "Means of performing emotion analysis and providing information" refers to a function that recognizes emotions from the user's voice and facial expressions and provides appropriate information and support based on those emotions.

[0208] A "means of recommending products" is a system that suggests the most suitable products based on the user's preferences and emotional state.

[0209] "Dialogue generation means for emotionally engaging through conversations in virtual stores" refers to technology that generates conversations in a virtual reality environment to enable emotionally connected communication with users.

[0210] The system for realizing this invention mainly includes a server, a terminal, an emotion analysis module, and a dialogue generation engine. The terminal provides an interface for the user to input their goals and transmits that data to the server. The server receives this data and analyzes the goals using natural language processing techniques. Libraries such as Python's NLTK and spaCy can be used for this purpose.

[0211] Next, the server executes a machine learning algorithm to generate an action plan tailored to the user's individual information. By using TensorFlow or Scikit-learn, it makes predictions based on past data and patterns to create the optimal action plan.

[0212] Emotion analysis is performed using data from the device's built-in camera and microphone. Tools such as the Affectiva SDK and Google® Cloud Speech-to-Text are used to analyze facial expressions and voice to identify the user's emotional state. The server then uses this emotional data to recommend mental health care content and products tailored to the user.

[0213] For example, if a user sets the goal of "improving their language skills to succeed overseas," the system will suggest the necessary learning steps and materials to achieve that goal. Furthermore, if anxiety is detected through emotion analysis, the server will provide relaxation content and encouraging messages.

[0214] In the virtual store, products are recommended based on sentiment analysis results, and the dialogue generation engine generates natural conversations with the user. This utilizes a generative AI model based on OpenAI's GPT, and prompts such as "Generate product categories to recommend when the user is excited" are input.

[0215] In this way, it is possible to build a system that supports users in achieving their goals and improves the user experience.

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The terminal receives text data about the goal from the user as input. The user enters the goal using the terminal's interface and prepares to send the input data to the server.

[0219] Step 2:

[0220] The server receives the input goal and analyzes it using natural language processing. This process uses Python's NLTK and spaCy to tokenize the text and perform sentiment analysis, clarifying the structure of the goal.

[0221] Step 3:

[0222] Based on the goals analyzed by the server, an action plan is generated. Using TensorFlow and Scikit-learn, the optimal steps and resources for the input data are systematically determined. This output is then shaped into an action plan for the user.

[0223] Step 4:

[0224] The device's camera and microphone capture the user's facial expressions and voice as input data. The device sends this data to a server to understand the user's emotional state in real time.

[0225] Step 5:

[0226] The server performs emotion analysis. It uses the Affectiva SDK and Google Cloud Speech-to-Text to analyze facial expressions and voice to identify the user's emotions. The resulting emotional state data is then used for the following processes.

[0227] Step 6:

[0228] The server generates appropriate mental health care content based on the results of emotion analysis, providing comprehensive support. The server uses a generative AI model to create prompts and executes instructions such as, "Generate relaxation content that would be recommended when the user is feeling anxious."

[0229] Step 7:

[0230] In a virtual store, the server recommends products based on the user's emotional state and uses a generative AI model to create conversations that allow for emotional interaction with the user. A prototyping GPT-based model generates rich dialogue content, and output based on the input information is provided through the dialogue interface.

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

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

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

[0234] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0247] This invention is implemented as a system to provide the necessary support to ensure that users achieve their set goals without fail. This system consists of terminals, servers, and software programs, and utilizes advanced technologies such as natural language processing, machine learning, and data analysis.

[0248] First, users input their goals in text format using a device. These goals can be diverse, but must include specific achievements. The device analyzes and refines the input goals using natural language processing technology. During the analysis process, the device may ask additional questions to the user as needed to further concretize the goals.

[0249] The analyzed target data is sent from the terminal to the server. Upon receiving this target data, the server uses a pre-trained machine learning algorithm to generate an action plan optimized for the individual user. This action plan includes steps to be achieved, necessary materials, and information sources to refer to.

[0250] Furthermore, the server references a wealth of information sources on the internet and automatically selects (curates) learning content relevant to the user's goals and action plans. This selected content is provided to the user through their device, allowing them to deepen their self-study based on that content.

[0251] Furthermore, users are required to periodically report their progress using their devices. This progress data is sent to the server in real time, and the server quickly generates feedback based on this data, which is then provided to the user via their device. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0252] For example, if a user sets a goal such as "I want to acquire business English conversation skills," the system can recommend relevant online lessons, provide a list of necessary vocabulary words, and suggest the next steps based on their learning progress.

[0253] In this way, this system efficiently and effectively supports the goal achievement process by providing individually optimized support to users.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The user enters the details of their objective into the terminal. The terminal sends the received objective to a natural language processing module for initial analysis.

[0257] Step 2:

[0258] The device presents the user with additional questions to obtain more specific information based on the analysis results. The user then answers these questions.

[0259] Step 3:

[0260] The device integrates the user's responses and sends the resulting target data to the server in JSON format.

[0261] Step 4:

[0262] The server analyzes the received target data and uses machine learning algorithms to generate an individually optimized action plan based on the user's characteristics.

[0263] Step 5:

[0264] The server automatically searches the internet for relevant information sources and curates learning content. The selected content is then sent to the device.

[0265] Step 6:

[0266] Users perform activities according to their action plan via a terminal and input their progress into the terminal. The input data is immediately sent to the server.

[0267] Step 7:

[0268] The server analyzes progress data in real time and generates evaluations and feedback. This feedback includes suggestions for improvement and next steps.

[0269] Step 8:

[0270] The device receives feedback from the server and presents it to the user. Based on that feedback, the user decides on their next action.

[0271] (Example 1)

[0272] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] In today's world, there is a need for systems that effectively support individuals in achieving their goals. Conventional support systems often struggle to customize action plans to suit the specific circumstances of each user, and the information they provide is frequently inappropriate. This results in inefficient goal achievement for users.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes means for analyzing goals entered by the user via a terminal and refining them using natural language processing technology, means for generating an individualized action plan using a machine learning algorithm based on the refined goals, and means for selecting and providing educational content related to the action plan from information sources. This makes it possible to provide an optimal action plan according to the user's situation and to select relevant learning content.

[0276] "Goals" refer to the specific results or accomplishments that users wish to achieve.

[0277] "Analysis" refers to the process of analyzing input content using natural language processing techniques to refine or break down information.

[0278] "Natural language processing technology" refers to the technology used to process and understand human language using computers, and includes text analysis and data extraction.

[0279] A "machine learning algorithm" refers to a mathematical method that allows computers to learn from data and make improved decisions based on that learning experience.

[0280] The "action plan" refers to a plan that includes specific steps and actions to assist the user in achieving their goals.

[0281] The "educational content" refers to information and materials aimed at acquiring the knowledge and skills necessary for goal achievement.

[0282] The "information source" refers to a source on the Internet or other media that provides relevant data and knowledge.

[0283] "Refinement" refers to the process of information analysis and content supplementation to make the input goals clearer and more detailed.

[0284] "Selection" refers to the process of extracting highly relevant ones from various information sources and picking up only the necessary content.

[0285] "Feedback" refers to the evaluation, improvement suggestions, and advice provided regarding the user's actions and progress.

[0286] This invention is configured as a system for efficiently assisting the user in achieving their goals. It mainly consists of a terminal, a server, and a plurality of software components.

[0287] First, the user inputs their goals via the terminal. The goals are specific things to be achieved and are input in the form of "improve English business conversation skills" in a text form. The terminal analyzes this text using natural language processing technology to refine the goals. Python's natural language processing libraries (such as NLTK and spaCy) are used for the analysis.

[0288] The analyzed goal data is sent from the terminal to the server, and the server receives it. The server uses machine learning algorithms to generate an individualized action plan. Analysis tools such as Scikit-learn and TensorFlow are utilized for this. The action plan includes specific learning steps and recommended information.

[0289] Furthermore, the server selects and provides relevant educational content from internet sources. By searching its extensive database, it can present users with courses and materials tailored to their goals. For example, it can suggest, "We recommend taking this course once a week."

[0290] Users periodically report their progress via their devices. An example of their progress might be, "This week I learned 10 business terms." The server receives this information in real time, analyzes the user's progress, and generates feedback. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0291] An example of a prompt message might be: "Please enter a specific goal you would like to achieve. Example: Improve my English business conversation skills."

[0292] This system can individually optimize and effectively support the user's goal achievement process.

[0293] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0294] Step 1:

[0295] The user uses a device to input their goal. The entered goal is in text format; for example, it might be "Improve my English business conversation skills." This text data is then passed to the device as input.

[0296] Step 2:

[0297] The terminal analyzes the input text data using natural language processing techniques. Here, a Python natural language processing library (NLTK or spaCy) is used to extract target keywords and important attributes. This process involves splitting the text into tokens and tagging them by part of speech. As a result, refined target data is generated.

[0298] Step 3:

[0299] The terminal sends the analyzed target data to the server. This is done via a secure communication protocol (e.g., HTTPS using SSL). The transmitted data is expressed in JSON format, containing the specific details of the target.

[0300] Step 4:

[0301] The server uses machine learning algorithms based on the received target data to generate a personalized action plan. Here, it uses Scikit-learn or TensorFlow models and analyzes past training data and similar targets to recommend the most appropriate training steps and resources. The output of this process is a plan that includes specific action steps.

[0302] Step 5:

[0303] The server selects appropriate educational content from the internet based on the action plan and collects data from the information sources. It performs web scraping using Python's BeautifulSoup and extracts links to online courses and video lessons related to the goals. This process outputs automatically selected learning resources.

[0304] Step 6:

[0305] The server sends the selected educational content and action plan to the terminal. The terminal displays this on the screen to the user, encouraging them to use it. Specifically, it supports the user's learning by providing clickable links and downloadable materials at each step of the action plan.

[0306] Step 7:

[0307] The user regularly reports their learning progress on the terminal. This input includes specific progress information such as the number and content of the knowledge items acquired. The terminal sends this to the server in real time.

[0308] Step 8:

[0309] The server generates feedback based on the received progress data. By utilizing the generation AI model, evaluations, improvement measures, and advice for maintaining motivation based on the user's progress are created. This feedback is provided to the user via the terminal.

[0310] (Application Example 1)

[0311] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] Even if a user sets a goal, it is often difficult to effectively execute an action plan towards achieving it. Also, without appropriate feedback and support, it is difficult to maintain motivation towards goal achievement. The purpose of the present invention is to solve these problems and provide a system that supports users in effectively achieving their goals.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0314] In this invention, the server includes means for analyzing the goals set by the user and generating an individualized action plan based on the goals, means for automatically selecting information sources related to the generated action plan and providing learning support, means for receiving the user's progress status in real time, analyzing the progress status, and providing feedback to the user, and means for presenting information to support goal achievement using a visual assistance device. Thereby, the user can effectively execute actions towards goal achievement while receiving information visually and continuously receive support through feedback.

[0315] A "user" is someone who uses this system to achieve their own goals.

[0316] "Goals" refer to specific items or conditions that users wish to achieve.

[0317] "Analysis" refers to the process of analyzing and refining the goals set by the user using natural language processing technology and other methods.

[0318] An "action plan" is a plan that includes individualized, specific action steps and necessary information based on analyzed goals.

[0319] "Information sources" refer to information available on the internet or in databases that is relevant to action plans and supports users' learning.

[0320] "Progress status" refers to the degree of achievement and the progress of efforts toward the goals set by the user.

[0321] "Feedback" refers to responses that include evaluations, suggestions for improvement, and advice for maintaining motivation, based on progress.

[0322] A "visual assistance device" is a device that allows users to receive information visually, and usually refers to a wearable device.

[0323] This invention is an advanced system designed to support users in achieving their goals. It primarily consists of a server, terminals, and visual assistance devices, and utilizes natural language processing, machine learning, and data analysis technologies. Specific embodiments are described below.

[0324] First, the user inputs their desired goal via text or voice using a device. The server analyzes this goal using a natural language processing library (e.g., spaCy) to refine it. During this process, additional questions may be displayed on the device as needed to prompt the user for further input. The analyzed goal data is sent to the server, where a machine learning library (e.g., TensorFlow) generates an individualized action plan. This action plan is then sent to the device and presented to the user through a visual aid. The visual aid is envisioned to be a wearable device such as smart glasses.

[0325] The server also automatically selects relevant information and learning content from the internet and other data sources and sends it to the terminal. This information helps users more effectively execute their action plans. Users perform daily activities based on their action plans and report their progress to the server via their terminal. This progress data is analyzed in real time on the server, and feedback is generated. The feedback includes an assessment of achievement, suggestions for improvement, and advice to boost motivation, and is provided to the user through visual aids.

[0326] For example, when a store employee sets a sales target for a new product, using a visual aid allows them to interact with customers while checking real-time information on successful sales cases and popular products. This supports the optimal approach to achieving the target.

[0327] An example of a prompt to input into the generating AI model would be: "To design an application that helps store staff achieve their goals, consider the flow from goal setting to providing feedback."

[0328] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0329] Step 1:

[0330] The user enters their goal using a terminal, either as text or voice. The entered data is sent directly to the server. The server uses a natural language processing library to analyze the text data and refine the goal. If voice data is used, speech recognition software is used to convert it to text. The analyzed data is then formatted to meet the user's specific goal requirements.

[0331] Step 2:

[0332] The server receives refined goal data and generates personalized action plans using machine learning models. It takes analyzed goal data as input and identifies feasible tasks and necessary resources based on it. In this process, data analysis algorithms select the optimal plan and send the results to the terminal.

[0333] Step 3:

[0334] The terminal receives the action plan generated from the server and presents it visually to the user through a visual aid. At this point, the information is displayed on the screen in an easy-to-understand format so that the user can understand the details of the plan. Based on this information, the user plans and carries out their daily activities.

[0335] Step 4:

[0336] Users report their progress to the server via their devices. This data is stored on the server in real time and processed by a data analysis engine. Based on the input progress data, the current level of achievement and any problems are analyzed, and the next steps to take are determined.

[0337] Step 5:

[0338] The server generates feedback based on the analysis of progress data and provides it to the user through the terminal and visual aids. This feedback includes areas for improvement, suggestions for next actions, and encouraging messages to boost motivation. The user then uses this feedback to adjust their actions and move towards achieving their goals.

[0339] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0340] This invention is implemented in a more advanced form by incorporating an emotion engine as a system that provides support for achieving user-defined goals. This system consists of a terminal, a server, and an emotion engine as its main components, and utilizes natural language processing, machine learning, emotion recognition technology, and the like.

[0341] In the initial stages of the system, users input their goals as text via a terminal. The terminal analyzes the received goals using natural language processing technology. This analysis includes prompting additional questions, and the terminal asks the user questions as needed to help them refine their goals.

[0342] Detailed user goal information is sent from the terminal to the server. Based on this goal data, the server generates an optimal action plan tailored to the user's individual characteristics and circumstances. The generated action plan includes the steps and reference information necessary to achieve the goals.

[0343] A key feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. The recognized emotional data is sent to a server, which then generates mental care content for the user based on this data. This content includes encouragement and relaxation techniques tailored to the emotional state.

[0344] Furthermore, the server uses all the data, including emotional state and progress information, to optimize action suggestions to help maintain user motivation. The learning environment and action plan are also adjusted in response to changes in emotions.

[0345] For example, if a user sets the goal of "improving their English skills to work abroad," the system will recommend lessons on necessary vocabulary and grammar. When the user's emotional state indicates tension or anxiety, the server will provide content to help them relax and support them in maintaining their motivation.

[0346] Through this system, users can receive support tailored to their individual needs, and the process toward achieving their goals can be advanced effectively and sustainably.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The user enters their desired goals into the device. The device analyzes this input data using natural language processing technology to identify the basic objective.

[0350] Step 2:

[0351] The device evaluates the analyzed data and, if it determines that the goal needs to be made more specific, displays additional questions to the user. By answering these questions, the user sets the goal more concretely.

[0352] Step 3:

[0353] The device formats the specified goal data and sends it to the server. The server receives this data and generates a personalized action plan that takes the user's characteristics into account.

[0354] Step 4:

[0355] The server automatically curates learning content by selecting relevant information sources from the internet that align with the user's goals. This content is then sent to the device and presented to the user.

[0356] Step 5:

[0357] Users progress through learning activities based on recommended content and action plans. Progress is periodically entered into the device, and this data is sent to the server.

[0358] Step 6:

[0359] The server uses an emotion engine to analyze the user's facial expressions and voice data to understand their emotional state. This emotional data is then used to generate mental care content tailored to each individual's situation.

[0360] Step 7:

[0361] The server integrates and analyzes the acquired emotional and progress data to generate feedback and suggestions for the next action for the user. This feedback also includes advice on maintaining motivation based on the user's emotional state.

[0362] Step 8:

[0363] The device presents the user with feedback and advice received from the server. Based on this, the user further modifies their action plan and continues their activities toward their goals.

[0364] (Example 2)

[0365] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0366] In today's world, where it is essential to provide individually optimized action plans based on user-defined goals, it is difficult to grasp users' progress and emotional states in real time and provide appropriate feedback and mental care accordingly. Furthermore, there is a lack of efficient means to provide learning support from diverse information sources.

[0367] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0368] In this invention, the server includes means for analyzing user-set goals and generating an individualized action plan, means for automatically selecting information sources related to the generated action plan and providing learning support, and means for analyzing the user's emotional state and generating and providing content for mental care based on emotional information. This enables support tailored to each user's characteristics and circumstances, and facilitates the smooth progress of the process toward achieving goals.

[0369] "Analyzing goals" means using natural language processing technology to extract and understand the content of the goals set by the user.

[0370] An "individualized action plan" is a plan that includes optimized action plans and steps based on each user's individual goals.

[0371] "Automatically selecting information sources" means automatically choosing various databases and materials relevant to the purpose using machine learning technology.

[0372] "Providing learning support" means providing learning materials and resources to improve users' knowledge and skills.

[0373] "Receiving progress in real time" means instantly incorporating user activity and learning progress into the system.

[0374] Providing feedback means offering evaluations and suggestions for improvement regarding the user's progress and actions, and providing information to encourage their next steps.

[0375] "Analyzing emotional state" means inferring a user's psychological state from their facial expressions and voice, and then determining their emotions.

[0376] "Content for mental care" refers to advice and relaxation methods provided to support the mental health of users.

[0377] "Generative AI technology" is a technology that uses artificial intelligence to generate new information and data.

[0378] A "remote device" is an internet-connected electronic device that can be accessed by servers and users.

[0379] This invention is a system that provides advanced support for achieving user-defined goals. The system primarily consists of a terminal, a server, and an emotion engine. The system utilizes natural language processing, machine learning, and emotion recognition technologies.

[0380] The user enters their goal through the device. This goal is analyzed by natural language processing software installed on the device (e.g., Python's NLTK library), which then derives specific content and additional questions to help the user achieve the goal. For example, if the user sets a goal such as "I want to gain confidence in giving presentations in English," a detailed action plan will be presented based on that goal.

[0381] The analyzed target data is sent from the terminal to the server. The server generates an action plan using a generative AI model (e.g., TensorFlow). This plan includes curating relevant information and tasks to be performed. The analysis results are delivered to a remote device via data communication, making them accessible to the user.

[0382] Furthermore, the emotion engine analyzes the user's facial expressions and voice via the device to evaluate their emotional state. Using libraries such as OpenCV, it analyzes facial expressions in real time and generates and provides mental care content based on this analysis. This content includes suggestions for relaxation-oriented music.

[0383] As a result, this system can provide precise and flexible support tailored to the individual needs of each user, and optimize the process to achieve goals.

[0384] A concrete example of a prompt might be: "The user has the goal of 'improving their English skills to work abroad.' Use a generative AI model to propose an action plan that aligns with this goal, and further adjust mental support based on the results of an analysis of their emotional state."

[0385] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0386] Step 1:

[0387] The user uses a terminal to input their set goal in text format. The entered text is sent to the goal analysis module. Here, the input is the user's goal text, and the output is text ready for analysis.

[0388] Step 2:

[0389] The terminal uses a natural language processing engine to analyze the input target text. It uses the Python NLTK library to extract keywords and sentence structure from the text. This clarifies the content of the goal and, if necessary, generates additional questions such as, "What steps are needed to achieve this goal?". The input is the target text from Step 1, and the output is a keyword list and additional questions.

[0390] Step 3:

[0391] Once the user answers additional questions, the device re-analyzes the responses and prepares to send the final target information to the server. This process updates the text data based on the new information and packages it in JSON format. The input is the user's answers, and the output is the updated target information.

[0392] Step 4:

[0393] The terminal sends target information formatted in JSON format to the server. A secure communication protocol is used to safely transmit the data. The input here is the formatted target information, and the output is the server's confirmation of receipt.

[0394] Step 5:

[0395] The server analyzes the received target information and generates an optimal action plan using a generative AI model. It uses the TensorFlow library to create action suggestions based on user patterns and past success stories. The input is JSON data, and the output is an action plan.

[0396] Step 6:

[0397] The generated action plan is stored on the server, and relevant information sources are automatically selected. Relevant information is searched from various databases, curated, and prepared for user presentation. The input is the action plan, and the output is a list of recommended information.

[0398] Step 7:

[0399] The server sends the action plan and information list to the terminal. This allows the user to access the detailed action plan via the terminal. The input is the action plan and information list, and the output is what is presented to the user.

[0400] Step 8:

[0401] The user inputs progress information into the system via a terminal. The terminal sends this data to the server in real time. At this stage, the input is progress information, and the output is the receipt of new data on the server.

[0402] Step 9:

[0403] The server analyzes the received progress data, and the progress management module generates feedback for the user. Based on the progress data, it analyzes which steps are on schedule and provides specific improvement suggestions. The input is progress information, and the output is a feedback message.

[0404] Step 10:

[0405] The emotion engine analyzes the user's facial expressions and voice to evaluate their emotional state. The device collects user emotion data using libraries such as OpenCV, and this data is analyzed on the server. The input is the user's voice and video data, and the output is the emotion evaluation result.

[0406] Step 11:

[0407] The server generates mental care content tailored to the user based on the emotion assessment results. It selects relaxation music from a music streaming service and sends it to the device as digital content. The input is the emotion assessment results, and the output is the mental care content.

[0408] (Application Example 2)

[0409] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0410] In modern times, the process of achieving user-defined goals often suffers from a lack of support tailored to individual needs, resulting in lower success rates. Furthermore, traditional support systems fail to consider users' emotional states and are ineffective in maintaining their motivation. Additionally, the lack of personalized, emotionally responsive interactions in shopping experiences makes it difficult to provide a highly satisfying experience.

[0411] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0412] In this invention, the server includes means for analyzing user-set goals and generating an action plan, means for collecting information sources and providing learning support, means for analyzing progress and providing feedback, means for performing emotion analysis and providing information, means for recommending products, and means for generating dialogue for emotional interaction through conversations in a virtual store. This makes it possible to provide users with personalized support according to their emotional state and to effectively and sustainably advance the goal achievement process.

[0413] "Means of analyzing goals" refers to techniques for understanding the goals set by users and analyzing their purpose and the steps required in detail.

[0414] "Means for generating action plans" refers to technologies that, based on analyzed goals, devise specific steps and strategies for users to efficiently achieve those goals.

[0415] "Means of collecting information sources and providing learning support" refers to methods that automatically gather necessary data and reference information from the internet and other sources to support users' learning and goal achievement.

[0416] "Means of analyzing progress and providing feedback" refers to technologies that monitor the user's progress toward their goals and propose appropriate evaluations and improvement plans based on that progress.

[0417] "Means of performing emotion analysis and providing information" refers to a function that recognizes emotions from the user's voice and facial expressions and provides appropriate information and support based on those emotions.

[0418] A "means of recommending products" is a system that suggests the most suitable products based on the user's preferences and emotional state.

[0419] "Dialogue generation means for emotionally engaging through conversations in virtual stores" refers to technology that generates conversations in a virtual reality environment to enable emotionally connected communication with users.

[0420] The system for realizing this invention mainly includes a server, a terminal, an emotion analysis module, and a dialogue generation engine. The terminal provides an interface for the user to input their goals and transmits that data to the server. The server receives this data and analyzes the goals using natural language processing techniques. Libraries such as Python's NLTK and spaCy can be used for this purpose.

[0421] Next, the server executes a machine learning algorithm to generate an action plan tailored to the user's individual information. By using TensorFlow or Scikit-learn, it makes predictions based on past data and patterns to create the optimal action plan.

[0422] Emotion analysis is performed using data from the device's built-in camera and microphone. Tools such as the Affectiva SDK and Google Cloud Speech-to-Text are used to analyze facial expressions and voice to identify the user's emotional state. The server then uses this emotional data to recommend mental health care content and products tailored to the user.

[0423] For example, if a user sets the goal of "improving their language skills to succeed overseas," the system will suggest the necessary learning steps and materials to achieve that goal. Furthermore, if anxiety is detected through emotion analysis, the server will provide relaxation content and encouraging messages.

[0424] In the virtual store, products are recommended based on sentiment analysis results, and the dialogue generation engine generates natural conversations with the user. This utilizes a generative AI model based on OpenAI's GPT, and prompts such as "Generate product categories to recommend when the user is excited" are input.

[0425] In this way, it is possible to build a system that supports users in achieving their goals and improves the user experience.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The terminal receives text data about the goal from the user as input. The user enters the goal using the terminal's interface and prepares to send the input data to the server.

[0429] Step 2:

[0430] The server receives the input goal and analyzes it using natural language processing. This process uses Python's NLTK and spaCy to tokenize the text and perform sentiment analysis, clarifying the structure of the goal.

[0431] Step 3:

[0432] Based on the goals analyzed by the server, an action plan is generated. Using TensorFlow and Scikit-learn, the optimal steps and resources for the input data are systematically determined. This output is then shaped into an action plan for the user.

[0433] Step 4:

[0434] The device's camera and microphone capture the user's facial expressions and voice as input data. The device sends this data to a server to understand the user's emotional state in real time.

[0435] Step 5:

[0436] The server performs emotion analysis. It uses the Affectiva SDK and Google Cloud Speech-to-Text to analyze facial expressions and voice to identify the user's emotions. The resulting emotional state data is then used for the following processes.

[0437] Step 6:

[0438] The server generates appropriate mental health care content based on the results of emotion analysis, providing comprehensive support. The server uses a generative AI model to create prompts and executes instructions such as, "Generate relaxation content that would be recommended when the user is feeling anxious."

[0439] Step 7:

[0440] In a virtual store, the server recommends products based on the user's emotional state and uses a generative AI model to create conversations that allow for emotional interaction with the user. A prototyping GPT-based model generates rich dialogue content, and output based on the input information is provided through the dialogue interface.

[0441] 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.

[0442] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] 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.

[0447] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] 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.

[0449] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0451] 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.

[0452] 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.

[0453] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0454] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0456] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0457] This invention is implemented as a system to provide the necessary support to ensure that users achieve their set goals without fail. This system consists of terminals, servers, and software programs, and utilizes advanced technologies such as natural language processing, machine learning, and data analysis.

[0458] First, users input their goals in text format using a device. These goals can be diverse, but must include specific achievements. The device analyzes and refines the input goals using natural language processing technology. During the analysis process, the device may ask additional questions to the user as needed to further concretize the goals.

[0459] The analyzed target data is sent from the terminal to the server. Upon receiving this target data, the server uses a pre-trained machine learning algorithm to generate an action plan optimized for the individual user. This action plan includes steps to be achieved, necessary materials, and information sources to refer to.

[0460] Furthermore, the server references a wealth of information sources on the internet and automatically selects (curates) learning content relevant to the user's goals and action plans. This selected content is provided to the user through their device, allowing them to deepen their self-study based on that content.

[0461] Furthermore, users are required to periodically report their progress using their devices. This progress data is sent to the server in real time, and the server quickly generates feedback based on this data, which is then provided to the user via their device. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0462] For example, if a user sets a goal such as "I want to acquire business English conversation skills," the system can recommend relevant online lessons, provide a list of necessary vocabulary words, and suggest the next steps based on their learning progress.

[0463] In this way, this system efficiently and effectively supports the goal achievement process by providing individually optimized support to users.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] The user enters the details of their objective into the terminal. The terminal sends the received objective to a natural language processing module for initial analysis.

[0467] Step 2:

[0468] The device presents the user with additional questions to obtain more specific information based on the analysis results. The user then answers these questions.

[0469] Step 3:

[0470] The device integrates the user's responses and sends the resulting target data to the server in JSON format.

[0471] Step 4:

[0472] The server analyzes the received target data and uses machine learning algorithms to generate an individually optimized action plan based on the user's characteristics.

[0473] Step 5:

[0474] The server automatically searches the internet for relevant information sources and curates learning content. The selected content is then sent to the device.

[0475] Step 6:

[0476] Users perform activities according to their action plan via a terminal and input their progress into the terminal. The input data is immediately sent to the server.

[0477] Step 7:

[0478] The server analyzes progress data in real time and generates evaluations and feedback. This feedback includes suggestions for improvement and next steps.

[0479] Step 8:

[0480] The device receives feedback from the server and presents it to the user. Based on that feedback, the user decides on their next action.

[0481] (Example 1)

[0482] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0483] In today's world, there is a need for systems that effectively support individuals in achieving their goals. Conventional support systems often struggle to customize action plans to suit the specific circumstances of each user, and the information they provide is frequently inappropriate. This results in inefficient goal achievement for users.

[0484] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0485] In this invention, the server includes means for analyzing goals entered by the user via a terminal and refining them using natural language processing technology, means for generating an individualized action plan using a machine learning algorithm based on the refined goals, and means for selecting and providing educational content related to the action plan from information sources. This makes it possible to provide an optimal action plan according to the user's situation and to select relevant learning content.

[0486] "Goals" refer to the specific results or accomplishments that users wish to achieve.

[0487] "Analysis" refers to the process of analyzing input content using natural language processing techniques to refine or break down information.

[0488] "Natural language processing technology" refers to the technology used to process and understand human language using computers, and includes text analysis and data extraction.

[0489] A "machine learning algorithm" refers to a mathematical method that allows computers to learn from data and make improved decisions based on that learning experience.

[0490] An "action plan" refers to a plan that includes specific steps and actions to support users in achieving their goals.

[0491] "Educational content" refers to information and materials aimed at acquiring the knowledge and skills necessary to achieve a goal.

[0492] "Information source" refers to a source on the internet or other media that provides relevant data or knowledge.

[0493] "Elaboration" refers to the process of analyzing information and supplementing content to make the entered goals clearer and more detailed.

[0494] "Selection" refers to the process of extracting highly relevant information from diverse sources and picking out only the necessary content.

[0495] "Feedback" refers to evaluations, suggestions for improvement, and advice provided regarding a user's behavior and progress.

[0496] This invention is configured as a system that efficiently supports users in achieving their goals. It mainly consists of a terminal, a server, and multiple software components.

[0497] First, the user enters their goal via the terminal. The goal is entered as a specific item they want to achieve, in the form of a text field, such as "Improve my English business conversation skills." The terminal analyzes this text using natural language processing technology to refine the goal. Python natural language processing libraries (such as NLTK or spaCy) are used for the analysis.

[0498] The analyzed target data is sent from the terminal to the server, which receives it. The server uses machine learning algorithms to generate a personalized action plan. This utilizes analytical tools such as Scikit-learn and TensorFlow. The action plan includes specific learning steps and recommendations.

[0499] Furthermore, the server selects and provides relevant educational content from internet sources. By searching its extensive database, it can present users with courses and materials tailored to their goals. For example, it can suggest, "We recommend taking this course once a week."

[0500] Users periodically report their progress via their devices. An example of their progress might be, "This week I learned 10 business terms." The server receives this information in real time, analyzes the user's progress, and generates feedback. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0501] An example of a prompt message might be: "Please enter a specific goal you would like to achieve. Example: Improve my English business conversation skills."

[0502] This system can individually optimize and effectively support the user's goal achievement process.

[0503] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0504] Step 1:

[0505] The user uses a device to input their goal. The entered goal is in text format; for example, it might be "Improve my English business conversation skills." This text data is then passed to the device as input.

[0506] Step 2:

[0507] The terminal analyzes the input text data using natural language processing techniques. Here, a Python natural language processing library (NLTK or spaCy) is used to extract target keywords and important attributes. This process involves splitting the text into tokens and tagging them by part of speech. As a result, refined target data is generated.

[0508] Step 3:

[0509] The terminal sends the analyzed target data to the server. This is done via a secure communication protocol (e.g., HTTPS using SSL). The transmitted data is expressed in JSON format, containing the specific details of the target.

[0510] Step 4:

[0511] The server uses machine learning algorithms based on the received target data to generate a personalized action plan. Here, it uses Scikit-learn or TensorFlow models and analyzes past training data and similar targets to recommend the most appropriate training steps and resources. The output of this process is a plan that includes specific action steps.

[0512] Step 5:

[0513] The server selects appropriate educational content from the internet based on the action plan and collects data from the information sources. It performs web scraping using Python's BeautifulSoup and extracts links to online courses and video lessons related to the goals. This process outputs automatically selected learning resources.

[0514] Step 6:

[0515] The server sends the selected educational content and action plan to the terminal. The terminal displays this on the screen to the user, encouraging them to use it. Specifically, it supports the user's learning by providing clickable links and downloadable materials at each step of the action plan.

[0516] Step 7:

[0517] Users periodically report their learning progress via their devices. This input includes specific progress information, such as the number and content of knowledge items acquired. The devices transmit this information to the server in real time.

[0518] Step 8:

[0519] The server generates feedback based on the received progress data. Using a generation AI model, evaluations, improvement suggestions, and motivational advice are created based on the user's progress. This feedback is then delivered to the user via their device.

[0520] (Application Example 1)

[0521] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0522] Even when users set goals, it is often difficult for them to effectively execute action plans to achieve them. Furthermore, without appropriate feedback and support, it is difficult to maintain motivation toward achieving goals. The present invention aims to solve these problems and provide a system that supports users in effectively achieving their goals.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0524] In this invention, the server includes means for analyzing goals set by the user and generating an individualized action plan based on those goals; means for automatically selecting information sources related to the generated action plan and providing learning support; means for receiving the user's progress in real time, analyzing that progress, and providing feedback to the user; and means for presenting information that supports goal achievement using a visual aid device. As a result, the user can effectively take actions toward achieving their goals while receiving information visually, and can receive continuous support through feedback.

[0525] A "user" is someone who uses this system to achieve their own goals.

[0526] "Goals" refer to specific items or conditions that users wish to achieve.

[0527] "Analysis" refers to the process of analyzing and refining the goals set by the user using natural language processing technology and other methods.

[0528] An "action plan" is a plan that includes individualized, specific action steps and necessary information based on analyzed goals.

[0529] "Information sources" refer to information available on the internet or in databases that is relevant to action plans and supports users' learning.

[0530] "Progress status" refers to the degree of achievement and the progress of efforts toward the goals set by the user.

[0531] "Feedback" refers to responses that include evaluations, suggestions for improvement, and advice for maintaining motivation, based on progress.

[0532] A "visual assistance device" is a device that allows users to receive information visually, and usually refers to a wearable device.

[0533] This invention is an advanced system designed to support users in achieving their goals. It primarily consists of a server, terminals, and visual assistance devices, and utilizes natural language processing, machine learning, and data analysis technologies. Specific embodiments are described below.

[0534] First, the user inputs their desired goal via text or voice using a device. The server analyzes this goal using a natural language processing library (e.g., spaCy) to refine it. During this process, additional questions may be displayed on the device as needed to prompt the user for further input. The analyzed goal data is sent to the server, where a machine learning library (e.g., TensorFlow) generates an individualized action plan. This action plan is then sent to the device and presented to the user through a visual aid. The visual aid is envisioned to be a wearable device such as smart glasses.

[0535] The server also automatically selects relevant information and learning content from the internet and other data sources and sends it to the terminal. This information helps users more effectively execute their action plans. Users perform daily activities based on their action plans and report their progress to the server via their terminal. This progress data is analyzed in real time on the server, and feedback is generated. The feedback includes an assessment of achievement, suggestions for improvement, and advice to boost motivation, and is provided to the user through visual aids.

[0536] For example, when a store employee sets a sales target for a new product, using a visual aid allows them to interact with customers while checking real-time information on successful sales cases and popular products. This supports the optimal approach to achieving the target.

[0537] An example of a prompt to input into the generating AI model would be: "To design an application that helps store staff achieve their goals, consider the flow from goal setting to providing feedback."

[0538] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0539] Step 1:

[0540] The user enters their goal using a terminal, either as text or voice. The entered data is sent directly to the server. The server uses a natural language processing library to analyze the text data and refine the goal. If voice data is used, speech recognition software is used to convert it to text. The analyzed data is then formatted to meet the user's specific goal requirements.

[0541] Step 2:

[0542] The server receives refined goal data and generates personalized action plans using machine learning models. It takes analyzed goal data as input and identifies feasible tasks and necessary resources based on it. In this process, data analysis algorithms select the optimal plan and send the results to the terminal.

[0543] Step 3:

[0544] The terminal receives the action plan generated from the server and presents it visually to the user through a visual aid. At this point, the information is displayed on the screen in an easy-to-understand format so that the user can understand the details of the plan. Based on this information, the user plans and carries out their daily activities.

[0545] Step 4:

[0546] Users report their progress to the server via their devices. This data is stored on the server in real time and processed by a data analysis engine. Based on the input progress data, the current level of achievement and any problems are analyzed, and the next steps to take are determined.

[0547] Step 5:

[0548] The server generates feedback based on the analysis of progress data and provides it to the user through the terminal and visual aids. This feedback includes areas for improvement, suggestions for next actions, and encouraging messages to boost motivation. The user then uses this feedback to adjust their actions and move towards achieving their goals.

[0549] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0550] This invention is implemented in a more advanced form by incorporating an emotion engine as a system that provides support for achieving user-defined goals. This system consists of a terminal, a server, and an emotion engine as its main components, and utilizes natural language processing, machine learning, emotion recognition technology, and the like.

[0551] In the initial stages of the system, users input their goals as text via a terminal. The terminal analyzes the received goals using natural language processing technology. This analysis includes prompting additional questions, and the terminal asks the user questions as needed to help them refine their goals.

[0552] Detailed user goal information is sent from the terminal to the server. Based on this goal data, the server generates an optimal action plan tailored to the user's individual characteristics and circumstances. The generated action plan includes the steps and reference information necessary to achieve the goals.

[0553] A key feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. The recognized emotional data is sent to a server, which then generates mental care content for the user based on this data. This content includes encouragement and relaxation techniques tailored to the emotional state.

[0554] Furthermore, the server uses all the data, including emotional state and progress information, to optimize action suggestions to help maintain user motivation. The learning environment and action plan are also adjusted in response to changes in emotions.

[0555] For example, if a user sets the goal of "improving their English skills to work abroad," the system will recommend lessons on necessary vocabulary and grammar. When the user's emotional state indicates tension or anxiety, the server will provide content to help them relax and support them in maintaining their motivation.

[0556] Through this system, users can receive support tailored to their individual needs, and the process toward achieving their goals can be advanced effectively and sustainably.

[0557] The following describes the processing flow.

[0558] Step 1:

[0559] The user enters their desired goals into the device. The device analyzes this input data using natural language processing technology to identify the basic objective.

[0560] Step 2:

[0561] The device evaluates the analyzed data and, if it determines that the goal needs to be made more specific, displays additional questions to the user. By answering these questions, the user sets the goal more concretely.

[0562] Step 3:

[0563] The device formats the specified goal data and sends it to the server. The server receives this data and generates a personalized action plan that takes the user's characteristics into account.

[0564] Step 4:

[0565] The server automatically curates learning content by selecting relevant information sources from the internet that align with the user's goals. This content is then sent to the device and presented to the user.

[0566] Step 5:

[0567] Users progress through learning activities based on recommended content and action plans. Progress is periodically entered into the device, and this data is sent to the server.

[0568] Step 6:

[0569] The server uses an emotion engine to analyze the user's facial expressions and voice data to understand their emotional state. This emotional data is then used to generate mental care content tailored to each individual's situation.

[0570] Step 7:

[0571] The server integrates and analyzes the acquired emotional and progress data to generate feedback and suggestions for the next action for the user. This feedback also includes advice on maintaining motivation based on the user's emotional state.

[0572] Step 8:

[0573] The device presents the user with feedback and advice received from the server. Based on this, the user further modifies their action plan and continues their activities toward their goals.

[0574] (Example 2)

[0575] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0576] In today's world, where it is essential to provide individually optimized action plans based on user-defined goals, it is difficult to grasp users' progress and emotional states in real time and provide appropriate feedback and mental care accordingly. Furthermore, there is a lack of efficient means to provide learning support from diverse information sources.

[0577] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0578] In this invention, the server includes means for analyzing user-set goals and generating an individualized action plan, means for automatically selecting information sources related to the generated action plan and providing learning support, and means for analyzing the user's emotional state and generating and providing content for mental care based on emotional information. This enables support tailored to each user's characteristics and circumstances, and facilitates the smooth progress of the process toward achieving goals.

[0579] "Analyzing goals" means using natural language processing technology to extract and understand the content of the goals set by the user.

[0580] An "individualized action plan" is a plan that includes optimized action plans and steps based on each user's individual goals.

[0581] "Automatically selecting information sources" means automatically choosing various databases and materials relevant to the purpose using machine learning technology.

[0582] "Providing learning support" means providing learning materials and resources to improve users' knowledge and skills.

[0583] "Receiving progress in real time" means instantly incorporating user activity and learning progress into the system.

[0584] Providing feedback means offering evaluations and suggestions for improvement regarding the user's progress and actions, and providing information to encourage their next steps.

[0585] "Analyzing emotional state" means inferring a user's psychological state from their facial expressions and voice, and then determining their emotions.

[0586] "Content for mental care" refers to advice and relaxation methods provided to support the mental health of users.

[0587] "Generative AI technology" is a technology that uses artificial intelligence to generate new information and data.

[0588] A "remote device" is an internet-connected electronic device that can be accessed by servers and users.

[0589] This invention is a system that provides advanced support for achieving user-defined goals. The system primarily consists of a terminal, a server, and an emotion engine. The system utilizes natural language processing, machine learning, and emotion recognition technologies.

[0590] The user enters their goal through the device. This goal is analyzed by natural language processing software installed on the device (e.g., Python's NLTK library), which then derives specific content and additional questions to help the user achieve the goal. For example, if the user sets a goal such as "I want to gain confidence in giving presentations in English," a detailed action plan will be presented based on that goal.

[0591] The analyzed target data is sent from the terminal to the server. The server generates an action plan using a generative AI model (e.g., TensorFlow). This plan includes curating relevant information and tasks to be performed. The analysis results are delivered to a remote device via data communication, making them accessible to the user.

[0592] Furthermore, the emotion engine analyzes the user's facial expressions and voice via the device to evaluate their emotional state. Using libraries such as OpenCV, it analyzes facial expressions in real time and generates and provides mental care content based on this analysis. This content includes suggestions for relaxation-oriented music.

[0593] As a result, this system can provide precise and flexible support tailored to the individual needs of each user, and optimize the process to achieve goals.

[0594] A concrete example of a prompt might be: "The user has the goal of 'improving their English skills to work abroad.' Use a generative AI model to propose an action plan that aligns with this goal, and further adjust mental support based on the results of an analysis of their emotional state."

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The user uses a terminal to input their set goal in text format. The entered text is sent to the goal analysis module. Here, the input is the user's goal text, and the output is text ready for analysis.

[0598] Step 2:

[0599] The terminal uses a natural language processing engine to analyze the input target text. It uses the Python NLTK library to extract keywords and sentence structure from the text. This clarifies the content of the goal and, if necessary, generates additional questions such as, "What steps are needed to achieve this goal?". The input is the target text from Step 1, and the output is a keyword list and additional questions.

[0600] Step 3:

[0601] Once the user answers additional questions, the device re-analyzes the responses and prepares to send the final target information to the server. This process updates the text data based on the new information and packages it in JSON format. The input is the user's answers, and the output is the updated target information.

[0602] Step 4:

[0603] The terminal sends target information formatted in JSON format to the server. A secure communication protocol is used to safely transmit the data. The input here is the formatted target information, and the output is the server's confirmation of receipt.

[0604] Step 5:

[0605] The server analyzes the received target information and generates an optimal action plan using a generative AI model. It uses the TensorFlow library to create action suggestions based on user patterns and past success stories. The input is JSON data, and the output is an action plan.

[0606] Step 6:

[0607] The generated action plan is stored on the server, and relevant information sources are automatically selected. Relevant information is searched from various databases, curated, and prepared for user presentation. The input is the action plan, and the output is a list of recommended information.

[0608] Step 7:

[0609] The server sends the action plan and information list to the terminal. This allows the user to access the detailed action plan via the terminal. The input is the action plan and information list, and the output is what is presented to the user.

[0610] Step 8:

[0611] The user inputs progress information into the system via a terminal. The terminal sends this data to the server in real time. At this stage, the input is progress information, and the output is the receipt of new data on the server.

[0612] Step 9:

[0613] The server analyzes the received progress data, and the progress management module generates feedback for the user. Based on the progress data, it analyzes which steps are on schedule and provides specific improvement suggestions. The input is progress information, and the output is a feedback message.

[0614] Step 10:

[0615] The emotion engine analyzes the user's facial expressions and voice to evaluate their emotional state. The device collects user emotion data using libraries such as OpenCV, and this data is analyzed on the server. The input is the user's voice and video data, and the output is the emotion evaluation result.

[0616] Step 11:

[0617] The server generates mental care content tailored to the user based on the emotion assessment results. It selects relaxation music from a music streaming service and sends it to the device as digital content. The input is the emotion assessment results, and the output is the mental care content.

[0618] (Application Example 2)

[0619] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0620] In modern times, the process of achieving user-defined goals often suffers from a lack of support tailored to individual needs, resulting in lower success rates. Furthermore, traditional support systems fail to consider users' emotional states and are ineffective in maintaining their motivation. Additionally, the lack of personalized, emotionally responsive interactions in shopping experiences makes it difficult to provide a highly satisfying experience.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0622] In this invention, the server includes means for analyzing user-set goals and generating an action plan, means for collecting information sources and providing learning support, means for analyzing progress and providing feedback, means for performing emotion analysis and providing information, means for recommending products, and means for generating dialogue for emotional interaction through conversations in a virtual store. This makes it possible to provide users with personalized support according to their emotional state and to effectively and sustainably advance the goal achievement process.

[0623] "Means of analyzing goals" refers to techniques for understanding the goals set by users and analyzing their purpose and the steps required in detail.

[0624] "Means for generating action plans" refers to technologies that, based on analyzed goals, devise specific steps and strategies for users to efficiently achieve those goals.

[0625] "Means of collecting information sources and providing learning support" refers to methods that automatically gather necessary data and reference information from the internet and other sources to support users' learning and goal achievement.

[0626] "Means of analyzing progress and providing feedback" refers to technologies that monitor the user's progress toward their goals and propose appropriate evaluations and improvement plans based on that progress.

[0627] "Means of performing emotion analysis and providing information" refers to a function that recognizes emotions from the user's voice and facial expressions and provides appropriate information and support based on those emotions.

[0628] A "means of recommending products" is a system that suggests the most suitable products based on the user's preferences and emotional state.

[0629] "Dialogue generation means for emotionally engaging through conversations in virtual stores" refers to technology that generates conversations in a virtual reality environment to enable emotionally connected communication with users.

[0630] The system for realizing this invention mainly includes a server, a terminal, an emotion analysis module, and a dialogue generation engine. The terminal provides an interface for the user to input their goals and transmits that data to the server. The server receives this data and analyzes the goals using natural language processing techniques. Libraries such as Python's NLTK and spaCy can be used for this purpose.

[0631] Next, the server executes a machine learning algorithm to generate an action plan tailored to the user's individual information. By using TensorFlow or Scikit-learn, it makes predictions based on past data and patterns to create the optimal action plan.

[0632] Emotion analysis is performed using data from the device's built-in camera and microphone. Tools such as the Affectiva SDK and Google Cloud Speech-to-Text are used to analyze facial expressions and voice to identify the user's emotional state. The server then uses this emotional data to recommend mental health care content and products tailored to the user.

[0633] For example, if a user sets the goal of "improving their language skills to succeed overseas," the system will suggest the necessary learning steps and materials to achieve that goal. Furthermore, if anxiety is detected through emotion analysis, the server will provide relaxation content and encouraging messages.

[0634] In the virtual store, products are recommended based on sentiment analysis results, and the dialogue generation engine generates natural conversations with the user. This utilizes a generative AI model based on OpenAI's GPT, and prompts such as "Generate product categories to recommend when the user is excited" are input.

[0635] In this way, it is possible to build a system that supports users in achieving their goals and improves the user experience.

[0636] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0637] Step 1:

[0638] The terminal receives text data about the goal from the user as input. The user enters the goal using the terminal's interface and prepares to send the input data to the server.

[0639] Step 2:

[0640] The server receives the input goal and analyzes it using natural language processing. This process uses Python's NLTK and spaCy to tokenize the text and perform sentiment analysis, clarifying the structure of the goal.

[0641] Step 3:

[0642] Based on the goals analyzed by the server, an action plan is generated. Using TensorFlow and Scikit-learn, the optimal steps and resources for the input data are systematically determined. This output is then shaped into an action plan for the user.

[0643] Step 4:

[0644] The device's camera and microphone capture the user's facial expressions and voice as input data. The device sends this data to a server to understand the user's emotional state in real time.

[0645] Step 5:

[0646] The server performs emotion analysis. It uses the Affectiva SDK and Google Cloud Speech-to-Text to analyze facial expressions and voice to identify the user's emotions. The resulting emotional state data is then used for the following processes.

[0647] Step 6:

[0648] The server generates appropriate mental health care content based on the results of emotion analysis, providing comprehensive support. The server uses a generative AI model to create prompts and executes instructions such as, "Generate relaxation content that would be recommended when the user is feeling anxious."

[0649] Step 7:

[0650] In a virtual store, the server recommends products based on the user's emotional state and uses a generative AI model to create conversations that allow for emotional interaction with the user. A prototyping GPT-based model generates rich dialogue content, and output based on the input information is provided through the dialogue interface.

[0651] 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.

[0652] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0653] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0654] [Fourth Embodiment]

[0655] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0656] 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.

[0657] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0658] 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.

[0659] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0660] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0661] 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.

[0662] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0663] 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.

[0664] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0665] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0666] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0667] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] This invention is implemented as a system to provide the necessary support to ensure that users achieve their set goals without fail. This system consists of terminals, servers, and software programs, and utilizes advanced technologies such as natural language processing, machine learning, and data analysis.

[0669] First, users input their goals in text format using a device. These goals can be diverse, but must include specific achievements. The device analyzes and refines the input goals using natural language processing technology. During the analysis process, the device may ask additional questions to the user as needed to further concretize the goals.

[0670] The analyzed target data is sent from the terminal to the server. Upon receiving this target data, the server uses a pre-trained machine learning algorithm to generate an action plan optimized for the individual user. This action plan includes steps to be achieved, necessary materials, and information sources to refer to.

[0671] Furthermore, the server references a wealth of information sources on the internet and automatically selects (curates) learning content relevant to the user's goals and action plans. This selected content is provided to the user through their device, allowing them to deepen their self-study based on that content.

[0672] Furthermore, users are required to periodically report their progress using their devices. This progress data is sent to the server in real time, and the server quickly generates feedback based on this data, which is then provided to the user via their device. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0673] For example, if a user sets a goal such as "I want to acquire business English conversation skills," the system can recommend relevant online lessons, provide a list of necessary vocabulary words, and suggest the next steps based on their learning progress.

[0674] In this way, this system efficiently and effectively supports the goal achievement process by providing individually optimized support to users.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The user enters the details of their objective into the terminal. The terminal sends the received objective to a natural language processing module for initial analysis.

[0678] Step 2:

[0679] The device presents the user with additional questions to obtain more specific information based on the analysis results. The user then answers these questions.

[0680] Step 3:

[0681] The device integrates the user's responses and sends the resulting target data to the server in JSON format.

[0682] Step 4:

[0683] The server analyzes the received target data and uses machine learning algorithms to generate an individually optimized action plan based on the user's characteristics.

[0684] Step 5:

[0685] The server automatically searches the internet for relevant information sources and curates learning content. The selected content is then sent to the device.

[0686] Step 6:

[0687] Users perform activities according to their action plan via a terminal and input their progress into the terminal. The input data is immediately sent to the server.

[0688] Step 7:

[0689] The server analyzes progress data in real time and generates evaluations and feedback. This feedback includes suggestions for improvement and next steps.

[0690] Step 8:

[0691] The device receives feedback from the server and presents it to the user. Based on that feedback, the user decides on their next action.

[0692] (Example 1)

[0693] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0694] In today's world, there is a need for systems that effectively support individuals in achieving their goals. Conventional support systems often struggle to customize action plans to suit the specific circumstances of each user, and the information they provide is frequently inappropriate. This results in inefficient goal achievement for users.

[0695] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0696] In this invention, the server includes means for analyzing goals entered by the user via a terminal and refining them using natural language processing technology, means for generating an individualized action plan using a machine learning algorithm based on the refined goals, and means for selecting and providing educational content related to the action plan from information sources. This makes it possible to provide an optimal action plan according to the user's situation and to select relevant learning content.

[0697] "Goals" refer to the specific results or accomplishments that users wish to achieve.

[0698] "Analysis" refers to the process of analyzing input content using natural language processing techniques to refine or break down information.

[0699] "Natural language processing technology" refers to the technology used to process and understand human language using computers, and includes text analysis and data extraction.

[0700] A "machine learning algorithm" refers to a mathematical method that allows computers to learn from data and make improved decisions based on that learning experience.

[0701] An "action plan" refers to a plan that includes specific steps and actions to support users in achieving their goals.

[0702] "Educational content" refers to information and materials aimed at acquiring the knowledge and skills necessary to achieve a goal.

[0703] "Information source" refers to a source on the internet or other media that provides relevant data or knowledge.

[0704] "Elaboration" refers to the process of analyzing information and supplementing content to make the entered goals clearer and more detailed.

[0705] "Selection" refers to the process of extracting highly relevant information from diverse sources and picking out only the necessary content.

[0706] "Feedback" refers to evaluations, suggestions for improvement, and advice provided regarding a user's behavior and progress.

[0707] This invention is configured as a system that efficiently supports users in achieving their goals. It mainly consists of a terminal, a server, and multiple software components.

[0708] First, the user enters their goal via the terminal. The goal is entered as a specific item they want to achieve, in the form of a text field, such as "Improve my English business conversation skills." The terminal analyzes this text using natural language processing technology to refine the goal. Python natural language processing libraries (such as NLTK or spaCy) are used for the analysis.

[0709] The analyzed target data is sent from the terminal to the server, which receives it. The server uses machine learning algorithms to generate a personalized action plan. This utilizes analytical tools such as Scikit-learn and TensorFlow. The action plan includes specific learning steps and recommendations.

[0710] Furthermore, the server selects and provides relevant educational content from internet sources. By searching its extensive database, it can present users with courses and materials tailored to their goals. For example, it can suggest, "We recommend taking this course once a week."

[0711] Users periodically report their progress via their devices. An example of their progress might be, "This week I learned 10 business terms." The server receives this information in real time, analyzes the user's progress, and generates feedback. This feedback includes evaluations, suggestions for improvement, and advice to maintain motivation.

[0712] An example of a prompt message might be: "Please enter a specific goal you would like to achieve. Example: Improve my English business conversation skills."

[0713] This system can individually optimize and effectively support the user's goal achievement process.

[0714] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0715] Step 1:

[0716] The user uses a device to input their goal. The entered goal is in text format; for example, it might be "Improve my English business conversation skills." This text data is then passed to the device as input.

[0717] Step 2:

[0718] The terminal analyzes the input text data using natural language processing techniques. Here, a Python natural language processing library (NLTK or spaCy) is used to extract target keywords and important attributes. This process involves splitting the text into tokens and tagging them by part of speech. As a result, refined target data is generated.

[0719] Step 3:

[0720] The terminal sends the analyzed target data to the server. This is done via a secure communication protocol (e.g., HTTPS using SSL). The transmitted data is expressed in JSON format, containing the specific details of the target.

[0721] Step 4:

[0722] The server uses machine learning algorithms based on the received target data to generate a personalized action plan. Here, it uses Scikit-learn or TensorFlow models and analyzes past training data and similar targets to recommend the most appropriate training steps and resources. The output of this process is a plan that includes specific action steps.

[0723] Step 5:

[0724] The server selects appropriate educational content from the internet based on the action plan and collects data from the information sources. It performs web scraping using Python's BeautifulSoup and extracts links to online courses and video lessons related to the goals. This process outputs automatically selected learning resources.

[0725] Step 6:

[0726] The server sends the selected educational content and action plan to the terminal. The terminal displays this on the screen to the user, encouraging them to use it. Specifically, it supports the user's learning by providing clickable links and downloadable materials at each step of the action plan.

[0727] Step 7:

[0728] Users periodically report their learning progress via their devices. This input includes specific progress information, such as the number and content of knowledge items acquired. The devices transmit this information to the server in real time.

[0729] Step 8:

[0730] The server generates feedback based on the received progress data. Using a generation AI model, evaluations, improvement suggestions, and motivational advice are created based on the user's progress. This feedback is then delivered to the user via their device.

[0731] (Application Example 1)

[0732] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0733] Even when users set goals, it is often difficult for them to effectively execute action plans to achieve them. Furthermore, without appropriate feedback and support, it is difficult to maintain motivation toward achieving goals. The present invention aims to solve these problems and provide a system that supports users in effectively achieving their goals.

[0734] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0735] In this invention, the server includes means for analyzing goals set by the user and generating an individualized action plan based on those goals; means for automatically selecting information sources related to the generated action plan and providing learning support; means for receiving the user's progress in real time, analyzing that progress, and providing feedback to the user; and means for presenting information that supports goal achievement using a visual aid device. As a result, the user can effectively take actions toward achieving their goals while receiving information visually, and can receive continuous support through feedback.

[0736] A "user" is someone who uses this system to achieve their own goals.

[0737] "Goals" refer to specific items or conditions that users wish to achieve.

[0738] "Analysis" refers to the process of analyzing and refining the goals set by the user using natural language processing technology and other methods.

[0739] An "action plan" is a plan that includes individualized, specific action steps and necessary information based on analyzed goals.

[0740] "Information sources" refer to information available on the internet or in databases that is relevant to action plans and supports users' learning.

[0741] "Progress status" refers to the degree of achievement and the progress of efforts toward the goals set by the user.

[0742] "Feedback" refers to responses that include evaluations, suggestions for improvement, and advice for maintaining motivation, based on progress.

[0743] A "visual assistance device" is a device that allows users to receive information visually, and usually refers to a wearable device.

[0744] This invention is an advanced system designed to support users in achieving their goals. It primarily consists of a server, terminals, and visual assistance devices, and utilizes natural language processing, machine learning, and data analysis technologies. Specific embodiments are described below.

[0745] First, the user inputs their desired goal via text or voice using a device. The server analyzes this goal using a natural language processing library (e.g., spaCy) to refine it. During this process, additional questions may be displayed on the device as needed to prompt the user for further input. The analyzed goal data is sent to the server, where a machine learning library (e.g., TensorFlow) generates an individualized action plan. This action plan is then sent to the device and presented to the user through a visual aid. The visual aid is envisioned to be a wearable device such as smart glasses.

[0746] The server also automatically selects relevant information and learning content from the internet and other data sources and sends it to the terminal. This information helps users more effectively execute their action plans. Users perform daily activities based on their action plans and report their progress to the server via their terminal. This progress data is analyzed in real time on the server, and feedback is generated. The feedback includes an assessment of achievement, suggestions for improvement, and advice to boost motivation, and is provided to the user through visual aids.

[0747] For example, when a store employee sets a sales target for a new product, using a visual aid allows them to interact with customers while checking real-time information on successful sales cases and popular products. This supports the optimal approach to achieving the target.

[0748] An example of a prompt to input into the generating AI model would be: "To design an application that helps store staff achieve their goals, consider the flow from goal setting to providing feedback."

[0749] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0750] Step 1:

[0751] The user enters their goal using a terminal, either as text or voice. The entered data is sent directly to the server. The server uses a natural language processing library to analyze the text data and refine the goal. If voice data is used, speech recognition software is used to convert it to text. The analyzed data is then formatted to meet the user's specific goal requirements.

[0752] Step 2:

[0753] The server receives refined goal data and generates personalized action plans using machine learning models. It takes analyzed goal data as input and identifies feasible tasks and necessary resources based on it. In this process, data analysis algorithms select the optimal plan and send the results to the terminal.

[0754] Step 3:

[0755] The terminal receives the action plan generated from the server and presents it visually to the user through a visual aid. At this point, the information is displayed on the screen in an easy-to-understand format so that the user can understand the details of the plan. Based on this information, the user plans and carries out their daily activities.

[0756] Step 4:

[0757] Users report their progress to the server via their devices. This data is stored on the server in real time and processed by a data analysis engine. Based on the input progress data, the current level of achievement and any problems are analyzed, and the next steps to take are determined.

[0758] Step 5:

[0759] The server generates feedback based on the analysis of progress data and provides it to the user through the terminal and visual aids. This feedback includes areas for improvement, suggestions for next actions, and encouraging messages to boost motivation. The user then uses this feedback to adjust their actions and move towards achieving their goals.

[0760] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0761] This invention is implemented in a more advanced form by incorporating an emotion engine as a system that provides support for achieving user-defined goals. This system consists of a terminal, a server, and an emotion engine as its main components, and utilizes natural language processing, machine learning, emotion recognition technology, and the like.

[0762] In the initial stages of the system, users input their goals as text via a terminal. The terminal analyzes the received goals using natural language processing technology. This analysis includes prompting additional questions, and the terminal asks the user questions as needed to help them refine their goals.

[0763] Detailed user goal information is sent from the terminal to the server. Based on this goal data, the server generates an optimal action plan tailored to the user's individual characteristics and circumstances. The generated action plan includes the steps and reference information necessary to achieve the goals.

[0764] A key feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. The recognized emotional data is sent to a server, which then generates mental care content for the user based on this data. This content includes encouragement and relaxation techniques tailored to the emotional state.

[0765] Furthermore, the server uses all the data, including emotional state and progress information, to optimize action suggestions to help maintain user motivation. The learning environment and action plan are also adjusted in response to changes in emotions.

[0766] For example, if a user sets the goal of "improving their English skills to work abroad," the system will recommend lessons on necessary vocabulary and grammar. When the user's emotional state indicates tension or anxiety, the server will provide content to help them relax and support them in maintaining their motivation.

[0767] Through this system, users can receive support tailored to their individual needs, and the process toward achieving their goals can be advanced effectively and sustainably.

[0768] The following describes the processing flow.

[0769] Step 1:

[0770] The user enters their desired goals into the device. The device analyzes this input data using natural language processing technology to identify the basic objective.

[0771] Step 2:

[0772] The device evaluates the analyzed data and, if it determines that the goal needs to be made more specific, displays additional questions to the user. By answering these questions, the user sets the goal more concretely.

[0773] Step 3:

[0774] The device formats the specified goal data and sends it to the server. The server receives this data and generates a personalized action plan that takes the user's characteristics into account.

[0775] Step 4:

[0776] The server automatically curates learning content by selecting relevant information sources from the internet that align with the user's goals. This content is then sent to the device and presented to the user.

[0777] Step 5:

[0778] Users progress through learning activities based on recommended content and action plans. Progress is periodically entered into the device, and this data is sent to the server.

[0779] Step 6:

[0780] The server uses an emotion engine to analyze the user's facial expressions and voice data to understand their emotional state. This emotional data is then used to generate mental care content tailored to each individual's situation.

[0781] Step 7:

[0782] The server integrates and analyzes the acquired emotional and progress data to generate feedback and suggestions for the next action for the user. This feedback also includes advice on maintaining motivation based on the user's emotional state.

[0783] Step 8:

[0784] The device presents the user with feedback and advice received from the server. Based on this, the user further modifies their action plan and continues their activities toward their goals.

[0785] (Example 2)

[0786] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] In today's world, where it is essential to provide individually optimized action plans based on user-defined goals, it is difficult to grasp users' progress and emotional states in real time and provide appropriate feedback and mental care accordingly. Furthermore, there is a lack of efficient means to provide learning support from diverse information sources.

[0788] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0789] In this invention, the server includes means for analyzing user-set goals and generating an individualized action plan, means for automatically selecting information sources related to the generated action plan and providing learning support, and means for analyzing the user's emotional state and generating and providing content for mental care based on emotional information. This enables support tailored to each user's characteristics and circumstances, and facilitates the smooth progress of the process toward achieving goals.

[0790] "Analyzing goals" means using natural language processing technology to extract and understand the content of the goals set by the user.

[0791] An "individualized action plan" is a plan that includes optimized action plans and steps based on each user's individual goals.

[0792] "Automatically selecting information sources" means automatically choosing various databases and materials relevant to the purpose using machine learning technology.

[0793] "Providing learning support" means providing learning materials and resources to improve users' knowledge and skills.

[0794] "Receiving progress in real time" means instantly incorporating user activity and learning progress into the system.

[0795] Providing feedback means offering evaluations and suggestions for improvement regarding the user's progress and actions, and providing information to encourage their next steps.

[0796] "Analyzing emotional state" means inferring a user's psychological state from their facial expressions and voice, and then determining their emotions.

[0797] "Content for mental care" refers to advice and relaxation methods provided to support the mental health of users.

[0798] "Generative AI technology" is a technology that uses artificial intelligence to generate new information and data.

[0799] A "remote device" is an internet-connected electronic device that can be accessed by servers and users.

[0800] This invention is a system that provides advanced support for achieving user-defined goals. The system primarily consists of a terminal, a server, and an emotion engine. The system utilizes natural language processing, machine learning, and emotion recognition technologies.

[0801] The user enters their goal through the device. This goal is analyzed by natural language processing software installed on the device (e.g., Python's NLTK library), which then derives specific content and additional questions to help the user achieve the goal. For example, if the user sets a goal such as "I want to gain confidence in giving presentations in English," a detailed action plan will be presented based on that goal.

[0802] The analyzed target data is sent from the terminal to the server. The server generates an action plan using a generative AI model (e.g., TensorFlow). This plan includes curating relevant information and tasks to be performed. The analysis results are delivered to a remote device via data communication, making them accessible to the user.

[0803] Furthermore, the emotion engine analyzes the user's facial expressions and voice via the device to evaluate their emotional state. Using libraries such as OpenCV, it analyzes facial expressions in real time and generates and provides mental care content based on this analysis. This content includes suggestions for relaxation-oriented music.

[0804] As a result, this system can provide precise and flexible support tailored to the individual needs of each user, and optimize the process to achieve goals.

[0805] A concrete example of a prompt might be: "The user has the goal of 'improving their English skills to work abroad.' Use a generative AI model to propose an action plan that aligns with this goal, and further adjust mental support based on the results of an analysis of their emotional state."

[0806] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0807] Step 1:

[0808] The user uses a terminal to input their set goal in text format. The entered text is sent to the goal analysis module. Here, the input is the user's goal text, and the output is text ready for analysis.

[0809] Step 2:

[0810] The terminal uses a natural language processing engine to analyze the input target text. It uses the Python NLTK library to extract keywords and sentence structure from the text. This clarifies the content of the goal and, if necessary, generates additional questions such as, "What steps are needed to achieve this goal?". The input is the target text from Step 1, and the output is a keyword list and additional questions.

[0811] Step 3:

[0812] Once the user answers additional questions, the device re-analyzes the responses and prepares to send the final target information to the server. This process updates the text data based on the new information and packages it in JSON format. The input is the user's answers, and the output is the updated target information.

[0813] Step 4:

[0814] The terminal sends target information formatted in JSON format to the server. A secure communication protocol is used to safely transmit the data. The input here is the formatted target information, and the output is the server's confirmation of receipt.

[0815] Step 5:

[0816] The server analyzes the received target information and generates an optimal action plan using a generative AI model. It uses the TensorFlow library to create action suggestions based on user patterns and past success stories. The input is JSON data, and the output is an action plan.

[0817] Step 6:

[0818] The generated action plan is stored on the server, and relevant information sources are automatically selected. Relevant information is searched from various databases, curated, and prepared for user presentation. The input is the action plan, and the output is a list of recommended information.

[0819] Step 7:

[0820] The server sends the action plan and information list to the terminal. This allows the user to access the detailed action plan via the terminal. The input is the action plan and information list, and the output is what is presented to the user.

[0821] Step 8:

[0822] The user inputs progress information into the system via a terminal. The terminal sends this data to the server in real time. At this stage, the input is progress information, and the output is the receipt of new data on the server.

[0823] Step 9:

[0824] The server analyzes the received progress data, and the progress management module generates feedback for the user. Based on the progress data, it analyzes which steps are on schedule and provides specific improvement suggestions. The input is progress information, and the output is a feedback message.

[0825] Step 10:

[0826] The emotion engine analyzes the user's facial expressions and voice to evaluate their emotional state. The device collects user emotion data using libraries such as OpenCV, and this data is analyzed on the server. The input is the user's voice and video data, and the output is the emotion evaluation result.

[0827] Step 11:

[0828] The server generates mental care content tailored to the user based on the emotion assessment results. It selects relaxation music from a music streaming service and sends it to the device as digital content. The input is the emotion assessment results, and the output is the mental care content.

[0829] (Application Example 2)

[0830] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0831] In modern times, the process of achieving user-defined goals often suffers from a lack of support tailored to individual needs, resulting in lower success rates. Furthermore, traditional support systems fail to consider users' emotional states and are ineffective in maintaining their motivation. Additionally, the lack of personalized, emotionally responsive interactions in shopping experiences makes it difficult to provide a highly satisfying experience.

[0832] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0833] In this invention, the server includes means for analyzing user-set goals and generating an action plan, means for collecting information sources and providing learning support, means for analyzing progress and providing feedback, means for performing emotion analysis and providing information, means for recommending products, and means for generating dialogue for emotional interaction through conversations in a virtual store. This makes it possible to provide users with personalized support according to their emotional state and to effectively and sustainably advance the goal achievement process.

[0834] "Means of analyzing goals" refers to techniques for understanding the goals set by users and analyzing their purpose and the steps required in detail.

[0835] "Means for generating action plans" refers to technologies that, based on analyzed goals, devise specific steps and strategies for users to efficiently achieve those goals.

[0836] "Means of collecting information sources and providing learning support" refers to methods that automatically gather necessary data and reference information from the internet and other sources to support users' learning and goal achievement.

[0837] "Means of analyzing progress and providing feedback" refers to technologies that monitor the user's progress toward their goals and propose appropriate evaluations and improvement plans based on that progress.

[0838] "Means of performing emotion analysis and providing information" refers to a function that recognizes emotions from the user's voice and facial expressions and provides appropriate information and support based on those emotions.

[0839] A "means of recommending products" is a system that suggests the most suitable products based on the user's preferences and emotional state.

[0840] "Dialogue generation means for emotionally engaging through conversations in virtual stores" refers to technology that generates conversations in a virtual reality environment to enable emotionally connected communication with users.

[0841] The system for realizing this invention mainly includes a server, a terminal, an emotion analysis module, and a dialogue generation engine. The terminal provides an interface for the user to input their goals and transmits that data to the server. The server receives this data and analyzes the goals using natural language processing techniques. Libraries such as Python's NLTK and spaCy can be used for this purpose.

[0842] Next, the server executes a machine learning algorithm to generate an action plan tailored to the user's individual information. By using TensorFlow or Scikit-learn, it makes predictions based on past data and patterns to create the optimal action plan.

[0843] Emotion analysis is performed using data from the device's built-in camera and microphone. Tools such as the Affectiva SDK and Google Cloud Speech-to-Text are used to analyze facial expressions and voice to identify the user's emotional state. The server then uses this emotional data to recommend mental health care content and products tailored to the user.

[0844] For example, if a user sets the goal of "improving their language skills to succeed overseas," the system will suggest the necessary learning steps and materials to achieve that goal. Furthermore, if anxiety is detected through emotion analysis, the server will provide relaxation content and encouraging messages.

[0845] In the virtual store, products are recommended based on sentiment analysis results, and the dialogue generation engine generates natural conversations with the user. This utilizes a generative AI model based on OpenAI's GPT, and prompts such as "Generate product categories to recommend when the user is excited" are input.

[0846] In this way, it is possible to build a system that supports users in achieving their goals and improves the user experience.

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The terminal receives text data about the goal from the user as input. The user enters the goal using the terminal's interface and prepares to send the input data to the server.

[0850] Step 2:

[0851] The server receives the input goal and analyzes it using natural language processing. This process uses Python's NLTK and spaCy to tokenize the text and perform sentiment analysis, clarifying the structure of the goal.

[0852] Step 3:

[0853] Based on the goals analyzed by the server, an action plan is generated. Using TensorFlow and Scikit-learn, the optimal steps and resources for the input data are systematically determined. This output is then shaped into an action plan for the user.

[0854] Step 4:

[0855] The device's camera and microphone capture the user's facial expressions and voice as input data. The device sends this data to a server to understand the user's emotional state in real time.

[0856] Step 5:

[0857] The server performs emotion analysis. It uses the Affectiva SDK and Google Cloud Speech-to-Text to analyze facial expressions and voice to identify the user's emotions. The resulting emotional state data is then used for the following processes.

[0858] Step 6:

[0859] The server generates appropriate mental health care content based on the results of emotion analysis, providing comprehensive support. The server uses a generative AI model to create prompts and executes instructions such as, "Generate relaxation content that would be recommended when the user is feeling anxious."

[0860] Step 7:

[0861] In a virtual store, the server recommends products based on the user's emotional state and uses a generative AI model to create conversations that allow for emotional interaction with the user. A prototyping GPT-based model generates rich dialogue content, and output based on the input information is provided through the dialogue interface.

[0862] 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.

[0863] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0864] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0865] 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.

[0866] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0867] 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.

[0868] 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.

[0869] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0870] 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."

[0871] 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.

[0872] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0873] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0882] 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.

[0883] The following is further disclosed regarding the embodiments described above.

[0884] (Claim 1)

[0885] A processing means that analyzes the goals set by the user and generates an individualized action plan based on those goals,

[0886] A means of automatically curating information sources related to the generated action plan and providing learning support,

[0887] A means for receiving user progress in real time, analyzing said progress, and providing feedback to the user,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, further comprising means for presenting additional questions to the user based on the analyzed goals and for concretizing the goals.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for analyzing the emotional state of a user and generating and providing content for mental care.

[0893] "Example 1"

[0894] (Claim 1)

[0895] A means for analyzing a goal entered by a user via a terminal and refining the goal using natural language processing technology,

[0896] A means for generating an individualized action plan using a pre-trained machine learning algorithm based on refined goals,

[0897] A means of selecting and providing educational content related to the action plan from information sources,

[0898] A means for receiving the user's progress in real time from the terminal and generating feedback that provides evaluations and improvement suggestions based on that progress,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, further comprising means for assisting the refinement of goals by presenting additional questions to the user based on the analyzed goals.

[0902] (Claim 3)

[0903] The system according to claim 1, further comprising means for linking the generated feedback with learning content from diverse sources to support the deepening of the user's understanding.

[0904] "Application Example 1"

[0905] (Claim 1)

[0906] A processing means that analyzes the goals set by the user and generates an individualized action plan based on those goals,

[0907] A means of automatically selecting information sources related to the generated action plan and providing learning support,

[0908] A means for receiving user progress in real time, analyzing said progress, and providing feedback to the user,

[0909] A means of presenting information that supports goal achievement using a visual aid,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, further comprising means for presenting additional questions to the user based on the analyzed goals and for concretizing the goals.

[0913] (Claim 3)

[0914] The system according to claim 1, further comprising means for analyzing the emotional state of a user and generating and providing content for psychological support.

[0915] "Example 2 of combining an emotion engine"

[0916] (Claim 1)

[0917] A processing means that analyzes the goals set by the user and generates an individualized action plan based on those goals,

[0918] A means of automatically selecting information sources related to the generated action plan and providing learning support,

[0919] A means for receiving user progress in real time, analyzing said progress, and providing feedback to the user,

[0920] A means of analyzing the emotional state of users and generating and providing content for mental care based on emotional information,

[0921] A means of concretizing the goals by presenting additional questions based on the analyzed goals,

[0922] A means of dynamically optimizing action plans and adjusting proposals using generative AI technology,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, comprising means for determining the emotional state of a user by analyzing their facial expressions and voice, and providing content for relaxation based on that determination.

[0926] (Claim 3)

[0927] The system according to claim 1, further comprising means for providing analysis results and action plans as user-accessible information by transmitting them to a remote device using data communication means.

[0928] "Application example 2 of combining emotional engines"

[0929] (Claim 1)

[0930] A means for analyzing goals set by the user and generating an individualized action plan based on those goals,

[0931] A means of automatically collecting information sources related to the generated action plan and providing learning support,

[0932] A means for receiving user progress in real time, analyzing said progress, and providing feedback to the user,

[0933] A means of emotion analysis for recognizing the emotional state of a user and providing information accordingly,

[0934] A means of recommending products based on the results of the sentiment analysis,

[0935] A means of generating dialogue for emotionally interacting with users through conversations in virtual stores,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising means for presenting additional questions to the user based on the analyzed goals and for concretizing the goals.

[0939] (Claim 3)

[0940] The system according to claim 1, further comprising means for analyzing the emotional state of a user, generating and providing content for mental care, and means for recommending products according to the user's emotions. [Explanation of symbols]

[0941] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A processing means that analyzes the goals set by the user and generates an individualized action plan based on those goals, A means of automatically curating information sources related to the generated action plan and providing learning support, A means for receiving user progress in real time, analyzing said progress, and providing feedback to the user, A system that includes this.

2. The system according to claim 1, further comprising means for presenting additional questions to the user based on the analyzed goals and for concretizing the goals.

3. The system according to claim 1, further comprising means for analyzing the emotional state of a user and generating and providing content for mental care.

Images